Token | at |
Token ID | 379 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
reck | +8.374 |
idential | +8.349 |
osher | +7.893 |
aren | +7.802 |
Reserved | +7.795 |
Neg logit contributions | |
analys | -8.538 |
countries | -8.463 |
researchers | -7.886 |
physicists | -7.871 |
physicist | -7.837 |
Token | the |
Token ID | 262 |
Feature activation | +9.43e+00 |
Pos logit contributions | |
reck | +9.295 |
idential | +9.280 |
Shore | +8.846 |
Reserved | +8.796 |
osher | +8.772 |
Neg logit contributions | |
analys | -7.657 |
countries | -7.608 |
researchers | -6.985 |
physicists | -6.970 |
scientist | -6.899 |
Token | corner |
Token ID | 5228 |
Feature activation | +6.03e+00 |
Pos logit contributions | |
reck | +9.820 |
idential | +9.732 |
osher | +9.385 |
Shore | +9.380 |
Reserved | +9.360 |
Neg logit contributions | |
analys | -6.019 |
countries | -5.986 |
researchers | -5.377 |
physicists | -5.373 |
physicist | -5.304 |
Token | of |
Token ID | 286 |
Feature activation | +2.22e+01 |
Pos logit contributions | |
reck | +5.840 |
idential | +5.820 |
osher | +5.533 |
Reserved | +5.461 |
Shore | +5.452 |
Neg logit contributions | |
countries | -4.457 |
analys | -4.454 |
researchers | -4.082 |
physicists | -4.061 |
physicist | -4.052 |
Token | Kirby |
Token ID | 23965 |
Feature activation | +1.72e+01 |
Pos logit contributions | |
Shore | +16.698 |
Pleasant | +16.275 |
Jefferson | +15.832 |
reck | +15.806 |
idential | +15.707 |
Neg logit contributions | |
analys | -16.050 |
countries | -14.952 |
physicists | -14.149 |
experiments | -14.110 |
regimes | -13.940 |
Token | and |
Token ID | 290 |
Feature activation | +2.76e+01 |
Pos logit contributions | |
reck | +12.273 |
idential | +12.225 |
Shore | +12.152 |
Pleasant | +11.769 |
aren | +11.542 |
Neg logit contributions | |
analys | -13.965 |
countries | -13.602 |
physicists | -12.675 |
physicist | -12.552 |
researchers | -12.457 |
Token | Richmond |
Token ID | 16940 |
Feature activation | +2.04e+01 |
Pos logit contributions | |
Shore | +20.488 |
Pleasant | +20.244 |
Jefferson | +19.856 |
Reserved | +19.031 |
reck | +18.858 |
Neg logit contributions | |
analys | -17.354 |
countries | -16.126 |
physicists | -15.159 |
experiments | -15.049 |
regimes | -14.964 |
Token | . |
Token ID | 13 |
Feature activation | +7.57e+00 |
Pos logit contributions | |
idential | +16.995 |
Shore | +16.562 |
reck | +16.429 |
Reserved | +16.145 |
Pleasant | +16.135 |
Neg logit contributions | |
analys | -13.357 |
countries | -12.259 |
physicist | -11.945 |
physicists | -11.919 |
scientist | -11.554 |
Token | Needless |
Token ID | 39114 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
idential | +7.326 |
reck | +7.290 |
osher | +6.928 |
Reserved | +6.905 |
aren | +6.857 |
Neg logit contributions | |
countries | -5.721 |
analys | -5.698 |
researchers | -5.232 |
physicists | -5.189 |
scientist | -5.148 |
Token | to |
Token ID | 284 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
countries | +0.879 |
analys | +0.823 |
researchers | +0.778 |
example | +0.755 |
experiments | +0.749 |
Neg logit contributions | |
idential | -2.224 |
reck | -2.199 |
osher | -2.140 |
aren | -2.079 |
Reserved | -2.078 |
Token | say |
Token ID | 910 |
Feature activation | +1.65e+01 |
Pos logit contributions | |
countries | +1.186 |
analys | +1.116 |
researchers | +1.052 |
example | +1.052 |
scientist | +1.017 |
Neg logit contributions | |
idential | -2.370 |
reck | -2.354 |
osher | -2.313 |
Reserved | -2.235 |
idelines | -2.230 |
Token | corner |
Token ID | 5228 |
Feature activation | +6.58e+00 |
Pos logit contributions | |
reck | +11.589 |
idential | +11.418 |
Shore | +11.344 |
Pleasant | +11.200 |
Reserved | +11.154 |
Neg logit contributions | |
analys | -7.816 |
countries | -7.741 |
physicists | -6.988 |
physicist | -6.911 |
researchers | -6.901 |
Token | of |
Token ID | 286 |
Feature activation | +1.70e+01 |
Pos logit contributions | |
reck | +5.932 |
idential | +5.888 |
osher | +5.629 |
Pleasant | +5.609 |
Shore | +5.585 |
Neg logit contributions | |
analys | -5.139 |
countries | -5.049 |
physicist | -4.702 |
physicists | -4.680 |
scientist | -4.667 |
Token | West |
Token ID | 2688 |
Feature activation | +2.39e+01 |
Pos logit contributions | |
Shore | +12.857 |
Pleasant | +12.674 |
reck | +12.478 |
idential | +12.471 |
Reserved | +12.259 |
Neg logit contributions | |
analys | -13.838 |
countries | -13.172 |
physicists | -12.460 |
physicist | -12.286 |
experiments | -12.284 |
Token | heimer |
Token ID | 16288 |
Feature activation | +1.73e+01 |
Pos logit contributions | |
reck | +18.719 |
Shore | +18.508 |
Pleasant | +17.946 |
idential | +17.863 |
Jefferson | +17.207 |
Neg logit contributions | |
analys | -15.942 |
countries | -14.995 |
physicists | -14.400 |
regimes | -13.923 |
experiments | -13.854 |
Token | and |
Token ID | 290 |
Feature activation | +2.48e+01 |
Pos logit contributions | |
idential | +11.628 |
Shore | +11.579 |
reck | +11.536 |
Pleasant | +11.141 |
Reserved | +10.910 |
Neg logit contributions | |
analys | -14.945 |
countries | -14.267 |
physicists | -13.498 |
physicist | -13.364 |
experiments | -13.194 |
Token | Mont |
Token ID | 5575 |
Feature activation | +2.76e+01 |
Pos logit contributions | |
Shore | +18.564 |
Pleasant | +18.324 |
Jefferson | +17.444 |
Reserved | +17.217 |
idential | +16.851 |
Neg logit contributions | |
analys | -17.218 |
countries | -15.910 |
regimes | -15.080 |
physicists | -15.080 |
experiments | -14.929 |
Token | rose |
Token ID | 13698 |
Feature activation | +2.09e+01 |
Pos logit contributions | |
idential | +17.419 |
reck | +17.349 |
aren | +16.313 |
osher | +16.117 |
Pleasant | +16.078 |
Neg logit contributions | |
analys | -20.841 |
countries | -20.120 |
physicists | -19.236 |
physicist | -18.720 |
regimes | -18.583 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
idential | +17.662 |
Shore | +17.505 |
reck | +17.244 |
Pleasant | +17.145 |
honoring | +17.024 |
Neg logit contributions | |
analys | -12.748 |
countries | -11.513 |
physicist | -11.477 |
physicists | -11.261 |
scientist | -11.165 |
Token | I |
Token ID | 314 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
idential | +10.696 |
reck | +10.565 |
Reserved | +10.307 |
Shore | +10.257 |
Pleasant | +10.235 |
Neg logit contributions | |
analys | -9.212 |
countries | -9.097 |
physicists | -8.428 |
researchers | -8.292 |
experiments | -8.283 |
Token | know |
Token ID | 760 |
Feature activation | +8.83e+00 |
Pos logit contributions | |
idential | +4.417 |
reck | +4.395 |
osher | +4.228 |
Reserved | +4.133 |
aren | +4.123 |
Neg logit contributions | |
countries | -2.884 |
analys | -2.834 |
researchers | -2.630 |
scientist | -2.571 |
physicists | -2.565 |
Token | this |
Token ID | 428 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
idential | +8.583 |
reck | +8.557 |
osher | +8.081 |
Shore | +8.068 |
aren | +8.066 |
Neg logit contributions | |
analys | -6.300 |
countries | -6.262 |
researchers | -5.709 |
physicist | -5.680 |
scientist | -5.671 |
Token | . |
Token ID | 13 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
idential | +3.299 |
reck | +3.286 |
osher | +3.115 |
aren | +3.047 |
Reserved | +3.045 |
Neg logit contributions | |
countries | -3.121 |
analys | -3.080 |
researchers | -2.890 |
scientist | -2.843 |
physicists | -2.843 |
Token |
|
Token ID | 198 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
countries | +0.148 |
analys | +0.144 |
researchers | +0.135 |
scientist | +0.132 |
example | +0.132 |
Neg logit contributions | |
idential | -0.223 |
reck | -0.222 |
osher | -0.212 |
rict | -0.207 |
aren | -0.207 |
Token |
|
Token ID | 198 |
Feature activation | +9.98e+00 |
Pos logit contributions | |
idential | +3.721 |
reck | +3.703 |
osher | +3.549 |
aren | +3.471 |
Reserved | +3.469 |
Neg logit contributions | |
countries | -2.514 |
analys | -2.465 |
researchers | -2.292 |
scientist | -2.243 |
physicists | -2.238 |
Token | 24 |
Token ID | 1731 |
Feature activation | +9.99e+00 |
Pos logit contributions | |
reck | +7.399 |
idential | +7.275 |
aren | +6.775 |
osher | +6.755 |
Reserved | +6.732 |
Neg logit contributions | |
analys | -9.753 |
countries | -9.541 |
researchers | -8.912 |
physicists | -8.891 |
physicist | -8.861 |
Token | 11 |
Token ID | 1157 |
Feature activation | +2.37e+01 |
Pos logit contributions | |
idential | +7.217 |
reck | +7.148 |
Shore | +6.829 |
Reserved | +6.785 |
Pleasant | +6.699 |
Neg logit contributions | |
analys | -9.649 |
countries | -9.427 |
physicists | -8.909 |
researchers | -8.847 |
physicist | -8.830 |
Token | S |
Token ID | 311 |
Feature activation | +2.71e+01 |
Pos logit contributions | |
Shore | +17.391 |
Pleasant | +17.328 |
Reserved | +16.565 |
Jefferson | +16.404 |
idential | +16.349 |
Neg logit contributions | |
analys | -17.529 |
countries | -16.178 |
physicists | -15.482 |
regimes | -15.274 |
experiments | -15.248 |
Token | . |
Token ID | 13 |
Feature activation | +2.29e+01 |
Pos logit contributions | |
reck | +21.617 |
idential | +21.098 |
aren | +20.596 |
Pleasant | +20.562 |
idelines | +20.502 |
Neg logit contributions | |
analys | -16.348 |
countries | -15.306 |
physicists | -14.505 |
physicist | -14.318 |
regimes | -14.156 |
Token | Shepherd |
Token ID | 30890 |
Feature activation | +8.84e+00 |
Pos logit contributions | |
Pleasant | +17.226 |
Shore | +17.114 |
reck | +16.706 |
idential | +16.598 |
Jefferson | +16.360 |
Neg logit contributions | |
analys | -16.778 |
countries | -15.648 |
regimes | -15.095 |
physicists | -14.984 |
experiments | -14.717 |
Token | Today |
Token ID | 6288 |
Feature activation | +6.68e+00 |
Pos logit contributions | |
idential | +6.758 |
reck | +6.727 |
osher | +6.324 |
aren | +6.253 |
Shore | +6.246 |
Neg logit contributions | |
analys | -8.362 |
countries | -8.251 |
researchers | -7.677 |
physicists | -7.677 |
experiments | -7.622 |
Token | : |
Token ID | 25 |
Feature activation | +2.09e+01 |
Pos logit contributions | |
idential | +5.761 |
reck | +5.737 |
osher | +5.421 |
aren | +5.310 |
Reserved | +5.307 |
Neg logit contributions | |
countries | -5.849 |
analys | -5.788 |
researchers | -5.430 |
physicists | -5.357 |
scientist | -5.350 |
Token | Tor |
Token ID | 4022 |
Feature activation | +9.64e+00 |
Pos logit contributions | |
Shore | +16.033 |
Pleasant | +15.835 |
Reserved | +15.698 |
reck | +15.589 |
idential | +15.436 |
Neg logit contributions | |
analys | -15.188 |
countries | -14.434 |
physicists | -13.538 |
regimes | -13.352 |
experiments | -13.340 |
Token | Ty |
Token ID | 7039 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
idential | +4.953 |
reck | +4.935 |
osher | +4.641 |
rict | +4.540 |
aren | +4.536 |
Neg logit contributions | |
countries | -5.741 |
analys | -5.721 |
researchers | -5.347 |
physicists | -5.300 |
scientist | -5.275 |
Token | cer |
Token ID | 2189 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
reck | +4.571 |
idential | +4.536 |
osher | +4.285 |
aren | +4.200 |
rict | +4.191 |
Neg logit contributions | |
countries | -4.676 |
analys | -4.648 |
researchers | -4.357 |
physicists | -4.300 |
scientist | -4.295 |
Token | , |
Token ID | 11 |
Feature activation | +7.87e+00 |
Pos logit contributions | |
countries | +0.557 |
analys | +0.544 |
researchers | +0.516 |
scientist | +0.508 |
experiments | +0.507 |
Neg logit contributions | |
idential | -0.562 |
reck | -0.558 |
osher | -0.531 |
Reserved | -0.518 |
aren | -0.518 |
Token | 43 |
Token ID | 5946 |
Feature activation | +5.89e+00 |
Pos logit contributions | |
idential | +7.578 |
reck | +7.529 |
osher | +7.160 |
aren | +7.077 |
Reserved | +7.060 |
Neg logit contributions | |
countries | -5.874 |
analys | -5.859 |
researchers | -5.352 |
physicists | -5.305 |
physicist | -5.287 |
Token | 15 |
Token ID | 1314 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
reck | +3.739 |
idential | +3.736 |
osher | +3.472 |
Reserved | +3.370 |
aren | +3.352 |
Neg logit contributions | |
analys | -6.362 |
countries | -6.340 |
researchers | -6.005 |
scientist | -5.936 |
physicist | -5.935 |
Token | Mont |
Token ID | 5575 |
Feature activation | +2.59e+01 |
Pos logit contributions | |
reck | +9.650 |
idential | +9.514 |
osher | +9.064 |
Shore | +9.042 |
Pleasant | +8.956 |
Neg logit contributions | |
analys | -10.523 |
countries | -10.264 |
researchers | -9.556 |
physicists | -9.477 |
scientist | -9.428 |
Token | rose |
Token ID | 13698 |
Feature activation | +1.40e+01 |
Pos logit contributions | |
idential | +11.486 |
reck | +11.111 |
aren | +10.285 |
osher | +9.962 |
rict | +9.343 |
Neg logit contributions | |
analys | -27.624 |
countries | -26.507 |
physicists | -25.718 |
experiments | -25.140 |
regimes | -25.128 |
Token | has |
Token ID | 468 |
Feature activation | +6.65e+00 |
Pos logit contributions | |
idential | +13.568 |
reck | +13.467 |
Shore | +13.027 |
Reserved | +13.005 |
osher | +12.898 |
Neg logit contributions | |
analys | -9.239 |
countries | -8.872 |
physicists | -8.087 |
researchers | -8.053 |
physicist | -8.034 |
Token | housed |
Token ID | 23707 |
Feature activation | +9.03e+00 |
Pos logit contributions | |
idential | +6.858 |
reck | +6.855 |
osher | +6.539 |
Reserved | +6.458 |
aren | +6.447 |
Neg logit contributions | |
countries | -4.524 |
analys | -4.503 |
researchers | -4.103 |
physicists | -4.039 |
physicist | -4.038 |
Token | some |
Token ID | 617 |
Feature activation | +6.53e+00 |
Pos logit contributions | |
reck | +9.179 |
idential | +9.173 |
osher | +8.758 |
Reserved | +8.741 |
rict | +8.701 |
Neg logit contributions | |
analys | -5.965 |
countries | -5.850 |
researchers | -5.304 |
scientist | -5.271 |
physicist | -5.266 |
Token | exceptional |
Token ID | 15313 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
reck | +6.112 |
idential | +6.021 |
osher | +5.758 |
Shore | +5.685 |
Reserved | +5.679 |
Neg logit contributions | |
analys | -4.926 |
countries | -4.809 |
researchers | -4.422 |
physicist | -4.411 |
scientist | -4.400 |
Token | through |
Token ID | 832 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
countries | +3.127 |
analys | +3.070 |
researchers | +2.843 |
scientist | +2.779 |
experiments | +2.762 |
Neg logit contributions | |
idential | -4.943 |
reck | -4.800 |
osher | -4.716 |
Reserved | -4.656 |
aren | -4.614 |
Token | her |
Token ID | 607 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
countries | +1.296 |
analys | +1.269 |
researchers | +1.178 |
experiments | +1.153 |
example | +1.143 |
Neg logit contributions | |
idential | -1.947 |
reck | -1.920 |
osher | -1.855 |
Reserved | -1.815 |
aren | -1.809 |
Token | family |
Token ID | 1641 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
idential | +2.746 |
reck | +2.731 |
osher | +2.610 |
aren | +2.563 |
Reserved | +2.558 |
Neg logit contributions | |
countries | -1.863 |
analys | -1.829 |
researchers | -1.698 |
scientist | -1.662 |
physicists | -1.660 |
Token | brunch |
Token ID | 50219 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
idential | +3.936 |
reck | +3.935 |
osher | +3.727 |
aren | +3.662 |
Reserved | +3.644 |
Neg logit contributions | |
countries | -3.599 |
analys | -3.564 |
researchers | -3.330 |
physicists | -3.293 |
physicist | -3.282 |
Token | at |
Token ID | 379 |
Feature activation | +8.46e+00 |
Pos logit contributions | |
idential | +0.773 |
reck | +0.761 |
osher | +0.731 |
Reserved | +0.713 |
aren | +0.711 |
Neg logit contributions | |
countries | -0.642 |
analys | -0.632 |
researchers | -0.591 |
experiments | -0.581 |
example | -0.579 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.54e+01 |
Pos logit contributions | |
reck | +8.053 |
idential | +8.043 |
Shore | +7.727 |
osher | +7.639 |
Pleasant | +7.593 |
Neg logit contributions | |
analys | -6.149 |
countries | -6.050 |
physicists | -5.605 |
researchers | -5.555 |
scientist | -5.553 |
Token | ih |
Token ID | 4449 |
Feature activation | +2.03e+01 |
Pos logit contributions | |
idential | +11.263 |
reck | +10.978 |
rict | +10.384 |
osher | +10.135 |
aren | +9.946 |
Neg logit contributions | |
analys | -25.611 |
countries | -24.485 |
scientist | -23.504 |
physicists | -23.476 |
experiments | -23.443 |
Token | ana |
Token ID | 2271 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
idential | +8.601 |
reck | +8.023 |
aren | +7.788 |
ouls | +7.006 |
osher | +6.854 |
Neg logit contributions | |
analys | -23.325 |
countries | -22.583 |
physicists | -22.154 |
regimes | -21.861 |
scientist | -21.860 |
Token | restaurant |
Token ID | 7072 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
reck | +9.232 |
idential | +9.223 |
Shore | +8.898 |
osher | +8.898 |
Reserved | +8.605 |
Neg logit contributions | |
analys | -9.940 |
countries | -9.525 |
physicists | -9.173 |
physicist | -9.092 |
scientist | -9.010 |
Token | in |
Token ID | 287 |
Feature activation | +7.66e+00 |
Pos logit contributions | |
reck | +9.495 |
idential | +9.256 |
Shore | +8.856 |
osher | +8.804 |
aren | +8.731 |
Neg logit contributions | |
countries | -8.704 |
analys | -8.675 |
physicists | -8.165 |
physicist | -8.140 |
scientist | -8.124 |
Token | LA |
Token ID | 9131 |
Feature activation | +7.68e+00 |
Pos logit contributions | |
idential | +5.926 |
reck | +5.860 |
Shore | +5.599 |
Pleasant | +5.509 |
osher | +5.462 |
Neg logit contributions | |
analys | -6.988 |
countries | -6.823 |
physicists | -6.524 |
scientist | -6.452 |
physicist | -6.445 |
Token | the |
Token ID | 262 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
idential | +6.517 |
reck | +6.495 |
osher | +6.159 |
Shore | +6.094 |
aren | +6.085 |
Neg logit contributions | |
countries | -4.536 |
analys | -4.519 |
researchers | -4.064 |
scientist | -4.049 |
physicists | -4.035 |
Token | intersection |
Token ID | 16246 |
Feature activation | +9.67e+00 |
Pos logit contributions | |
countries | +0.811 |
analys | +0.788 |
researchers | +0.761 |
scientist | +0.744 |
physicist | +0.741 |
Neg logit contributions | |
idential | -0.851 |
reck | -0.839 |
osher | -0.801 |
aren | -0.784 |
Reserved | -0.776 |
Token | of |
Token ID | 286 |
Feature activation | +1.52e+01 |
Pos logit contributions | |
reck | +8.535 |
idential | +8.481 |
Shore | +8.101 |
honoring | +8.039 |
Pleasant | +8.002 |
Neg logit contributions | |
analys | -7.360 |
countries | -7.334 |
scientist | -6.802 |
physicist | -6.785 |
physicists | -6.770 |
Token | Bl |
Token ID | 1086 |
Feature activation | +1.60e+01 |
Pos logit contributions | |
idential | +11.770 |
reck | +11.709 |
Shore | +11.699 |
Pleasant | +11.529 |
Reserved | +11.281 |
Neg logit contributions | |
analys | -12.410 |
countries | -11.899 |
physicists | -11.273 |
physicist | -11.159 |
scientist | -11.147 |
Token | oor |
Token ID | 2675 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
reck | +11.145 |
idential | +10.872 |
aren | +10.173 |
osher | +10.052 |
rict | +9.893 |
Neg logit contributions | |
analys | -15.244 |
countries | -14.841 |
physicists | -14.322 |
researchers | -14.146 |
physicist | -14.096 |
Token | St |
Token ID | 520 |
Feature activation | +2.51e+01 |
Pos logit contributions | |
reck | +9.242 |
idential | +9.086 |
Shore | +8.923 |
Pleasant | +8.508 |
Reserved | +8.419 |
Neg logit contributions | |
analys | -12.291 |
countries | -12.174 |
physicist | -11.419 |
physicists | -11.417 |
scientist | -11.260 |
Token | . |
Token ID | 13 |
Feature activation | +2.10e+01 |
Pos logit contributions | |
idential | +16.013 |
reck | +15.756 |
Shore | +15.282 |
aren | +15.187 |
rict | +15.127 |
Neg logit contributions | |
analys | -18.746 |
countries | -18.217 |
physicist | -17.765 |
physicists | -17.762 |
scientist | -17.305 |
Token | W |
Token ID | 370 |
Feature activation | +2.05e+01 |
Pos logit contributions | |
idential | +14.443 |
reck | +14.259 |
Shore | +14.242 |
Pleasant | +13.887 |
rict | +13.380 |
Neg logit contributions | |
analys | -16.189 |
countries | -15.949 |
physicist | -15.320 |
physicists | -15.293 |
scientist | -15.083 |
Token | . |
Token ID | 13 |
Feature activation | +1.84e+01 |
Pos logit contributions | |
reck | +14.274 |
idential | +13.810 |
aren | +13.181 |
Shore | +13.166 |
ouls | +12.670 |
Neg logit contributions | |
analys | -16.604 |
countries | -15.826 |
physicist | -15.510 |
physicists | -15.384 |
scientist | -15.159 |
Token | and |
Token ID | 290 |
Feature activation | +2.30e+01 |
Pos logit contributions | |
reck | +13.039 |
Shore | +12.966 |
idential | +12.904 |
Pleasant | +12.442 |
Reserved | +12.067 |
Neg logit contributions | |
analys | -14.794 |
countries | -14.440 |
physicist | -13.898 |
physicists | -13.856 |
scientist | -13.615 |
Token | Mill |
Token ID | 9212 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
Shore | +17.257 |
Pleasant | +16.930 |
idential | +16.142 |
Jefferson | +16.063 |
reck | +16.033 |
Neg logit contributions | |
analys | -16.335 |
countries | -15.541 |
physicists | -14.918 |
physicist | -14.738 |
regimes | -14.612 |
Token | the |
Token ID | 262 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
reck | +11.427 |
idential | +11.352 |
Shore | +11.019 |
Pleasant | +10.974 |
Reserved | +10.822 |
Neg logit contributions | |
analys | -10.439 |
countries | -10.233 |
physicists | -9.587 |
physicist | -9.457 |
scientist | -9.422 |
Token | corner |
Token ID | 5228 |
Feature activation | +6.58e+00 |
Pos logit contributions | |
reck | +11.589 |
idential | +11.418 |
Shore | +11.344 |
Pleasant | +11.200 |
Reserved | +11.154 |
Neg logit contributions | |
analys | -7.816 |
countries | -7.741 |
physicists | -6.988 |
physicist | -6.911 |
researchers | -6.901 |
Token | of |
Token ID | 286 |
Feature activation | +1.70e+01 |
Pos logit contributions | |
reck | +5.932 |
idential | +5.888 |
osher | +5.629 |
Pleasant | +5.609 |
Shore | +5.585 |
Neg logit contributions | |
analys | -5.139 |
countries | -5.049 |
physicist | -4.702 |
physicists | -4.680 |
scientist | -4.667 |
Token | West |
Token ID | 2688 |
Feature activation | +2.39e+01 |
Pos logit contributions | |
Shore | +12.857 |
Pleasant | +12.674 |
reck | +12.478 |
idential | +12.471 |
Reserved | +12.259 |
Neg logit contributions | |
analys | -13.838 |
countries | -13.172 |
physicists | -12.460 |
physicist | -12.286 |
experiments | -12.284 |
Token | heimer |
Token ID | 16288 |
Feature activation | +1.73e+01 |
Pos logit contributions | |
reck | +18.719 |
Shore | +18.508 |
Pleasant | +17.946 |
idential | +17.863 |
Jefferson | +17.207 |
Neg logit contributions | |
analys | -15.942 |
countries | -14.995 |
physicists | -14.400 |
regimes | -13.923 |
experiments | -13.854 |
Token | and |
Token ID | 290 |
Feature activation | +2.48e+01 |
Pos logit contributions | |
idential | +11.628 |
Shore | +11.579 |
reck | +11.536 |
Pleasant | +11.141 |
Reserved | +10.910 |
Neg logit contributions | |
analys | -14.945 |
countries | -14.267 |
physicists | -13.498 |
physicist | -13.364 |
experiments | -13.194 |
Token | Mont |
Token ID | 5575 |
Feature activation | +2.76e+01 |
Pos logit contributions | |
Shore | +18.564 |
Pleasant | +18.324 |
Jefferson | +17.444 |
Reserved | +17.217 |
idential | +16.851 |
Neg logit contributions | |
analys | -17.218 |
countries | -15.910 |
regimes | -15.080 |
physicists | -15.080 |
experiments | -14.929 |
Token | rose |
Token ID | 13698 |
Feature activation | +2.09e+01 |
Pos logit contributions | |
idential | +17.419 |
reck | +17.349 |
aren | +16.313 |
osher | +16.117 |
Pleasant | +16.078 |
Neg logit contributions | |
analys | -20.841 |
countries | -20.120 |
physicists | -19.236 |
physicist | -18.720 |
regimes | -18.583 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
idential | +17.662 |
Shore | +17.505 |
reck | +17.244 |
Pleasant | +17.145 |
honoring | +17.024 |
Neg logit contributions | |
analys | -12.748 |
countries | -11.513 |
physicist | -11.477 |
physicists | -11.261 |
scientist | -11.165 |
Token | I |
Token ID | 314 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
idential | +10.696 |
reck | +10.565 |
Reserved | +10.307 |
Shore | +10.257 |
Pleasant | +10.235 |
Neg logit contributions | |
analys | -9.212 |
countries | -9.097 |
physicists | -8.428 |
researchers | -8.292 |
experiments | -8.283 |
Token | know |
Token ID | 760 |
Feature activation | +8.83e+00 |
Pos logit contributions | |
idential | +4.417 |
reck | +4.395 |
osher | +4.228 |
Reserved | +4.133 |
aren | +4.123 |
Neg logit contributions | |
countries | -2.884 |
analys | -2.834 |
researchers | -2.630 |
scientist | -2.571 |
physicists | -2.565 |
Token | - |
Token ID | 12 |
Feature activation | -6.56e+00 |
Pos logit contributions | |
countries | +4.039 |
analys | +3.818 |
researchers | +3.714 |
physicists | +3.599 |
scientist | +3.577 |
Neg logit contributions | |
idential | -4.876 |
reck | -4.796 |
osher | -4.567 |
Reserved | -4.441 |
ouls | -4.435 |
Token | 10 |
Token ID | 940 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
countries | +5.960 |
analys | +5.744 |
researchers | +5.531 |
scientist | +5.437 |
physicists | +5.431 |
Neg logit contributions | |
idential | -5.256 |
reck | -5.051 |
osher | -4.898 |
Reserved | -4.850 |
Shore | -4.702 |
Token | brewers |
Token ID | 36669 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
countries | +3.119 |
analys | +2.921 |
researchers | +2.827 |
physicists | +2.716 |
experiments | +2.696 |
Neg logit contributions | |
idential | -5.117 |
reck | -5.059 |
osher | -4.875 |
rict | -4.722 |
idelines | -4.716 |
Token | now |
Token ID | 783 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
idential | +0.468 |
reck | +0.464 |
osher | +0.446 |
Reserved | +0.432 |
aren | +0.431 |
Neg logit contributions | |
countries | -0.362 |
analys | -0.357 |
researchers | -0.332 |
scientist | -0.325 |
physicists | -0.324 |
Token | in |
Token ID | 287 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
idential | +2.507 |
reck | +2.498 |
osher | +2.365 |
