Token | the |
Token ID | 262 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
ulf | +4.290 |
rer | +4.249 |
Mouth | +4.027 |
IPM | +3.815 |
deserts | +3.731 |
Neg logit contributions | |
ilitarian | -4.586 |
>) | -4.294 |
xxxxxxxx | -3.850 |
spot | -3.839 |
romeda | -3.765 |
Token | future |
Token ID | 2003 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
ulf | +2.511 |
rer | +2.457 |
Mouth | +2.309 |
IPM | +2.213 |
ê | +2.173 |
Neg logit contributions | |
ilitarian | -2.361 |
>) | -2.224 |
xxxxxxxx | -1.992 |
romeda | -1.976 |
spot | -1.966 |
Token | of |
Token ID | 286 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ulf | +3.167 |
rer | +3.114 |
Mouth | +2.863 |
IPM | +2.751 |
ê | +2.710 |
Neg logit contributions | |
ilitarian | -3.589 |
>) | -3.419 |
xxxxxxxx | -3.050 |
romeda | -3.036 |
spot | -3.003 |
Token | R |
Token ID | 371 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
ulf | +1.268 |
rer | +1.243 |
Mouth | +1.155 |
IPM | +1.117 |
ê | +1.107 |
Neg logit contributions | |
ilitarian | -1.200 |
>) | -1.147 |
xxxxxxxx | -1.024 |
romeda | -1.017 |
spot | -1.016 |
Token | country |
Token ID | 1499 |
Feature activation | +9.97e+00 |
Pos logit contributions | |
ulf | +4.189 |
rer | +4.134 |
Mouth | +3.745 |
ê | +3.707 |
IPM | +3.602 |
Neg logit contributions | |
ilitarian | -4.357 |
>) | -4.131 |
romeda | -3.777 |
spot | -3.711 |
xxxxxxxx | -3.688 |
Token | just |
Token ID | 655 |
Feature activation | +2.23e+01 |
Pos logit contributions | |
rer | +6.027 |
ulf | +5.982 |
Mouth | +5.423 |
ê | +5.169 |
IPM | +5.099 |
Neg logit contributions | |
ilitarian | -7.412 |
>) | -6.950 |
xxxxxxxx | -6.251 |
romeda | -6.243 |
spot | -6.045 |
Token | got |
Token ID | 1392 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
ulf | +8.498 |
rer | +8.442 |
deserts | +7.381 |
Mouth | +7.214 |
iner | +7.188 |
Neg logit contributions | |
ilitarian | -17.115 |
>) | -15.987 |
romeda | -15.189 |
xxxxxxxx | -14.845 |
akeru | -14.761 |
Token | way |
Token ID | 835 |
Feature activation | +8.54e+00 |
Pos logit contributions | |
ulf | +6.574 |
rer | +6.425 |
Mouth | +5.713 |
iner | +5.584 |
IPM | +5.522 |
Neg logit contributions | |
ilitarian | -8.093 |
>) | -7.606 |
xxxxxxxx | -6.932 |
romeda | -6.780 |
spot | -6.720 |
Token | brighter |
Token ID | 26083 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
ulf | +5.230 |
rer | +5.228 |
Mouth | +4.583 |
ê | +4.464 |
iner | +4.445 |
Neg logit contributions | |
ilitarian | -6.431 |
>) | -6.036 |
xxxxxxxx | -5.464 |
romeda | -5.425 |
Revival | -5.325 |
Token | !!! |
Token ID | 10185 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ulf | +2.233 |
rer | +2.195 |
Mouth | +2.028 |
IPM | +1.926 |
ê | +1.915 |
Neg logit contributions | |
ilitarian | -2.562 |
>) | -2.436 |
xxxxxxxx | -2.192 |
romeda | -2.176 |
spot | -2.167 |
Token | Cong |
Token ID | 2908 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
ulf | +0.780 |
rer | +0.767 |
Mouth | +0.714 |
IPM | +0.688 |
ê | +0.681 |
Neg logit contributions | |
ilitarian | -0.760 |
>) | -0.726 |
xxxxxxxx | -0.650 |
romeda | -0.645 |
spot | -0.643 |
Token | turret |
Token ID | 28101 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
ulf | +5.769 |
rer | +5.688 |
IPM | +5.132 |
Mouth | +5.004 |
iner | +4.964 |
Neg logit contributions | |
ilitarian | -7.015 |
>) | -6.772 |
xxxxxxxx | -6.077 |
romeda | -5.861 |
ozy | -5.816 |
Token | rover |
Token ID | 35761 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ulf | +2.258 |
rer | +2.220 |
Mouth | +2.012 |
IPM | +1.966 |
ê | +1.939 |
Neg logit contributions | |
ilitarian | -2.502 |
>) | -2.413 |
xxxxxxxx | -2.175 |
romeda | -2.136 |
Eliot | -2.108 |
Token | planner |
Token ID | 42351 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
ulf | +1.307 |
rer | +1.287 |
Mouth | +1.181 |
IPM | +1.155 |
ê | +1.136 |
Neg logit contributions | |
ilitarian | -1.328 |
>) | -1.277 |
xxxxxxxx | -1.146 |
romeda | -1.130 |
spot | -1.117 |
Token | at |
Token ID | 379 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
ulf | +2.676 |
rer | +2.641 |
Mouth | +2.393 |
IPM | +2.336 |
ê | +2.284 |
Neg logit contributions | |
ilitarian | -3.019 |
>) | -2.923 |
xxxxxxxx | -2.601 |
romeda | -2.548 |
spot | -2.529 |
Token | NASA |
Token ID | 8884 |
Feature activation | +1.31e+01 |
Pos logit contributions | |
ulf | +4.349 |
rer | +4.259 |
Mouth | +4.024 |
IPM | +3.987 |
deserts | +3.769 |
Neg logit contributions | |
ilitarian | -4.358 |
>) | -4.186 |
xxxxxxxx | -3.758 |
spot | -3.650 |
romeda | -3.610 |
Token | 's |
Token ID | 338 |
Feature activation | +2.23e+01 |
Pos logit contributions | |
ulf | +6.155 |
rer | +6.088 |
IPM | +5.474 |
Mouth | +5.386 |
iner | +5.166 |
Neg logit contributions | |
ilitarian | -11.131 |
>) | -10.759 |
xxxxxxxx | -9.950 |
ozy | -9.681 |
":[ | -9.626 |
Token | Jet |
Token ID | 19013 |
Feature activation | +9.64e+00 |
Pos logit contributions | |
rer | +9.689 |
ulf | +9.417 |
IPM | +9.189 |
deserts | +9.088 |
Mouth | +8.888 |
Neg logit contributions | |
ilitarian | -17.089 |
>) | -15.926 |
xxxxxxxx | -15.001 |
":[ | -14.819 |
ozy | -14.521 |
Token | Prop |
Token ID | 8772 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
ulf | +4.606 |
rer | +4.390 |
Mouth | +4.192 |
IPM | +3.726 |
iner | +3.686 |
Neg logit contributions | |
ilitarian | -8.597 |
>) | -8.338 |
xxxxxxxx | -7.743 |
romeda | -7.513 |
Eliot | -7.403 |
Token | ulsion |
Token ID | 15204 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