aren | +2.321 |
Reserved | +2.315 |
Neg logit contributions | |
countries | -2.371 |
analys | -2.341 |
researchers | -2.196 |
physicists | -2.164 |
scientist | -2.162 |
Token | H |
Token ID | 367 |
Feature activation | +2.48e+01 |
Pos logit contributions | |
idential | +4.124 |
reck | +4.110 |
osher | +3.892 |
Reserved | +3.837 |
aren | +3.835 |
Neg logit contributions | |
countries | -3.408 |
analys | -3.396 |
researchers | -3.156 |
physicists | -3.123 |
scientist | -3.117 |
Token | abling |
Token ID | 11716 |
Feature activation | +9.96e+00 |
Pos logit contributions | |
reck | +15.779 |
idential | +15.236 |
aren | +15.152 |
rict | +14.340 |
ibel | +14.109 |
Neg logit contributions | |
countries | -19.181 |
analys | -19.028 |
scientist | -18.658 |
physicists | -18.290 |
physicist | -18.260 |
Token | bo |
Token ID | 2127 |
Feature activation | +7.57e+00 |
Pos logit contributions | |
reck | +7.192 |
idential | +6.771 |
rict | +6.407 |
osher | +6.388 |
aren | +6.377 |
Neg logit contributions | |
analys | -9.306 |
countries | -9.095 |
physicists | -8.773 |
researchers | -8.744 |
physicist | -8.731 |
Token | , |
Token ID | 11 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
idential | +5.879 |
reck | +5.874 |
osher | +5.544 |
aren | +5.485 |
rict | +5.431 |
Neg logit contributions | |
analys | -6.804 |
countries | -6.759 |
physicists | -6.384 |
researchers | -6.376 |
physicist | -6.374 |
Token | he |
Token ID | 339 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
idential | +0.110 |
reck | +0.110 |
osher | +0.104 |
aren | +0.102 |
rict | +0.101 |
Neg logit contributions | |
countries | -0.092 |
analys | -0.090 |
researchers | -0.085 |
physicists | -0.083 |
scientist | -0.083 |
Token | says |
Token ID | 1139 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
countries | +8.930 |
analys | +8.822 |
experiments | +8.372 |
researchers | +8.211 |
scientist | +7.935 |
Neg logit contributions | |
idential | -12.520 |
reck | -12.361 |
osher | -12.250 |
Reserved | -11.573 |
unicip | -11.445 |
Token | addresses |
Token ID | 9405 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
idential | +4.955 |
reck | +4.934 |
osher | +4.698 |
aren | +4.606 |
Reserved | +4.606 |
Neg logit contributions | |
countries | -3.942 |
analys | -3.895 |
researchers | -3.621 |
physicists | -3.575 |
scientist | -3.567 |
Token | had |
Token ID | 550 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
idential | +10.511 |
reck | +10.422 |
aren | +9.960 |
rict | +9.869 |
Shore | +9.782 |
Neg logit contributions | |
countries | -8.806 |
analys | -8.756 |
physicists | -8.162 |
physicist | -8.134 |
scientist | -8.102 |
Token | such |
Token ID | 884 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
idential | +4.938 |
reck | +4.918 |
osher | +4.698 |
aren | +4.616 |
Reserved | +4.614 |
Neg logit contributions | |
countries | -3.328 |
analys | -3.283 |
researchers | -3.030 |
physicists | -2.977 |
scientist | -2.975 |
Token | a |
Token ID | 257 |
Feature activation | +2.19e+01 |
Pos logit contributions | |
reck | +12.674 |
idential | +12.661 |
Reserved | +12.017 |
rict | +11.971 |
Shore | +11.952 |
Neg logit contributions | |
analys | -8.556 |
countries | -8.168 |
physicist | -7.593 |
scientist | -7.587 |
physicists | -7.549 |
Token | long |
Token ID | 890 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
reck | +19.110 |
idential | +18.811 |
Shore | +18.209 |
Pleasant | +18.019 |
rict | +17.955 |
Neg logit contributions | |
analys | -13.046 |
countries | -12.667 |
physicists | -11.739 |
experiments | -11.694 |
researchers | -11.393 |
Token | and |
Token ID | 290 |
Feature activation | +2.48e+01 |
Pos logit contributions | |
idential | +12.370 |
reck | +12.175 |
Shore | +11.577 |
osher | +11.477 |
rict | +11.357 |
Neg logit contributions | |
analys | -10.661 |
countries | -10.624 |
physicists | -9.947 |
physicist | -9.823 |
researchers | -9.761 |
Token | st |
Token ID | 336 |
Feature activation | +1.73e+01 |
Pos logit contributions | |
idential | +20.379 |
reck | +20.248 |
Pleasant | +19.562 |
rict | +19.449 |
honoring | +19.424 |
Neg logit contributions | |
analys | -12.914 |
countries | -12.647 |
physicist | -12.400 |
physicists | -12.211 |
scientist | -11.731 |
Token | oried |
Token ID | 42058 |
Feature activation | +2.19e+01 |
Pos logit contributions | |
reck | +7.826 |
idential | +7.748 |
rict | +6.801 |
osher | +6.678 |
aren | +6.562 |
Neg logit contributions | |
countries | -20.210 |
analys | -20.169 |
physicists | -19.226 |
regimes | -18.895 |
experiments | -18.870 |
Token | history |
Token ID | 2106 |
Feature activation | +1.87e+01 |
Pos logit contributions | |
reck | +16.320 |
idential | +16.200 |
Shore | +15.914 |
Pleasant | +15.563 |
honoring | +15.454 |
Neg logit contributions | |
analys | -15.373 |
countries | -15.025 |
physicists | -14.337 |
physicist | -13.831 |
researchers | -13.719 |
Token | of |
Token ID | 286 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
reck | +14.184 |
honoring | +13.992 |
idential | +13.902 |
aren | +13.367 |
Shore | +13.317 |
Neg logit contributions | |
countries | -13.037 |
analys | -13.009 |
physicist | -12.291 |
scientist | -12.166 |
physicists | -12.134 |
Token | failure |
Token ID | 5287 |
Feature activation | +8.76e+00 |
Pos logit contributions | |
reck | +13.556 |
idential | +13.521 |
honoring | +12.908 |
Shore | +12.798 |
Reserved | +12.776 |
Neg logit contributions | |
analys | -8.348 |
countries | -8.294 |
physicist | -7.726 |
physicists | -7.638 |
scientist | -7.558 |
Token | , |
Token ID | 11 |
Feature activation | +1.72e+01 |
Pos logit contributions | |
idential | +8.472 |
reck | +8.356 |
Shore | +7.916 |
rict | +7.888 |
aren | +7.877 |
Neg logit contributions | |
analys | -9.027 |
countries | -8.896 |
physicist | -8.398 |
scientist | -8.369 |
physicists | -8.319 |
Token | Z |
Token ID | 1168 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
idential | +15.807 |
Shore | +15.125 |
reck | +15.107 |
Reserved | +15.067 |
Pleasant | +14.802 |
Neg logit contributions | |
analys | -11.123 |
countries | -10.969 |
physicists | -10.360 |
scientist | -10.305 |
physicist | -10.260 |
Token | oning |
Token ID | 12484 |
Feature activation | +9.37e+00 |
Pos logit contributions | |
idential | +6.771 |
reck | +6.641 |
osher | +6.068 |
aren | +5.927 |
rict | +5.912 |
Neg logit contributions | |
analys | -13.778 |
countries | -13.639 |
researchers | -13.041 |
scientist | -12.957 |
physicists | -12.941 |
Token | for |
Token ID | 329 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
idential | +8.226 |
reck | +8.133 |
osher | +7.711 |
Reserved | +7.697 |
Shore | +7.619 |
Neg logit contributions | |
analys | -7.713 |
countries | -7.669 |
physicists | -7.115 |
researchers | -7.068 |
scientist | -7.047 |
Token | Quality |
Token ID | 14156 |
Feature activation | +5.37e+00 |
Pos logit contributions | |
idential | +9.821 |
reck | +9.582 |
Reserved | +9.215 |
Shore | +9.191 |
Pleasant | +9.063 |
Neg logit contributions | |
analys | -8.967 |
countries | -8.772 |
physicists | -8.252 |
physicist | -8.233 |
scientist | -8.206 |
Token | and |
Token ID | 290 |
Feature activation | +2.47e+01 |
Pos logit contributions | |
idential | +4.373 |
reck | +4.307 |
osher | +4.064 |
Reserved | +4.006 |
aren | +3.989 |
Neg logit contributions | |
analys | -4.925 |
countries | -4.916 |
researchers | -4.589 |
physicists | -4.570 |
scientist | -4.562 |
Token | Aff |
Token ID | 6708 |
Feature activation | +1.93e+01 |
Pos logit contributions | |
idential | +20.069 |
Reserved | +19.666 |
Pleasant | +19.461 |
Shore | +19.375 |
reck | +18.673 |
Neg logit contributions | |
analys | -15.212 |
countries | -14.521 |
physicists | -13.997 |
physicist | -13.797 |
scientist | -13.354 |
Token | ord |
Token ID | 585 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
idential | +10.077 |
reck | +8.645 |
aren | +8.274 |
erved | +8.097 |
rict | +7.878 |
Neg logit contributions | |
analys | -21.479 |
countries | -20.794 |
physicists | -20.360 |
physicist | -20.152 |
scientist | -20.124 |
Token | ability |
Token ID | 1799 |
Feature activation | +5.96e+00 |
Pos logit contributions | |
idential | +3.108 |
reck | +3.072 |
osher | +2.848 |
aren | +2.801 |
Reserved | +2.776 |
Neg logit contributions | |
countries | -4.737 |
analys | -4.727 |
researchers | -4.456 |
physicists | -4.443 |
physicist | -4.428 |
Token | , |
Token ID | 11 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
idential | +4.669 |
reck | +4.586 |
osher | +4.296 |
Reserved | +4.277 |
aren | +4.242 |
Neg logit contributions | |
analys | -5.617 |
countries | -5.548 |
physicists | -5.230 |
scientist | -5.217 |
physicist | -5.205 |
Token | would |
Token ID | 561 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
idential | +2.999 |
reck | +2.987 |
osher | +2.833 |
aren | +2.773 |
Reserved | +2.768 |
Neg logit contributions | |
countries | -2.805 |
analys | -2.769 |
researchers | -2.596 |
physicists | -2.555 |
scientist | -2.554 |
Token | . |
Token ID | 13 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
idential | +5.609 |
reck | +5.548 |
osher | +5.206 |
aren | +5.160 |
Shore | +5.131 |
Neg logit contributions | |
analys | -6.537 |
countries | -6.535 |
researchers | -6.072 |
physicists | -6.065 |
physicist | -6.045 |
Token |
|
Token ID | 198 |
Feature activation | +6.60e+00 |
Pos logit contributions | |
idential | +0.585 |
reck | +0.579 |
osher | +0.556 |
Reserved | +0.551 |
aren | +0.548 |
Neg logit contributions | |
analys | -0.462 |
countries | -0.460 |
researchers | -0.422 |
physicists | -0.420 |
physicist | -0.418 |
Token |
|
Token ID | 198 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
reck | +6.377 |
idential | +6.356 |
aren | +5.976 |
osher | +5.965 |
Reserved | +5.945 |
Neg logit contributions | |
analys | -4.986 |
countries | -4.966 |
physicists | -4.545 |
researchers | -4.538 |
physicist | -4.511 |
Token | 27 |
Token ID | 1983 |
Feature activation | +9.06e+00 |
Pos logit contributions | |
reck | +8.416 |
idential | +8.180 |
aren | +7.649 |
Reserved | +7.608 |
osher | +7.504 |
Neg logit contributions | |
analys | -12.535 |
countries | -12.131 |
physicists | -11.400 |
physicist | -11.346 |
researchers | -11.346 |
Token | 10 |
Token ID | 940 |
Feature activation | +2.08e+01 |
Pos logit contributions | |
idential | +6.418 |
reck | +6.362 |
Shore | +6.008 |
Reserved | +6.002 |
osher | +5.892 |
Neg logit contributions | |
analys | -8.962 |
countries | -8.786 |
physicists | -8.325 |
researchers | -8.270 |
physicist | -8.259 |
Token | Mont |
Token ID | 5575 |
Feature activation | +2.44e+01 |
Pos logit contributions | |
Shore | +15.329 |
Pleasant | +15.245 |
idential | +14.670 |
Reserved | +14.669 |
reck | +14.592 |
Neg logit contributions | |
analys | -16.501 |
countries | -15.358 |
physicists | -14.739 |
experiments | -14.455 |
regimes | -14.394 |
Token | rose |
Token ID | 13698 |
Feature activation | +1.44e+01 |
Pos logit contributions | |
idential | +16.417 |
reck | +16.332 |
Pleasant | +15.385 |
osher | +15.281 |
aren | +15.213 |
Neg logit contributions | |
analys | -19.579 |
countries | -19.146 |
physicists | -18.169 |
physicist | -17.606 |
researchers | -17.565 |
Token | Today |
Token ID | 6288 |
Feature activation | +6.55e+00 |
Pos logit contributions | |
idential | +12.792 |
reck | +12.703 |
Shore | +12.597 |
Reserved | +12.395 |
Pleasant | +12.264 |
Neg logit contributions | |
analys | -10.453 |
countries | -9.888 |
physicists | -9.312 |
experiments | -9.145 |
researchers | -9.083 |
Token | : |
Token ID | 25 |
Feature activation | +1.92e+01 |
Pos logit contributions | |
idential | +5.691 |
reck | +5.667 |
osher | +5.365 |
aren | +5.247 |
Reserved | +5.236 |
Neg logit contributions | |
countries | -5.704 |
analys | -5.631 |
researchers | -5.294 |
physicists | -5.212 |
scientist | -5.212 |
Token | BB |
Token ID | 12597 |
Feature activation | +8.38e+00 |
Pos logit contributions | |
Shore | +14.726 |
Pleasant | +14.589 |
Reserved | +14.508 |
reck | +14.452 |
idential | +14.325 |
Neg logit contributions | |
analys | -14.560 |
countries | -13.926 |
physicists | -13.078 |
experiments | -12.889 |
regimes | -12.832 |
Token | 's |
Token ID | 338 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
reck | +6.709 |
idential | +6.611 |
osher | +6.260 |
aren | +6.191 |
Reserved | +6.092 |
Neg logit contributions | |
analys | -7.649 |
countries | -7.607 |
researchers | -7.119 |
physicists | -7.048 |
physicist | -7.021 |
Token | of |
Token ID | 286 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
idential | +10.485 |
reck | +10.428 |
Shore | +10.049 |
Pleasant | +9.956 |
ouls | +9.820 |
Neg logit contributions | |
analys | -8.572 |
countries | -8.182 |
physicist | -7.645 |
physicists | -7.496 |
scientist | -7.468 |
Token | Battery |
Token ID | 23490 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
reck | +11.057 |
idential | +11.054 |
Shore | +10.668 |
Pleasant | +10.625 |
osher | +10.477 |
Neg logit contributions | |
analys | -9.735 |
countries | -9.439 |
physicists | -8.725 |
physicist | -8.689 |
researchers | -8.576 |
Token | Park |
Token ID | 3250 |
Feature activation | +1.85e+01 |
Pos logit contributions | |
idential | +6.483 |
reck | +6.199 |
Shore | +6.136 |
Reserved | +6.020 |
Pleasant | +5.956 |
Neg logit contributions | |
analys | -17.919 |
countries | -17.447 |
physicists | -16.621 |
physicist | -16.484 |
researchers | -16.482 |
Token | 's |
Token ID | 338 |
Feature activation | +2.44e+01 |
Pos logit contributions | |
idential | +14.837 |
reck | +14.394 |
Shore | +14.233 |
Pleasant | +13.922 |
Reserved | +13.798 |
Neg logit contributions | |
analys | -13.401 |
countries | -12.517 |
physicists | -11.453 |
physicist | -11.357 |
experiments | -11.239 |
Token | beauty |
Token ID | 8737 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
Shore | +21.160 |
reck | +21.125 |
Pleasant | +21.100 |
idential | +20.964 |
honoring | +20.504 |
Neg logit contributions | |
analys | -12.655 |
countries | -11.500 |
physicists | -10.503 |
alyst | -10.350 |
physicist | -10.274 |
Token | and |
Token ID | 290 |
Feature activation | +2.44e+01 |
Pos logit contributions | |
idential | +4.070 |
reck | +4.058 |
osher | +3.799 |
aren | +3.737 |
Reserved | +3.726 |
Neg logit contributions | |
countries | -4.774 |
analys | -4.773 |
researchers | -4.455 |
physicists | -4.417 |
physicist | -4.399 |
Token | they |
Token ID | 484 |
Feature activation | +8.64e+00 |
Pos logit contributions | |
idential | +21.281 |
Pleasant | +21.230 |
reck | +21.088 |
Shore | +21.065 |
honoring | +20.987 |
Neg logit contributions | |
analys | -12.671 |
countries | -11.578 |
ッド | -10.550 |
physicists | -10.463 |
regimes | -10.421 |
Token | regularly |
Token ID | 7987 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
reck | +8.353 |
idential | +8.344 |
aren | +7.880 |
osher | +7.868 |
rict | +7.818 |
Neg logit contributions | |
analys | -6.233 |
countries | -6.219 |
researchers | -5.670 |
physicist | -5.652 |
physicists | -5.626 |
Token | find |
Token ID | 1064 |
Feature activation | +5.87e+00 |
Pos logit contributions | |
reck | +11.274 |
idential | +11.225 |
osher | +10.742 |
Shore | +10.695 |
aren | +10.646 |
Neg logit contributions | |
analys | -7.276 |
countries | -7.243 |
physicist | -6.550 |
physicists | -6.545 |
researchers | -6.507 |
Token | rare |
Token ID | 4071 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
idential | +6.205 |
reck | +6.201 |
osher | +5.916 |
Reserved | +5.837 |
aren | +5.821 |
Neg logit contributions | |
countries | -3.889 |
analys | -3.863 |
researchers | -3.517 |
physicists | -3.474 |
physicist | -3.472 |
Token | Pokémon |
Token ID | 9887 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
idential | +1.429 |
reck | +1.421 |
osher | +1.363 |
aren | +1.335 |
Reserved | +1.332 |
Neg logit contributions | |
countries | -0.960 |
analys | -0.927 |
researchers | -0.876 |
scientist | -0.856 |
experiments | -0.850 |
Token | Castle |
Token ID | 11312 |
Feature activation | +1.68e+01 |
Pos logit contributions | |
idential | +5.810 |
reck | +5.782 |
Shore | +5.368 |
aren | +5.304 |
rict | +5.299 |
Neg logit contributions | |
analys | -16.714 |
countries | -16.086 |
physicists | -15.596 |
physicist | -15.505 |
scientist | -15.424 |
Token | because |
Token ID | 780 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
idential | +13.541 |
reck | +13.410 |
Shore | +13.013 |
Reserved | +12.699 |
Pleasant | +12.677 |
Neg logit contributions | |
analys | -12.810 |
countries | -12.086 |
physicist | -11.232 |
physicists | -11.173 |
experiments | -11.092 |
Token | of |
Token ID | 286 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
idential | +10.485 |
reck | +10.428 |
Shore | +10.049 |
Pleasant | +9.956 |
ouls | +9.820 |
Neg logit contributions | |
analys | -8.572 |
countries | -8.182 |
physicist | -7.645 |
physicists | -7.496 |
scientist | -7.468 |
Token | Battery |
Token ID | 23490 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
reck | +11.057 |
idential | +11.054 |
Shore | +10.668 |
Pleasant | +10.625 |
osher | +10.477 |
Neg logit contributions | |
analys | -9.735 |
countries | -9.439 |
physicists | -8.725 |
physicist | -8.689 |
researchers | -8.576 |
Token | Park |
Token ID | 3250 |
Feature activation | +1.85e+01 |
Pos logit contributions | |
idential | +6.483 |
reck | +6.199 |
Shore | +6.136 |
Reserved | +6.020 |
Pleasant | +5.956 |
Neg logit contributions | |
analys | -17.919 |
countries | -17.447 |
physicists | -16.621 |
physicist | -16.484 |
researchers | -16.482 |
Token | 's |
Token ID | 338 |
Feature activation | +2.44e+01 |
Pos logit contributions | |
idential | +14.837 |
reck | +14.394 |
Shore | +14.233 |
Pleasant | +13.922 |
Reserved | +13.798 |
Neg logit contributions | |
analys | -13.401 |
countries | -12.517 |
physicists | -11.453 |
physicist | -11.357 |
experiments | -11.239 |
Token | beauty |
Token ID | 8737 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
Shore | +21.160 |
reck | +21.125 |
Pleasant | +21.100 |
idential | +20.964 |
honoring | +20.504 |
Neg logit contributions | |
analys | -12.655 |
countries | -11.500 |
physicists | -10.503 |
alyst | -10.350 |
physicist | -10.274 |
Token | and |
Token ID | 290 |
Feature activation | +2.44e+01 |
Pos logit contributions | |
idential | +4.070 |
reck | +4.058 |
osher | +3.799 |
aren | +3.737 |
Reserved | +3.726 |
Neg logit contributions | |
countries | -4.774 |
analys | -4.773 |
researchers | -4.455 |
physicists | -4.417 |
physicist | -4.399 |
Token | they |
Token ID | 484 |
Feature activation | +8.64e+00 |
Pos logit contributions | |
idential | +21.281 |
Pleasant | +21.230 |
reck | +21.088 |
Shore | +21.065 |
honoring | +20.987 |
Neg logit contributions | |
analys | -12.671 |
countries | -11.578 |
ッド | -10.550 |
physicists | -10.463 |
regimes | -10.421 |
Token | regularly |
Token ID | 7987 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
reck | +8.353 |
idential | +8.344 |
aren | +7.880 |
osher | +7.868 |
rict | +7.818 |
Neg logit contributions | |
analys | -6.233 |
countries | -6.219 |
researchers | -5.670 |
physicist | -5.652 |
physicists | -5.626 |
Token | find |
Token ID | 1064 |
Feature activation | +5.87e+00 |
Pos logit contributions | |
reck | +11.274 |
idential | +11.225 |
osher | +10.742 |
Shore | +10.695 |
aren | +10.646 |
Neg logit contributions | |
analys | -7.276 |
countries | -7.243 |
physicist | -6.550 |
physicists | -6.545 |
researchers | -6.507 |
Token | to |
Token ID | 284 |
Feature activation | +8.87e+00 |
Pos logit contributions | |
idential | +3.310 |
reck | +3.294 |
osher | +3.124 |
rict | +3.113 |
aren | +3.095 |
Neg logit contributions | |
countries | -2.087 |
analys | -2.075 |
physicists | -1.883 |
researchers | -1.881 |
physicist | -1.878 |
Token | use |
Token ID | 779 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
idential | +8.793 |
reck | +8.678 |
osher | +8.226 |
rict | +8.215 |
aren | +8.154 |
Neg logit contributions | |
analys | -6.135 |
countries | -6.132 |
physicist | -5.534 |
researchers | -5.516 |
physicists | -5.510 |
Token | a |
Token ID | 257 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
idential | +11.075 |
reck | +10.915 |
rict | +10.416 |
Reserved | +10.395 |
osher | +10.301 |
Neg logit contributions | |
analys | -7.380 |
countries | -7.289 |
physicists | -6.654 |
physicist | -6.564 |
scientist | -6.472 |
Token | " |
Token ID | 366 |
Feature activation | +1.85e+01 |
Pos logit contributions | |
idential | +14.109 |
reck | +13.837 |
osher | +13.269 |
Reserved | +13.170 |
Shore | +13.099 |
Neg logit contributions | |
countries | -8.530 |
analys | -8.446 |
physicists | -7.723 |
experiments | -7.514 |
researchers | -7.468 |
Token | clear |
Token ID | 20063 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
reck | +15.395 |
idential | +14.584 |
aren | +13.812 |
rict | +13.457 |
osher | +13.315 |
Neg logit contributions | |
analys | -14.008 |
countries | -13.794 |
physicists | -12.977 |
physicist | -12.672 |
experiments | -12.638 |
Token | and |
Token ID | 290 |
Feature activation | +2.43e+01 |
Pos logit contributions | |
idential | +14.372 |
reck | +13.950 |
rict | +13.197 |
aren | +13.191 |
osher | +13.152 |
Neg logit contributions | |
countries | -8.700 |
analys | -8.614 |
physicists | -7.990 |
researchers | -7.815 |
experiments | -7.648 |
Token | convincing |
Token ID | 17101 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
idential | +19.792 |
reck | +19.457 |
ufficient | +19.089 |
rict | +19.020 |
Pleasant | +18.810 |
Neg logit contributions | |
countries | -13.685 |
analys | -13.427 |
enegger | -12.947 |
physicists | -12.874 |
physicist | -12.692 |
Token | evidence |
Token ID | 2370 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
idential | +14.237 |
reck | +13.879 |
aren | +13.266 |
rict | +13.199 |
osher | +13.050 |
Neg logit contributions | |
countries | -8.090 |
analys | -8.055 |
physicists | -7.386 |
researchers | -7.163 |
experiments | -7.060 |
Token | " |
Token ID | 1 |
Feature activation | +5.35e+00 |
Pos logit contributions | |
idential | +4.983 |
reck | +4.921 |
osher | +4.628 |
aren | +4.584 |
rict | +4.575 |
Neg logit contributions | |
countries | -4.823 |
analys | -4.758 |
researchers | -4.460 |
physicists | -4.451 |
physicist | -4.419 |
Token | standard |
Token ID | 3210 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
idential | +5.642 |
reck | +5.609 |
osher | +5.352 |
aren | +5.280 |
rict | +5.271 |
Neg logit contributions | |
countries | -3.600 |
analys | -3.539 |
researchers | -3.249 |
physicists | -3.217 |
physicist | -3.204 |
Token | in |
Token ID | 287 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
idential | +2.812 |
reck | +2.801 |
osher | +2.677 |
aren | +2.621 |
Reserved | +2.620 |
Neg logit contributions | |
countries | -2.013 |
analys | -1.983 |
researchers | -1.844 |
physicists | -1.802 |
scientist | -1.802 |
Token | on |
Token ID | 319 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
countries | +1.360 |
analys | +1.299 |
researchers | +1.260 |
scientist | +1.233 |
example | +1.225 |
Neg logit contributions | |
idential | -1.713 |
reck | -1.704 |
osher | -1.615 |
Reserved | -1.591 |
aren | -1.583 |
Token | . |
Token ID | 13 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
idential | +0.606 |
reck | +0.602 |
osher | +0.572 |
Reserved | +0.561 |
aren | +0.559 |
Neg logit contributions | |
countries | -0.463 |
analys | -0.451 |
researchers | -0.426 |
scientist | -0.416 |
example | -0.414 |
Token |
|
Token ID | 198 |
Feature activation | +6.74e+00 |
Pos logit contributions | |
reck | +2.824 |
idential | +2.823 |
osher | +2.684 |
rict | +2.623 |
aren | +2.623 |
Neg logit contributions | |
countries | -2.161 |
analys | -2.114 |
researchers | -1.987 |
scientist | -1.948 |
physicist | -1.939 |
Token |
|
Token ID | 198 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
reck | +6.470 |
idential | +6.454 |
aren | +6.073 |
osher | +6.039 |
rict | +6.031 |
Neg logit contributions | |
analys | -5.141 |
countries | -5.107 |
physicists | -4.686 |
researchers | -4.667 |
physicist | -4.643 |
Token | 43 |
Token ID | 3559 |
Feature activation | +1.35e+01 |
Pos logit contributions | |
reck | +9.466 |
idential | +9.331 |
aren | +8.735 |
osher | +8.687 |
Reserved | +8.552 |
Neg logit contributions | |
analys | -11.482 |
countries | -11.142 |
physicists | -10.397 |
physicist | -10.307 |
researchers | -10.241 |
Token | 15 |
Token ID | 1314 |
Feature activation | +2.43e+01 |
Pos logit contributions | |
idential | +9.718 |
reck | +9.555 |
Shore | +9.335 |
Reserved | +9.223 |
Pleasant | +9.173 |
Neg logit contributions | |
analys | -12.495 |
countries | -12.017 |
physicists | -11.445 |
physicist | -11.363 |
experiments | -11.339 |
Token | Mont |
Token ID | 5575 |
Feature activation | +2.14e+01 |
Pos logit contributions | |
Shore | +17.891 |
Pleasant | +17.870 |
Reserved | +17.128 |
idential | +16.935 |
Jefferson | +16.859 |
Neg logit contributions | |
analys | -17.537 |
countries | -16.125 |
physicists | -15.485 |
regimes | -15.310 |
experiments | -15.202 |
Token | rose |
Token ID | 13698 |
Feature activation | +1.99e+01 |
Pos logit contributions | |
idential | +15.733 |
reck | +15.428 |
Pleasant | +14.721 |
aren | +14.410 |
Shore | +14.308 |
Neg logit contributions | |
analys | -17.129 |
countries | -16.771 |
physicists | -15.987 |
researchers | -15.609 |
physicist | -15.543 |
Token | Today |
Token ID | 6288 |
Feature activation | +6.87e+00 |
Pos logit contributions | |
idential | +14.095 |
Shore | +14.066 |
reck | +13.999 |
Pleasant | +13.854 |
Reserved | +13.740 |
Neg logit contributions | |
analys | -16.045 |
countries | -15.415 |
physicists | -14.543 |
experiments | -14.395 |
physicist | -14.246 |
Token | : |
Token ID | 25 |
Feature activation | +2.06e+01 |
Pos logit contributions | |
idential | +5.020 |
reck | +4.919 |
Reserved | +4.616 |
osher | +4.606 |
Shore | +4.562 |
Neg logit contributions | |
analys | -6.651 |
countries | -6.481 |
physicists | -6.136 |
physicist | -6.091 |
experiments | -6.042 |
Token | Brass |
Token ID | 32309 |
Feature activation | +6.42e+00 |
Pos logit contributions | |
Shore | +15.810 |
Pleasant | +15.622 |
Reserved | +15.553 |
idential | +15.388 |
reck | +15.385 |
Neg logit contributions | |
analys | -14.908 |
countries | -14.158 |
physicists | -13.345 |
experiments | -13.089 |
regimes | -13.029 |
Token | own |
Token ID | 593 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
idential | +7.925 |
reck | +7.794 |
aren | +7.043 |
rict | +7.043 |
osher | +6.966 |
Neg logit contributions | |
analys | -19.233 |
countries | -18.700 |
physicists | -18.064 |
physicist | -17.873 |
scientist | -17.857 |
Token | construction |
Token ID | 5103 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
reck | +12.061 |
idential | +12.034 |
osher | +11.587 |
Shore | +11.536 |
Pleasant | +11.439 |
Neg logit contributions | |
analys | -9.279 |
countries | -9.210 |
physicists | -8.451 |
researchers | -8.394 |
experiments | -8.348 |
Token | site |
Token ID | 2524 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
countries | +2.939 |
analys | +2.914 |
researchers | +2.723 |
scientist | +2.692 |
example | +2.663 |
Neg logit contributions | |
idential | -4.711 |
reck | -4.621 |
ouls | -4.483 |
osher | -4.474 |
Reserved | -4.442 |
Token | at |
Token ID | 379 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
idential | +5.174 |
reck | +5.154 |
osher | +4.874 |
aren | +4.778 |
rict | +4.773 |
Neg logit contributions | |
countries | -4.690 |
analys | -4.622 |
researchers | -4.322 |
physicists | -4.275 |
scientist | -4.261 |
Token | Sixth |
Token ID | 28980 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
idential | +1.643 |
reck | +1.639 |
osher | +1.567 |
aren | +1.538 |
Reserved | +1.533 |
Neg logit contributions | |
countries | -1.153 |
analys | -1.132 |
researchers | -1.052 |
scientist | -1.028 |
physicists | -1.028 |
Token | and |
Token ID | 290 |
Feature activation | +2.42e+01 |
Pos logit contributions | |
idential | +7.023 |
reck | +6.926 |
Shore | +6.449 |
osher | +6.396 |
aren | +6.340 |
Neg logit contributions | |
analys | -9.916 |
countries | -9.758 |
physicists | -9.320 |
researchers | -9.285 |
physicist | -9.202 |
Token | Monroe |
Token ID | 26249 |
Feature activation | +1.80e+01 |
Pos logit contributions | |
Shore | +17.989 |
Pleasant | +17.979 |
Jefferson | +16.954 |
Reserved | +16.916 |
idential | +16.814 |
Neg logit contributions | |
analys | -17.209 |
countries | -15.879 |
physicists | -15.646 |
physicist | -15.281 |
scientist | -15.174 |
Token | streets |
Token ID | 6483 |
Feature activation | +9.22e+00 |
Pos logit contributions | |
idential | +15.200 |
reck | +14.853 |
Shore | +14.674 |
Pleasant | +14.212 |
Reserved | +14.077 |
Neg logit contributions | |
analys | -12.378 |
countries | -11.700 |
physicist | -11.606 |
physicists | -11.453 |
scientist | -11.351 |
Token | when |
Token ID | 618 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
idential | +8.105 |
reck | +8.026 |
osher | +7.532 |
rict | +7.492 |
Shore | +7.488 |
Neg logit contributions | |
countries | -7.485 |
analys | -7.421 |
physicists | -6.925 |
physicist | -6.896 |
researchers | -6.874 |
Token | he |
Token ID | 339 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
idential | +0.769 |
reck | +0.767 |
osher | +0.733 |
aren | +0.718 |
Reserved | +0.717 |
Neg logit contributions | |
countries | -0.612 |
analys | -0.601 |
researchers | -0.565 |
scientist | -0.552 |
physicists | -0.552 |
Token | was |
Token ID | 373 |
Feature activation | -7.26e+00 |
Pos logit contributions | |
idential | +1.101 |
reck | +1.092 |
osher | +1.059 |
aren | +1.025 |
Reserved | +1.024 |
Neg logit contributions | |
countries | -1.067 |
analys | -1.042 |
researchers | -0.995 |
scientist | -0.972 |
physicists | -0.969 |
Token | I |
Token ID | 314 |
Feature activation | +6.43e+00 |
Pos logit contributions | |
idential | +7.683 |
reck | +7.623 |
aren | +7.100 |
Reserved | +7.096 |
Shore | +7.093 |
Neg logit contributions | |
countries | -7.429 |
analys | -7.319 |
researchers | -6.783 |
physicists | -6.754 |
scientist | -6.733 |
Token | found |
Token ID | 1043 |
Feature activation | +1.31e+01 |
Pos logit contributions | |
reck | +6.170 |
idential | +6.165 |
osher | +5.814 |
aren | +5.762 |
Reserved | +5.745 |
Neg logit contributions | |
countries | -4.913 |
analys | -4.845 |
researchers | -4.504 |
physicists | -4.442 |
physicist | -4.441 |
Token | his |
Token ID | 465 |
Feature activation | +8.06e+00 |
Pos logit contributions | |
reck | +11.916 |
idential | +11.782 |
Shore | +11.229 |
Pleasant | +11.223 |
Reserved | +11.192 |
Neg logit contributions | |
analys | -9.022 |
countries | -8.910 |
physicists | -8.186 |
researchers | -8.125 |
physicist | -8.071 |
Token | style |
Token ID | 3918 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
reck | +8.312 |
idential | +8.283 |
osher | +7.831 |
aren | +7.813 |
Reserved | +7.805 |
Neg logit contributions | |
countries | -5.327 |
analys | -5.319 |
researchers | -4.841 |
physicists | -4.797 |
physicist | -4.755 |
Token | cold |
Token ID | 4692 |
Feature activation | +8.02e+00 |
Pos logit contributions | |
reck | +12.765 |
idential | +12.229 |
rict | +11.907 |
Pleasant | +11.782 |
Shore | +11.780 |
Neg logit contributions | |
countries | -9.294 |
analys | -9.205 |
physicist | -8.598 |
physicists | -8.542 |
researchers | -8.482 |
Token | and |
Token ID | 290 |
Feature activation | +2.42e+01 |
Pos logit contributions | |
reck | +6.448 |
idential | +6.381 |
osher | +6.004 |
aren | +5.998 |
rict | +5.969 |
Neg logit contributions | |
countries | -7.067 |
analys | -6.985 |
researchers | -6.597 |
physicists | -6.565 |
physicist | -6.539 |
Token | stiff |
Token ID | 15175 |
Feature activation | +9.88e+00 |
Pos logit contributions | |
reck | +20.393 |
Shore | +19.454 |
idential | +19.342 |
Reserved | +19.325 |
rict | +19.021 |
Neg logit contributions | |
countries | -12.594 |
analys | -12.338 |
physicist | -11.572 |
physicists | -11.519 |
enegger | -11.011 |
Token | , |
Token ID | 11 |
Feature activation | +7.18e+00 |
Pos logit contributions | |
idential | +7.824 |
reck | +7.670 |
rict | +7.352 |
aren | +7.330 |
osher | +7.223 |
Neg logit contributions | |
countries | -8.455 |
analys | -8.338 |
physicist | -7.940 |
physicists | -7.931 |
researchers | -7.913 |
Token | especially |
Token ID | 2592 |
Feature activation | +6.68e+00 |
Pos logit contributions | |
reck | +6.725 |
idential | +6.693 |
osher | +6.297 |
aren | +6.272 |
Reserved | +6.261 |
Neg logit contributions | |
countries | -5.447 |
analys | -5.341 |
researchers | -4.993 |
physicists | -4.957 |
physicist | -4.947 |
Token | in |
Token ID | 287 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
reck | +6.168 |
idential | +6.164 |
osher | +5.831 |
Reserved | +5.761 |
aren | +5.760 |
Neg logit contributions | |
countries | -5.244 |
analys | -5.169 |
researchers | -4.839 |
physicists | -4.781 |
scientist | -4.773 |
Token | earlier |
Token ID | 2961 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
idential | +3.762 |
reck | +3.750 |
osher | +3.577 |
aren | +3.523 |
Reserved | +3.521 |
Neg logit contributions | |
countries | -2.462 |
analys | -2.434 |
researchers | -2.248 |
physicists | -2.212 |
scientist | -2.203 |
Token | . |
Token ID | 13 |
Feature activation | +2.10e+01 |
Pos logit contributions | |
idential | +16.013 |
reck | +15.756 |
Shore | +15.282 |
aren | +15.187 |
rict | +15.127 |
Neg logit contributions | |
analys | -18.746 |
countries | -18.217 |
physicist | -17.765 |
physicists | -17.762 |
scientist | -17.305 |
Token | W |
Token ID | 370 |
Feature activation | +2.05e+01 |
Pos logit contributions | |
idential | +14.443 |
reck | +14.259 |
Shore | +14.242 |
Pleasant | +13.887 |
rict | +13.380 |
Neg logit contributions | |
analys | -16.189 |
countries | -15.949 |
physicist | -15.320 |
physicists | -15.293 |
scientist | -15.083 |
Token | . |
Token ID | 13 |
Feature activation | +1.84e+01 |
Pos logit contributions | |
reck | +14.274 |
idential | +13.810 |
aren | +13.181 |
Shore | +13.166 |
ouls | +12.670 |
Neg logit contributions | |
analys | -16.604 |
countries | -15.826 |
physicist | -15.510 |
physicists | -15.384 |
scientist | -15.159 |
Token | and |
Token ID | 290 |
Feature activation | +2.30e+01 |
Pos logit contributions | |
reck | +13.039 |
Shore | +12.966 |
idential | +12.904 |
Pleasant | +12.442 |
Reserved | +12.067 |
Neg logit contributions | |
analys | -14.794 |
countries | -14.440 |
physicist | -13.898 |
physicists | -13.856 |
scientist | -13.615 |
Token | Mill |
Token ID | 9212 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
Shore | +17.257 |
Pleasant | +16.930 |
idential | +16.142 |
Jefferson | +16.063 |
reck | +16.033 |
Neg logit contributions | |
analys | -16.335 |
countries | -15.541 |
physicists | -14.918 |
physicist | -14.738 |
regimes | -14.612 |
Token | Rd |
Token ID | 20769 |
Feature activation | +2.41e+01 |
Pos logit contributions | |
idential | +9.893 |
reck | +9.873 |
Shore | +9.393 |
aren | +9.185 |
osher | +9.043 |
Neg logit contributions | |
analys | -12.629 |
countries | -12.384 |
physicists | -11.809 |
physicist | -11.636 |
researchers | -11.567 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e+01 |
Pos logit contributions | |
reck | +14.284 |
idential | +14.153 |
Shore | +14.103 |
aren | +14.071 |
Pleasant | +13.831 |
Neg logit contributions | |
analys | -18.433 |
countries | -17.556 |
physicist | -17.151 |
physicists | -17.110 |
scientist | -16.767 |
Token | in |
Token ID | 287 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
idential | +14.201 |
reck | +14.074 |
Shore | +13.788 |
Pleasant | +13.471 |
Reserved | +13.463 |
Neg logit contributions | |
analys | -11.832 |
countries | -11.775 |
physicist | -11.035 |
physicists | -10.907 |
scientist | -10.903 |
Token | Et |
Token ID | 17906 |
Feature activation | +1.55e+01 |
Pos logit contributions | |
reck | +10.262 |
idential | +10.212 |
Shore | +9.961 |
Pleasant | +9.832 |
Reserved | +9.545 |
Neg logit contributions | |
analys | -9.972 |
countries | -9.901 |
physicists | -9.216 |
physicist | -9.202 |
scientist | -9.153 |
Token | obic |
Token ID | 20803 |
Feature activation | +7.43e+00 |
Pos logit contributions | |
reck | +11.039 |
idential | +10.641 |
iquette | +10.425 |
osher | +10.234 |
ouls | +9.940 |
Neg logit contributions | |
analys | -14.293 |
countries | -14.259 |
physicists | -13.534 |
scientist | -13.329 |
researchers | -13.310 |
Token | oke |
Token ID | 2088 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
idential | +3.816 |
reck | +3.792 |
osher | +3.425 |
aren | +3.340 |
rict | +3.332 |
Neg logit contributions | |
countries | -9.051 |
analys | -8.961 |
researchers | -8.571 |
physicists | -8.522 |
physicist | -8.502 |
Token |
|
Token ID | 198 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
reck | +3.690 |
idential | +3.658 |
osher | +3.466 |
aren | +3.440 |
Reserved | +3.426 |
Neg logit contributions | |
analys | -2.883 |
countries | -2.861 |
researchers | -2.623 |
physicists | -2.616 |
physicist | -2.595 |
Token | The |
Token ID | 464 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
idential | +1.543 |
reck | +1.532 |
osher | +1.454 |
Reserved | +1.420 |
aren | +1.419 |
Neg logit contributions | |
countries | -1.546 |
analys | -1.522 |
researchers | -1.434 |
scientist | -1.411 |
physicists | -1.411 |
Token | water |
Token ID | 1660 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
countries | +2.322 |
analys | +2.255 |
researchers | +2.148 |
scientist | +2.119 |
example | +2.104 |
Neg logit contributions | |
idential | -2.619 |
reck | -2.573 |
osher | -2.475 |
aren | -2.423 |
rict | -2.411 |
Token | was |
Token ID | 373 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
countries | +3.628 |
analys | +3.533 |
researchers | +3.326 |
scientist | +3.296 |
experiments | +3.288 |
Neg logit contributions | |
idential | -3.966 |
reck | -3.902 |
osher | -3.786 |
Reserved | -3.650 |
rict | -3.626 |
Token | clear |
Token ID | 1598 |
Feature activation | +7.84e+00 |
Pos logit contributions | |
idential | +2.678 |
reck | +2.663 |
osher | +2.541 |
aren | +2.492 |
Reserved | +2.488 |
Neg logit contributions | |
countries | -2.032 |
analys | -2.002 |
researchers | -1.861 |
physicists | -1.828 |
scientist | -1.828 |
Token | and |
Token ID | 290 |
Feature activation | +2.39e+01 |
Pos logit contributions | |
idential | +6.678 |
reck | +6.594 |
osher | +6.187 |
aren | +6.164 |
Shore | +6.095 |
Neg logit contributions | |
analys | -6.581 |
countries | -6.574 |
researchers | -6.165 |
physicists | -6.135 |
physicist | -6.095 |
Token | green |
Token ID | 4077 |
Feature activation | +6.46e+00 |
Pos logit contributions | |
reck | +19.341 |
Pleasant | +18.996 |
Shore | +18.840 |
idential | +18.735 |
spacious | +18.560 |
Neg logit contributions | |
analys | -12.982 |
countries | -12.585 |
enegger | -11.814 |
physicist | -11.767 |
physicists | -11.706 |
Token | over |
Token ID | 625 |
Feature activation | +9.37e+00 |
Pos logit contributions | |
idential | +5.358 |
reck | +5.326 |
osher | +4.990 |
aren | +4.953 |
Reserved | +4.896 |
Neg logit contributions | |
countries | -5.653 |
analys | -5.651 |
researchers | -5.300 |
physicists | -5.264 |
physicist | -5.249 |
Token | the |
Token ID | 262 |
Feature activation | +8.16e+00 |
Pos logit contributions | |
reck | +8.892 |
idential | +8.783 |
Shore | +8.443 |
osher | +8.311 |
Reserved | +8.273 |
Neg logit contributions | |
analys | -6.798 |
countries | -6.587 |
researchers | -6.207 |
physicists | -6.197 |
physicist | -6.170 |
Token | sand |
Token ID | 6450 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
reck | +8.086 |
idential | +8.022 |
Shore | +7.680 |
osher | +7.632 |
Reserved | +7.623 |
Neg logit contributions | |
analys | -5.644 |
countries | -5.586 |
researchers | -5.150 |
physicists | -5.112 |
physicist | -5.082 |
Token | and |
Token ID | 290 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
idential | +3.757 |
reck | +3.746 |
osher | +3.530 |
aren | +3.468 |
rict | +3.461 |
Neg logit contributions | |
countries | -3.646 |
analys | -3.624 |
researchers | -3.393 |
physicists | -3.355 |
physicist | -3.349 |
Token | restaurant |
Token ID | 7072 |
Feature activation | +6.67e+00 |
Pos logit contributions | |
idential | +10.880 |
reck | +10.837 |
osher | +10.351 |
Reserved | +10.237 |
Shore | +10.232 |
Neg logit contributions | |
analys | -8.060 |
countries | -7.893 |
researchers | -7.301 |
physicist | -7.289 |
physicists | -7.276 |
Token | / |
Token ID | 14 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
idential | +6.231 |
reck | +6.225 |
osher | +5.905 |
aren | +5.812 |
rict | +5.777 |
Neg logit contributions | |
countries | -5.224 |
analys | -5.212 |
researchers | -4.837 |
physicists | -4.789 |
physicist | -4.787 |
Token | bars |
Token ID | 34046 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
reck | +8.508 |
idential | +8.136 |
osher | +7.726 |
aren | +7.726 |
rict | +7.499 |
Neg logit contributions | |
analys | -10.207 |
countries | -10.206 |
physicists | -9.577 |
researchers | -9.531 |
physicist | -9.487 |
Token | in |
Token ID | 287 |
Feature activation | +1.80e+01 |
Pos logit contributions | |
reck | +10.033 |
idential | +9.926 |
aren | +9.436 |
osher | +9.432 |
rict | +9.341 |
Neg logit contributions | |
analys | -8.850 |
countries | -8.830 |
physicist | -8.270 |
physicists | -8.255 |
scientist | -8.235 |
Token | Forest |
Token ID | 9115 |
Feature activation | +2.09e+01 |
Pos logit contributions | |
Shore | +13.935 |
Pleasant | +13.856 |
idential | +13.600 |
reck | +13.556 |
Reserved | +12.986 |
Neg logit contributions | |
analys | -13.519 |
countries | -12.942 |
physicists | -12.656 |
physicist | -12.415 |
scientist | -12.210 |
Token | Park |
Token ID | 3250 |
Feature activation | +2.39e+01 |
Pos logit contributions | |
Shore | +11.021 |
idential | +10.787 |
reck | +10.706 |
Pleasant | +10.634 |
Reserved | +10.536 |
Neg logit contributions | |
analys | -21.470 |
countries | -20.448 |
physicists | -20.027 |
physicist | -19.597 |
experiments | -19.529 |
Token | and |
Token ID | 290 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
idential | +18.247 |
Shore | +18.030 |
Pleasant | +17.589 |
honoring | +17.543 |
reck | +17.422 |
Neg logit contributions | |
analys | -15.245 |
countries | -14.110 |
physicists | -13.884 |
physicist | -13.779 |
scientist | -13.519 |
Token | who |
Token ID | 508 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
idential | +13.532 |
reck | +13.364 |
Shore | +12.948 |
Pleasant | +12.877 |
Reserved | +12.782 |
Neg logit contributions | |
analys | -8.518 |
countries | -8.371 |
physicists | -7.739 |
physicist | -7.627 |
scientist | -7.589 |
Token | is |
Token ID | 318 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
idential | +3.667 |
reck | +3.656 |
osher | +3.473 |
aren | +3.397 |
Reserved | +3.392 |
Neg logit contributions | |
countries | -3.119 |
analys | -3.061 |
researchers | -2.874 |
scientist | -2.819 |
physicists | -2.816 |
Token | in |
Token ID | 287 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
countries | +1.394 |
analys | +1.383 |
researchers | +1.270 |
scientist | +1.253 |
example | +1.245 |
Neg logit contributions | |
idential | -2.322 |
reck | -2.312 |
osher | -2.211 |
ouls | -2.173 |
aren | -2.162 |
Token | favor |
Token ID | 2661 |
Feature activation | +7.33e+00 |
Pos logit contributions | |
countries | +0.447 |
analys | +0.436 |
researchers | +0.407 |
example | +0.400 |
scientist | +0.399 |
Neg logit contributions | |
reck | -0.549 |
idential | -0.548 |
osher | -0.526 |
aren | -0.515 |
rict | -0.508 |
Token | E |
Token ID | 412 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
countries | +7.400 |
analys | +7.209 |
researchers | +6.980 |
example | +6.955 |
experiments | +6.879 |
Neg logit contributions | |
idential | -6.573 |
reck | -6.408 |
osher | -6.251 |
ouls | -6.062 |
Reserved | -5.981 |
Token | ct |
Token ID | 310 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
idential | +2.790 |
reck | +2.768 |
osher | +2.632 |
Reserved | +2.565 |
aren | +2.553 |
Neg logit contributions | |
countries | -3.235 |
analys | -3.199 |
researchers | -3.025 |
scientist | -2.978 |
physicists | -2.971 |
Token | o |
Token ID | 78 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
countries | +3.265 |
example | +3.082 |
analys | +3.033 |
researchers | +3.025 |
scientist | +2.908 |
Neg logit contributions | |
idential | -4.825 |
Reserved | -4.690 |
reck | -4.682 |
osher | -4.584 |
ailability | -4.535 |
Token | - |
Token ID | 12 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
countries | +4.901 |
example | +4.553 |
researchers | +4.257 |
analys | +3.924 |
scientist | +3.886 |
Neg logit contributions | |
ailability | -15.825 |
idential | -15.396 |
ensical | -15.161 |
osher | -15.100 |
reck | -15.048 |
Token | 1 |
Token ID | 16 |
Feature activation | -9.45e+00 |
Pos logit contributions | |
countries | +2.260 |
analys | +2.130 |
example | +2.111 |
researchers | +2.103 |
scientist | +2.056 |
Neg logit contributions | |
idential | -2.376 |
reck | -2.314 |
osher | -2.281 |
Reserved | -2.200 |
rict | -2.146 |
Token | was |
Token ID | 373 |
Feature activation | -2.63e+01 |
Pos logit contributions | |
countries | +6.606 |
example | +6.165 |
researchers | +6.163 |
analys | +6.075 |
experiments | +5.952 |
Neg logit contributions | |
idential | -9.310 |
iquette | -8.901 |
idelines | -8.867 |
osher | -8.817 |
reck | -8.755 |
Token | also |
Token ID | 635 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
also | +9.329 |
example | +8.387 |
countries | +8.231 |
researchers | +8.082 |
later | +7.749 |
Neg logit contributions | |
ailability | -28.101 |
idelines | -26.922 |
idential | -26.687 |
osher | -26.569 |
ensical | -26.394 |
Token | filmed |
Token ID | 18976 |
Feature activation | -8.60e+00 |
Pos logit contributions | |
countries | +7.711 |
researchers | +7.358 |
experiments | +7.114 |
analys | +7.095 |
example | +7.081 |
Neg logit contributions | |
ailability | -13.541 |
idential | -13.451 |
osher | -13.436 |
ouls | -13.335 |
idelines | -13.311 |
Token | driving |
Token ID | 5059 |
Feature activation | -1.66e+01 |
Pos logit contributions | |
countries | +2.482 |
analys | +2.440 |
researchers | +1.974 |
example | +1.856 |
physicist | +1.793 |
Neg logit contributions | |
idential | -11.901 |
idelines | -11.886 |
osher | -11.772 |
ufficient | -11.386 |
reck | -11.384 |
Token | in |
Token ID | 287 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
countries | +6.793 |
example | +6.532 |
researchers | +6.093 |
analys | +5.757 |
experiments | +5.449 |
Neg logit contributions | |
ailability | -19.663 |
osher | -19.025 |
idential | -18.606 |
ensical | -18.547 |
idelines | -18.411 |
Token | the |
Token ID | 262 |
Feature activation | -8.57e+00 |
Pos logit contributions | |
countries | +5.022 |
example | +4.598 |
researchers | +4.474 |
analys | +4.229 |
experiments | +3.989 |
Neg logit contributions | |
ailability | -13.377 |
idential | -13.143 |
osher | -13.035 |
ensical | -12.943 |
reck | -12.867 |
Token | way |
Token ID | 835 |
Feature activation | -1.56e+01 |
Pos logit contributions | |
countries | +1.946 |
analys | +1.817 |
researchers | +1.736 |
experiments | +1.653 |
scientist | +1.635 |
Neg logit contributions | |
reck | -5.320 |
idential | -5.296 |
osher | -5.140 |
Reserved | -5.081 |
aren | -5.070 |
Token | into |
Token ID | 656 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
countries | +8.969 |
analys | +8.280 |
researchers | +8.147 |
experiments | +7.827 |
physicists | +7.737 |
Neg logit contributions | |
idential | -16.416 |
reck | -16.245 |
osher | -16.014 |
Reserved | -15.663 |
idelines | -15.496 |
Token | astronomy |
Token ID | 37145 |
Feature activation | -9.67e+00 |
Pos logit contributions | |
analys | +10.779 |
countries | +10.746 |
researchers | +10.371 |
experiments | +10.117 |
physicists | +10.042 |
Neg logit contributions | |
idential | -14.891 |
reck | -14.774 |
osher | -14.384 |
aren | -14.144 |
iquette | -13.952 |
Token | , |
Token ID | 11 |
Feature activation | -1.22e+01 |
Pos logit contributions | |
countries | +7.669 |
analys | +7.501 |
researchers | +7.356 |
experiments | +7.280 |
scientist | +7.047 |
Neg logit contributions | |
idential | -8.592 |
reck | -8.462 |
osher | -8.325 |
aren | -8.101 |
Reserved | -8.044 |
Token | � |
Token ID | 447 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
countries | +9.025 |
analys | +8.911 |
researchers | +8.825 |
scientist | +8.392 |
experiments | +8.331 |
Neg logit contributions | |
idential | -10.804 |
reck | -10.725 |
osher | -10.316 |
ouls | -10.255 |
Reserved | -10.168 |
Token | � |
Token ID | 251 |
Feature activation | -2.41e+01 |
Pos logit contributions | |
countries | +7.664 |
analys | +6.971 |
researchers | +6.954 |
example | +6.799 |
experiments | +6.649 |
Neg logit contributions | |
idential | -10.909 |
reck | -10.648 |
osher | -10.334 |
Shore | -9.979 |
unicip | -9.970 |
Token | he |
Token ID | 339 |
Feature activation | -2.21e+01 |
Pos logit contributions | |
researchers | +17.416 |
countries | +17.375 |
analys | +16.822 |
scientist | +16.507 |
physicist | +16.288 |
Neg logit contributions | |
idential | -15.982 |
reck | -15.963 |
iquette | -15.512 |
osher | -15.123 |
ouls | -15.102 |
Token | says |
Token ID | 1139 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
countries | +13.200 |
researchers | +12.428 |
analys | +12.388 |
experiments | +12.212 |
scientist | +11.948 |
Neg logit contributions | |
reck | -19.144 |
idential | -19.102 |
Reserved | -18.143 |
osher | -17.972 |
unicip | -17.949 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
countries | +10.013 |
analys | +9.808 |
researchers | +9.350 |
scientist | +9.155 |
example | +9.140 |
Neg logit contributions | |
reck | -9.675 |
idential | -9.645 |
osher | -9.139 |
Reserved | -9.026 |
rict | -8.871 |
Token |
|
Token ID | 198 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
countries | +10.640 |
researchers | +10.217 |
analys | +10.099 |
scientist | +9.858 |
example | +9.846 |
Neg logit contributions | |
idential | -13.018 |
reck | -12.875 |
osher | -12.810 |
ouls | -12.001 |
iquette | -11.880 |
Token |
|
Token ID | 198 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
idential | +2.668 |
reck | +2.646 |
osher | +2.558 |
Reserved | +2.484 |
aren | +2.482 |
Neg logit contributions | |
countries | -1.704 |
analys | -1.654 |
researchers | -1.553 |
example | -1.518 |
scientist | -1.511 |
Token | ago |
Token ID | 2084 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
idential | +0.708 |
reck | +0.706 |
osher | +0.673 |
aren | +0.659 |
Reserved | +0.658 |
Neg logit contributions | |
countries | -0.558 |
analys | -0.551 |
researchers | -0.513 |
physicists | -0.504 |
scientist | -0.504 |
Token | by |
Token ID | 416 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
idential | +1.767 |
reck | +1.758 |
osher | +1.655 |
aren | +1.621 |
Reserved | +1.617 |
Neg logit contributions | |
countries | -1.971 |
analys | -1.945 |
researchers | -1.836 |
scientist | -1.812 |
physicists | -1.812 |
Token | Julian |
Token ID | 18322 |
Feature activation | -8.62e+00 |
Pos logit contributions | |
countries | +2.305 |
analys | +2.259 |
researchers | +2.101 |
physicists | +2.001 |
scientist | +1.993 |
Neg logit contributions | |
reck | -3.676 |
idential | -3.650 |
osher | -3.533 |
aren | -3.449 |
Reserved | -3.424 |
Token | Assange |
Token ID | 21882 |
Feature activation | -1.53e+01 |