ilitarian | +1.370 |
>) | +1.334 |
xxxxxxxx | +1.201 |
romeda | +1.190 |
spot | +1.185 |
Neg logit contributions | |
ulf | -1.148 |
rer | -1.118 |
Mouth | -1.031 |
IPM | -0.995 |
ê | -0.984 |
Token | Laboratory |
Token ID | 18643 |
Feature activation | +7.67e+00 |
Pos logit contributions | |
ulf | +1.770 |
rer | +1.750 |
Mouth | +1.626 |
IPM | +1.564 |
ê | +1.562 |
Neg logit contributions | |
ilitarian | -1.773 |
>) | -1.664 |
xxxxxxxx | -1.521 |
romeda | -1.518 |
spot | -1.500 |
Token | in |
Token ID | 287 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
rer | +4.584 |
ulf | +4.544 |
Mouth | +4.063 |
iner | +3.897 |
IPM | +3.864 |
Neg logit contributions | |
ilitarian | -5.983 |
>) | -5.764 |
xxxxxxxx | -5.303 |
ozy | -5.240 |
romeda | -5.101 |
Token | abusive |
Token ID | 19546 |
Feature activation | -6.14e+00 |
Pos logit contributions | |
ilitarian | +3.150 |
>) | +3.111 |
xxxxxxxx | +2.756 |
romeda | +2.739 |
spot | +2.692 |
Neg logit contributions | |
ulf | -3.147 |
rer | -3.113 |
Mouth | -2.908 |
IPM | -2.814 |
ê | -2.730 |
Token | relationship |
Token ID | 2776 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
ilitarian | +4.287 |
>) | +4.232 |
xxxxxxxx | +3.779 |
spot | +3.751 |
Revival | +3.738 |
Neg logit contributions | |
ulf | -3.946 |
rer | -3.905 |
Mouth | -3.579 |
IPM | -3.542 |
deserts | -3.428 |
Token | and |
Token ID | 290 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
ulf | +0.295 |
rer | +0.289 |
Mouth | +0.267 |
IPM | +0.258 |
ê | +0.256 |
Neg logit contributions | |
ilitarian | -0.305 |
>) | -0.294 |
xxxxxxxx | -0.264 |
romeda | -0.261 |
spot | -0.260 |
Token | get |
Token ID | 651 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ulf | +0.095 |
rer | +0.093 |
Mouth | +0.086 |
IPM | +0.083 |
ê | +0.082 |
Neg logit contributions | |
ilitarian | -0.097 |
>) | -0.094 |
xxxxxxxx | -0.084 |
romeda | -0.083 |
spot | -0.083 |
Token | their |
Token ID | 511 |
Feature activation | +7.16e+00 |
Pos logit contributions | |
ilitarian | +0.964 |
>) | +0.933 |
xxxxxxxx | +0.836 |
spot | +0.825 |
romeda | +0.825 |
Neg logit contributions | |
ulf | -1.006 |
rer | -0.984 |
Mouth | -0.916 |
IPM | -0.889 |
ê | -0.878 |
Token | lives |
Token ID | 3160 |
Feature activation | +2.19e+01 |
Pos logit contributions | |
ulf | +4.631 |
rer | +4.551 |
Mouth | +4.322 |
deserts | +4.131 |
IPM | +4.050 |
Neg logit contributions | |
ilitarian | -5.193 |
>) | -4.933 |
romeda | -4.511 |
xxxxxxxx | -4.427 |
spot | -4.400 |
Token | back |
Token ID | 736 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
rer | +7.645 |
ulf | +7.626 |
together | +6.639 |
ê | +6.507 |
deserts | +6.255 |
Neg logit contributions | |
ilitarian | -18.930 |
>) | -17.712 |
xxxxxxxx | -15.998 |
romeda | -15.997 |
ozy | -15.958 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ulf | +5.876 |
rer | +5.643 |
ê | +5.028 |
Mouth | +4.873 |
ement | +4.746 |
Neg logit contributions | |
ilitarian | -8.664 |
>) | -8.347 |
romeda | -7.560 |
Eliot | -7.373 |
spot | -7.368 |
Token | � |
Token ID | 447 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ulf | +0.985 |
rer | +0.968 |
Mouth | +0.900 |
IPM | +0.862 |
ê | +0.856 |
Neg logit contributions | |
ilitarian | -1.090 |
>) | -1.045 |
xxxxxxxx | -0.939 |
romeda | -0.935 |
spot | -0.932 |
Token | � |
Token ID | 251 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ulf | +1.095 |
rer | +1.077 |
Mouth | +1.004 |
IPM | +0.973 |
ê | +0.971 |
Neg logit contributions | |
ilitarian | -0.896 |
>) | -0.849 |
xxxxxxxx | -0.752 |
romeda | -0.746 |
spot | -0.742 |
Token |
|
Token ID | 198 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
ulf | +0.724 |
rer | +0.711 |
Mouth | +0.658 |
IPM | +0.634 |
ê | +0.630 |
Neg logit contributions | |
ilitarian | -0.775 |
>) | -0.742 |
xxxxxxxx | -0.667 |
romeda | -0.663 |
spot | -0.660 |
Token |
|
Token ID | 198 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
ilitarian | +2.556 |
>) | +2.472 |
xxxxxxxx | +2.213 |
spot | +2.193 |
romeda | +2.144 |
Neg logit contributions | |
ulf | -2.969 |
rer | -2.877 |
Mouth | -2.648 |
IPM | -2.588 |
ê | -2.584 |
Token |
|
Token ID | 198 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
ulf | +1.537 |
rer | +1.515 |
Mouth | +1.381 |
ê | +1.335 |
IPM | +1.332 |
Neg logit contributions | |
ilitarian | -1.697 |
>) | -1.608 |
romeda | -1.474 |
xxxxxxxx | -1.435 |
spot | -1.427 |
Token | . |
Token ID | 13 |
Feature activation | -8.94e-02 |
Pos logit contributions | |
ulf | +3.232 |
rer | +3.195 |
Mouth | +2.851 |
IPM | +2.764 |
ê | +2.754 |
Neg logit contributions | |
ilitarian | -3.894 |
>) | -3.726 |
romeda | -3.438 |
Eliot | -3.362 |
xxxxxxxx | -3.318 |
Token | However |
Token ID | 2102 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
ilitarian | +0.066 |
>) | +0.064 |
xxxxxxxx | +0.057 |
romeda | +0.057 |
spot | +0.057 |
Neg logit contributions | |
ulf | -0.059 |
rer | -0.058 |
Mouth | -0.053 |
IPM | -0.051 |
ê | -0.051 |
Token | we |
Token ID | 356 |
Feature activation | +1.40e+01 |
Pos logit contributions | |
ulf | +1.602 |
rer | +1.579 |
Mouth | +1.469 |
IPM | +1.429 |
ê | +1.409 |
Neg logit contributions | |
ilitarian | -1.278 |
>) | -1.223 |
romeda | -1.071 |
xxxxxxxx | -1.063 |
spot | -1.053 |
Token | would |
Token ID | 561 |
Feature activation | +2.17e+01 |
Pos logit contributions | |
rer | +4.940 |
ulf | +4.835 |
IPM | +3.782 |
Mouth | +3.730 |
deserts | +3.696 |
Neg logit contributions | |