Pos logit contributions | |
countries | +5.415 |
analys | +5.341 |
researchers | +5.075 |
scientist | +4.889 |
example | +4.795 |
Neg logit contributions | |
reck | -8.961 |
idential | -8.876 |
osher | -8.661 |
aren | -8.466 |
rict | -8.425 |
Token | , |
Token ID | 11 |
Feature activation | -1.53e+01 |
Pos logit contributions | |
countries | +11.205 |
analys | +11.144 |
researchers | +10.593 |
scientist | +10.186 |
physicist | +9.857 |
Neg logit contributions | |
reck | -13.136 |
idential | -12.653 |
osher | -12.628 |
hetto | -12.199 |
idelines | -12.164 |
Token | the |
Token ID | 262 |
Feature activation | -2.39e+01 |
Pos logit contributions | |
analys | +10.443 |
countries | +10.312 |
researchers | +9.661 |
scientist | +9.189 |
physicist | +9.047 |
Neg logit contributions | |
osher | -13.996 |
reck | -13.973 |
idential | -13.823 |
iquette | -13.514 |
ouls | -13.483 |
Token | founder |
Token ID | 9119 |
Feature activation | -2.02e+01 |
Pos logit contributions | |
countries | +15.887 |
analys | +15.192 |
scientist | +15.158 |
latter | +15.050 |
researchers | +14.830 |
Neg logit contributions | |
iquette | -18.092 |
reck | -18.034 |
osher | -18.028 |
idelines | -17.947 |
unicip | -17.753 |
Token | of |
Token ID | 286 |
Feature activation | -1.74e+01 |
Pos logit contributions | |
countries | +14.293 |
analys | +13.877 |
researchers | +13.188 |
scientist | +13.104 |
example | +12.872 |
Neg logit contributions | |
idential | -17.129 |
reck | -17.058 |
osher | -16.807 |
aren | -16.197 |
Reserved | -16.186 |
Token | WikiLeaks |
Token ID | 19766 |
Feature activation | -1.25e+01 |
Pos logit contributions | |
countries | +10.045 |
analys | +9.987 |
researchers | +9.389 |
example | +8.948 |
experiments | +8.637 |
Neg logit contributions | |
osher | -16.978 |
idential | -16.914 |
unicip | -16.742 |
idelines | -16.673 |
reck | -16.657 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
countries | +9.672 |
analys | +9.510 |
researchers | +8.872 |
scientist | +8.608 |
experiments | +8.539 |
Neg logit contributions | |
reck | -10.735 |
osher | -10.656 |
idential | -10.584 |
idelines | -10.321 |
Reserved | -10.165 |
Token |
|
Token ID | 198 |
Feature activation | -6.85e+00 |
Pos logit contributions | |
countries | +7.124 |
analys | +6.788 |
researchers | +6.398 |
example | +6.230 |
scientist | +6.118 |
Neg logit contributions | |
reck | -10.923 |
idential | -10.643 |
osher | -10.579 |
aren | -10.106 |
hetto | -10.093 |
Token | violent |
Token ID | 24498 |
Feature activation | -7.15e+00 |
Pos logit contributions | |
countries | +2.955 |
analys | +2.844 |
researchers | +2.733 |
example | +2.705 |
scientist | +2.686 |
Neg logit contributions | |
idential | -2.458 |
reck | -2.342 |
osher | -2.284 |
Reserved | -2.244 |
Shore | -2.233 |
Token | ) |
Token ID | 8 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
countries | +5.771 |
analys | +5.565 |
researchers | +5.271 |
example | +5.259 |
scientist | +5.211 |
Neg logit contributions | |
reck | -6.558 |
idential | -6.551 |
osher | -6.250 |
Reserved | -6.135 |
aren | -6.051 |
Token | struggle |
Token ID | 6531 |
Feature activation | -8.85e+00 |
Pos logit contributions | |
countries | +3.017 |
analys | +2.870 |
example | +2.761 |
researchers | +2.703 |
scientist | +2.670 |
Neg logit contributions | |
idential | -4.656 |
reck | -4.595 |
osher | -4.439 |
aren | -4.336 |
ouls | -4.313 |
Token | , |
Token ID | 11 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
countries | +6.548 |
analys | +6.289 |
researchers | +5.947 |
example | +5.888 |
scientist | +5.771 |
Neg logit contributions | |
idential | -8.439 |
reck | -8.367 |
osher | -8.129 |
ouls | -7.932 |
Reserved | -7.907 |
Token | � |
Token ID | 447 |
Feature activation | -9.80e+00 |
Pos logit contributions | |
countries | +10.969 |
researchers | +10.630 |
analys | +10.607 |
example | +10.139 |
scientist | +10.050 |
Neg logit contributions | |
reck | -12.827 |
idential | -12.770 |
osher | -12.273 |
ouls | -11.986 |
iquette | -11.985 |
Token | � |
Token ID | 251 |
Feature activation | -2.33e+01 |
Pos logit contributions | |
countries | +6.071 |
researchers | +5.489 |
latter | +5.318 |
analys | +5.271 |
example | +5.268 |
Neg logit contributions | |
idential | -10.224 |
reck | -9.916 |
osher | -9.888 |
iquette | -9.496 |
ouls | -9.379 |
Token | Miz |
Token ID | 29975 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
countries | +17.486 |
researchers | +17.079 |
analys | +16.611 |
example | +16.175 |
scientist | +15.990 |
Neg logit contributions | |
reck | -15.361 |
idential | -15.264 |
osher | -14.449 |
hetto | -14.022 |
ouls | -13.973 |
Token | og |
Token ID | 519 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
countries | +2.327 |
analys | +2.214 |
researchers | +2.190 |
example | +2.135 |
scientist | +2.121 |
Neg logit contributions | |
reck | -3.035 |
idential | -3.015 |
Reserved | -2.956 |
osher | -2.864 |
Shore | -2.854 |
Token | uchi |
Token ID | 22200 |
Feature activation | -2.05e+01 |
Pos logit contributions | |
countries | +0.588 |
analys | +0.557 |
researchers | +0.542 |
example | +0.535 |
scientist | +0.529 |
Neg logit contributions | |
reck | -0.691 |
idential | -0.689 |
osher | -0.661 |
Reserved | -0.660 |
Shore | -0.660 |
Token | said |
Token ID | 531 |
Feature activation | -1.36e+01 |
Pos logit contributions | |
countries | +13.262 |
researchers | +12.540 |
analys | +12.342 |
scientist | +12.019 |
analyst | +11.878 |
Neg logit contributions | |
idential | -17.289 |
reck | -16.816 |
ouls | -16.669 |
osher | -16.390 |
iquette | -16.138 |
Token | at |
Token ID | 379 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
countries | +10.702 |
analys | +10.527 |
researchers | +9.978 |
experiments | +9.639 |
scientist | +9.580 |
Neg logit contributions | |
idential | -11.669 |
reck | -11.406 |
osher | -11.016 |
Reserved | -10.953 |
ouls | -10.813 |
Token | until |
Token ID | 1566 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
idential | +1.690 |
reck | +1.672 |
osher | +1.622 |
Reserved | +1.574 |
aren | +1.569 |
Neg logit contributions | |
countries | -1.081 |
analys | -1.063 |
researchers | -0.979 |
scientist | -0.952 |
physicists | -0.951 |
Token | well |
Token ID | 880 |
Feature activation | -5.59e+00 |
Pos logit contributions | |
countries | +3.104 |
analys | +3.024 |
researchers | +2.817 |
experiments | +2.724 |
example | +2.695 |
Neg logit contributions | |
reck | -4.359 |
idential | -4.352 |
osher | -4.245 |
Reserved | -4.124 |
ouls | -4.086 |
Token | into |
Token ID | 656 |
Feature activation | -9.13e+00 |
Pos logit contributions | |
countries | +3.767 |
analys | +3.682 |
researchers | +3.398 |
scientist | +3.289 |
physicists | +3.279 |
Neg logit contributions | |
idential | -5.977 |
reck | -5.928 |
osher | -5.737 |
Reserved | -5.561 |
aren | -5.542 |
Token | 2015 |
Token ID | 1853 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
countries | +6.010 |
analys | +5.846 |
researchers | +5.385 |
example | +5.235 |
experiments | +5.217 |
Neg logit contributions | |
reck | -9.610 |
idential | -9.602 |
osher | -9.379 |
aren | -9.001 |
iquette | -8.976 |
Token | ," |
Token ID | 553 |
Feature activation | -1.78e+01 |
Pos logit contributions | |
countries | +3.479 |
analys | +3.411 |
researchers | +3.208 |
example | +3.126 |
scientist | +3.120 |
Neg logit contributions | |
idential | -3.480 |
reck | -3.450 |
osher | -3.334 |
Reserved | -3.233 |
ouls | -3.189 |
Token | he |
Token ID | 339 |
Feature activation | -2.27e+01 |
Pos logit contributions | |
analys | +10.855 |
countries | +10.799 |
researchers | +10.246 |
scientist | +9.974 |
physicist | +9.933 |
Neg logit contributions | |
reck | -16.512 |
idential | -16.126 |
osher | -15.691 |
ouls | -15.519 |
iquette | -15.346 |
Token | said |
Token ID | 531 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
analys | +12.126 |
countries | +12.110 |
researchers | +11.360 |
scientist | +10.837 |
analyst | +10.687 |
Neg logit contributions | |
reck | -20.378 |
idential | -20.238 |
osher | -20.033 |
Reserved | -19.961 |
ouls | -19.811 |
Token | . |
Token ID | 13 |
Feature activation | -1.29e+01 |
Pos logit contributions | |
analys | +11.738 |
countries | +11.587 |
researchers | +10.743 |
experiments | +10.479 |
example | +10.454 |
Neg logit contributions | |
idential | -13.544 |
reck | -13.453 |
osher | -13.276 |
Reserved | -13.230 |
ouls | -12.737 |
Token |
|
Token ID | 198 |
Feature activation | -8.80e+00 |
Pos logit contributions | |
countries | +7.862 |
analys | +7.520 |
researchers | +7.019 |
example | +6.875 |
scientist | +6.735 |
Neg logit contributions | |
reck | -13.568 |
idential | -13.465 |
osher | -13.186 |
aren | -12.662 |
rict | -12.636 |
Token |
|
Token ID | 198 |
Feature activation | -9.97e+00 |
Pos logit contributions | |
countries | +3.942 |
example | +3.738 |
researchers | +3.516 |
analys | +3.289 |
scientist | +3.210 |
Neg logit contributions | |
ailability | -11.189 |
osher | -10.784 |
idential | -10.702 |
ensical | -10.488 |
reck | -10.487 |
Token | " |
Token ID | 1 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
countries | +7.729 |
analys | +7.195 |
example | +7.172 |
researchers | +7.163 |
scientist | +6.896 |
Neg logit contributions | |
idential | -8.643 |
osher | -8.449 |
reck | -8.223 |
honoring | -8.146 |
Reserved | -8.041 |
Token | can |
Token ID | 460 |
Feature activation | -2.03e+01 |
Pos logit contributions | |
countries | +10.239 |
analys | +9.853 |
researchers | +9.837 |
physicists | +9.550 |
scientist | +9.522 |
Neg logit contributions | |
idential | -11.342 |
osher | -10.931 |
reck | -10.860 |
Reserved | -10.831 |
Shore | -10.633 |
Token | make |
Token ID | 787 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
countries | +13.508 |
analys | +13.157 |
researchers | +13.100 |
scientist | +12.947 |
experiments | +12.796 |
Neg logit contributions | |
idential | -16.722 |
osher | -16.350 |
Reserved | -15.897 |
reck | -15.782 |
iquette | -15.752 |
Token | life |
Token ID | 1204 |
Feature activation | -2.15e+01 |
Pos logit contributions | |
countries | +8.924 |
analys | +8.574 |
researchers | +8.323 |
physicists | +8.159 |
experiments | +8.109 |
Neg logit contributions | |
idential | -11.594 |
reck | -11.090 |
osher | -10.910 |
iquette | -10.742 |
Reserved | -10.700 |
Token | , |
Token ID | 11 |
Feature activation | -1.38e+01 |
Pos logit contributions | |
countries | +15.071 |
researchers | +14.635 |
experiments | +14.630 |
analys | +14.533 |
scientist | +14.167 |
Neg logit contributions | |
osher | -16.063 |
idential | -15.735 |
Reserved | -15.407 |
hetto | -15.120 |
reck | -15.110 |
Token | � |
Token ID | 447 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
researchers | +9.657 |
countries | +9.564 |
analys | +9.354 |
scientist | +9.289 |
physicists | +9.109 |
Neg logit contributions | |
idential | -12.302 |
reck | -12.128 |
osher | -11.889 |
iquette | -11.713 |
Reserved | -11.691 |
Token | � |
Token ID | 251 |
Feature activation | -2.26e+01 |
Pos logit contributions | |
countries | +7.891 |
analys | +7.495 |
researchers | +7.266 |
scientist | +7.090 |
physicists | +7.045 |
Neg logit contributions | |
idential | -9.161 |
reck | -9.005 |
osher | -8.652 |
Shore | -8.357 |
rict | -8.324 |
Token | Dr |
Token ID | 1583 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
researchers | +17.063 |
countries | +16.534 |
analys | +16.337 |
scientist | +16.238 |
physicists | +16.180 |
Neg logit contributions | |
idential | -15.975 |
reck | -15.674 |
osher | -15.334 |
unicip | -15.312 |
iquette | -14.998 |
Token | Sas |
Token ID | 23771 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
countries | +2.642 |
analys | +2.612 |
researchers | +2.470 |
physicists | +2.438 |
scientist | +2.437 |
Neg logit contributions | |
idential | -2.073 |
reck | -2.063 |
osher | -1.937 |
aren | -1.890 |
Reserved | -1.886 |
Token | sel |
Token ID | 741 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
idential | +2.753 |
reck | +2.740 |
osher | +2.584 |
Reserved | +2.541 |
rict | +2.495 |
Neg logit contributions | |
countries | -3.541 |
analys | -3.486 |
researchers | -3.319 |
scientist | -3.272 |
example | -3.261 |
Token | ov |
Token ID | 709 |
Feature activation | -1.95e+01 |
Pos logit contributions | |
countries | +3.620 |
analys | +3.380 |
researchers | +3.340 |
example | +3.238 |
experiments | +3.196 |
Neg logit contributions | |
idential | -6.147 |
reck | -6.052 |
Reserved | -6.040 |
osher | -5.923 |
ailability | -5.869 |
Token | concluded |
Token ID | 8391 |
Feature activation | -9.04e+00 |
Pos logit contributions | |
countries | +12.390 |
analys | +12.082 |
researchers | +11.852 |
scientist | +11.665 |
physicist | +11.198 |
Neg logit contributions | |
idential | -17.094 |
reck | -16.410 |
osher | -16.280 |
ouls | -16.079 |
Reserved | -15.729 |
Token | que |
Token ID | 4188 |
Feature activation | -1.64e+01 |
Pos logit contributions | |
countries | +2.824 |
analys | +2.749 |
researchers | +2.642 |
example | +2.615 |
experiments | +2.595 |
Neg logit contributions | |
idential | -2.555 |
osher | -2.487 |
reck | -2.463 |
Reserved | -2.433 |
Shore | -2.418 |
Token | , |
Token ID | 11 |
Feature activation | -1.95e+01 |
Pos logit contributions | |
analys | +12.120 |
countries | +11.828 |
researchers | +11.464 |
scientist | +11.178 |
physicist | +11.055 |
Neg logit contributions | |
idential | -13.997 |
reck | -13.641 |
osher | -13.344 |
ouls | -12.933 |
Reserved | -12.877 |
Token | who |
Token ID | 508 |
Feature activation | -1.67e+01 |
Pos logit contributions | |
analys | +13.547 |
countries | +13.405 |
researchers | +13.136 |
scientist | +13.053 |
physicist | +13.002 |
Neg logit contributions | |
idential | -15.794 |
reck | -15.784 |
osher | -15.603 |
iquette | -15.437 |
ouls | -15.351 |
Token | is |
Token ID | 318 |
Feature activation | -2.04e+01 |
Pos logit contributions | |
countries | +12.338 |
analys | +12.266 |
researchers | +12.012 |
experiments | +11.706 |
scientist | +11.554 |
Neg logit contributions | |
idential | -13.845 |
osher | -13.649 |
reck | -13.619 |
iquette | -12.967 |
rict | -12.935 |
Token | the |
Token ID | 262 |
Feature activation | -1.67e+01 |
Pos logit contributions | |
analys | +14.691 |
countries | +13.938 |
scientist | +13.794 |
physicist | +13.732 |
researchers | +13.653 |
Neg logit contributions | |
idential | -16.533 |
reck | -16.518 |
osher | -16.120 |
iquette | -15.966 |
ouls | -15.673 |
Token | lead |
Token ID | 1085 |
Feature activation | -2.26e+01 |
Pos logit contributions | |
countries | +13.161 |
scientist | +13.089 |
physicist | +12.979 |
researchers | +12.905 |
analys | +12.836 |
Neg logit contributions | |
reck | -13.089 |
idential | -12.732 |
osher | -12.620 |
ouls | -12.370 |
iquette | -12.143 |
Token | author |
Token ID | 1772 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
scientist | +13.648 |
analys | +12.776 |
physicist | +12.760 |
researchers | +12.565 |
researcher | +12.170 |
Neg logit contributions | |
reck | -20.516 |
idential | -20.325 |
osher | -20.140 |
Reserved | -19.595 |
iquette | -19.536 |
Token | of |
Token ID | 286 |
Feature activation | -8.55e+00 |
Pos logit contributions | |
analys | +8.381 |
countries | +8.367 |
researchers | +7.788 |
scientist | +7.626 |
physicists | +7.525 |
Neg logit contributions | |
idential | -13.468 |
reck | -13.316 |
osher | -13.044 |
Reserved | -12.769 |
aren | -12.671 |
Token | a |
Token ID | 257 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
analys | +5.375 |
countries | +5.361 |
researchers | +5.004 |
experiments | +4.834 |
physicists | +4.819 |
Neg logit contributions | |
idential | -9.306 |
reck | -9.218 |
osher | -8.956 |
aren | -8.728 |
Reserved | -8.708 |
Token | paper |
Token ID | 3348 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
countries | +2.336 |
analys | +2.327 |
researchers | +2.176 |
scientist | +2.149 |
physicist | +2.103 |
Neg logit contributions | |
idential | -4.888 |
reck | -4.871 |
osher | -4.695 |
rict | -4.618 |
Reserved | -4.605 |
Token | accepted |
Token ID | 6292 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
analys | +2.924 |
countries | +2.844 |
researchers | +2.672 |
physicists | +2.596 |
scientist | +2.587 |
Neg logit contributions | |
idential | -4.138 |
reck | -4.077 |
osher | -3.972 |
aren | -3.878 |
Reserved | -3.868 |
Token | class |
Token ID | 1398 |
Feature activation | +7.49e+00 |
Pos logit contributions | |
countries | +5.341 |
analys | +5.300 |
researchers | +4.950 |
scientist | +4.900 |
example | +4.899 |
Neg logit contributions | |
reck | -4.865 |
idential | -4.812 |
osher | -4.739 |
ouls | -4.455 |
Reserved | -4.398 |
Token | Bradley |
Token ID | 16182 |
Feature activation | -6.49e+00 |
Pos logit contributions | |
idential | +6.531 |
reck | +6.500 |
Reserved | +6.050 |
rict | +6.021 |
osher | +6.018 |
Neg logit contributions | |
countries | -6.205 |
analys | -6.144 |
researchers | -5.755 |
physicists | -5.727 |
experiments | -5.692 |
Token | Manning |
Token ID | 15281 |
Feature activation | -9.44e+00 |
Pos logit contributions | |
countries | +5.507 |
analys | +5.383 |
researchers | +5.198 |
example | +5.094 |
scientist | +5.030 |
Neg logit contributions | |
reck | -5.536 |
osher | -5.463 |
idential | -5.459 |
ouls | -5.313 |
rict | -5.179 |
Token | , |
Token ID | 11 |
Feature activation | -1.46e+01 |
Pos logit contributions | |
analys | +7.403 |
countries | +7.402 |
researchers | +6.843 |
scientist | +6.729 |
example | +6.685 |
Neg logit contributions | |
reck | -8.292 |
idential | -8.285 |
osher | -8.080 |
aren | -7.708 |
ouls | -7.706 |
Token | who |
Token ID | 508 |
Feature activation | -1.39e+01 |
Pos logit contributions | |
countries | +9.953 |
analys | +9.838 |
researchers | +9.238 |
scientist | +8.881 |
example | +8.859 |
Neg logit contributions | |
idential | -13.414 |
osher | -13.374 |
reck | -13.294 |
iquette | -13.122 |
ouls | -12.991 |
Token | was |
Token ID | 373 |
Feature activation | -2.25e+01 |
Pos logit contributions | |
countries | +10.741 |
analys | +10.037 |
researchers | +9.942 |
experiments | +9.522 |
latter | +9.302 |
Neg logit contributions | |
osher | -12.104 |
idential | -12.025 |
reck | -11.769 |
hetto | -11.448 |
iquette | -11.371 |
Token | an |
Token ID | 281 |
Feature activation | -1.67e+01 |
Pos logit contributions | |
analys | +15.013 |
countries | +14.568 |
researchers | +13.337 |
scientist | +13.293 |
latter | +13.174 |
Neg logit contributions | |
idential | -18.209 |
iquette | -17.993 |
osher | -17.953 |
reck | -17.528 |
ouls | -17.260 |
Token | US |
Token ID | 1294 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
analys | +11.452 |
example | +11.116 |
countries | +10.949 |
analyst | +10.927 |
researchers | +10.200 |
Neg logit contributions | |
reck | -15.223 |
osher | -14.614 |
iquette | -14.324 |
idential | -14.313 |
idelines | -14.138 |
Token | army |
Token ID | 5428 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
countries | +8.212 |
analys | +7.952 |
scientist | +7.659 |
example | +7.575 |
analyst | +7.480 |
Neg logit contributions | |
reck | -11.354 |
osher | -11.297 |
iquette | -11.267 |
idential | -11.266 |
ouls | -11.221 |
Token | intelligence |
Token ID | 4430 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
analys | +10.666 |
scientist | +10.631 |
countries | +10.612 |
analyst | +10.600 |
physicist | +10.061 |
Neg logit contributions | |
ouls | -14.266 |
reck | -14.125 |
idential | -13.862 |
iquette | -13.784 |
osher | -13.636 |
Token | analyst |
Token ID | 12499 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
analys | +6.685 |
analyst | +6.620 |
scientist | +6.154 |
countries | +6.030 |
researchers | +5.751 |
Neg logit contributions | |
osher | -14.749 |
ouls | -14.648 |
idential | -14.639 |
reck | -14.605 |
iquette | -14.502 |
Token | Potter |
Token ID | 14179 |
Feature activation | -1.25e+01 |
Pos logit contributions | |
idential | +2.844 |
reck | +2.837 |
osher | +2.584 |
aren | +2.566 |
rict | +2.543 |
Neg logit contributions | |
countries | -6.175 |
analys | -6.144 |
physicists | -5.813 |
researchers | -5.774 |
physicist | -5.751 |
Token | , |
Token ID | 11 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
countries | +10.006 |
analys | +9.995 |
researchers | +9.514 |
scientist | +9.336 |
physicist | +9.175 |
Neg logit contributions | |
idential | -10.581 |
reck | -10.411 |
osher | -10.098 |
Reserved | -9.902 |
ouls | -9.833 |
Token | who |
Token ID | 508 |
Feature activation | -1.40e+01 |
Pos logit contributions | |
analys | +11.652 |
countries | +11.493 |
researchers | +11.136 |
scientist | +11.010 |
physicist | +10.596 |
Neg logit contributions | |
reck | -13.620 |
idential | -13.529 |
osher | -13.219 |
ouls | -13.069 |
iquette | -13.055 |
Token | is |
Token ID | 318 |
Feature activation | -1.76e+01 |
Pos logit contributions | |
countries | +10.470 |
analys | +10.370 |
researchers | +10.063 |
scientist | +9.718 |
experiments | +9.605 |
Neg logit contributions | |
idential | -12.378 |
reck | -12.187 |
osher | -11.992 |
ouls | -11.598 |
hetto | -11.595 |
Token | the |
Token ID | 262 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
analys | +12.526 |
countries | +11.898 |
scientist | +11.664 |
researchers | +11.555 |
physicist | +11.161 |
Neg logit contributions | |
reck | -15.524 |
idential | -15.516 |
osher | -15.048 |
ouls | -15.045 |
iquette | -15.006 |
Token | lead |
Token ID | 1085 |
Feature activation | -2.24e+01 |
Pos logit contributions | |
countries | +11.859 |
scientist | +11.602 |
analys | +11.587 |
researchers | +11.489 |
physicist | +11.031 |
Neg logit contributions | |
reck | -12.542 |
idential | -12.167 |
ouls | -11.854 |
osher | -11.812 |
iquette | -11.577 |
Token | author |
Token ID | 1772 |
Feature activation | -1.42e+01 |
Pos logit contributions | |
scientist | +12.520 |
analys | +11.898 |
researchers | +11.687 |
researcher | +11.441 |
countries | +11.116 |
Neg logit contributions | |
reck | -21.773 |
idential | -20.935 |
osher | -20.902 |
ouls | -20.851 |
hetto | -20.526 |
Token | of |
Token ID | 286 |
Feature activation | -6.14e+00 |
Pos logit contributions | |
analys | +9.694 |
countries | +9.497 |
researchers | +8.957 |
scientist | +8.822 |
physicist | +8.549 |
Neg logit contributions | |
idential | -13.790 |
reck | -13.580 |
osher | -13.389 |
Reserved | -13.104 |
ouls | -13.022 |
Token | a |
Token ID | 257 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
countries | +4.211 |
analys | +4.171 |
researchers | +3.878 |
scientist | +3.767 |
experiments | +3.749 |
Neg logit contributions | |
idential | -6.431 |
reck | -6.418 |
osher | -6.153 |
aren | -6.031 |
Reserved | -6.023 |
Token | paper |
Token ID | 3348 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
countries | +1.085 |
analys | +1.075 |
researchers | +0.994 |
scientist | +0.974 |
physicist | +0.944 |
Neg logit contributions | |
reck | -2.186 |
idential | -2.184 |
osher | -2.098 |
rict | -2.062 |
Reserved | -2.058 |
Token | published |
Token ID | 3199 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
analys | +2.945 |
countries | +2.871 |
researchers | +2.680 |
scientist | +2.600 |
physicists | +2.573 |
Neg logit contributions | |
idential | -4.152 |
reck | -4.098 |
osher | -3.985 |
aren | -3.893 |
Reserved | -3.885 |
Token | Universe |
Token ID | 11950 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
countries | +9.022 |
analys | +8.715 |
researchers | +8.656 |
scientist | +8.516 |
physicist | +8.188 |
Neg logit contributions | |
idential | -12.642 |
reck | -12.399 |
osher | -12.308 |
ouls | -11.896 |
unicip | -11.844 |
Token | and |
Token ID | 290 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
countries | +3.309 |
analys | +3.289 |
researchers | +3.121 |
scientist | +3.055 |
physicists | +3.055 |
Neg logit contributions | |
idential | -3.194 |
reck | -3.177 |
osher | -3.042 |
Reserved | -2.946 |
aren | -2.934 |
Token | the |
Token ID | 262 |
Feature activation | -8.91e+00 |
Pos logit contributions | |
countries | +2.538 |
analys | +2.486 |
researchers | +2.379 |
physicists | +2.319 |
scientist | +2.318 |
Neg logit contributions | |
idential | -3.295 |
reck | -3.268 |
osher | -3.152 |
Reserved | -3.075 |
aren | -3.069 |
Token | possibility |
Token ID | 5885 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
countries | +6.427 |
analys | +6.207 |
researchers | +6.135 |
scientist | +5.932 |
experiments | +5.905 |
Neg logit contributions | |
idential | -8.761 |
reck | -8.642 |
osher | -8.503 |
aren | -8.229 |
ouls | -8.228 |
Token | of |
Token ID | 286 |
Feature activation | -1.28e+01 |
Pos logit contributions | |
countries | +7.171 |
analys | +6.983 |
researchers | +6.628 |
physicists | +6.500 |
scientist | +6.451 |
Neg logit contributions | |
idential | -10.613 |
reck | -10.547 |
osher | -10.139 |
Reserved | -10.001 |
rict | -9.913 |
Token | life |
Token ID | 1204 |
Feature activation | -2.24e+01 |
Pos logit contributions | |
analys | +9.011 |
countries | +8.942 |
researchers | +8.465 |
experiments | +8.360 |
physicists | +8.215 |
Neg logit contributions | |
idential | -12.115 |
osher | -11.757 |
reck | -11.708 |
iquette | -11.480 |
idelines | -11.436 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
countries | +14.799 |
analys | +14.703 |
researchers | +14.444 |
experiments | +14.109 |
scientist | +13.897 |
Neg logit contributions | |
osher | -17.499 |
idential | -17.168 |
reck | -17.099 |
Reserved | -17.042 |
Shore | -16.526 |
Token |
|
Token ID | 198 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
countries | +7.077 |
researchers | +6.751 |
analys | +6.689 |
scientist | +6.539 |
physicist | +6.435 |
Neg logit contributions | |
idential | -10.126 |
reck | -9.971 |
osher | -9.969 |
rict | -9.440 |
iquette | -9.440 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
countries | +1.519 |
analys | +1.417 |
example | +1.391 |
researchers | +1.388 |
scientist | +1.313 |
Neg logit contributions | |
idential | -3.050 |
reck | -2.992 |
osher | -2.991 |
iquette | -2.838 |
idelines | -2.827 |
Token | The |
Token ID | 464 |
Feature activation | -1.57e+01 |
Pos logit contributions | |
countries | +8.023 |
researchers | +7.737 |
analys | +7.571 |
example | +7.557 |
scientist | +7.518 |
Neg logit contributions | |
idential | -9.723 |
osher | -9.387 |
Shore | -9.093 |
Reserved | -9.028 |
reck | -8.983 |
Token | Kepler |
Token ID | 40294 |
Feature activation | -1.44e+01 |
Pos logit contributions | |
researchers | +12.231 |
countries | +12.133 |
analys | +11.872 |
scientist | +11.761 |
physicists | +11.470 |
Neg logit contributions | |
idential | -12.812 |
osher | -12.411 |
reck | -12.210 |
Reserved | -11.786 |
iquette | -11.651 |
Token | Time |
Token ID | 7575 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
analys | +7.730 |
countries | +7.589 |
example | +7.315 |
researchers | +7.005 |
experiments | +6.985 |
Neg logit contributions | |
idential | -9.108 |
osher | -8.993 |
reck | -8.937 |
aren | -8.436 |
Reserved | -8.422 |
Token | 5 |
Token ID | 642 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
countries | +2.268 |
analys | +2.251 |
example | +2.096 |
researchers | +2.084 |
experiments | +2.048 |
Neg logit contributions | |
idential | -2.716 |
reck | -2.703 |
osher | -2.602 |
aren | -2.527 |
ouls | -2.491 |
Token | m |
Token ID | 76 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
countries | +3.552 |
analys | +3.496 |
example | +3.276 |
researchers | +3.266 |
experiments | +3.220 |
Neg logit contributions | |
idential | -4.009 |
reck | -3.980 |
osher | -3.817 |
aren | -3.711 |
Reserved | -3.672 |
Token | . |
Token ID | 764 |
Feature activation | -1.62e+01 |
Pos logit contributions | |
idential | +2.397 |
reck | +2.384 |
osher | +2.247 |
aren | +2.201 |
Reserved | +2.196 |
Neg logit contributions | |
countries | -2.688 |
analys | -2.658 |
researchers | -2.504 |
physicists | -2.471 |
scientist | -2.468 |
Token | You |
Token ID | 921 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
example | +10.499 |
countries | +10.440 |
analys | +10.274 |
researchers | +9.625 |
latter | +9.571 |
Neg logit contributions | |
idential | -14.390 |
reck | -14.377 |
osher | -13.971 |
iquette | -13.299 |
ouls | -13.173 |
Token | can |
Token ID | 460 |
Feature activation | -2.23e+01 |
Pos logit contributions | |
countries | +9.467 |
analys | +9.072 |
example | +8.933 |
researchers | +8.773 |
scientist | +8.400 |
Neg logit contributions | |
idential | -11.767 |
reck | -11.561 |
osher | -11.552 |
iquette | -10.843 |
ouls | -10.809 |
Token | also |
Token ID | 635 |
Feature activation | -1.40e+01 |
Pos logit contributions | |
countries | +11.805 |
example | +11.801 |
analys | +11.422 |
experiments | +10.728 |
researchers | +10.671 |
Neg logit contributions | |
osher | -20.263 |
idential | -20.222 |
reck | -19.929 |
idelines | -19.212 |
ufficient | -19.136 |
Token | stream |
Token ID | 4269 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
countries | +8.076 |
analys | +7.786 |
example | +7.747 |
experiments | +7.239 |
researchers | +7.183 |
Neg logit contributions | |
idential | -14.625 |
reck | -14.451 |
osher | -14.325 |
idelines | -13.713 |
ufficient | -13.665 |
Token | the |
Token ID | 262 |
Feature activation | -6.58e+00 |
Pos logit contributions | |
analys | +8.811 |
countries | +8.798 |
example | +8.364 |
experiments | +8.057 |
researchers | +7.993 |
Neg logit contributions | |
reck | -12.395 |
idential | -12.273 |
osher | -12.041 |
aren | -11.460 |
ouls | -11.438 |
Token | logs |
Token ID | 17259 |
Feature activation | -6.90e+00 |
Pos logit contributions | |
countries | +4.615 |
analys | +4.551 |
example | +4.288 |
researchers | +4.223 |
experiments | +4.158 |
Neg logit contributions | |
reck | -6.778 |
idential | -6.719 |
osher | -6.547 |
aren | -6.265 |
ouls | -6.219 |
Token | to |
Token ID | 284 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
countries | +4.622 |
analys | +4.598 |
example | +4.269 |
researchers | +4.161 |
experiments | +4.133 |
Neg logit contributions | |
idential | -7.162 |
reck | -7.159 |
osher | -6.968 |
aren | -6.715 |
Reserved | -6.707 |
Token | a |
Token ID | 257 |
Feature activation | +7.75e+00 |
Pos logit contributions | |
countries | +1.266 |
analys | +1.248 |
researchers | +1.145 |
example | +1.126 |
experiments | +1.120 |
Neg logit contributions | |
idential | -2.057 |
reck | -2.033 |
osher | -1.991 |
Reserved | -1.919 |
aren | -1.913 |
Token | decision |
Token ID | 2551 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
idential | +7.899 |
reck | +7.892 |
osher | +7.412 |
aren | +7.370 |
Reserved | +7.352 |
Neg logit contributions | |
countries | -5.308 |
analys | -5.195 |
researchers | -4.834 |
physicists | -4.783 |
experiments | -4.731 |
Token | , |
Token ID | 11 |
Feature activation | -7.80e+00 |
Pos logit contributions | |
analys | +2.093 |
countries | +2.077 |
researchers | +1.931 |
scientist | +1.898 |
example | +1.889 |
Neg logit contributions | |
idential | -2.240 |
reck | -2.199 |
osher | -2.150 |
Reserved | -2.076 |
ouls | -2.058 |
Token | � |
Token ID | 126 |
Feature activation | -9.61e+00 |
Pos logit contributions | |
analys | +6.107 |
countries | +5.865 |
researchers | +5.641 |
scientist | +5.427 |
example | +5.420 |
Neg logit contributions | |
idential | -7.313 |
reck | -7.249 |
osher | -7.093 |
Reserved | -6.795 |
rict | -6.782 |
Token | � |
Token ID | 242 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
countries | +5.222 |
analys | +4.753 |
researchers | +4.610 |
example | +4.511 |
latter | +4.392 |
Neg logit contributions | |
idential | -10.917 |
reck | -10.697 |
osher | -10.615 |
iquette | -10.364 |
hetto | -10.300 |
Token | he |
Token ID | 339 |
Feature activation | -2.21e+01 |
Pos logit contributions | |
analys | +9.986 |
countries | +9.676 |
researchers | +9.522 |
physicists | +8.943 |
example | +8.939 |
Neg logit contributions | |
idential | -11.131 |
reck | -10.764 |
osher | -10.666 |
Reserved | -10.330 |
hetto | -10.299 |
Token | said |
Token ID | 531 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
analys | +13.379 |
countries | +13.210 |
researchers | +13.190 |
experiments | +12.444 |
scientist | +12.290 |
Neg logit contributions | |
idential | -18.088 |
reck | -17.803 |
osher | -17.706 |
Reserved | -17.187 |
unicip | -17.166 |
Token | . |
Token ID | 13 |
Feature activation | -1.54e+01 |
Pos logit contributions | |
analys | +10.931 |
countries | +10.929 |
researchers | +10.339 |
physicists | +10.022 |
scientist | +10.019 |
Neg logit contributions | |
reck | -11.075 |
idential | -11.046 |
osher | -10.533 |
Reserved | -10.366 |
rict | -10.161 |
Token |
|
Token ID | 198 |
Feature activation | -7.69e+00 |
Pos logit contributions | |
countries | +10.175 |
analys | +9.986 |
researchers | +9.563 |
example | +9.326 |
scientist | +9.177 |
Neg logit contributions | |
idential | -14.569 |
reck | -14.544 |
osher | -14.152 |
aren | -13.462 |
rict | -13.432 |
Token |
|
Token ID | 198 |
Feature activation | -1.22e+01 |
Pos logit contributions | |
countries | +3.585 |
example | +3.399 |
researchers | +3.295 |
analys | +3.110 |
scientist | +2.992 |
Neg logit contributions | |
ailability | -9.553 |
osher | -9.349 |
idential | -9.316 |
reck | -9.140 |
ensical | -9.041 |
Token | � |
Token ID | 126 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
countries | +9.628 |
researchers | +9.374 |
analys | +9.238 |
example | +9.150 |
scientist | +8.999 |
Neg logit contributions | |
idential | -10.058 |
osher | -9.471 |
reck | -9.422 |
Shore | -9.073 |
Reserved | -9.045 |
Token | into |
Token ID | 656 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
countries | +8.969 |
analys | +8.280 |
researchers | +8.147 |
experiments | +7.827 |
physicists | +7.737 |
Neg logit contributions | |
idential | -16.416 |
reck | -16.245 |
osher | -16.014 |
Reserved | -15.663 |
idelines | -15.496 |
Token | astronomy |
Token ID | 37145 |
Feature activation | -9.67e+00 |
Pos logit contributions | |
analys | +10.779 |
countries | +10.746 |
researchers | +10.371 |
experiments | +10.117 |
physicists | +10.042 |
Neg logit contributions | |
idential | -14.891 |
reck | -14.774 |
osher | -14.384 |
aren | -14.144 |
iquette | -13.952 |
Token | , |
Token ID | 11 |
Feature activation | -1.22e+01 |
Pos logit contributions | |
countries | +7.669 |
analys | +7.501 |
researchers | +7.356 |
experiments | +7.280 |
scientist | +7.047 |
Neg logit contributions | |
idential | -8.592 |
reck | -8.462 |
osher | -8.325 |
aren | -8.101 |
Reserved | -8.044 |
Token | � |
Token ID | 447 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
countries | +9.025 |
analys | +8.911 |
researchers | +8.825 |
scientist | +8.392 |
experiments | +8.331 |
Neg logit contributions | |
idential | -10.804 |
reck | -10.725 |
osher | -10.316 |
ouls | -10.255 |
Reserved | -10.168 |
Token | � |
Token ID | 251 |
Feature activation | -2.41e+01 |
Pos logit contributions | |
countries | +7.664 |
analys | +6.971 |
researchers | +6.954 |
example | +6.799 |
experiments | +6.649 |
Neg logit contributions | |
idential | -10.909 |
reck | -10.648 |
osher | -10.334 |
Shore | -9.979 |
unicip | -9.970 |
Token | he |
Token ID | 339 |
Feature activation | -2.21e+01 |
Pos logit contributions | |
researchers | +17.416 |
countries | +17.375 |
analys | +16.822 |
scientist | +16.507 |
physicist | +16.288 |
Neg logit contributions | |
idential | -15.982 |
reck | -15.963 |
iquette | -15.512 |
osher | -15.123 |
ouls | -15.102 |
Token | says |
Token ID | 1139 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
countries | +13.200 |
researchers | +12.428 |
analys | +12.388 |
experiments | +12.212 |
scientist | +11.948 |
Neg logit contributions | |
reck | -19.144 |
idential | -19.102 |
Reserved | -18.143 |
osher | -17.972 |
unicip | -17.949 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
countries | +10.013 |
analys | +9.808 |
researchers | +9.350 |
scientist | +9.155 |
example | +9.140 |
Neg logit contributions | |
reck | -9.675 |
idential | -9.645 |
osher | -9.139 |
Reserved | -9.026 |
rict | -8.871 |
Token |
|
Token ID | 198 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
countries | +10.640 |
researchers | +10.217 |
analys | +10.099 |
scientist | +9.858 |
example | +9.846 |
Neg logit contributions | |
idential | -13.018 |
reck | -12.875 |
osher | -12.810 |
ouls | -12.001 |
iquette | -11.880 |
Token |
|
Token ID | 198 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
idential | +2.668 |
reck | +2.646 |
osher | +2.558 |
Reserved | +2.484 |
aren | +2.482 |
Neg logit contributions | |
countries | -1.704 |
analys | -1.654 |
researchers | -1.553 |
example | -1.518 |
scientist | -1.511 |
Token | Fake |
Token ID | 49233 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
countries | +1.777 |
analys | +1.722 |
researchers | +1.674 |
scientist | +1.638 |
example | +1.638 |
Neg logit contributions | |
idential | -1.749 |
reck | -1.689 |
osher | -1.648 |
Reserved | -1.591 |
rict | -1.579 |
Token | self |
Token ID | 2116 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
countries | +5.443 |
analys | +5.366 |
researchers | +4.984 |
example | +4.868 |
scientist | +4.846 |
Neg logit contributions | |
idential | -7.276 |
reck | -7.126 |
osher | -7.006 |
idelines | -6.835 |
ouls | -6.831 |
Token | - |
Token ID | 12 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
countries | +4.456 |
analys | +4.448 |
researchers | +4.130 |
experiments | +4.040 |
scientist | +4.024 |
Neg logit contributions | |
idential | -4.799 |
reck | -4.783 |
osher | -4.546 |
ouls | -4.491 |
Reserved | -4.465 |
Token | lim |
Token ID | 2475 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
countries | +2.441 |
analys | +2.404 |
researchers | +2.295 |
experiments | +2.272 |
scientist | +2.255 |
Neg logit contributions | |
idential | -1.247 |
reck | -1.209 |
osher | -1.163 |
Reserved | -1.133 |
ouls | -1.120 |
Token | iting |
Token ID | 1780 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
countries | +3.794 |
analys | +3.736 |
researchers | +3.516 |
experiments | +3.485 |
scientist | +3.443 |
Neg logit contributions | |
idential | -3.593 |
reck | -3.590 |
osher | -3.370 |
Reserved | -3.364 |
ouls | -3.335 |
Token | ," |
Token ID | 553 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
countries | +0.776 |
analys | +0.765 |
researchers | +0.721 |
scientist | +0.708 |
physicists | +0.706 |
Neg logit contributions | |
idential | -0.745 |
reck | -0.741 |
osher | -0.704 |
Reserved | -0.686 |
aren | -0.684 |
Token | he |
Token ID | 339 |
Feature activation | -2.20e+01 |
Pos logit contributions | |
countries | +10.984 |
analys | +10.598 |
researchers | +10.258 |
scientist | +10.142 |
physicist | +9.983 |
Neg logit contributions | |
reck | -10.869 |
idential | -10.850 |
osher | -10.421 |
ouls | -10.226 |
aren | -10.127 |
Token | told |
Token ID | 1297 |
Feature activation | -1.80e+01 |
Pos logit contributions | |
countries | +11.601 |
analys | +10.950 |
researchers | +10.231 |
experiments | +9.945 |
scientist | +9.920 |
Neg logit contributions | |
idential | -20.030 |
reck | -19.902 |
osher | -19.621 |
Reserved | -19.613 |
unicip | -19.446 |
Token | the |
Token ID | 262 |
Feature activation | -1.44e+01 |
Pos logit contributions | |
countries | +12.961 |
researchers | +12.375 |
analys | +12.244 |
scientist | +11.539 |
physicists | +11.494 |
Neg logit contributions | |
reck | -14.973 |
osher | -14.883 |
idential | -14.439 |
hetto | -13.917 |
unicip | -13.805 |
Token | BBC |
Token ID | 7823 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
countries | +9.368 |
researchers | +8.652 |
analys | +8.472 |
scientist | +8.304 |
BBC | +8.241 |
Neg logit contributions | |
reck | -14.384 |
idential | -14.005 |
osher | -13.911 |
unicip | -13.198 |
ouls | -13.171 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
countries | +8.352 |
analys | +8.111 |
researchers | +7.681 |
scientist | +7.603 |
physicist | +7.487 |
Neg logit contributions | |
reck | -9.438 |
idential | -9.250 |
osher | -9.065 |
Reserved | -8.828 |
ouls | -8.733 |
Token | WHO |
Token ID | 19494 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
countries | +10.906 |
analys | +10.065 |
researchers | +10.006 |
scientist | +9.864 |
example | +9.854 |
Neg logit contributions | |
reck | -10.990 |
osher | -10.940 |
idential | -10.918 |
ouls | -10.171 |
hetto | -10.164 |
Token | oud |
Token ID | 2778 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
idential | +1.292 |
reck | +1.270 |
osher | +1.040 |
Reserved | +0.955 |
aren | +0.940 |
Neg logit contributions | |
countries | -7.552 |
analys | -7.498 |
researchers | -7.237 |
scientist | -7.171 |
physicists | -7.171 |
Token | wasn |
Token ID | 2492 |
Feature activation | -8.10e+00 |
Pos logit contributions | |
idential | +2.388 |
reck | +2.356 |
osher | +2.230 |
Reserved | +2.150 |
rict | +2.147 |
Neg logit contributions | |
countries | -3.162 |
analys | -3.104 |
researchers | -2.971 |
scientist | -2.921 |
experiments | -2.914 |
Token | 't |
Token ID | 470 |
Feature activation | -9.93e+00 |
Pos logit contributions | |
countries | +3.680 |
example | +3.432 |
researchers | +3.356 |
analys | +3.177 |
scientist | +3.027 |
Neg logit contributions | |
ailability | -9.947 |
idential | -9.667 |
osher | -9.611 |
reck | -9.576 |
ensical | -9.422 |
Token | the |
Token ID | 262 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
countries | +4.632 |
example | +4.313 |
researchers | +4.193 |
analys | +4.148 |
scientist | +3.804 |
Neg logit contributions | |
ailability | -12.070 |
osher | -11.923 |
idential | -11.912 |
reck | -11.804 |
ensical | -11.405 |
Token | one |
Token ID | 530 |
Feature activation | -1.82e+01 |
Pos logit contributions | |
example | +3.930 |
countries | +3.737 |
scientist | +3.331 |
researchers | +3.109 |
latter | +3.027 |
Neg logit contributions | |
ailability | -19.851 |
idential | -19.637 |
osher | -19.490 |
idelines | -19.429 |
reck | -19.261 |
Token | tried |
Token ID | 3088 |
Feature activation | -2.19e+01 |
Pos logit contributions | |
countries | +7.278 |
experiments | +7.126 |
researchers | +6.798 |
scientist | +6.688 |
example | +6.587 |
Neg logit contributions | |
idential | -21.281 |
osher | -21.001 |
ailability | -20.695 |
idelines | -19.994 |
Reserved | -19.865 |
Token | to |
Token ID | 284 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
countries | +5.484 |
example | +4.911 |
researchers | +4.491 |
analys | +4.151 |
experiments | +3.994 |
Neg logit contributions | |
ailability | -29.865 |
ensical | -27.028 |
osher | -27.007 |
idential | -26.798 |
reck | -26.093 |
Token | steal |
Token ID | 8711 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
countries | +1.995 |
analys | +1.864 |
researchers | +1.773 |
example | +1.719 |
scientist | +1.660 |
Neg logit contributions | |
idential | -5.268 |
reck | -5.249 |
osher | -5.095 |
Reserved | -5.007 |
aren | -4.978 |
Token | dragon |
Token ID | 10441 |
Feature activation | -8.62e+00 |
Pos logit contributions | |
countries | +1.764 |
analys | +1.665 |
example | +1.594 |
scientist | +1.567 |
researchers | +1.566 |
Neg logit contributions | |
idential | -4.714 |
reck | -4.596 |
osher | -4.529 |
Reserved | -4.435 |
ouls | -4.386 |
Token | , |
Token ID | 11 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
countries | +5.658 |
example | +5.454 |
researchers | +5.190 |
analys | +4.998 |
scientist | +4.870 |
Neg logit contributions | |
ailability | -9.164 |
osher | -8.804 |
idential | -8.697 |
reck | -8.563 |
ensical | -8.386 |
Token | cause |
Token ID | 2728 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
countries | +6.407 |
example | +6.041 |
analys | +5.891 |
scientist | +5.752 |
latter | +5.499 |
Neg logit contributions | |
osher | -10.897 |
idential | -10.787 |
reck | -10.701 |
idelines | -10.320 |
ouls | -10.256 |
Token | it |
Token ID | 340 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
countries | +4.789 |
analys | +4.279 |
researchers | +4.204 |
example | +4.125 |
physicists | +4.112 |
Neg logit contributions | |
idential | -7.490 |
osher | -7.371 |
reck | -7.340 |
Reserved | -7.050 |
iquette | -7.034 |
Token | with |
Token ID | 351 |
Feature activation | -6.18e+00 |
Pos logit contributions | |
countries | +3.967 |
analys | +3.768 |
researchers | +3.585 |
experiments | +3.511 |
example | +3.496 |
Neg logit contributions | |
idential | -5.525 |
reck | -5.434 |
osher | -5.362 |
Reserved | -5.159 |
ouls | -5.094 |
Token | Iran |
Token ID | 4068 |
Feature activation | -8.92e+00 |
Pos logit contributions | |
countries | +4.482 |
analys | +4.203 |
example | +3.932 |
researchers | +3.928 |
experiments | +3.904 |
Neg logit contributions | |
idential | -6.338 |
reck | -6.175 |
osher | -6.095 |
aren | -5.889 |
ouls | -5.826 |
Token | , |
Token ID | 11 |
Feature activation | -6.22e+00 |
Pos logit contributions | |
countries | +7.100 |
analys | +6.661 |
researchers | +6.534 |
experiments | +6.388 |
example | +6.382 |
Neg logit contributions | |
reck | -7.902 |
idential | -7.887 |
osher | -7.855 |
Reserved | -7.530 |
rict | -7.473 |
Token | encouraging |
Token ID | 12577 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
countries | +4.881 |
analys | +4.653 |
researchers | +4.385 |
example | +4.285 |
physicists | +4.269 |
Neg logit contributions | |
idential | -5.992 |
reck | -5.849 |
osher | -5.766 |
iquette | -5.616 |
ouls | -5.544 |
Token | the |
Token ID | 262 |
Feature activation | -2.19e+01 |
Pos logit contributions | |
countries | +12.069 |
researchers | +10.685 |
analys | +10.230 |
regimes | +10.217 |
physicists | +10.203 |
Neg logit contributions | |
idential | -13.652 |
osher | -13.260 |
reck | -13.236 |
iquette | -12.780 |
ouls | -12.671 |
Token | Iranian |
Token ID | 10704 |
Feature activation | -2.18e+01 |
Pos logit contributions | |
countries | +17.372 |
latter | +15.822 |
researchers | +15.482 |
example | +15.288 |
regimes | +15.223 |
Neg logit contributions | |
idential | -15.905 |
osher | -15.164 |
reck | -14.820 |
unicip | -14.693 |
iquette | -14.606 |
Token | armed |
Token ID | 6936 |
Feature activation | -1.73e+01 |
Pos logit contributions | |
countries | +15.703 |
researchers | +14.367 |
scientist | +14.364 |
physicists | +14.245 |
example | +14.194 |
Neg logit contributions | |
idential | -17.616 |
osher | -17.326 |
reck | -16.731 |
Reserved | -16.070 |
erved | -16.060 |
Token | forces |
Token ID | 3386 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
countries | +9.536 |
regimes | +8.438 |
researchers | +8.318 |
scientist | +8.258 |
jihadists | +8.090 |
Neg logit contributions | |
idential | -18.478 |
osher | -18.242 |
reck | -17.881 |
ouls | -17.114 |
Reserved | -17.087 |
Token | to |
Token ID | 284 |
Feature activation | -9.67e+00 |
Pos logit contributions | |
countries | +6.695 |
analys | +6.215 |
researchers | +5.963 |
scientist | +5.779 |
experiments | +5.697 |
Neg logit contributions | |
idential | -11.370 |
reck | -11.202 |
osher | -11.025 |
Reserved | -10.666 |
ouls | -10.548 |
Token | stay |
Token ID | 2652 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
countries | +6.703 |
analys | +6.175 |
researchers | +6.047 |
scientist | +6.021 |
example | +5.985 |
Neg logit contributions | |
idential | -9.595 |
reck | -9.530 |
osher | -9.230 |
ouls | -9.039 |
aren | -9.004 |
Token | a |
Token ID | 257 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
countries | +8.431 |
analys | +7.922 |
researchers | +7.348 |
example | +7.316 |
experiments | +7.143 |
Neg logit contributions | |
idential | -12.623 |
reck | -12.528 |
osher | -12.240 |
aren | -12.029 |
Reserved | -12.023 |
Token | pand |
Token ID | 19798 |
Feature activation | -9.38e+00 |
Pos logit contributions | |
countries | +3.210 |
analys | +3.090 |
researchers | +2.853 |
scientist | +2.853 |
example | +2.812 |
Neg logit contributions | |
idential | -4.829 |
reck | -4.826 |
osher | -4.638 |
aren | -4.593 |
ouls | -4.583 |
Token | emic |
Token ID | 5314 |
Feature activation | -8.19e+00 |
Pos logit contributions | |
countries | +5.851 |
example | +5.517 |
analys | +5.446 |
researchers | +5.185 |
scientist | +5.092 |
Neg logit contributions | |
reck | -9.483 |
osher | -9.067 |
ouls | -9.036 |
honoring | -9.014 |
Shore | -9.004 |
Token | situation |
Token ID | 3074 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
countries | +6.287 |
analys | +6.070 |
example | +5.646 |
researchers | +5.612 |
scientist | +5.561 |
Neg logit contributions | |
idential | -7.777 |
reck | -7.776 |
osher | -7.601 |
ouls | -7.409 |
Reserved | -7.306 |
Token | ," |
Token ID | 553 |
Feature activation | -1.75e+01 |
Pos logit contributions | |
countries | +2.736 |
analys | +2.689 |
researchers | +2.517 |
scientist | +2.459 |
example | +2.450 |
Neg logit contributions | |
idential | -2.872 |
reck | -2.856 |
osher | -2.751 |
Reserved | -2.674 |
ouls | -2.658 |
Token | he |
Token ID | 339 |
Feature activation | -2.18e+01 |
Pos logit contributions | |
countries | +11.634 |
analys | +11.228 |
researchers | +10.891 |
scientist | +10.827 |
physicist | +10.591 |
Neg logit contributions | |
reck | -15.490 |
idential | -15.080 |
osher | -14.930 |
ouls | -14.701 |
aren | -14.599 |
Token | said |
Token ID | 531 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
countries | +11.787 |
analys | +11.052 |
researchers | +10.492 |
scientist | +10.286 |
experiments | +9.902 |
Neg logit contributions | |
idential | -19.868 |
reck | -19.757 |
osher | -19.514 |
ouls | -19.434 |
Reserved | -19.392 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e+01 |
Pos logit contributions | |
countries | +10.061 |
analys | +10.056 |
researchers | +9.104 |
experiments | +8.876 |
scientist | +8.789 |
Neg logit contributions | |
idential | -11.860 |
reck | -11.734 |
osher | -11.588 |
Reserved | -11.515 |
ouls | -11.258 |
Token | Although |
Token ID | 4900 |
Feature activation | -5.82e+00 |
Pos logit contributions | |
countries | +10.562 |
analys | +9.794 |
researchers | +9.639 |
scientist | +9.406 |
example | +9.396 |
Neg logit contributions | |
reck | -11.443 |
osher | -11.339 |
idential | -11.181 |
ouls | -10.675 |
hetto | -10.540 |
Token | most |
Token ID | 749 |
Feature activation | -9.50e+00 |
Pos logit contributions | |
countries | +4.355 |
analys | +4.185 |
researchers | +4.025 |
scientist | +3.832 |
experiments | +3.818 |
Neg logit contributions | |
reck | -5.908 |
idential | -5.850 |
osher | -5.717 |
aren | -5.491 |
ouls | -5.469 |
Token | suff |
Token ID | 3027 |
Feature activation | -7.63e+00 |
Pos logit contributions | |
countries | +6.807 |
analys | +6.072 |
researchers | +6.069 |
experiments | +5.744 |
scientist | +5.654 |
Neg logit contributions | |
reck | -9.986 |
idential | -9.913 |
osher | -9.718 |
iquette | -9.389 |
ouls | -9.223 |
Token | as |
Token ID | 355 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
countries | +3.889 |
analys | +3.720 |
researchers | +3.539 |
physicists | +3.439 |
physicist | +3.430 |
Neg logit contributions | |
idential | -4.724 |
reck | -4.679 |
osher | -4.502 |
ouls | -4.404 |
Reserved | -4.387 |
Token | will |
Token ID | 481 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
countries | +5.202 |
analys | +4.847 |
researchers | +4.660 |
example | +4.539 |
physicists | +4.525 |
Neg logit contributions | |
idential | -5.396 |
reck | -5.334 |
osher | -5.205 |
ouls | -4.983 |
Reserved | -4.981 |
Token | the |
Token ID | 262 |
Feature activation | -9.54e+00 |
Pos logit contributions | |
countries | +7.869 |
analys | +7.269 |
researchers | +6.754 |
experiments | +6.527 |
example | +6.492 |
Neg logit contributions | |