ilitarian | -13.282 |
>) | -13.087 |
romeda | -12.318 |
xxxxxxxx | -12.047 |
spot | -11.864 |
Token | like |
Token ID | 588 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
rer | +4.521 |
ulf | +3.900 |
aver | +3.374 |
Mouth | +3.298 |
edit | +2.999 |
Neg logit contributions | |
ilitarian | -20.751 |
>) | -19.670 |
romeda | -19.326 |
Revival | -19.282 |
spot | -18.749 |
Token | to |
Token ID | 284 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
ulf | +2.716 |
rer | +2.703 |
Mouth | +2.426 |
ê | +2.320 |
IPM | +2.312 |
Neg logit contributions | |
ilitarian | -3.533 |
>) | -3.335 |
romeda | -3.058 |
spot | -3.014 |
xxxxxxxx | -2.980 |
Token | remind |
Token ID | 7101 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
rer | +4.214 |
ulf | +3.705 |
Mouth | +3.348 |
IPM | +3.170 |
deserts | +3.140 |
Neg logit contributions | |
ilitarian | -9.745 |
>) | -9.499 |
spot | -8.795 |
Eliot | -8.674 |
AIN | -8.629 |
Token | you |
Token ID | 345 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
ulf | +0.255 |
rer | +0.250 |
Mouth | +0.231 |
IPM | +0.223 |
ê | +0.221 |
Neg logit contributions | |
ilitarian | -0.282 |
>) | -0.272 |
xxxxxxxx | -0.244 |
romeda | -0.243 |
spot | -0.243 |
Token | once |
Token ID | 1752 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
ilitarian | +1.068 |
>) | +1.029 |
xxxxxxxx | +0.916 |
romeda | +0.893 |
spot | +0.889 |
Neg logit contributions | |
ulf | -1.420 |
rer | -1.394 |
Mouth | -1.312 |
IPM | -1.277 |
ê | -1.269 |
Token | a |
Token ID | 257 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
ulf | +2.727 |
rer | +2.689 |
Mouth | +2.516 |
IPM | +2.410 |
ê | +2.385 |
Neg logit contributions | |
ilitarian | -2.711 |
>) | -2.604 |
xxxxxxxx | -2.344 |
romeda | -2.322 |
spot | -2.298 |
Token | public |
Token ID | 1171 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
ulf | +3.445 |
rer | +3.437 |
Mouth | +3.207 |
ê | +3.027 |
IPM | +3.024 |
Neg logit contributions | |
ilitarian | -3.613 |
>) | -3.465 |
xxxxxxxx | -3.114 |
romeda | -3.084 |
spot | -3.021 |
Token | street |
Token ID | 4675 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
ilitarian | +1.152 |
>) | +1.111 |
xxxxxxxx | +0.986 |
spot | +0.982 |
romeda | +0.971 |
Neg logit contributions | |
ulf | -1.360 |
rer | -1.332 |
Mouth | -1.239 |
IPM | -1.203 |
ê | -1.192 |
Token | shall |
Token ID | 2236 |
Feature activation | +9.85e+00 |
Pos logit contributions | |
ulf | +3.808 |
rer | +3.804 |
Mouth | +3.456 |
ê | +3.327 |
IPM | +3.218 |
Neg logit contributions | |
ilitarian | -4.312 |
>) | -4.151 |
romeda | -3.795 |
xxxxxxxx | -3.741 |
ozy | -3.640 |
Token | maintain |
Token ID | 5529 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
rer | +5.711 |
ulf | +5.657 |
Mouth | +4.899 |
ê | +4.778 |
iner | +4.739 |
Neg logit contributions | |
ilitarian | -7.761 |
>) | -7.273 |
romeda | -7.004 |
xxxxxxxx | -6.628 |
Eliot | -6.553 |
Token | any |
Token ID | 597 |
Feature activation | +2.16e+01 |
Pos logit contributions | |
rer | +8.355 |
ulf | +7.904 |
Mouth | +7.394 |
deserts | +7.180 |
ement | +7.075 |
Neg logit contributions | |
ilitarian | -10.876 |
>) | -10.459 |
romeda | -10.015 |
ozy | -9.571 |
xxxxxxxx | -9.353 |
Token | sidewalk |
Token ID | 24058 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
rer | +11.375 |
Mouth | +10.456 |
ement | +10.389 |
ulf | +10.368 |
deserts | +9.926 |
Neg logit contributions | |
ilitarian | -13.731 |
>) | -13.569 |
romeda | -12.687 |
ozy | -12.318 |
akeru | -11.690 |
Token | in |
Token ID | 287 |
Feature activation | +7.25e+00 |
Pos logit contributions | |
rer | +7.814 |
ulf | +7.513 |
Mouth | +7.103 |
aver | +6.652 |
ement | +6.614 |
Neg logit contributions | |
ilitarian | -9.506 |
>) | -9.333 |
romeda | -8.585 |
ozy | -8.254 |
xxxxxxxx | -8.029 |
Token | such |
Token ID | 884 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
rer | +4.682 |
ulf | +4.599 |
Mouth | +4.269 |
ê | +4.092 |
deserts | +4.072 |
Neg logit contributions | |
ilitarian | -5.169 |
>) | -5.061 |
romeda | -4.575 |
xxxxxxxx | -4.476 |
spot | -4.397 |
Token | condition |
Token ID | 4006 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
rer | +6.150 |
ulf | +5.882 |
Mouth | +5.617 |
deserts | +5.357 |
ement | +5.169 |
Neg logit contributions | |
ilitarian | -8.133 |
>) | -7.858 |
romeda | -7.081 |
xxxxxxxx | -6.958 |
ozy | -6.890 |
Token | that |
Token ID | 326 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
ulf | +1.711 |
rer | +1.678 |
Mouth | +1.548 |
IPM | +1.483 |
ê | +1.478 |
Neg logit contributions | |
ilitarian | -1.837 |
>) | -1.767 |
romeda | -1.600 |
xxxxxxxx | -1.589 |
spot | -1.560 |
Token | Enemy |
Token ID | 21785 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
ulf | +0.535 |
rer | +0.523 |
Mouth | +0.484 |
ê | +0.468 |
IPM | +0.467 |
Neg logit contributions | |
ilitarian | -0.493 |
>) | -0.473 |
xxxxxxxx | -0.423 |
romeda | -0.421 |
spot | -0.418 |
Token | of |
Token ID | 286 |
Feature activation | +8.32e+00 |
Pos logit contributions | |
ulf | +3.460 |
rer | +3.373 |
Mouth | +3.091 |
ê | +2.920 |
ement | +2.853 |
Neg logit contributions | |
ilitarian | -4.488 |
>) | -4.405 |
xxxxxxxx | -3.925 |
romeda | -3.916 |
spot | -3.851 |
Token | the |
Token ID | 262 |
Feature activation | +7.69e+00 |
Pos logit contributions | |
ulf | +5.011 |
rer | +4.722 |
Mouth | +4.608 |
ê | +4.453 |
IPM | +4.209 |
Neg logit contributions | |
ilitarian | -6.535 |
>) | -6.106 |
romeda | -5.721 |
xxxxxxxx | -5.645 |