idential | -10.120 |
reck | -9.995 |
osher | -9.601 |
Reserved | -9.506 |
aren | -9.455 |
Token | 2015 |
Token ID | 1853 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
countries | +7.488 |
analys | +6.853 |
researchers | +6.522 |
example | +6.495 |
latter | +6.408 |
Neg logit contributions | |
idential | -9.227 |
reck | -9.070 |
osher | -8.735 |
aren | -8.620 |
Reserved | -8.514 |
Token | Iranian |
Token ID | 10704 |
Feature activation | -1.68e+01 |
Pos logit contributions | |
countries | +9.053 |
analys | +8.056 |
example | +7.814 |
researchers | +7.788 |
experiments | +7.702 |
Neg logit contributions | |
idential | -10.820 |
reck | -10.596 |
osher | -10.319 |
Reserved | -9.866 |
ufficient | -9.840 |
Token | nuclear |
Token ID | 4523 |
Feature activation | -2.18e+01 |
Pos logit contributions | |
countries | +10.177 |
example | +9.474 |
scientist | +9.424 |
researchers | +9.354 |
physicist | +9.351 |
Neg logit contributions | |
idential | -16.406 |
osher | -15.917 |
reck | -15.866 |
Reserved | -15.812 |
erved | -15.490 |
Token | deal |
Token ID | 1730 |
Feature activation | -8.93e+00 |
Pos logit contributions | |
countries | +11.384 |
scientist | +10.856 |
physicist | +10.641 |
experiments | +10.440 |
example | +10.422 |
Neg logit contributions | |
osher | -21.984 |
idential | -21.203 |
Reserved | -20.576 |
reck | -20.504 |
ouls | -20.276 |
Token | , |
Token ID | 11 |
Feature activation | -9.34e+00 |
Pos logit contributions | |
countries | +7.229 |
analys | +6.903 |
researchers | +6.459 |
scientist | +6.294 |
physicists | +6.293 |
Neg logit contributions | |
idential | -8.028 |
reck | -7.878 |
osher | -7.745 |
Reserved | -7.617 |
ouls | -7.409 |
Token | which |
Token ID | 543 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
countries | +7.121 |
analys | +6.659 |
researchers | +6.474 |
physicist | +6.207 |
scientist | +6.204 |
Neg logit contributions | |
idential | -8.950 |
reck | -8.897 |
osher | -8.617 |
ouls | -8.496 |
hetto | -8.437 |
Token | Britain |
Token ID | 5491 |
Feature activation | -7.12e+00 |
Pos logit contributions | |
countries | +5.027 |
analys | +4.693 |
researchers | +4.558 |
physicists | +4.400 |
scientist | +4.387 |
Neg logit contributions | |
idential | -5.244 |
reck | -5.198 |
osher | -4.975 |
hetto | -4.845 |
aren | -4.795 |
Token | helped |
Token ID | 4193 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
countries | +6.155 |
analys | +5.793 |
researchers | +5.503 |
scientist | +5.465 |
physicist | +5.358 |
Neg logit contributions | |
osher | -6.279 |
idential | -6.195 |
reck | -6.152 |
hetto | -5.842 |
ouls | -5.798 |
Token | with |
Token ID | 351 |
Feature activation | -6.18e+00 |
Pos logit contributions | |
countries | +3.967 |
analys | +3.768 |
researchers | +3.585 |
experiments | +3.511 |
example | +3.496 |
Neg logit contributions | |
idential | -5.525 |
reck | -5.434 |
osher | -5.362 |
Reserved | -5.159 |
ouls | -5.094 |
Token | Iran |
Token ID | 4068 |
Feature activation | -8.92e+00 |
Pos logit contributions | |
countries | +4.482 |
analys | +4.203 |
example | +3.932 |
researchers | +3.928 |
experiments | +3.904 |
Neg logit contributions | |
idential | -6.338 |
reck | -6.175 |
osher | -6.095 |
aren | -5.889 |
ouls | -5.826 |
Token | , |
Token ID | 11 |
Feature activation | -6.22e+00 |
Pos logit contributions | |
countries | +7.100 |
analys | +6.661 |
researchers | +6.534 |
experiments | +6.388 |
example | +6.382 |
Neg logit contributions | |
reck | -7.902 |
idential | -7.887 |
osher | -7.855 |
Reserved | -7.530 |
rict | -7.473 |
Token | encouraging |
Token ID | 12577 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
countries | +4.881 |
analys | +4.653 |
researchers | +4.385 |
example | +4.285 |
physicists | +4.269 |
Neg logit contributions | |
idential | -5.992 |
reck | -5.849 |
osher | -5.766 |
iquette | -5.616 |
ouls | -5.544 |
Token | the |
Token ID | 262 |
Feature activation | -2.19e+01 |
Pos logit contributions | |
countries | +12.069 |
researchers | +10.685 |
analys | +10.230 |
regimes | +10.217 |
physicists | +10.203 |
Neg logit contributions | |
idential | -13.652 |
osher | -13.260 |
reck | -13.236 |
iquette | -12.780 |
ouls | -12.671 |
Token | Iranian |
Token ID | 10704 |
Feature activation | -2.18e+01 |
Pos logit contributions | |
countries | +17.372 |
latter | +15.822 |
researchers | +15.482 |
example | +15.288 |
regimes | +15.223 |
Neg logit contributions | |
idential | -15.905 |
osher | -15.164 |
reck | -14.820 |
unicip | -14.693 |
iquette | -14.606 |
Token | armed |
Token ID | 6936 |
Feature activation | -1.73e+01 |
Pos logit contributions | |
countries | +15.703 |
researchers | +14.367 |
scientist | +14.364 |
physicists | +14.245 |
example | +14.194 |
Neg logit contributions | |
idential | -17.616 |
osher | -17.326 |
reck | -16.731 |
Reserved | -16.070 |
erved | -16.060 |
Token | forces |
Token ID | 3386 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
countries | +9.536 |
regimes | +8.438 |
researchers | +8.318 |
scientist | +8.258 |
jihadists | +8.090 |
Neg logit contributions | |
idential | -18.478 |
osher | -18.242 |
reck | -17.881 |
ouls | -17.114 |
Reserved | -17.087 |
Token | to |
Token ID | 284 |
Feature activation | -9.67e+00 |
Pos logit contributions | |
countries | +6.695 |
analys | +6.215 |
researchers | +5.963 |
scientist | +5.779 |
experiments | +5.697 |
Neg logit contributions | |
idential | -11.370 |
reck | -11.202 |
osher | -11.025 |
Reserved | -10.666 |
ouls | -10.548 |
Token | stay |
Token ID | 2652 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
countries | +6.703 |
analys | +6.175 |
researchers | +6.047 |
scientist | +6.021 |
example | +5.985 |
Neg logit contributions | |
idential | -9.595 |
reck | -9.530 |
osher | -9.230 |
ouls | -9.039 |
aren | -9.004 |
Token | in |
Token ID | 287 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
idential | +0.131 |
reck | +0.130 |
osher | +0.126 |
aren | +0.123 |
Reserved | +0.122 |
Neg logit contributions | |
countries | -0.084 |
analys | -0.081 |
researchers | -0.076 |
scientist | -0.073 |
physicists | -0.073 |
Token | Increases |
Token ID | 28544 |
Feature activation | -7.78e+00 |
Pos logit contributions | |
countries | +5.747 |
researchers | +5.399 |
analys | +5.392 |
example | +5.359 |
experiments | +5.236 |
Neg logit contributions | |
idential | -6.198 |
osher | -5.887 |
reck | -5.784 |
Shore | -5.624 |
Reserved | -5.577 |
Token | growth |
Token ID | 3349 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
countries | +5.359 |
analys | +5.161 |
researchers | +4.997 |
example | +4.834 |
experiments | +4.825 |
Neg logit contributions | |
reck | -7.989 |
idential | -7.950 |
osher | -7.721 |
iquette | -7.396 |
Reserved | -7.366 |
Token | hormone |
Token ID | 17770 |
Feature activation | -1.45e+01 |
Pos logit contributions | |
countries | +8.819 |
analys | +8.210 |
researchers | +7.929 |
experiments | +7.730 |
scientist | +7.557 |
Neg logit contributions | |
reck | -15.396 |
osher | -15.331 |
idential | -15.252 |
iquette | -14.820 |
ouls | -14.470 |
Token | ( |
Token ID | 357 |
Feature activation | -1.44e+01 |
Pos logit contributions | |
countries | +9.469 |
analys | +9.147 |
researchers | +8.856 |
experiments | +8.607 |
scientist | +8.453 |
Neg logit contributions | |
osher | -13.710 |
reck | -13.545 |
idential | -13.510 |
aren | -12.763 |
idelines | -12.703 |
Token | the |
Token ID | 1169 |
Feature activation | -2.02e+01 |
Pos logit contributions | |
countries | +12.439 |
researchers | +11.944 |
analys | +11.814 |
example | +11.803 |
scientist | +11.559 |
Neg logit contributions | |
idential | -10.243 |
osher | -9.803 |
reck | -9.692 |
Shore | -9.347 |
Reserved | -9.264 |
Token | opposite |
Token ID | 6697 |
Feature activation | -2.17e+01 |
Pos logit contributions | |
countries | +13.839 |
latter | +13.177 |
researchers | +13.105 |
analys | +13.105 |
example | +13.043 |
Neg logit contributions | |
idential | -16.214 |
reck | -16.141 |
osher | -15.720 |
ouls | -14.929 |
ibel | -14.871 |
Token | of |
Token ID | 286 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
example | +8.756 |
countries | +8.554 |
researchers | +7.836 |
analys | +7.625 |
experiments | +7.358 |
Neg logit contributions | |
ailability | -23.509 |
idential | -23.335 |
osher | -23.306 |
iquette | -22.539 |
reck | -22.347 |
Token | insulin |
Token ID | 14588 |
Feature activation | -1.81e+01 |
Pos logit contributions | |
countries | +7.604 |
analys | +7.299 |
researchers | +7.104 |
example | +6.976 |
experiments | +6.729 |
Neg logit contributions | |
reck | -11.537 |
idential | -11.348 |
osher | -10.985 |
iquette | -10.822 |
idelines | -10.620 |
Token | ). |
Token ID | 737 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
countries | +11.187 |
analys | +10.675 |
researchers | +10.437 |
experiments | +10.350 |
example | +10.283 |
Neg logit contributions | |
reck | -16.357 |
idential | -16.271 |
osher | -16.098 |
Reserved | -15.458 |
hetto | -14.899 |
Token |
|
Token ID | 198 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
countries | +7.588 |
analys | +7.276 |
researchers | +6.952 |
example | +6.755 |
experiments | +6.741 |
Neg logit contributions | |
idential | -11.650 |
reck | -11.578 |
osher | -11.185 |
aren | -10.814 |
Reserved | -10.775 |
Token |
|
Token ID | 198 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
idential | +1.978 |
reck | +1.960 |
osher | +1.904 |
Reserved | +1.840 |
aren | +1.837 |
Neg logit contributions | |
countries | -1.225 |
analys | -1.180 |
researchers | -1.115 |
example | -1.093 |
scientist | -1.081 |
Token | Fitzgerald |
Token ID | 28397 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
idential | +0.177 |
reck | +0.176 |
osher | +0.169 |
ouls | +0.159 |
aren | +0.159 |
Neg logit contributions | |
countries | -0.228 |
analys | -0.221 |
example | -0.214 |
researchers | -0.214 |
physicist | -0.212 |
Token | . |
Token ID | 13 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
countries | +0.277 |
analys | +0.273 |
researchers | +0.258 |
scientist | +0.254 |
physicists | +0.253 |
Neg logit contributions | |
idential | -0.257 |
reck | -0.255 |
osher | -0.242 |
Reserved | -0.236 |
aren | -0.235 |
Token |
|
Token ID | 198 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
idential | +3.836 |
reck | +3.823 |
osher | +3.649 |
aren | +3.563 |
rict | +3.556 |
Neg logit contributions | |
countries | -3.062 |
analys | -3.010 |
researchers | -2.812 |
scientist | -2.765 |
physicist | -2.760 |
Token |
|
Token ID | 198 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
idential | +4.509 |
reck | +4.493 |
osher | +4.290 |
aren | +4.212 |
Reserved | +4.206 |
Neg logit contributions | |
countries | -3.122 |
analys | -3.075 |
researchers | -2.847 |
physicists | -2.794 |
scientist | -2.793 |
Token | If |
Token ID | 1532 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
reck | +4.253 |
idential | +4.253 |
osher | +4.007 |
aren | +3.945 |
Reserved | +3.926 |
Neg logit contributions | |
countries | -4.117 |
analys | -4.080 |
researchers | -3.815 |
physicists | -3.760 |
scientist | -3.753 |
Token | Annie |
Token ID | 25860 |
Feature activation | +1.44e+01 |
Pos logit contributions | |
idential | +1.614 |
reck | +1.607 |
osher | +1.544 |
aren | +1.503 |
Reserved | +1.503 |
Neg logit contributions | |
countries | -1.248 |
analys | -1.226 |
researchers | -1.146 |
scientist | -1.123 |
physicists | -1.122 |
Token | Hall |
Token ID | 4789 |
Feature activation | +8.33e+00 |
Pos logit contributions | |
reck | +9.015 |
idential | +8.689 |
Shore | +8.419 |
rict | +8.100 |
Reserved | +8.017 |
Neg logit contributions | |
analys | -13.786 |
countries | -13.557 |
physicists | -12.646 |
physicist | -12.638 |
scientist | -12.541 |
Token | and |
Token ID | 290 |
Feature activation | +8.24e+00 |
Pos logit contributions | |
reck | +7.562 |
idential | +7.549 |
aren | +7.082 |
osher | +7.077 |
Reserved | +6.998 |
Neg logit contributions | |
countries | -6.534 |
analys | -6.498 |
researchers | -5.982 |
physicists | -5.973 |
physicist | -5.959 |
Token | Inter |
Token ID | 4225 |
Feature activation | +1.60e+01 |
Pos logit contributions | |
reck | +7.433 |
idential | +7.421 |
Shore | +6.993 |
Reserved | +6.926 |
aren | +6.913 |
Neg logit contributions | |
countries | -6.452 |
analys | -6.444 |
researchers | -5.922 |
physicists | -5.881 |
physicist | -5.828 |
Token | iors |
Token ID | 12706 |
Feature activation | +1.62e+01 |
Pos logit contributions | |
idential | +7.202 |
reck | +7.090 |
rict | +6.259 |
osher | +6.242 |
aren | +6.242 |
Neg logit contributions | |
analys | -19.496 |
countries | -18.863 |
physicist | -18.298 |
scientist | -18.267 |
physicists | -18.248 |
Token | didn |
Token ID | 1422 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
reck | +14.249 |
idential | +14.112 |
aren | +13.723 |
Shore | +13.205 |
Reserved | +13.200 |
Neg logit contributions | |
analys | -10.914 |
countries | -10.825 |
physicist | -10.035 |
physicists | -9.857 |
scientist | -9.763 |
Token | something |
Token ID | 1223 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
idential | +1.622 |
reck | +1.606 |
osher | +1.548 |
aren | +1.510 |
Reserved | +1.508 |
Neg logit contributions | |
countries | -1.117 |
analys | -1.094 |
researchers | -1.013 |
experiments | -0.989 |
physicists | -0.989 |
Token | . |
Token ID | 13 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
idential | +0.146 |
reck | +0.144 |
osher | +0.139 |
Reserved | +0.136 |
aren | +0.135 |
Neg logit contributions | |
countries | -0.106 |
analys | -0.103 |
researchers | -0.097 |
physicists | -0.095 |
scientist | -0.094 |
Token | And |
Token ID | 843 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
countries | +2.174 |
analys | +2.041 |
researchers | +1.951 |
example | +1.947 |
scientist | +1.907 |
Neg logit contributions | |
idential | -3.158 |
reck | -3.124 |
osher | -3.075 |
ouls | -2.917 |
rict | -2.905 |
Token | proposing |
Token ID | 24634 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
countries | +2.416 |
analys | +2.333 |
researchers | +2.213 |
example | +2.150 |
physicists | +2.149 |
Neg logit contributions | |
idential | -2.961 |
reck | -2.883 |
osher | -2.822 |
Reserved | -2.719 |
ouls | -2.708 |
Token | wildly |
Token ID | 20278 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
idential | +2.441 |
reck | +2.419 |
osher | +2.323 |
Reserved | +2.270 |
aren | +2.270 |
Neg logit contributions | |
countries | -1.758 |
analys | -1.718 |
researchers | -1.602 |
scientist | -1.567 |
physicists | -1.567 |
Token | unaff |
Token ID | 25312 |
Feature activation | +1.59e+01 |
Pos logit contributions | |
reck | +10.271 |
idential | +10.108 |
aren | +9.566 |
Shore | +9.454 |
rict | +9.416 |
Neg logit contributions | |
analys | -10.498 |
countries | -10.292 |
physicists | -9.644 |
physicist | -9.620 |
researchers | -9.608 |
Token | ordable |
Token ID | 16819 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
idential | +6.833 |
reck | +6.618 |
aren | +5.771 |
osher | +5.719 |
rict | +5.580 |
Neg logit contributions | |
analys | -20.070 |
countries | -19.443 |
scientist | -18.837 |
physicists | -18.703 |
researchers | -18.677 |
Token | stuff |
Token ID | 3404 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
countries | +0.884 |
analys | +0.830 |
researchers | +0.783 |
experiments | +0.771 |
example | +0.763 |
Neg logit contributions | |
idential | -1.501 |
reck | -1.481 |
osher | -1.439 |
Reserved | -1.399 |
ouls | -1.397 |
Token | is |
Token ID | 318 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
countries | +1.292 |
analys | +1.253 |
researchers | +1.189 |
experiments | +1.169 |
example | +1.164 |
Neg logit contributions | |
idential | -1.315 |
reck | -1.301 |
osher | -1.255 |
Reserved | -1.215 |
ouls | -1.198 |
Token | itself |
Token ID | 2346 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
countries | +5.045 |
analys | +4.835 |
researchers | +4.581 |
example | +4.554 |
experiments | +4.469 |
Neg logit contributions | |
idential | -6.449 |
reck | -6.193 |
osher | -6.167 |
ouls | -6.091 |
Reserved | -6.085 |
Token | a |
Token ID | 257 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
countries | +0.707 |
analys | +0.690 |
researchers | +0.641 |
example | +0.633 |
experiments | +0.628 |
Neg logit contributions | |
idential | -1.093 |
reck | -1.072 |
osher | -1.045 |
Reserved | -1.024 |
ouls | -1.024 |
Token |
|
Token ID | 198 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
countries | +2.110 |
analys | +2.093 |
researchers | +1.936 |
physicists | +1.908 |
physicist | +1.904 |
Neg logit contributions | |
idential | -2.840 |
reck | -2.834 |
osher | -2.699 |
aren | -2.656 |
Reserved | -2.654 |
Token |
|
Token ID | 198 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
idential | +4.557 |
reck | +4.542 |
osher | +4.332 |
aren | +4.258 |
Reserved | +4.251 |
Neg logit contributions | |
countries | -3.179 |
analys | -3.135 |
researchers | -2.899 |
physicists | -2.849 |
scientist | -2.845 |
Token | 5 |
Token ID | 20 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
reck | +1.315 |
idential | +1.283 |
osher | +1.193 |
aren | +1.176 |
rict | +1.164 |
Neg logit contributions | |
analys | -2.121 |
countries | -2.110 |
researchers | -1.996 |
scientist | -1.985 |
physicist | -1.983 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
countries | +2.003 |
example | +1.867 |
analys | +1.866 |
researchers | +1.841 |
scientist | +1.787 |
Neg logit contributions | |
idential | -2.400 |
reck | -2.348 |
osher | -2.338 |
iquette | -2.198 |
idelines | -2.193 |
Token | Crystal |
Token ID | 12969 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
reck | +8.601 |
idential | +8.499 |
Shore | +8.279 |
Reserved | +8.258 |
Pleasant | +8.078 |
Neg logit contributions | |
analys | -8.622 |
countries | -8.532 |
physicists | -7.955 |
researchers | -7.930 |
physicist | -7.836 |
Token | Emb |
Token ID | 13302 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
reck | +3.809 |
idential | +3.794 |
osher | +3.573 |
Shore | +3.548 |
Reserved | +3.534 |
Neg logit contributions | |
countries | -4.190 |
analys | -4.175 |
researchers | -3.889 |
physicists | -3.882 |
physicist | -3.849 |
Token | ry |
Token ID | 563 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
reck | +8.063 |
idential | +7.622 |
rict | +7.070 |
aren | +7.065 |
osher | +6.770 |
Neg logit contributions | |
analys | -16.064 |
countries | -15.889 |
physicists | -15.082 |
physicist | -14.860 |
researchers | -14.807 |
Token | o |
Token ID | 78 |
Feature activation | +6.99e+00 |
Pos logit contributions | |
idential | +0.437 |
reck | +0.432 |
osher | +0.413 |
Reserved | +0.412 |
aren | +0.404 |
Neg logit contributions | |
countries | -0.365 |
analys | -0.352 |
example | -0.337 |
researchers | -0.336 |
scientist | -0.330 |
Token | 04 |
Token ID | 8702 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
reck | +5.830 |
idential | +5.792 |
Reserved | +5.447 |
aren | +5.440 |
osher | +5.431 |
Neg logit contributions | |
countries | -6.077 |
analys | -6.043 |
researchers | -5.654 |
physicists | -5.643 |
physicist | -5.606 |
Token | : |
Token ID | 25 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
countries | +1.313 |
analys | +1.238 |
example | +1.218 |
researchers | +1.205 |
scientist | +1.163 |
Neg logit contributions | |
idential | -1.739 |
osher | -1.705 |
reck | -1.703 |
idelines | -1.603 |
ufficient | -1.598 |
Token | 30 |
Token ID | 1270 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
idential | +1.370 |
reck | +1.345 |
osher | +1.304 |
Reserved | +1.238 |
rict | +1.237 |
Neg logit contributions | |
countries | -1.553 |
analys | -1.507 |
researchers | -1.449 |
example | -1.443 |
scientist | -1.423 |
Token | because |
Token ID | 780 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
reck | +0.447 |
idential | +0.446 |
osher | +0.426 |
aren | +0.415 |
ouls | +0.414 |
Neg logit contributions | |
countries | -0.325 |
analys | -0.317 |
researchers | -0.298 |
example | -0.292 |
scientist | -0.290 |
Token | they |
Token ID | 484 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
idential | +2.655 |
reck | +2.635 |
osher | +2.493 |
aren | +2.442 |
Reserved | +2.438 |
Neg logit contributions | |
countries | -2.887 |
analys | -2.866 |
researchers | -2.683 |
physicists | -2.656 |
physicist | -2.654 |
Token | mistakenly |
Token ID | 33168 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
idential | +9.946 |
reck | +9.858 |
aren | +9.545 |
rict | +9.301 |
Reserved | +9.213 |
Neg logit contributions | |
analys | -9.111 |
countries | -8.990 |
physicist | -8.375 |
researchers | -8.287 |
physicists | -8.280 |
Token | believe |
Token ID | 1975 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
idential | +9.740 |
reck | +9.640 |
aren | +9.195 |
rict | +9.149 |
Reserved | +9.033 |
Neg logit contributions | |
analys | -8.764 |
countries | -8.738 |
physicist | -8.055 |
physicists | -8.050 |
researchers | -8.049 |
Token | school |
Token ID | 1524 |
Feature activation | +7.51e+00 |
Pos logit contributions | |
idential | +10.559 |
reck | +10.419 |
rict | +10.165 |
osher | +10.060 |
aren | +9.985 |
Neg logit contributions | |
analys | -8.911 |
countries | -8.600 |
physicists | -8.012 |
physicist | -7.982 |
scientist | -7.896 |
Token | leaders |
Token ID | 2766 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
idential | +7.223 |
reck | +7.151 |
osher | +6.850 |
rict | +6.763 |
aren | +6.738 |
Neg logit contributions | |
analys | -5.607 |
countries | -5.573 |
researchers | -5.061 |
physicists | -5.057 |
physicist | -5.057 |
Token | are |
Token ID | 389 |
Feature activation | +6.07e+00 |
Pos logit contributions | |
reck | +12.523 |
idential | +12.435 |
aren | +12.018 |
rict | +11.765 |
honoring | +11.694 |
Neg logit contributions | |
analys | -11.032 |
countries | -10.811 |
physicist | -10.218 |
physicists | -10.126 |
researchers | -10.019 |
Token | up |
Token ID | 510 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
reck | +6.113 |
idential | +6.099 |
osher | +5.821 |
aren | +5.746 |
rict | +5.737 |
Neg logit contributions | |
countries | -4.246 |
analys | -4.197 |
researchers | -3.873 |
physicist | -3.832 |
physicists | -3.819 |
Token | to |
Token ID | 284 |
Feature activation | +6.19e+00 |
Pos logit contributions | |
countries | +0.186 |
analys | +0.184 |
researchers | +0.170 |
physicists | +0.167 |
scientist | +0.167 |
Neg logit contributions | |
idential | -0.281 |
reck | -0.280 |
osher | -0.267 |
aren | -0.262 |
Reserved | -0.262 |
Token | the |
Token ID | 262 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
idential | +5.873 |
reck | +5.836 |
osher | +5.571 |
rict | +5.455 |
aren | +5.420 |
Neg logit contributions | |
countries | -4.714 |
analys | -4.690 |
researchers | -4.343 |
physicist | -4.306 |
scientist | -4.299 |
Token | task |
Token ID | 4876 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
reck | +4.867 |
idential | +4.857 |
osher | +4.665 |
rict | +4.592 |
aren | +4.582 |
Neg logit contributions | |
countries | -2.189 |
analys | -2.160 |
researchers | -1.940 |
physicists | -1.893 |
scientist | -1.893 |
Token | this |
Token ID | 428 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
countries | +1.094 |
analys | +1.071 |
researchers | +1.001 |
scientist | +0.981 |
example | +0.978 |
Neg logit contributions | |
idential | -1.685 |
reck | -1.661 |
osher | -1.603 |
aren | -1.560 |
rict | -1.551 |
Token | product |
Token ID | 1720 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
countries | +0.539 |
analys | +0.532 |
researchers | +0.487 |
example | +0.481 |
scientist | +0.480 |
Neg logit contributions | |
idential | -0.910 |
reck | -0.896 |
osher | -0.869 |
aren | -0.845 |
Reserved | -0.844 |
Token | anything |
Token ID | 1997 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
idential | +3.171 |
reck | +3.153 |
osher | +3.021 |
aren | +2.963 |
Reserved | +2.959 |
Neg logit contributions | |
countries | -2.042 |
analys | -2.008 |
researchers | -1.856 |
scientist | -1.818 |
physicists | -1.816 |
Token | lower |
Token ID | 2793 |
Feature activation | +9.53e+00 |
Pos logit contributions | |
idential | +5.192 |
reck | +5.188 |
osher | +4.955 |
aren | +4.894 |
rict | +4.869 |
Neg logit contributions | |
countries | -3.636 |
analys | -3.595 |
researchers | -3.300 |
physicist | -3.255 |
physicists | -3.248 |
Token | than |
Token ID | 621 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
idential | +8.693 |
reck | +8.657 |
rict | +8.252 |
aren | +8.177 |
osher | +8.147 |
Neg logit contributions | |
countries | -7.047 |
analys | -7.009 |
physicists | -6.488 |
researchers | -6.487 |
physicist | -6.461 |
Token | a |
Token ID | 257 |
Feature activation | +1.63e+01 |
Pos logit contributions | |
reck | +11.935 |
idential | +11.776 |
Reserved | +11.253 |
osher | +11.237 |
Shore | +11.224 |
Neg logit contributions | |
countries | -9.059 |
analys | -8.962 |
researchers | -8.321 |
physicists | -8.230 |
physicist | -8.163 |
Token | 5 |
Token ID | 642 |
Feature activation | +6.63e+00 |
Pos logit contributions | |
reck | +14.856 |
idential | +14.549 |
Shore | +14.097 |
Reserved | +14.017 |
osher | +14.014 |
Neg logit contributions | |
countries | -10.814 |
analys | -10.769 |
researchers | -9.908 |
physicists | -9.759 |
experiments | -9.721 |
Token | + |
Token ID | 10 |
Feature activation | +7.77e+00 |
Pos logit contributions | |
reck | +6.214 |
idential | +6.173 |
osher | +5.852 |
Shore | +5.788 |
rict | +5.780 |
Neg logit contributions | |
countries | -5.069 |
analys | -5.035 |
researchers | -4.693 |
physicists | -4.627 |
physicist | -4.608 |
Token | you |
Token ID | 345 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
reck | +7.863 |
idential | +7.829 |
osher | +7.475 |
Shore | +7.439 |
aren | +7.436 |
Neg logit contributions | |
countries | -5.187 |
analys | -5.170 |
researchers | -4.740 |
physicists | -4.678 |
physicist | -4.662 |
Token | don |
Token ID | 836 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
idential | +0.440 |
reck | +0.428 |
osher | +0.414 |
Reserved | +0.395 |
rict | +0.391 |
Neg logit contributions | |
countries | -0.510 |
analys | -0.497 |
researchers | -0.476 |
physicists | -0.469 |
scientist | -0.467 |
Token | 't |
Token ID | 470 |
Feature activation | +7.51e+00 |
Pos logit contributions | |
idential | +4.559 |
reck | +4.538 |
osher | +4.347 |
aren | +4.255 |
Reserved | +4.251 |
Neg logit contributions | |
countries | -3.086 |
analys | -3.026 |
researchers | -2.811 |
scientist | -2.753 |
physicists | -2.748 |
Token | so |
Token ID | 523 |
Feature activation | +7.01e+00 |
Pos logit contributions | |
idential | +6.969 |
reck | +6.891 |
osher | +6.588 |
Reserved | +6.501 |
aren | +6.472 |
Neg logit contributions | |
countries | -5.569 |
analys | -5.525 |
researchers | -5.077 |
physicists | -5.045 |
scientist | -5.028 |
Token | stay |
Token ID | 2652 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
idential | +6.838 |
reck | +6.814 |
osher | +6.478 |
Reserved | +6.415 |
aren | +6.412 |
Neg logit contributions | |
countries | -5.092 |
analys | -5.078 |
researchers | -4.629 |
scientist | -4.601 |
physicist | -4.584 |
Token | and |
Token ID | 290 |
Feature activation | +9.77e+00 |
Pos logit contributions | |
idential | +6.144 |
reck | +6.138 |
osher | +5.796 |
Reserved | +5.742 |
aren | +5.734 |
Neg logit contributions | |
countries | -4.968 |
analys | -4.925 |
researchers | -4.548 |
physicists | -4.501 |
scientist | -4.485 |
Token | enjoy |
Token ID | 2883 |
Feature activation | +7.36e+00 |
Pos logit contributions | |
reck | +9.671 |
idential | +9.650 |
aren | +9.190 |
Reserved | +9.177 |
osher | +9.170 |
Neg logit contributions | |
countries | -6.591 |
analys | -6.583 |
physicists | -5.914 |
researchers | -5.911 |
physicist | -5.894 |
Token | the |
Token ID | 262 |
Feature activation | +6.12e+00 |
Pos logit contributions | |
idential | +7.173 |
reck | +7.145 |
osher | +6.796 |
Shore | +6.778 |
Reserved | +6.737 |
Neg logit contributions | |
analys | -5.289 |
countries | -5.288 |
researchers | -4.818 |
physicists | -4.775 |
physicist | -4.739 |
Token | woods |
Token ID | 16479 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
idential | +6.046 |
reck | +6.014 |
osher | +5.732 |
Reserved | +5.660 |
Shore | +5.651 |
Neg logit contributions | |
analys | -4.442 |
countries | -4.439 |
researchers | -4.054 |
physicists | -3.998 |
physicist | -3.977 |
Token | and |
Token ID | 290 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
idential | +5.512 |
reck | +5.492 |
osher | +5.181 |
aren | +5.122 |
Reserved | +5.092 |
Neg logit contributions | |
countries | -5.210 |
analys | -5.174 |
researchers | -4.820 |
physicists | -4.773 |
physicist | -4.755 |
Token | water |
Token ID | 1660 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
idential | +9.700 |
reck | +9.660 |
Shore | +9.287 |
Pleasant | +9.186 |
rict | +9.156 |
Neg logit contributions | |
analys | -7.004 |
countries | -6.812 |
physicists | -6.217 |
researchers | -6.214 |
physicist | -6.212 |
Token | falls |
Token ID | 23348 |
Feature activation | +8.76e+00 |
Pos logit contributions | |
countries | +1.028 |
analys | +1.001 |
researchers | +0.952 |
scientist | +0.940 |
example | +0.939 |
Neg logit contributions | |
idential | -1.118 |
reck | -1.111 |
osher | -1.067 |
rict | -1.030 |
Reserved | -1.026 |
Token | . |
Token ID | 13 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
idential | +7.771 |
reck | +7.764 |
aren | +7.323 |
osher | +7.310 |
Reserved | +7.289 |
Neg logit contributions | |
countries | -6.993 |
analys | -6.952 |
researchers | -6.430 |
physicists | -6.362 |
physicist | -6.353 |
Token |
|
Token ID | 198 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
idential | +4.716 |
reck | +4.688 |
osher | +4.471 |
Reserved | +4.418 |
aren | +4.399 |
Neg logit contributions | |
countries | -3.641 |
analys | -3.619 |
researchers | -3.333 |
physicists | -3.289 |
scientist | -3.280 |
Token | mistaken |
Token ID | 16011 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
reck | +4.671 |
idential | +4.668 |
osher | +4.428 |
aren | +4.349 |
rict | +4.338 |
Neg logit contributions | |
countries | -3.755 |
analys | -3.705 |
researchers | -3.437 |
physicists | -3.389 |
physicist | -3.388 |
Token | or |
Token ID | 393 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
reck | +4.243 |
idential | +4.238 |
osher | +3.967 |
rict | +3.880 |
aren | +3.876 |
Neg logit contributions | |
countries | -4.872 |
analys | -4.795 |
researchers | -4.508 |
physicists | -4.484 |
physicist | -4.475 |
Token | that |
Token ID | 326 |
Feature activation | +5.10e+00 |
Pos logit contributions | |
reck | +13.818 |
idential | +13.344 |
aren | +12.928 |
Shore | +12.797 |
honoring | +12.718 |
Neg logit contributions | |
analys | -9.632 |
countries | -9.543 |
physicist | -8.663 |
physicists | -8.558 |
researchers | -8.450 |
Token | what |
Token ID | 644 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
reck | +5.308 |
idential | +5.300 |
osher | +5.050 |
aren | +4.986 |
rict | +4.967 |
Neg logit contributions | |
countries | -3.428 |
analys | -3.360 |
researchers | -3.068 |
physicist | -3.046 |
physicists | -3.043 |
Token | she |
Token ID | 673 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
countries | +2.640 |
analys | +2.603 |
researchers | +2.530 |
scientist | +2.466 |
physicists | +2.449 |
Neg logit contributions | |
idential | -2.524 |
reck | -2.503 |
osher | -2.381 |
rict | -2.306 |
Reserved | -2.306 |
Token | called |
Token ID | 1444 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
countries | +0.556 |
analys | +0.553 |
researchers | +0.525 |
scientist | +0.513 |
physicists | +0.507 |
Neg logit contributions | |
idential | -0.635 |
reck | -0.630 |
osher | -0.609 |
Reserved | -0.592 |
rict | -0.586 |
Token | soft |
Token ID | 2705 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
reck | +4.201 |
idential | +4.187 |
osher | +3.988 |
aren | +3.923 |
rict | +3.914 |
Neg logit contributions | |
countries | -3.102 |
analys | -3.051 |
researchers | -2.813 |
physicists | -2.790 |
physicist | -2.783 |
Token | tissue |
Token ID | 10712 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
countries | +1.058 |
analys | +1.043 |
researchers | +0.975 |
scientist | +0.958 |
physicists | +0.953 |
Neg logit contributions | |
idential | -1.346 |
reck | -1.339 |
osher | -1.274 |
Reserved | -1.254 |
aren | -1.248 |
Token | was |
Token ID | 373 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
idential | +0.097 |
reck | +0.097 |
osher | +0.092 |
Reserved | +0.089 |
aren | +0.089 |
Neg logit contributions | |
countries | -0.088 |
analys | -0.087 |
researchers | -0.083 |
experiments | -0.081 |
scientist | -0.080 |
Token | really |
Token ID | 1107 |
Feature activation | +5.72e-03 |
Pos logit contributions | |
countries | +0.963 |
analys | +0.962 |
researchers | +0.896 |
scientist | +0.875 |
experiments | +0.868 |
Neg logit contributions | |
idential | -1.385 |
reck | -1.371 |
osher | -1.316 |
aren | -1.288 |
Reserved | -1.286 |
Token | bio |
Token ID | 13401 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
idential | +0.006 |
reck | +0.006 |
osher | +0.006 |
aren | +0.006 |
Reserved | +0.006 |
Neg logit contributions | |
countries | -0.004 |
analys | -0.004 |
researchers | -0.004 |
scientist | -0.004 |
experiments | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
idential | +1.095 |
reck | +1.091 |
osher | +1.048 |
Reserved | +1.029 |
aren | +1.029 |
Neg logit contributions | |
countries | -0.590 |
analys | -0.578 |
researchers | -0.529 |
scientist | -0.517 |
physicists | -0.516 |
Token | ' |
Token ID | 705 |
Feature activation | +6.23e+00 |
Pos logit contributions | |
idential | +3.396 |
reck | +3.385 |
osher | +3.233 |
aren | +3.186 |
Reserved | +3.185 |
Neg logit contributions | |
countries | -2.093 |
analys | -2.072 |
researchers | -1.895 |
scientist | -1.861 |
physicists | -1.860 |
Token | National |
Token ID | 16186 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
reck | +5.106 |
idential | +4.936 |
aren | +4.674 |
osher | +4.659 |
rict | +4.573 |
Neg logit contributions | |
analys | -5.696 |
countries | -5.642 |
researchers | -5.274 |
physicists | -5.231 |
physicist | -5.228 |
Token | Review |
Token ID | 6602 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
idential | +7.523 |
reck | +7.458 |
Shore | +7.106 |
osher | +7.059 |
Reserved | +7.059 |
Neg logit contributions | |
analys | -9.691 |
countries | -9.621 |
physicists | -8.938 |
researchers | -8.912 |
experiments | -8.864 |
Token | ,' |
Token ID | 4032 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
idential | +3.031 |
reck | +3.005 |
osher | +2.833 |
Reserved | +2.764 |
aren | +2.760 |
Neg logit contributions | |
countries | -3.620 |
analys | -3.600 |
researchers | -3.362 |
physicists | -3.340 |
physicist | -3.333 |
Token | a |
Token ID | 257 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
idential | +0.462 |
reck | +0.461 |
osher | +0.442 |
Reserved | +0.430 |
aren | +0.430 |
Neg logit contributions | |
countries | -0.352 |
analys | -0.345 |
researchers | -0.323 |
scientist | -0.315 |
physicists | -0.315 |
Token | magazine |
Token ID | 7093 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
idential | +2.461 |
reck | +2.444 |
osher | +2.352 |
aren | +2.306 |
Reserved | +2.297 |
Neg logit contributions | |
countries | -1.559 |
analys | -1.525 |
researchers | -1.422 |
scientist | -1.402 |
physicist | -1.396 |
Token | that |
Token ID | 326 |
Feature activation | +8.78e+00 |
Pos logit contributions | |
countries | +0.407 |
analys | +0.402 |
researchers | +0.377 |
scientist | +0.367 |
example | +0.367 |
Neg logit contributions | |
idential | -0.511 |
reck | -0.507 |
osher | -0.485 |
aren | -0.473 |
Reserved | -0.471 |
Token | 's |
Token ID | 338 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
idential | +8.149 |
reck | +8.105 |
osher | +7.675 |
Shore | +7.658 |
Reserved | +7.614 |
Neg logit contributions | |
countries | -6.641 |
analys | -6.627 |
physicist | -6.049 |
researchers | -6.046 |
scientist | -6.039 |
Token | been |
Token ID | 587 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
idential | +0.118 |
reck | +0.116 |
osher | +0.112 |
aren | +0.110 |
Reserved | +0.109 |
Neg logit contributions | |
countries | -0.077 |
analys | -0.077 |
researchers | -0.071 |
scientist | -0.069 |
physicists | -0.068 |
Token | pretty |
Token ID | 2495 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
idential | +0.615 |
reck | +0.605 |
osher | +0.587 |
ouls | +0.571 |
aren | +0.571 |
Neg logit contributions | |
countries | -0.392 |
analys | -0.391 |
researchers | -0.358 |
scientist | -0.347 |
physicists | -0.346 |
Token | companies |
Token ID | 2706 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
countries | +8.840 |
analys | +8.067 |
researchers | +7.836 |
regimes | +7.712 |
scientist | +7.667 |
Neg logit contributions | |
idential | -8.971 |
reck | -8.945 |
osher | -8.579 |
rict | -8.244 |
aren | -8.239 |
Token | are |
Token ID | 389 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
idential | +3.511 |
reck | +3.496 |
osher | +3.312 |
aren | +3.243 |
Reserved | +3.237 |
Neg logit contributions | |
countries | -3.388 |
analys | -3.347 |
researchers | -3.141 |
physicists | -3.093 |
scientist | -3.091 |
Token | controlled |
Token ID | 6856 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
countries | +2.235 |
analys | +2.145 |
researchers | +1.994 |
physicists | +1.947 |
example | +1.946 |
Neg logit contributions | |
idential | -3.088 |
reck | -3.055 |
osher | -2.949 |
aren | -2.871 |
Reserved | -2.849 |
Token | by |
Token ID | 416 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
idential | +1.956 |
reck | +1.946 |
osher | +1.838 |
aren | +1.803 |
rict | +1.802 |
Neg logit contributions | |
countries | -1.881 |
analys | -1.877 |
researchers | -1.756 |
physicist | -1.737 |
physicists | -1.735 |
Token | foreigners |
Token ID | 19670 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
countries | +0.013 |
analys | +0.013 |
researchers | +0.012 |
scientist | +0.012 |
physicists | +0.012 |
Neg logit contributions | |
idential | -0.022 |
reck | -0.022 |
osher | -0.021 |
aren | -0.021 |
Reserved | -0.021 |
Token | who |
Token ID | 508 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
countries | +3.668 |
analys | +3.540 |
researchers | +3.321 |
scientist | +3.231 |
physicists | +3.217 |
Neg logit contributions | |
reck | -4.024 |
idential | -4.008 |
osher | -3.845 |
rict | -3.712 |
Reserved | -3.703 |
Token | have |
Token ID | 423 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
idential | +3.227 |
reck | +3.215 |
osher | +3.062 |
Reserved | +2.994 |
aren | +2.991 |
Neg logit contributions | |
countries | -2.698 |
analys | -2.654 |
researchers | -2.480 |
scientist | -2.437 |
physicists | -2.437 |
Token | made |
Token ID | 925 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
countries | +3.619 |
analys | +3.373 |
researchers | +3.188 |
experiments | +3.157 |
example | +3.145 |
Neg logit contributions | |
reck | -4.287 |
idential | -4.285 |
osher | -4.181 |
aren | -4.005 |
iquette | -3.970 |
Token | millions |
Token ID | 5242 |
Feature activation | -6.41e+00 |
Pos logit contributions | |
countries | +2.305 |
analys | +2.127 |
experiments | +2.018 |
researchers | +2.015 |
example | +2.012 |
Neg logit contributions | |
idential | -3.071 |
reck | -3.016 |
osher | -2.937 |
aren | -2.830 |
Reserved | -2.825 |
Token | from |
Token ID | 422 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
countries | +4.656 |
analys | +4.569 |
researchers | +4.106 |
example | +4.057 |
scientist | +4.026 |
Neg logit contributions | |
idential | -6.430 |
reck | -6.327 |
osher | -6.151 |
iquette | -5.944 |
Reserved | -5.936 |
Token | them |
Token ID | 606 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
countries | +2.064 |
analys | +1.968 |
researchers | +1.806 |
example | +1.784 |
experiments | +1.782 |
Neg logit contributions | |
idential | -2.886 |
reck | -2.848 |
osher | -2.751 |
aren | -2.669 |
Reserved | -2.662 |
Token | � |
Token ID | 247 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
idential | +2.400 |
reck | +2.384 |
osher | +2.267 |
aren | +2.207 |
Reserved | +2.201 |
Neg logit contributions | |
countries | -2.374 |
analys | -2.322 |
researchers | -2.197 |
scientist | -2.162 |
physicists | -2.153 |
Token | s |
Token ID | 82 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
idential | +2.355 |
reck | +2.344 |
osher | +2.212 |
aren | +2.159 |
Reserved | +2.156 |
Neg logit contributions | |
countries | -2.689 |
analys | -2.654 |
researchers | -2.507 |
scientist | -2.470 |
physicists | -2.468 |
Token | comments |
Token ID | 3651 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
reck | +12.433 |
idential | +12.419 |
Pleasant | +11.645 |
Shore | +11.628 |
osher | +11.628 |
Neg logit contributions | |
analys | -7.607 |
countries | -7.356 |
physicists | -6.821 |
physicist | -6.680 |
researchers | -6.592 |
Token | and |
Token ID | 290 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
idential | +8.822 |
reck | +8.801 |
osher | +8.254 |
aren | +8.240 |
honoring | +8.154 |
Neg logit contributions | |
countries | -7.937 |
analys | -7.872 |
physicists | -7.353 |
physicist | -7.308 |
researchers | -7.280 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
reck | +11.986 |
idential | +11.935 |
aren | +11.253 |
Shore | +11.243 |
Pleasant | +11.200 |
Neg logit contributions | |
analys | -6.971 |
countries | -6.855 |
physicists | -6.294 |
physicist | -6.220 |
scientist | -6.140 |
Token | about |
Token ID | 546 |
Feature activation | +8.77e+00 |
Pos logit contributions | |
idential | +3.058 |
reck | +3.047 |
osher | +2.906 |
aren | +2.850 |
Reserved | +2.845 |
Neg logit contributions | |
countries | -2.298 |
analys | -2.262 |
researchers | -2.106 |
physicists | -2.066 |
scientist | -2.066 |
Token | what |
Token ID | 644 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
reck | +8.745 |
idential | +8.729 |
osher | +8.265 |
Reserved | +8.254 |
aren | +8.245 |
Neg logit contributions | |
analys | -5.973 |
countries | -5.914 |
physicists | -5.460 |
physicist | -5.418 |
scientist | -5.394 |
Token | sort |
Token ID | 3297 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
idential | +4.795 |
reck | +4.778 |
osher | +4.557 |
aren | +4.476 |
Reserved | +4.470 |
Neg logit contributions | |
countries | -3.436 |
analys | -3.389 |
researchers | -3.139 |
physicists | -3.085 |
scientist | -3.083 |
Token | of |
Token ID | 286 |
Feature activation | +7.42e+00 |
Pos logit contributions | |
idential | +0.735 |
reck | +0.729 |
osher | +0.691 |
rict | +0.679 |
aren | +0.678 |
Neg logit contributions | |
analys | -0.584 |
countries | -0.567 |
physicists | -0.528 |
physicist | -0.528 |
researchers | -0.525 |
Token | material |
Token ID | 2587 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
idential | +7.782 |
reck | +7.735 |
osher | +7.347 |
Reserved | +7.280 |
rict | +7.248 |
Neg logit contributions | |
analys | -4.840 |
countries | -4.799 |
physicists | -4.368 |
researchers | -4.352 |
physicist | -4.333 |
Token | will |
Token ID | 481 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
idential | +13.441 |
reck | +13.384 |
Shore | +12.999 |
aren | +12.890 |
Reserved | +12.860 |
Neg logit contributions | |
analys | -10.251 |
countries | -9.834 |
physicist | -9.290 |
physicists | -9.208 |
scientist | -9.157 |
Token | only |
Token ID | 691 |
Feature activation | +9.12e+00 |
Pos logit contributions | |
countries | +2.554 |
analys | +2.514 |
researchers | +2.314 |
example | +2.252 |
physicists | +2.246 |
Neg logit contributions | |
idential | -3.561 |
reck | -3.531 |
osher | -3.427 |
Reserved | -3.332 |
ouls | -3.328 |
Token | a |
Token ID | 257 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
reck | +9.068 |
idential | +9.065 |
osher | +8.567 |
rict | +8.555 |
Shore | +8.473 |
Neg logit contributions | |
analys | -5.957 |
countries | -5.906 |
researchers | -5.525 |
physicists | -5.477 |
physicist | -5.466 |
Token | qualified |
Token ID | 10617 |
Feature activation | +6.03e+00 |
Pos logit contributions | |
reck | +11.561 |
idential | +11.474 |
osher | +10.920 |
Shore | +10.861 |
Pleasant | +10.778 |
Neg logit contributions | |
analys | -7.960 |
countries | -7.867 |
researchers | -7.339 |
physicists | -7.274 |
experiments | -7.251 |
Token | majority |
Token ID | 3741 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
idential | +5.663 |
reck | +5.643 |
osher | +5.356 |
rict | +5.257 |
aren | +5.256 |
Neg logit contributions | |
countries | -4.599 |
analys | -4.594 |
researchers | -4.258 |
physicists | -4.209 |
experiments | -4.190 |
Token | of |
Token ID | 286 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
idential | +2.725 |
reck | +2.717 |
osher | +2.577 |
aren | +2.527 |
Reserved | +2.524 |
Neg logit contributions | |
countries | -2.372 |
analys | -2.343 |
researchers | -2.193 |
physicists | -2.160 |
scientist | -2.156 |
Token | EU |
Token ID | 4576 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
countries | +1.927 |
analys | +1.822 |
researchers | +1.727 |
physicists | +1.673 |
example | +1.664 |
Neg logit contributions | |
idential | -2.743 |
reck | -2.741 |
osher | -2.615 |
aren | -2.562 |
Reserved | -2.524 |
Token | member |
Token ID | 2888 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
countries | +3.806 |
analys | +3.376 |
researchers | +3.308 |
physicists | +3.146 |
scientist | +3.123 |
Neg logit contributions | |
idential | -5.836 |
reck | -5.793 |
osher | -5.576 |
Reserved | -5.458 |
ouls | -5.403 |
Token | states |
Token ID | 2585 |
Feature activation | +7.62e+00 |
Pos logit contributions | |
countries | +6.055 |
analys | +4.776 |
researchers | +4.586 |
regimes | +4.366 |
experiments | +4.270 |
Neg logit contributions | |
idential | -15.625 |
reck | -15.087 |
osher | -14.949 |
Reserved | -14.619 |
hetto | -14.529 |
Token | . |
Token ID | 13 |
Feature activation | -7.79e+00 |
Pos logit contributions | |
reck | +6.728 |
idential | +6.711 |
aren | +6.274 |
osher | +6.269 |
rict | +6.227 |
Neg logit contributions | |
countries | -6.160 |
analys | -6.120 |
researchers | -5.770 |
physicist | -5.730 |
physicists | -5.714 |
Token |
|
Token ID | 198 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
countries | +5.116 |
analys | +4.737 |
example | +4.450 |
researchers | +4.447 |
scientist | +4.284 |
Neg logit contributions | |
reck | -8.135 |
idential | -8.128 |
osher | -7.943 |
ouls | -7.671 |
aren | -7.580 |
Token |
|
Token ID | 198 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
countries | +2.196 |
example | +1.995 |
analys | +1.974 |
researchers | +1.970 |
scientist | +1.843 |
Neg logit contributions | |
idential | -4.682 |
osher | -4.601 |
reck | -4.587 |
ailability | -4.461 |
iquette | -4.368 |
Token | amazingly |
Token ID | 32513 |
Feature activation | +6.58e+00 |
Pos logit contributions | |
countries | +1.416 |
analys | +1.390 |
researchers | +1.287 |
scientist | +1.268 |
experiments | +1.262 |
Neg logit contributions | |
idential | -2.054 |
reck | -2.030 |
osher | -1.977 |
Reserved | -1.913 |
aren | -1.909 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
reck | +5.955 |
idential | +5.928 |
osher | +5.585 |
aren | +5.544 |
rict | +5.504 |
Neg logit contributions | |
countries | -5.255 |
analys | -5.194 |
researchers | -4.877 |
physicists | -4.795 |
physicist | -4.787 |
Token | We |
Token ID | 775 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
idential | +1.428 |
reck | +1.422 |
osher | +1.363 |
aren | +1.325 |
rict | +1.323 |
Neg logit contributions | |
countries | -1.077 |
analys | -1.051 |
researchers | -0.983 |
scientist | -0.966 |
physicist | -0.965 |
Token | thought |
Token ID | 1807 |
Feature activation | +6.34e+00 |
Pos logit contributions | |
countries | +0.668 |
analys | +0.650 |
researchers | +0.620 |
physicists | +0.609 |
scientist | +0.606 |
Neg logit contributions | |
idential | -0.665 |
reck | -0.656 |
osher | -0.632 |
Reserved | -0.608 |
rict | -0.605 |
Token | we |
Token ID | 356 |
Feature activation | +4.98e+00 |
Pos logit contributions | |
reck | +5.713 |
idential | +5.659 |
osher | +5.381 |
aren | +5.320 |
Shore | +5.310 |
Neg logit contributions | |
countries | -5.067 |
analys | -5.038 |
researchers | -4.700 |
scientist | -4.636 |
physicist | -4.622 |
Token | were |
Token ID | 547 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
reck | +3.895 |
idential | +3.894 |
osher | +3.637 |
aren | +3.595 |
rict | +3.562 |
Neg logit contributions | |
countries | -4.698 |
analys | -4.665 |
researchers | -4.390 |
physicist | -4.345 |
scientist | -4.337 |
Token | just |
Token ID | 655 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
countries | +0.122 |
analys | +0.120 |
researchers | +0.110 |
physicists | +0.108 |
scientist | +0.108 |
Neg logit contributions | |
idential | -0.209 |
reck | -0.207 |
osher | -0.199 |
Reserved | -0.195 |
aren | -0.195 |
Token | going |
Token ID | 1016 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
countries | +1.486 |
analys | +1.459 |
researchers | +1.336 |
experiments | +1.309 |
physicists | +1.308 |
Neg logit contributions | |
idential | -2.673 |
reck | -2.621 |
osher | -2.545 |
Reserved | -2.485 |
aren | -2.480 |
Token | to |
Token ID | 284 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
countries | +7.381 |
analys | +6.942 |
researchers | +6.515 |
experiments | +6.377 |
example | +6.344 |
Neg logit contributions | |
idential | -13.935 |
reck | -13.790 |
osher | -13.220 |
Reserved | -13.179 |
ufficient | -12.993 |
Token | make |
Token ID | 787 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
countries | +2.292 |
analys | +2.179 |
researchers | +2.067 |
example | +2.033 |
experiments | +2.031 |
Neg logit contributions | |
idential | -3.600 |
reck | -3.534 |
osher | -3.422 |
aren | -3.327 |
Reserved | -3.309 |
Token | a |
Token ID | 257 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
countries | +1.601 |
analys | +1.523 |
researchers | +1.422 |
experiments | +1.419 |
example | +1.414 |
Neg logit contributions | |
idential | -2.624 |
reck | -2.575 |
osher | -2.488 |
aren | -2.426 |
rict | -2.419 |
Token |
|
Token ID | 198 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
idential | +2.298 |
reck | +2.280 |
osher | +2.208 |
Reserved | +2.141 |
aren | +2.138 |
Neg logit contributions | |
countries | -1.461 |
analys | -1.415 |
researchers | -1.335 |
example | -1.304 |
scientist | -1.295 |
Token | C |
Token ID | 34 |
Feature activation | +8.14e+00 |
Pos logit contributions | |
idential | +1.743 |
reck | +1.728 |
osher | +1.639 |
Reserved | +1.599 |
aren | +1.594 |
Neg logit contributions | |
countries | -1.849 |
analys | -1.818 |
researchers | -1.722 |
scientist | -1.693 |
physicists | -1.693 |
Token | aj |
Token ID | 1228 |
Feature activation | +5.69e+00 |
Pos logit contributions | |
reck | +5.656 |
idential | +5.530 |
osher | +5.215 |
aren | +5.193 |
rict | +5.122 |
Neg logit contributions | |
analys | -8.340 |
countries | -8.327 |
physicists | -7.845 |
researchers | -7.840 |
physicist | -7.811 |
Token | un |
Token ID | 403 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
idential | +2.924 |
reck | +2.904 |
osher | +2.642 |
aren | +2.584 |
rict | +2.501 |
Neg logit contributions | |
analys | -6.949 |
countries | -6.922 |
researchers | -6.565 |
physicists | -6.563 |
physicist | -6.550 |
Token | Bo |
Token ID | 3248 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
reck | +4.902 |