spot | -5.613 |
Token | State |
Token ID | 1812 |
Feature activation | +5.00e+00 |
Pos logit contributions | |
ulf | +3.585 |
rer | +3.503 |
Mouth | +3.447 |
ê | +3.047 |
IPM | +2.991 |
Neg logit contributions | |
ilitarian | -6.932 |
>) | -6.699 |
spot | -6.238 |
xxxxxxxx | -6.178 |
romeda | -6.164 |
Token | : |
Token ID | 25 |
Feature activation | +8.93e+00 |
Pos logit contributions | |
ulf | +2.851 |
rer | +2.726 |
Mouth | +2.538 |
ê | +2.377 |
IPM | +2.370 |
Neg logit contributions | |
ilitarian | -4.132 |
>) | -4.050 |
romeda | -3.747 |
xxxxxxxx | -3.707 |
uration | -3.575 |
Token | The |
Token ID | 383 |
Feature activation | +2.13e+01 |
Pos logit contributions | |
ulf | +5.294 |
rer | +5.162 |
Mouth | +5.100 |
ement | +4.436 |
Philos | +4.345 |
Neg logit contributions | |
ilitarian | -6.909 |
>) | -6.435 |
romeda | -6.041 |
xxxxxxxx | -5.927 |
uration | -5.878 |
Token | Life |
Token ID | 5155 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
ulf | +9.363 |
rer | +9.174 |
Mouth | +8.997 |
Philos | +8.360 |
ashi | +8.202 |
Neg logit contributions | |
ilitarian | -17.547 |
>) | -17.463 |
romeda | -16.127 |
itime | -15.226 |
akeru | -15.207 |
Token | of |
Token ID | 286 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
ulf | +6.685 |
rer | +5.685 |
Mouth | +5.292 |
Edited | +4.892 |
ashi | +4.790 |
Neg logit contributions | |
ilitarian | -12.448 |
>) | -12.250 |
romeda | -11.750 |
itime | -10.919 |
xxxxxxxx | -10.766 |
Token | Murray |
Token ID | 12164 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
ulf | +4.078 |
Mouth | +3.505 |
rer | +3.385 |
Aman | +3.114 |
ê | +3.070 |
Neg logit contributions | |
ilitarian | -12.676 |
>) | -12.228 |
ozy | -11.604 |
romeda | -11.462 |
xxxxxxxx | -11.370 |
Token | N |
Token ID | 399 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
ulf | +2.347 |
rer | +2.271 |
Mouth | +2.043 |
IPM | +1.958 |
ê | +1.950 |
Neg logit contributions | |
ilitarian | -3.726 |
>) | -3.608 |
romeda | -3.299 |
xxxxxxxx | -3.265 |
spot | -3.217 |
Token | . |
Token ID | 13 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ulf | +0.207 |
rer | +0.203 |
Mouth | +0.187 |
IPM | +0.180 |
ê | +0.180 |
Neg logit contributions | |
ilitarian | -0.216 |
>) | -0.209 |
xxxxxxxx | -0.188 |
romeda | -0.186 |
spot | -0.185 |
Token | . |
Token ID | 13 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
ulf | +1.440 |
rer | +1.416 |
Mouth | +1.318 |
IPM | +1.268 |
ê | +1.265 |
Neg logit contributions | |
ilitarian | -1.433 |
>) | -1.381 |
xxxxxxxx | -1.228 |
romeda | -1.223 |
spot | -1.207 |
Token |
|
Token ID | 198 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
ulf | +0.029 |
rer | +0.029 |
Mouth | +0.027 |
IPM | +0.026 |
ê | +0.026 |
Neg logit contributions | |
ilitarian | -0.027 |
>) | -0.026 |
xxxxxxxx | -0.023 |
romeda | -0.023 |
spot | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -6.64e+00 |
Pos logit contributions | |
ilitarian | +0.320 |
>) | +0.310 |
xxxxxxxx | +0.277 |
spot | +0.273 |
romeda | +0.272 |
Neg logit contributions | |
ulf | -0.342 |
rer | -0.336 |
Mouth | -0.312 |
IPM | -0.303 |
ê | -0.300 |
Token | The |
Token ID | 464 |
Feature activation | +6.70e+00 |
Pos logit contributions | |
>) | +4.097 |
ilitarian | +4.067 |
xxxxxxxx | +3.788 |
spot | +3.679 |
romeda | +3.451 |
Neg logit contributions | |
ulf | -4.769 |
rer | -4.621 |
Mouth | -4.460 |
IPM | -4.407 |
deserts | -4.352 |
Token | versatile |
Token ID | 21362 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
ulf | +4.434 |
rer | +4.411 |
Mouth | +4.170 |
IPM | +3.898 |
ê | +3.861 |
Neg logit contributions | |
ilitarian | -4.668 |
>) | -4.461 |
xxxxxxxx | -4.061 |
spot | -3.988 |
romeda | -3.983 |
Token | and |
Token ID | 290 |
Feature activation | +2.12e+01 |
Pos logit contributions | |
rer | +6.811 |
ulf | +6.597 |
Mouth | +6.264 |
IPM | +5.697 |
iner | +5.664 |
Neg logit contributions | |
ilitarian | -8.063 |
>) | -7.652 |
xxxxxxxx | -7.081 |
romeda | -6.925 |
spot | -6.660 |
Token | athletic |
Token ID | 15177 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
rer | +11.275 |
ulf | +10.743 |
Mouth | +9.875 |
IPM | +9.822 |
aver | +9.787 |
Neg logit contributions | |
ilitarian | -13.881 |
>) | -13.391 |
xxxxxxxx | -12.122 |
AIN | -11.592 |
ozy | -11.590 |
Token | Western |
Token ID | 4885 |
Feature activation | +4.97e+00 |
Pos logit contributions | |
rer | +7.545 |
ulf | +7.354 |
Mouth | +7.023 |
iner | +6.385 |
IPM | +6.363 |
Neg logit contributions | |
ilitarian | -8.086 |
>) | -7.667 |
xxxxxxxx | -6.940 |
romeda | -6.849 |
spot | -6.706 |
Token | Australian |
Token ID | 6638 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
ulf | +3.404 |
rer | +3.399 |
Mouth | +3.158 |
ê | +2.990 |
IPM | +2.985 |
Neg logit contributions | |
ilitarian | -3.455 |
>) | -3.303 |
romeda | -3.000 |
xxxxxxxx | -2.983 |
spot | -2.920 |
Token | quickly |
Token ID | 2952 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
rer | +8.567 |
ulf | +8.430 |
Mouth | +7.589 |
deserts | +7.417 |
iner | +7.417 |
Neg logit contributions | |
ilitarian | -9.434 |
>) | -9.010 |
xxxxxxxx | -7.984 |
romeda | -7.792 |
AIN | -7.671 |
Token | cement |
Token ID | 20534 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
ulf | +6.365 |
rer | +6.290 |
deserts | +5.621 |
iner | +5.506 |
IPM | +5.486 |
Neg logit contributions | |
ilitarian | -7.762 |
>) | -7.738 |
romeda | -6.676 |
xxxxxxxx | -6.633 |
Revival | -6.536 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ulf | +4.831 |