idential | +4.893 |
osher | +4.653 |
aren | +4.571 |
Reserved | +4.560 |
Neg logit contributions | |
countries | -4.181 |
analys | -4.179 |
researchers | -3.841 |
physicists | -3.819 |
physicist | -3.804 |
Token | il |
Token ID | 346 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
reck | +3.295 |
idential | +3.294 |
osher | +3.106 |
aren | +3.030 |
rict | +3.000 |
Neg logit contributions | |
countries | -4.231 |
analys | -4.199 |
researchers | -3.956 |
physicists | -3.915 |
scientist | -3.910 |
Token | | |
Token ID | 930 |
Feature activation | +5.67e+00 |
Pos logit contributions | |
idential | +0.426 |
reck | +0.424 |
osher | +0.401 |
aren | +0.392 |
Reserved | +0.392 |
Neg logit contributions | |
countries | -0.408 |
analys | -0.401 |
researchers | -0.378 |
scientist | -0.372 |
physicists | -0.370 |
Token | C |
Token ID | 327 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
idential | +4.946 |
reck | +4.933 |
osher | +4.664 |
Reserved | +4.614 |
aren | +4.578 |
Neg logit contributions | |
countries | -4.822 |
analys | -4.788 |
researchers | -4.463 |
physicists | -4.426 |
physicist | -4.399 |
Token | aj |
Token ID | 1228 |
Feature activation | +8.73e+00 |
Pos logit contributions | |
reck | +8.361 |
idential | +8.042 |
aren | +7.580 |
rict | +7.516 |
osher | +7.501 |
Neg logit contributions | |
analys | -14.811 |
countries | -14.717 |
physicists | -14.086 |
physicist | -14.018 |
researchers | -13.859 |
Token | un |
Token ID | 403 |
Feature activation | +8.83e+00 |
Pos logit contributions | |
idential | +4.215 |
reck | +4.199 |
osher | +3.835 |
aren | +3.771 |
ouls | +3.583 |
Neg logit contributions | |
analys | -10.769 |
countries | -10.650 |
physicists | -10.214 |
physicist | -10.139 |
researchers | -10.136 |
Token | Kitchen |
Token ID | 22541 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
reck | +7.463 |
idential | +7.390 |
osher | +7.126 |
Reserved | +7.045 |
Shore | +7.039 |
Neg logit contributions | |
analys | -7.377 |
countries | -7.305 |
physicists | -6.807 |
researchers | -6.778 |
physicist | -6.749 |
Token | . |
Token ID | 13 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
idential | +1.135 |
reck | +1.129 |
osher | +1.077 |
Reserved | +1.053 |
aren | +1.051 |
Neg logit contributions | |
countries | -0.881 |
analys | -0.864 |
researchers | -0.804 |
scientist | -0.790 |
example | -0.785 |
Token | � |
Token ID | 447 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
countries | +3.683 |
analys | +3.533 |
researchers | +3.348 |
example | +3.326 |
scientist | +3.256 |
Neg logit contributions | |
idential | -5.480 |
reck | -5.437 |
osher | -5.315 |
ouls | -5.080 |
rict | -5.044 |
Token | � |
Token ID | 251 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
countries | +3.058 |
analys | +2.758 |
example | +2.685 |
researchers | +2.678 |
experiments | +2.546 |
Neg logit contributions | |
idential | -6.462 |
reck | -6.375 |
osher | -6.238 |
Shore | -5.962 |
ouls | -5.951 |
Token |
|
Token ID | 198 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
countries | +7.112 |
analys | +6.905 |
researchers | +6.522 |
example | +6.417 |
scientist | +6.338 |
Neg logit contributions | |
idential | -10.543 |
reck | -10.389 |
osher | -10.029 |
ouls | -9.746 |
rict | -9.693 |
Token |
|
Token ID | 198 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
idential | +1.706 |
reck | +1.688 |
osher | +1.644 |
Reserved | +1.587 |
aren | +1.584 |
Neg logit contributions | |
countries | -1.035 |
analys | -0.996 |
researchers | -0.943 |
example | -0.928 |
scientist | -0.914 |
Token | The |
Token ID | 464 |
Feature activation | -5.90e+00 |
Pos logit contributions | |
idential | +1.044 |
reck | +1.027 |
osher | +0.984 |
Reserved | +0.961 |
rict | +0.955 |
Neg logit contributions | |
countries | -0.969 |
analys | -0.952 |
researchers | -0.898 |
scientist | -0.883 |
example | -0.881 |
Token | same |
Token ID | 976 |
Feature activation | -7.42e+00 |
Pos logit contributions | |
countries | +4.502 |
analys | +4.353 |
researchers | +4.169 |
scientist | +4.068 |
example | +4.064 |
Neg logit contributions | |
idential | -5.780 |
reck | -5.672 |
osher | -5.448 |
Reserved | -5.271 |
rict | -5.250 |
Token | applies |
Token ID | 8991 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
countries | +5.914 |
analys | +5.719 |
researchers | +5.513 |
example | +5.489 |
scientist | +5.422 |
Neg logit contributions | |
idential | -6.851 |
reck | -6.667 |
osher | -6.594 |
rict | -6.209 |
iquette | -6.204 |
Token | to |
Token ID | 284 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
reck | +3.065 |
idential | +3.064 |
osher | +2.908 |
aren | +2.875 |
Shore | +2.857 |
Neg logit contributions | |
countries | -2.125 |
analys | -2.095 |
researchers | -1.933 |
scientist | -1.918 |
physicist | -1.916 |
Token | De |
Token ID | 1024 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
reck | +3.232 |
idential | +3.230 |
osher | +3.061 |
aren | +3.012 |
Reserved | +3.008 |
Neg logit contributions | |
countries | -2.701 |
analys | -2.663 |
researchers | -2.485 |
physicists | -2.454 |
scientist | -2.447 |
Token | G |
Token ID | 402 |
Feature activation | +8.82e+00 |
Pos logit contributions | |
reck | +4.144 |
idential | +4.126 |
osher | +3.926 |
aren | +3.883 |
Reserved | +3.831 |
Neg logit contributions | |
countries | -3.981 |
analys | -3.945 |
researchers | -3.683 |
physicists | -3.659 |
physicist | -3.630 |
Token | have |
Token ID | 423 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
countries | +1.774 |
analys | +1.712 |
researchers | +1.593 |
scientist | +1.578 |
physicist | +1.571 |
Neg logit contributions | |
idential | -2.040 |
reck | -1.999 |
osher | -1.912 |
rict | -1.876 |
iquette | -1.868 |
Token | each |
Token ID | 1123 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
countries | +2.237 |
analys | +2.116 |
researchers | +2.011 |
example | +1.977 |
scientist | +1.976 |
Neg logit contributions | |
idential | -2.679 |
reck | -2.640 |
osher | -2.566 |
aren | -2.479 |
ouls | -2.445 |
Token | invested |
Token ID | 13356 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
countries | +2.336 |
analys | +2.240 |
researchers | +2.117 |
scientist | +2.093 |
example | +2.091 |
Neg logit contributions | |
idential | -2.492 |
reck | -2.432 |
osher | -2.386 |
Reserved | -2.271 |
aren | -2.258 |
Token | about |
Token ID | 546 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
countries | +2.067 |
analys | +1.944 |
researchers | +1.808 |
example | +1.750 |
scientist | +1.744 |
Neg logit contributions | |
idential | -3.843 |
reck | -3.809 |
osher | -3.677 |
Reserved | -3.582 |
iquette | -3.564 |
Token | $ |
Token ID | 720 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
idential | +2.417 |
reck | +2.401 |
osher | +2.270 |
aren | +2.212 |
Reserved | +2.210 |
Neg logit contributions | |
countries | -2.616 |
analys | -2.577 |
researchers | -2.428 |
scientist | -2.391 |
physicists | -2.389 |
Token | 700 |
Token ID | 9879 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
idential | +1.615 |
reck | +1.601 |
osher | +1.508 |
Reserved | +1.460 |
aren | +1.457 |
Neg logit contributions | |
countries | -2.201 |
analys | -2.163 |
researchers | -2.060 |
scientist | -2.031 |
example | -2.028 |
Token | million |
Token ID | 1510 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
countries | +1.072 |
analys | +1.048 |
researchers | +0.975 |
scientist | +0.957 |
physicists | +0.955 |
Neg logit contributions | |
idential | -1.486 |
reck | -1.477 |
osher | -1.406 |
Reserved | -1.379 |
aren | -1.379 |
Token | over |
Token ID | 625 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
countries | +1.253 |
analys | +1.226 |
researchers | +1.138 |
scientist | +1.114 |
physicists | +1.112 |
Neg logit contributions | |
idential | -1.643 |
reck | -1.628 |
osher | -1.555 |
Reserved | -1.519 |
aren | -1.514 |
Token | the |
Token ID | 262 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
countries | +0.902 |
analys | +0.878 |
researchers | +0.815 |
scientist | +0.796 |
example | +0.795 |
Neg logit contributions | |
idential | -1.344 |
reck | -1.337 |
osher | -1.282 |
Reserved | -1.254 |
aren | -1.250 |
Token | past |
Token ID | 1613 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
countries | +3.001 |
analys | +2.872 |
researchers | +2.622 |
example | +2.571 |
physicist | +2.547 |
Neg logit contributions | |
idential | -5.878 |
reck | -5.807 |
osher | -5.646 |
aren | -5.477 |
rict | -5.443 |
Token | six |
Token ID | 2237 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
countries | +1.342 |
analys | +1.301 |
researchers | +1.209 |
example | +1.199 |
scientist | +1.178 |
Neg logit contributions | |
idential | -2.049 |
reck | -2.024 |
osher | -1.953 |
Reserved | -1.899 |
aren | -1.897 |
Token | � |
Token ID | 250 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
countries | +0.160 |
analys | +0.157 |
researchers | +0.147 |
scientist | +0.144 |
physicists | +0.144 |
Neg logit contributions | |
idential | -0.205 |
reck | -0.203 |
osher | -0.195 |
Reserved | -0.189 |
aren | -0.189 |
Token | big |
Token ID | 14261 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
countries | +1.802 |
analys | +1.768 |
researchers | +1.685 |
example | +1.663 |
physicist | +1.658 |
Neg logit contributions | |
idential | -1.494 |
reck | -1.442 |
osher | -1.393 |
Reserved | -1.374 |
Shore | -1.344 |
Token | tsunami |
Token ID | 31019 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
countries | +0.403 |
analys | +0.393 |
researchers | +0.368 |
scientist | +0.361 |
example | +0.360 |
Neg logit contributions | |
idential | -0.558 |
reck | -0.550 |
osher | -0.528 |
Reserved | -0.520 |
aren | -0.517 |
Token | , |
Token ID | 11 |
Feature activation | -9.19e+00 |
Pos logit contributions | |
countries | +8.096 |
analys | +8.001 |
example | +7.558 |
researchers | +7.551 |
scientist | +7.339 |
Neg logit contributions | |
idential | -10.168 |
reck | -9.906 |
osher | -9.766 |
Reserved | -9.527 |
ouls | -9.479 |
Token | � |
Token ID | 447 |
Feature activation | -6.89e+00 |
Pos logit contributions | |
countries | +6.330 |
analys | +6.173 |
researchers | +5.934 |
example | +5.665 |
physicists | +5.648 |
Neg logit contributions | |
idential | -9.074 |
reck | -8.772 |
osher | -8.656 |
Reserved | -8.494 |
aren | -8.475 |
Token | � |
Token ID | 251 |
Feature activation | -1.94e+01 |
Pos logit contributions | |
countries | +5.230 |
analys | +4.956 |
researchers | +4.800 |
example | +4.661 |
scientist | +4.660 |
Neg logit contributions | |
idential | -6.581 |
reck | -6.470 |
osher | -6.258 |
rict | -6.025 |
ouls | -6.016 |
Token | says |
Token ID | 1139 |
Feature activation | -9.45e+00 |
Pos logit contributions | |
countries | +14.703 |
researchers | +14.411 |
analys | +14.215 |
physicists | +13.645 |
example | +13.629 |
Neg logit contributions | |
idential | -14.318 |
iquette | -13.467 |
osher | -13.406 |
reck | -13.347 |
Reserved | -12.978 |
Token | N |
Token ID | 399 |
Feature activation | +9.80e+00 |
Pos logit contributions | |
countries | +8.543 |
analys | +8.472 |
researchers | +8.399 |
physicist | +8.187 |
scientist | +8.170 |
Neg logit contributions | |
idential | -7.396 |
reck | -7.165 |
osher | -6.953 |
rict | -6.706 |
aren | -6.704 |
Token | ett |
Token ID | 3087 |
Feature activation | +6.90e+00 |
Pos logit contributions | |
reck | +4.941 |
idential | +4.851 |
aren | +4.371 |
osher | +4.335 |
rict | +4.169 |
Neg logit contributions | |
countries | -11.864 |
analys | -11.847 |
physicists | -11.152 |
researchers | -11.144 |
scientist | -11.098 |
Token | les |
Token ID | 829 |
Feature activation | -7.62e+00 |
Pos logit contributions | |
idential | +3.489 |
reck | +3.486 |
osher | +3.135 |
aren | +3.057 |
rict | +3.008 |
Neg logit contributions | |
countries | -8.466 |
analys | -8.439 |
researchers | -8.030 |
scientist | -7.976 |
physicists | -7.971 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
countries | +6.633 |
analys | +6.561 |
researchers | +6.247 |
scientist | +6.121 |
physicist | +6.084 |
Neg logit contributions | |
idential | -6.453 |
reck | -6.379 |
osher | -6.099 |
Reserved | -5.935 |
rict | -5.930 |
Token | is |
Token ID | 318 |
Feature activation | -4.78e+00 |
Pos logit contributions | |
idential | +2.586 |
reck | +2.575 |
osher | +2.448 |
aren | +2.387 |
Reserved | +2.386 |
Neg logit contributions | |
countries | -2.435 |
analys | -2.406 |
researchers | -2.255 |
scientist | -2.218 |
physicists | -2.214 |
Token | a |
Token ID | 257 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
countries | +3.552 |
analys | +3.511 |
researchers | +3.284 |
example | +3.218 |
scientist | +3.204 |
Neg logit contributions | |
idential | -4.716 |
reck | -4.626 |
osher | -4.504 |
ouls | -4.477 |
Reserved | -4.412 |
Token | malicious |
Token ID | 17412 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
idential | +4.158 |
reck | +4.143 |
osher | +3.957 |
aren | +3.887 |
Reserved | +3.882 |
Neg logit contributions | |
countries | -2.856 |
analys | -2.813 |
researchers | -2.604 |
scientist | -2.555 |
physicists | -2.554 |
Token | fabrication |
Token ID | 38876 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
idential | +1.139 |
reck | +1.132 |
osher | +1.089 |
aren | +1.070 |
Reserved | +1.069 |
Neg logit contributions | |
countries | -0.764 |
analys | -0.757 |
researchers | -0.698 |
example | -0.692 |
scientist | -0.692 |
Token | ," |
Token ID | 553 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
countries | +1.678 |
analys | +1.675 |
researchers | +1.559 |
scientist | +1.538 |
experiments | +1.534 |
Neg logit contributions | |
idential | -1.808 |
reck | -1.784 |
osher | -1.729 |
Reserved | -1.670 |
ouls | -1.668 |
Token | MacDonald |
Token ID | 37131 |
Feature activation | -1.36e+01 |
Pos logit contributions | |
countries | +4.378 |
analys | +4.347 |
researchers | +4.139 |
scientist | +4.021 |
physicist | +3.996 |
Neg logit contributions | |
reck | -4.512 |
idential | -4.465 |
osher | -4.140 |
aren | -4.115 |
rict | -4.099 |
Token | concludes |
Token ID | 18978 |
Feature activation | -7.70e+00 |
Pos logit contributions | |
analys | +8.960 |
countries | +8.767 |
researchers | +8.399 |
experiments | +8.131 |
scientist | +7.884 |
Neg logit contributions | |
idential | -13.396 |
reck | -13.361 |
osher | -12.816 |
Reserved | -12.797 |
aren | -12.479 |
Token | . |
Token ID | 13 |
Feature activation | -7.91e+00 |
Pos logit contributions | |
analys | +6.616 |
countries | +6.604 |
researchers | +6.161 |
physicist | +6.039 |
physicists | +6.037 |
Neg logit contributions | |
idential | -6.593 |
reck | -6.545 |
osher | -6.246 |
Reserved | -6.139 |
aren | -6.046 |
Token | Which |
Token ID | 9022 |
Feature activation | -5.61e+00 |
Pos logit contributions | |
countries | +5.799 |
analys | +5.640 |
researchers | +5.316 |
example | +5.184 |
scientist | +5.169 |
Neg logit contributions | |
idential | -7.686 |
reck | -7.678 |
osher | -7.276 |
rict | -7.107 |
ouls | -7.104 |
Token | means |
Token ID | 1724 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
countries | +4.649 |
analys | +4.482 |
researchers | +4.327 |
scientist | +4.231 |
physicists | +4.189 |
Neg logit contributions | |
idential | -5.217 |
reck | -5.116 |
osher | -4.848 |
ouls | -4.754 |
Reserved | -4.742 |
Token | the |
Token ID | 262 |
Feature activation | -5.94e+00 |
Pos logit contributions | |
idential | +2.557 |
reck | +2.548 |
osher | +2.423 |
aren | +2.375 |
Reserved | +2.370 |
Neg logit contributions | |
countries | -2.139 |
analys | -2.110 |
researchers | -1.969 |
physicists | -1.937 |
scientist | -1.936 |
Token |
|
Token ID | 198 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
countries | +2.555 |
analys | +2.437 |
researchers | +2.306 |
example | +2.246 |
scientist | +2.221 |
Neg logit contributions | |
reck | -4.245 |
idential | -4.244 |
osher | -4.101 |
rict | -3.981 |
aren | -3.979 |
Token |
|
Token ID | 198 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
idential | +5.389 |
reck | +5.381 |
osher | +5.097 |
aren | +5.047 |
Reserved | +5.030 |
Neg logit contributions | |
countries | -3.920 |
analys | -3.893 |
researchers | -3.578 |
physicists | -3.542 |
scientist | -3.525 |
Token | " |
Token ID | 1 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
idential | +2.613 |
reck | +2.600 |
osher | +2.444 |
aren | +2.384 |
Reserved | +2.380 |
Neg logit contributions | |
countries | -3.260 |
analys | -3.223 |
researchers | -3.048 |
physicists | -3.007 |
scientist | -3.006 |
Token | If |
Token ID | 1532 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
idential | +2.951 |
reck | +2.931 |
osher | +2.785 |
Reserved | +2.708 |
aren | +2.705 |
Neg logit contributions | |
countries | -3.057 |
analys | -3.006 |
researchers | -2.839 |
scientist | -2.793 |
physicists | -2.789 |
Token | I |
Token ID | 314 |
Feature activation | -9.34e-02 |
Pos logit contributions | |
idential | +2.303 |
reck | +2.298 |
osher | +2.202 |
Reserved | +2.143 |
aren | +2.143 |
Neg logit contributions | |
countries | -1.770 |
analys | -1.723 |
researchers | -1.618 |
scientist | -1.577 |
physicists | -1.575 |
Token | were |
Token ID | 547 |
Feature activation | -1.45e+01 |
Pos logit contributions | |
countries | +0.083 |
analys | +0.081 |
researchers | +0.077 |
example | +0.076 |
scientist | +0.076 |
Neg logit contributions | |
idential | -0.080 |
reck | -0.080 |
osher | -0.078 |
Reserved | -0.075 |
ouls | -0.075 |
Token | going |
Token ID | 1016 |
Feature activation | -1.68e+01 |
Pos logit contributions | |
countries | +10.717 |
analys | +10.341 |
researchers | +9.821 |
example | +9.679 |
scientist | +9.671 |
Neg logit contributions | |
idential | -12.636 |
reck | -12.496 |
osher | -12.247 |
ouls | -11.983 |
iquette | -11.924 |
Token | to |
Token ID | 284 |
Feature activation | -9.63e+00 |
Pos logit contributions | |
countries | +11.369 |
analys | +10.437 |
researchers | +10.113 |
example | +10.009 |
experiments | +9.725 |
Neg logit contributions | |
reck | -15.872 |
idential | -15.757 |
Reserved | -15.449 |
osher | -15.356 |
ufficient | -15.092 |
Token | pit |
Token ID | 6028 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
countries | +7.281 |
analys | +6.808 |
example | +6.567 |
researchers | +6.545 |
scientist | +6.423 |
Neg logit contributions | |
reck | -8.966 |
idential | -8.939 |
osher | -8.755 |
ufficient | -8.391 |
ouls | -8.381 |
Token | a |
Token ID | 257 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
countries | +2.599 |
analys | +2.430 |
researchers | +2.312 |
example | +2.283 |
scientist | +2.255 |
Neg logit contributions | |
idential | -3.799 |
reck | -3.790 |
osher | -3.655 |
Reserved | -3.588 |
aren | -3.533 |
Token | city |
Token ID | 1748 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
idential | +5.533 |
reck | +5.509 |
osher | +5.272 |
aren | +5.179 |
Reserved | +5.170 |
Neg logit contributions | |
countries | -3.525 |
analys | -3.461 |
researchers | -3.194 |
scientist | -3.141 |
physicist | -3.129 |
Token | is |
Token ID | 318 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
countries | +7.083 |
analys | +6.724 |
researchers | +6.539 |
experiments | +6.353 |
scientist | +6.314 |
Neg logit contributions | |
idential | -7.094 |
reck | -6.994 |
osher | -6.804 |
Reserved | -6.458 |
hetto | -6.457 |
Token | corporate |
Token ID | 6355 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
countries | +7.305 |
analys | +7.069 |
researchers | +6.625 |
example | +6.440 |
scientist | +6.325 |
Neg logit contributions | |
idential | -10.134 |
reck | -9.945 |
osher | -9.834 |
iquette | -9.524 |
ouls | -9.335 |
Token | welfare |
Token ID | 9490 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
idential | +1.488 |
reck | +1.479 |
osher | +1.411 |
aren | +1.377 |
Reserved | +1.376 |
Neg logit contributions | |
countries | -1.224 |
analys | -1.200 |
researchers | -1.125 |
scientist | -1.103 |
physicists | -1.102 |
Token | of |
Token ID | 286 |
Feature activation | -7.23e+00 |
Pos logit contributions | |
countries | +4.669 |
analys | +4.422 |
researchers | +4.229 |
example | +4.135 |
experiments | +4.135 |
Neg logit contributions | |
idential | -5.637 |
reck | -5.563 |
osher | -5.437 |
ouls | -5.260 |
aren | -5.196 |
Token | the |
Token ID | 262 |
Feature activation | -8.58e+00 |
Pos logit contributions | |
countries | +5.621 |
analys | +5.159 |
researchers | +5.085 |
example | +4.900 |
physicists | +4.869 |
Neg logit contributions | |
idential | -7.042 |
reck | -6.924 |
osher | -6.767 |
aren | -6.497 |
idelines | -6.493 |
Token | first |
Token ID | 717 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
countries | +6.637 |
analys | +5.986 |
researchers | +5.876 |
scientist | +5.700 |
physicist | +5.672 |
Neg logit contributions | |
idential | -8.532 |
reck | -8.286 |
osher | -8.194 |
idelines | -7.806 |
iquette | -7.784 |
Token | water |
Token ID | 1660 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
countries | +10.251 |
analys | +9.319 |
example | +9.123 |
researchers | +9.041 |
scientist | +8.945 |
Neg logit contributions | |
idential | -12.621 |
reck | -12.300 |
osher | -12.244 |
aren | -11.679 |
idelines | -11.534 |
Token | , |
Token ID | 11 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
countries | +10.587 |
analys | +9.970 |
researchers | +9.761 |
physicist | +9.699 |
scientist | +9.677 |
Neg logit contributions | |
idential | -10.389 |
osher | -10.041 |
ouls | -9.917 |
reck | -9.884 |
aren | -9.684 |
Token | an |
Token ID | 281 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
countries | +1.550 |
analys | +1.513 |
researchers | +1.410 |
scientist | +1.394 |
physicist | +1.390 |
Neg logit contributions | |
reck | -2.290 |
idential | -2.277 |
osher | -2.176 |
Reserved | -2.168 |
aren | -2.162 |
Token | enormous |
Token ID | 9812 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
countries | +5.054 |
analys | +4.954 |
example | +4.856 |
researchers | +4.675 |
experiments | +4.573 |
Neg logit contributions | |
reck | -6.305 |
idential | -6.183 |
osher | -5.934 |
idelines | -5.774 |
Reserved | -5.770 |
Token | White |
Token ID | 2635 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
idential | +1.876 |
reck | +1.870 |
osher | +1.791 |
aren | +1.751 |
rict | +1.746 |
Neg logit contributions | |
countries | -1.332 |
analys | -1.299 |
researchers | -1.215 |
scientist | -1.197 |
physicist | -1.192 |
Token | in |
Token ID | 287 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
countries | +2.796 |
analys | +2.757 |
researchers | +2.613 |
scientist | +2.570 |
physicist | +2.565 |
Neg logit contributions | |
idential | -3.023 |
reck | -2.959 |
osher | -2.896 |
Reserved | -2.801 |
ouls | -2.754 |
Token | perfect |
Token ID | 2818 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
countries | +1.385 |
analys | +1.350 |
researchers | +1.274 |
example | +1.256 |
scientist | +1.251 |
Neg logit contributions | |
idential | -1.443 |
reck | -1.432 |
osher | -1.362 |
Reserved | -1.326 |
aren | -1.317 |
Token | health |
Token ID | 1535 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
idential | +3.472 |
reck | +3.459 |
osher | +3.291 |
aren | +3.232 |
Reserved | +3.223 |
Neg logit contributions | |
countries | -2.708 |
analys | -2.674 |
researchers | -2.488 |
physicists | -2.445 |
scientist | -2.443 |
Token | , |
Token ID | 11 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
countries | +1.345 |
analys | +1.321 |
researchers | +1.256 |
scientist | +1.231 |
physicist | +1.229 |
Neg logit contributions | |
idential | -1.376 |
reck | -1.367 |
osher | -1.318 |
Reserved | -1.278 |
aren | -1.263 |
Token | Dahl |
Token ID | 41471 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
idential | +4.293 |
reck | +4.280 |
osher | +4.033 |
aren | +3.995 |
rict | +3.971 |
Neg logit contributions | |
countries | -3.764 |
analys | -3.715 |
researchers | -3.454 |
physicists | -3.413 |
scientist | -3.401 |
Token | went |
Token ID | 1816 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
countries | +0.013 |
analys | +0.013 |
researchers | +0.012 |
scientist | +0.012 |
physicists | +0.012 |
Neg logit contributions | |
idential | -0.014 |
reck | -0.014 |
osher | -0.014 |
Reserved | -0.013 |
aren | -0.013 |
Token | back |
Token ID | 736 |
Feature activation | -8.00e+00 |
Pos logit contributions | |
countries | +8.294 |
analys | +8.122 |
researchers | +7.579 |
example | +7.394 |
scientist | +7.302 |
Neg logit contributions | |
idential | -13.053 |
reck | -13.014 |
osher | -12.692 |
ufficient | -12.597 |
Reserved | -12.475 |
Token | to |
Token ID | 284 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
countries | +4.605 |
analys | +4.500 |
researchers | +4.086 |
scientist | +3.950 |
example | +3.932 |
Neg logit contributions | |
idential | -8.982 |
reck | -8.969 |
osher | -8.728 |
Reserved | -8.706 |
ouls | -8.454 |
Token | the |
Token ID | 262 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
idential | +0.756 |
reck | +0.756 |
osher | +0.725 |
Reserved | +0.709 |
aren | +0.706 |
Neg logit contributions | |
countries | -0.503 |
analys | -0.495 |
researchers | -0.457 |
scientist | -0.448 |
experiments | -0.446 |
Token | drawing |
Token ID | 8263 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
idential | +0.608 |
reck | +0.603 |
osher | +0.577 |
aren | +0.564 |
Reserved | +0.562 |
Neg logit contributions | |
countries | -0.443 |
analys | -0.432 |
researchers | -0.406 |
scientist | -0.398 |
experiments | -0.397 |
Token | board |
Token ID | 3096 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
countries | +4.284 |
analys | +4.141 |
scientist | +3.922 |
researchers | +3.921 |
physicist | +3.837 |
Neg logit contributions | |
idential | -4.977 |
reck | -4.877 |
osher | -4.594 |
Reserved | -4.590 |
ouls | -4.550 |