rer | +4.823 |
Mouth | +4.526 |
IPM | +4.244 |
ê | +4.222 |
Neg logit contributions | |
ilitarian | -5.165 |
>) | -4.964 |
spot | -4.382 |
romeda | -4.351 |
xxxxxxxx | -4.292 |
Token | talks |
Token ID | 6130 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
ulf | +0.723 |
rer | +0.709 |
Mouth | +0.660 |
IPM | +0.637 |
ê | +0.631 |
Neg logit contributions | |
ilitarian | -0.709 |
>) | -0.680 |
xxxxxxxx | -0.608 |
romeda | -0.603 |
spot | -0.602 |
Token | she |
Token ID | 673 |
Feature activation | +7.20e+00 |
Pos logit contributions | |
rer | +6.139 |
ulf | +6.119 |
Mouth | +5.515 |
ê | +5.268 |
iner | +5.116 |
Neg logit contributions | |
ilitarian | -8.258 |
>) | -7.877 |
romeda | -7.045 |
xxxxxxxx | -6.926 |
Revival | -6.813 |
Token | and |
Token ID | 290 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
ulf | +4.322 |
rer | +4.290 |
Mouth | +3.901 |
ê | +3.864 |
deserts | +3.770 |
Neg logit contributions | |
ilitarian | -5.586 |
>) | -5.285 |
romeda | -4.873 |
xxxxxxxx | -4.707 |
spot | -4.677 |
Token | I |
Token ID | 314 |
Feature activation | +9.81e+00 |
Pos logit contributions | |
ulf | +2.135 |
rer | +2.118 |
Mouth | +1.965 |
IPM | +1.873 |
ê | +1.858 |
Neg logit contributions | |
ilitarian | -2.225 |
>) | -2.138 |
xxxxxxxx | -1.892 |
spot | -1.884 |
romeda | -1.880 |
Token | would |
Token ID | 561 |
Feature activation | +2.12e+01 |
Pos logit contributions | |
rer | +5.349 |
ulf | +5.310 |
ê | +4.662 |
Mouth | +4.639 |
iner | +4.555 |
Neg logit contributions | |
ilitarian | -7.970 |
>) | -7.435 |
romeda | -6.819 |
xxxxxxxx | -6.793 |
Revival | -6.773 |
Token | have |
Token ID | 423 |
Feature activation | +1.82e+01 |
Pos logit contributions | |
ulf | +8.791 |
rer | +8.613 |
iner | +8.080 |
ê | +7.994 |
Mouth | +7.815 |
Neg logit contributions | |
ilitarian | -16.168 |
>) | -14.764 |
Revival | -14.046 |
romeda | -14.013 |
xxxxxxxx | -13.657 |
Token | . |
Token ID | 13 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
rer | +8.478 |
ulf | +8.424 |
Mouth | +8.025 |
deserts | +7.617 |
ê | +7.369 |
Neg logit contributions | |
ilitarian | -14.221 |
>) | -13.015 |
spot | -11.905 |
Revival | -11.882 |
romeda | -11.862 |
Token | They |
Token ID | 1119 |
Feature activation | +8.46e+00 |
Pos logit contributions | |
ulf | +3.474 |
rer | +3.463 |
Mouth | +3.344 |
IPM | +3.108 |
ê | +3.091 |
Neg logit contributions | |
ilitarian | -3.802 |
>) | -3.549 |
romeda | -3.230 |
spot | -3.165 |
xxxxxxxx | -3.143 |
Token | were |
Token ID | 547 |
Feature activation | +8.04e+00 |
Pos logit contributions | |
rer | +5.129 |
ulf | +5.049 |
Mouth | +4.477 |
ê | +4.365 |
deserts | +4.340 |
Neg logit contributions | |
ilitarian | -6.486 |
>) | -6.206 |
romeda | -5.591 |
xxxxxxxx | -5.573 |
spot | -5.471 |
Token | not |
Token ID | 407 |
Feature activation | +8.24e+00 |
Pos logit contributions | |
ulf | +4.718 |
rer | +4.689 |
Mouth | +4.396 |
deserts | +4.182 |
IPM | +4.120 |
Neg logit contributions | |
ilitarian | -6.285 |
>) | -5.837 |
xxxxxxxx | -5.304 |
romeda | -5.273 |
spot | -5.150 |
Token | engineer |
Token ID | 11949 |
Feature activation | -5.75e+00 |
Pos logit contributions | |
ilitarian | +2.441 |
>) | +2.382 |
xxxxxxxx | +2.133 |
romeda | +2.127 |
Eliot | +2.099 |
Neg logit contributions | |
ulf | -2.484 |
rer | -2.454 |
Mouth | -2.269 |
IPM | -2.162 |
ê | -2.160 |
Token | in |
Token ID | 287 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
ilitarian | +3.327 |
>) | +3.194 |
spot | +2.876 |
xxxxxxxx | +2.850 |
romeda | +2.834 |
Neg logit contributions | |
ulf | -4.439 |
rer | -4.347 |
Mouth | -4.143 |
IPM | -4.026 |
ê | -4.008 |
Token | charge |
Token ID | 3877 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
ulf | +3.415 |
rer | +3.393 |
Mouth | +3.144 |
IPM | +3.036 |
ê | +3.017 |
Neg logit contributions | |
ilitarian | -3.550 |
>) | -3.380 |
romeda | -3.074 |
xxxxxxxx | -3.043 |
spot | -2.991 |
Token | of |
Token ID | 286 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
ilitarian | +2.902 |
>) | +2.766 |
spot | +2.484 |
xxxxxxxx | +2.483 |
Eliot | +2.451 |
Neg logit contributions | |
ulf | -3.449 |
rer | -3.370 |
Mouth | -3.191 |
IPM | -3.095 |
ê | -3.071 |
Token | SpaceX |
Token ID | 26549 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
ulf | +6.978 |
rer | +6.842 |
Mouth | +6.341 |
IPM | +6.204 |
ê | +6.101 |
Neg logit contributions | |
ilitarian | -8.588 |
>) | -8.394 |
romeda | -7.483 |
xxxxxxxx | -7.468 |
ozy | -7.392 |
Token | 's |
Token ID | 338 |
Feature activation | +2.10e+01 |
Pos logit contributions | |
ulf | +5.594 |
rer | +5.533 |
Mouth | +5.036 |
IPM | +4.826 |
ê | +4.819 |
Neg logit contributions | |
ilitarian | -7.978 |
>) | -7.732 |
xxxxxxxx | -6.996 |
romeda | -6.903 |
ozy | -6.850 |
Token | software |
Token ID | 3788 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
rer | +11.150 |
ulf | +11.049 |
Mouth | +10.859 |
IPM | +10.725 |
deserts | +10.173 |
Neg logit contributions | |
ilitarian | -13.174 |
>) | -12.808 |
ozy | -11.701 |
xxxxxxxx | -11.422 |
AIN | -11.402 |
Token | : |
Token ID | 25 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
ilitarian | +1.679 |
>) | +1.613 |
xxxxxxxx | +1.448 |
romeda | +1.436 |
spot | +1.434 |
Neg logit contributions | |
ulf | -1.924 |
rer | -1.886 |
Mouth | -1.760 |
IPM | -1.697 |
ê | -1.681 |
Token | " |
Token ID | 366 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
ilitarian | +1.101 |
>) | +1.061 |
xxxxxxxx | +0.949 |
romeda | +0.940 |
spot | +0.936 |
Neg logit contributions | |
ulf | -1.183 |
rer | -1.157 |
Mouth | -1.073 |
IPM | -1.045 |
ê | -1.033 |
Token | I |
Token ID | 40 |
Feature activation | -8.36e+00 |
Pos logit contributions | |
ilitarian | +2.309 |
>) | +2.268 |
xxxxxxxx | +2.039 |
spot | +2.013 |
romeda | +1.953 |
Neg logit contributions | |
ulf | -2.731 |
rer | -2.674 |
Mouth | -2.519 |
IPM | -2.466 |
deserts | -2.392 |
Token | thought |
Token ID | 1807 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
ilitarian | +4.904 |
>) | +4.859 |
weighed | +4.526 |
xxxxxxxx | +4.343 |
spot | +4.298 |
Neg logit contributions | |
ulf | -6.110 |
rer | -5.916 |
OTOS | -5.697 |
Mouth | -5.696 |
� | -5.613 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
ulf | +1.066 |
rer | +1.047 |
Mouth | +0.949 |
IPM | +0.908 |
ê | +0.878 |
Neg logit contributions | |
ilitarian | -1.867 |
>) | -1.804 |
xxxxxxxx | -1.668 |
spot | -1.647 |
romeda | -1.646 |
Token |
|
Token ID | 198 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
ulf | +1.971 |
rer | +1.944 |
Mouth | +1.788 |
IPM | +1.730 |
ê | +1.712 |
Neg logit contributions | |
ilitarian | -2.211 |
>) | -2.109 |
romeda | -1.908 |
xxxxxxxx | -1.887 |
spot | -1.882 |
Token |
|
Token ID | 198 |
Feature activation | +5.56e+00 |
Pos logit contributions | |
ulf | +3.090 |
rer | +3.049 |
Mouth | +2.727 |
IPM | +2.663 |
ê | +2.635 |
Neg logit contributions | |
ilitarian | -4.019 |
>) | -3.740 |
romeda | -3.562 |
xxxxxxxx | -3.357 |
Revival | -3.354 |
Token | Recommend |
Token ID | 41248 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
ulf | +1.961 |
rer | +1.924 |
Mouth | +1.549 |
OTOS | +1.525 |
ê | +1.504 |
Neg logit contributions | |
ilitarian | -5.760 |
>) | -5.514 |
romeda | -5.248 |
xxxxxxxx | -5.066 |
Eliot | -5.056 |
Token | Share |
Token ID | 8734 |
Feature activation | +6.53e+00 |
Pos logit contributions | |
rer | +4.134 |
ulf | +3.795 |
Mouth | +3.737 |
IPM | +3.442 |
ê | +3.321 |
Neg logit contributions | |
ilitarian | -10.664 |
>) | -10.246 |
spot | -9.698 |
romeda | -9.535 |
ozy | -9.527 |
Token | this |
Token ID | 428 |
Feature activation | +2.05e+01 |
Pos logit contributions | |
rer | +3.999 |
ulf | +3.826 |
IPM | +3.551 |
Mouth | +3.472 |
deserts | +3.384 |
Neg logit contributions | |
ilitarian | -5.096 |
>) | -4.958 |
romeda | -4.467 |
xxxxxxxx | -4.450 |
spot | -4.395 |
Token | comment |
Token ID | 2912 |
Feature activation | +8.80e+00 |
Pos logit contributions | |
rer | +3.977 |
IPM | +3.427 |
ulf | +3.012 |
Mouth | +2.975 |
iner | +2.394 |
Neg logit contributions | |
ilitarian | -21.992 |
>) | -20.817 |
arsity | -20.064 |
romeda | -19.934 |
AIN | -19.738 |
Token | on |
Token ID | 319 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
rer | +5.108 |
ulf | +4.745 |
Mouth | +4.321 |
IPM | +4.263 |
ê | +4.019 |
Neg logit contributions | |
ilitarian | -7.225 |
>) | -6.957 |
romeda | -6.221 |
xxxxxxxx | -6.219 |
spot | -6.196 |
Token | Facebook |
Token ID | 3203 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
rer | +7.346 |
ulf | +7.201 |
IPM | +6.720 |
Mouth | +6.590 |
ê | +6.394 |
Neg logit contributions | |
ilitarian | -6.667 |
>) | -6.550 |
romeda | -5.584 |
xxxxxxxx | -5.324 |
spot | -5.290 |
Token | Share |
Token ID | 8734 |
Feature activation | +6.29e+00 |
Pos logit contributions | |
ulf | +4.084 |
rer | +4.042 |
IPM | +3.677 |
Mouth | +3.580 |
deserts | +3.363 |
Neg logit contributions | |
ilitarian | -10.474 |
>) | -10.328 |
romeda | -9.431 |
xxxxxxxx | -9.179 |
arsity | -9.143 |
Token | this |
Token ID | 428 |
Feature activation | +1.54e+01 |
Pos logit contributions | |
rer | +3.888 |
ulf | +3.830 |
IPM | +3.491 |
Mouth | +3.438 |
deserts | +3.369 |
Neg logit contributions | |
ilitarian | -4.797 |
>) | -4.659 |
romeda | -4.194 |
xxxxxxxx | -4.181 |
spot | -4.161 |
Token | enforce |
Token ID | 4605 |
Feature activation | +6.90e+00 |
Pos logit contributions | |
ulf | +3.454 |
rer | +3.452 |
Mouth | +3.153 |
IPM | +3.058 |
ê | +2.954 |
Neg logit contributions | |
ilitarian | -4.151 |
>) | -3.967 |
xxxxxxxx | -3.606 |
romeda | -3.551 |
spot | -3.504 |
Token | dawn |
Token ID | 17577 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
ulf | +4.435 |
rer | +4.418 |
Mouth | +4.090 |
IPM | +3.958 |
deserts | +3.868 |
Neg logit contributions | |
ilitarian | -5.017 |
>) | -4.842 |
xxxxxxxx | -4.433 |
romeda | -4.228 |
spot | -4.184 |
Token | - |
Token ID | 12 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
ulf | +2.752 |
rer | +2.741 |
Mouth | +2.469 |
IPM | +2.393 |
ê | +2.368 |
Neg logit contributions | |
ilitarian | -3.392 |
>) | -3.254 |
xxxxxxxx | -2.963 |
romeda | -2.898 |
spot | -2.837 |
Token | to |
Token ID | 1462 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
ulf | +3.550 |
rer | +3.461 |
ê | +3.069 |
Mouth | +3.048 |
aver | +2.988 |
Neg logit contributions | |
ilitarian | -4.168 |
>) | -3.997 |
xxxxxxxx | -3.672 |
romeda | -3.644 |
Eliot | -3.569 |
Token | - |
Token ID | 12 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
ulf | +2.252 |
rer | +2.205 |
Mouth | +1.993 |
ê | +1.937 |
IPM | +1.902 |
Neg logit contributions | |
ilitarian | -2.907 |
>) | -2.792 |
xxxxxxxx | -2.524 |
spot | -2.515 |
romeda | -2.487 |
Token | d |
Token ID | 67 |
Feature activation | +2.04e+01 |
Pos logit contributions | |
ulf | +2.200 |
rer | +2.137 |
Mouth | +1.966 |
ê | +1.948 |
IPM | +1.900 |
Neg logit contributions | |
ilitarian | -1.997 |
>) | -1.923 |
xxxxxxxx | -1.716 |
romeda | -1.693 |
Eliot | -1.668 |
Token | usk |
Token ID | 17990 |
Feature activation | +6.93e+00 |
Pos logit contributions | |
awn | +6.152 |
ulf | +5.732 |
iner | +5.361 |
ê | +5.181 |
rer | +5.104 |
Neg logit contributions | |
ilitarian | -19.356 |
>) | -19.019 |
xxxxxxxx | -18.607 |
Revival | -18.268 |
Eliot | -18.210 |
Token | park |
Token ID | 3952 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
rer | +4.084 |
ulf | +4.062 |
Mouth | +3.672 |
IPM | +3.615 |
deserts | +3.550 |
Neg logit contributions | |
ilitarian | -5.463 |
>) | -5.233 |
xxxxxxxx | -4.786 |
romeda | -4.636 |
spot | -4.535 |
Token | hours |
Token ID | 2250 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
ulf | +1.107 |
rer | +1.096 |
Mouth | +0.992 |
IPM | +0.963 |
ê | +0.952 |
Neg logit contributions | |
ilitarian | -1.396 |
>) | -1.345 |
xxxxxxxx | -1.221 |
romeda | -1.211 |
spot | -1.192 |
Token | at |
Token ID | 379 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
ulf | +2.770 |
rer | +2.730 |
Mouth | +2.498 |
IPM | +2.415 |
ê | +2.383 |
Neg logit contributions | |
ilitarian | -3.129 |
>) | -3.002 |
romeda | -2.707 |
xxxxxxxx | -2.700 |
spot | -2.639 |
Token | Battery |
Token ID | 23490 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
ulf | +1.621 |
rer | +1.604 |
Mouth | +1.493 |
IPM | +1.436 |
ê | +1.410 |
Neg logit contributions | |
ilitarian | -1.631 |
>) | -1.574 |
xxxxxxxx | -1.413 |
romeda | -1.397 |
spot | -1.383 |
Token | It |
Token ID | 1026 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
ulf | +0.833 |
rer | +0.818 |
Mouth | +0.755 |
IPM | +0.731 |
ê | +0.727 |
Neg logit contributions | |
ilitarian | -0.843 |
>) | -0.804 |
romeda | -0.723 |
xxxxxxxx | -0.718 |
spot | -0.712 |
Token | has |
Token ID | 468 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ulf | +0.508 |
rer | +0.500 |
Mouth | +0.458 |
IPM | +0.442 |
ê | +0.440 |
Neg logit contributions | |
ilitarian | -0.558 |
>) | -0.539 |
xxxxxxxx | -0.486 |
romeda | -0.481 |
spot | -0.478 |
Token | to |
Token ID | 284 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
ulf | +0.762 |
rer | +0.750 |
Mouth | +0.692 |
IPM | +0.671 |
ê | +0.662 |
Neg logit contributions | |
ilitarian | -0.788 |
>) | -0.760 |
xxxxxxxx | -0.682 |
romeda | -0.674 |
spot | -0.673 |
Token | pass |
Token ID | 1208 |
Feature activation | +6.59e+00 |
Pos logit contributions | |
ilitarian | +3.213 |
>) | +3.073 |
spot | +2.757 |
weighed | +2.744 |
xxxxxxxx | +2.742 |
Neg logit contributions | |
ulf | -3.723 |
rer | -3.591 |
Mouth | -3.450 |
IPM | -3.317 |
ê | -3.255 |
Token | the |
Token ID | 262 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
ulf | +4.314 |
rer | +4.195 |
Mouth | +3.872 |
IPM | +3.778 |
ê | +3.729 |
Neg logit contributions | |
ilitarian | -4.787 |
>) | -4.671 |
spot | -4.100 |
xxxxxxxx | -4.091 |
romeda | -4.055 |
Token | smell |
Token ID | 8508 |
Feature activation | +1.99e+01 |
Pos logit contributions | |
ulf | +2.602 |
rer | +2.547 |
Mouth | +2.373 |
IPM | +2.292 |
ê | +2.251 |
Neg logit contributions | |
ilitarian | -2.781 |
>) | -2.693 |
xxxxxxxx | -2.411 |
romeda | -2.409 |
spot | -2.386 |
Token | test |
Token ID | 1332 |
Feature activation | +5.95e+00 |
Pos logit contributions | |
rer | +7.776 |
ulf | +7.167 |
deserts | +5.849 |
ê | +5.837 |
Mouth | +5.400 |
Neg logit contributions | |
>) | -16.779 |
ilitarian | -16.734 |
Revival | -15.041 |
romeda | -14.981 |
xxxxxxxx | -14.838 |
Token | ," |
Token ID | 553 |
Feature activation | +6.32e+00 |
Pos logit contributions | |
rer | +3.560 |
ulf | +3.516 |
Mouth | +3.145 |
IPM | +3.047 |
ê | +3.005 |
Neg logit contributions | |
ilitarian | -4.648 |
>) | -4.538 |
xxxxxxxx | -3.994 |
romeda | -3.980 |
spot | -3.977 |
Token | he |
Token ID | 339 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
rer | +3.908 |
ulf | +3.886 |
Mouth | +3.586 |
IPM | +3.374 |
ê | +3.368 |
Neg logit contributions | |
ilitarian | -4.751 |
>) | -4.548 |
xxxxxxxx | -4.155 |
spot | -4.120 |
romeda | -4.094 |
Token | said |
Token ID | 531 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
ulf | +2.112 |
rer | +2.087 |
Mouth | +1.854 |
ê | +1.781 |
IPM | +1.763 |
Neg logit contributions | |
ilitarian | -3.049 |
>) | -2.947 |
xxxxxxxx | -2.699 |
romeda | -2.674 |
spot | -2.639 |
Token | of |
Token ID | 286 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
ulf | +0.194 |
rer | +0.190 |
Mouth | +0.176 |
IPM | +0.170 |
ê | +0.169 |
Neg logit contributions | |
ilitarian | -0.199 |
>) | -0.192 |
xxxxxxxx | -0.173 |
romeda | -0.171 |
spot | -0.170 |
Token | If |
Token ID | 1532 |
Feature activation | +1.40e+01 |
Pos logit contributions | |
ulf | +3.660 |
rer | +3.598 |
Mouth | +3.211 |
ê | +3.161 |
IPM | +3.132 |
Neg logit contributions | |
ilitarian | -4.058 |
>) | -3.780 |
romeda | -3.578 |
Eliot | -3.429 |
weighed | -3.388 |
Token | a |
Token ID | 257 |
Feature activation | +1.58e+01 |
Pos logit contributions | |
rer | +8.257 |
ulf | +8.091 |
Mouth | +7.338 |
IPM | +7.235 |
deserts | +6.941 |
Neg logit contributions | |
ilitarian | -9.982 |
>) | -9.450 |
romeda | -8.829 |
xxxxxxxx | -8.578 |
ozy | -8.298 |
Token | homeowner |
Token ID | 40130 |
Feature activation | +8.63e+00 |
Pos logit contributions | |
rer | +9.786 |
ulf | +9.321 |
Mouth | +8.913 |
ement | +8.381 |
IPM | +8.163 |
Neg logit contributions | |
ilitarian | -10.099 |
>) | -9.638 |
romeda | -9.093 |
xxxxxxxx | -8.731 |
Eliot | -8.315 |
Token | � |
Token ID | 447 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
rer | +5.329 |
ulf | +5.276 |
deserts | +4.779 |
Mouth | +4.666 |
IPM | +4.495 |
Neg logit contributions | |
ilitarian | -6.491 |
>) | -6.146 |
romeda | -5.719 |
xxxxxxxx | -5.503 |
spot | -5.430 |
Token | � |
Token ID | 247 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
ulf | +3.164 |
rer | +3.105 |
Mouth | +2.899 |
ê | +2.773 |
IPM | +2.746 |
Neg logit contributions | |
ilitarian | -3.087 |
>) | -2.848 |
xxxxxxxx | -2.603 |
romeda | -2.586 |
spot | -2.574 |
Token | s |
Token ID | 82 |
Feature activation | +1.99e+01 |
Pos logit contributions | |
ulf | +2.890 |
rer | +2.865 |
Mouth | +2.638 |
ê | +2.557 |
IPM | +2.539 |
Neg logit contributions | |
ilitarian | -2.164 |
>) | -2.047 |
romeda | -1.831 |
xxxxxxxx | -1.800 |
Eliot | -1.740 |
Token | curb |
Token ID | 20799 |
Feature activation | +7.38e+00 |
Pos logit contributions | |
rer | +11.462 |
ulf | +10.891 |
Mouth | +10.396 |
deserts | +9.880 |
IPM | +9.756 |
Neg logit contributions | |
ilitarian | -12.723 |
>) | -11.923 |
romeda | -11.580 |
xxxxxxxx | -10.913 |
ozy | -10.791 |
Token | , |
Token ID | 11 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
rer | +4.878 |
ulf | +4.799 |
Mouth | +4.381 |
ê | +4.227 |
IPM | +4.106 |
Neg logit contributions | |
ilitarian | -5.297 |
>) | -5.060 |
romeda | -4.659 |
xxxxxxxx | -4.505 |
Eliot | -4.465 |
Token | g |
Token ID | 308 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
rer | +7.995 |
ulf | +7.864 |
Mouth | +7.285 |
IPM | +7.154 |
ê | +6.970 |
Neg logit contributions | |
ilitarian | -9.086 |
>) | -8.947 |
romeda | -7.933 |
xxxxxxxx | -7.921 |
ozy | -7.601 |
Token | utter |
Token ID | 10381 |
Feature activation | +9.96e+00 |
Pos logit contributions | |
ulf | +3.906 |
rer | +3.572 |
ê | +3.019 |
ement | +2.922 |
aver | +2.882 |
Neg logit contributions | |
ilitarian | -9.689 |
>) | -9.631 |
romeda | -8.810 |
Revival | -8.809 |
xxxxxxxx | -8.728 |
Token | , |
Token ID | 11 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
rer | +5.729 |
ulf | +5.609 |
Mouth | +5.180 |
ê | +4.867 |
IPM | +4.800 |
Neg logit contributions | |
ilitarian | -7.860 |
>) | -7.497 |
romeda | -6.855 |
xxxxxxxx | -6.783 |
Eliot | -6.562 |
Token | is |
Token ID | 318 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
ilitarian | +0.693 |
>) | +0.666 |
xxxxxxxx | +0.600 |
spot | +0.594 |
romeda | +0.591 |
Neg logit contributions | |
ulf | -0.689 |
rer | -0.674 |
Mouth | -0.623 |
IPM | -0.607 |
ê | -0.600 |
Token | making |
Token ID | 1642 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
ulf | +2.057 |
rer | +2.034 |
Mouth | +1.909 |
IPM | +1.824 |
ê | +1.799 |
Neg logit contributions | |
ilitarian | -2.128 |
>) | -2.047 |
xxxxxxxx | -1.832 |
romeda | -1.808 |
spot | -1.782 |
Token | his |
Token ID | 465 |
Feature activation | +6.99e+00 |
Pos logit contributions | |
ulf | +1.833 |
rer | +1.818 |
Mouth | +1.697 |
IPM | +1.633 |
ê | +1.586 |
Neg logit contributions | |
ilitarian | -1.968 |
>) | -1.903 |
xxxxxxxx | -1.712 |
romeda | -1.701 |
spot | -1.679 |
Token | classmates |
Token ID | 28999 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
ulf | +3.971 |
rer | +3.964 |
Mouth | +3.768 |
IPM | +3.511 |
deserts | +3.507 |
Neg logit contributions | |
ilitarian | -5.434 |
>) | -5.302 |
xxxxxxxx | -4.878 |
romeda | -4.852 |
ozy | -4.659 |
Token | ' |
Token ID | 6 |
Feature activation | +6.09e+00 |
Pos logit contributions | |
ulf | +6.348 |
rer | +6.312 |
Mouth | +5.899 |
deserts | +5.654 |
ê | +5.518 |
Neg logit contributions | |
ilitarian | -7.325 |
>) | -7.184 |
xxxxxxxx | -6.460 |
romeda | -6.236 |
spot | -6.083 |
Token | lives |
Token ID | 3160 |
Feature activation | +1.99e+01 |
Pos logit contributions | |
ulf | +4.005 |
rer | +3.964 |
Mouth | +3.776 |
deserts | +3.600 |
IPM | +3.579 |
Neg logit contributions | |
ilitarian | -4.307 |
>) | -4.158 |
romeda | -3.742 |
xxxxxxxx | -3.734 |
spot | -3.599 |
Token | miserable |
Token ID | 22444 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
rer | +9.723 |
ulf | +9.360 |
deserts | +8.732 |
iner | +8.602 |
mosquit | +8.338 |
Neg logit contributions | |
ilitarian | -14.236 |
>) | -14.077 |
xxxxxxxx | -12.846 |
romeda | -12.385 |
Revival | -12.367 |
Token | , |
Token ID | 11 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ulf | +3.395 |
rer | +3.386 |
Mouth | +3.060 |
deserts | +2.924 |
ê | +2.920 |
Neg logit contributions | |
ilitarian | -4.057 |
>) | -3.970 |
xxxxxxxx | -3.537 |
romeda | -3.535 |
spot | -3.439 |
Token | this |
Token ID | 428 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
ulf | +0.963 |
rer | +0.947 |
Mouth | +0.882 |
IPM | +0.848 |
ê | +0.838 |
Neg logit contributions | |
ilitarian | -1.005 |
>) | -0.972 |
xxxxxxxx | -0.870 |
romeda | -0.862 |
spot | -0.855 |
Token | time |
Token ID | 640 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ulf | +0.219 |
rer | +0.215 |
Mouth | +0.200 |
IPM | +0.194 |
ê | +0.192 |
Neg logit contributions | |
ilitarian | -0.203 |
>) | -0.196 |
xxxxxxxx | -0.175 |
romeda | -0.173 |
spot | -0.172 |
Token | thanks |
Token ID | 5176 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
ulf | +0.785 |
rer | +0.773 |
Mouth | +0.714 |
IPM | +0.690 |
ê | +0.684 |
Neg logit contributions | |
ilitarian | -0.803 |
>) | -0.775 |
xxxxxxxx | -0.694 |
romeda | -0.687 |
spot | -0.682 |
Token | Z |
Token ID | 1168 |
Feature activation | +9.00e+00 |
Pos logit contributions | |
ulf | +0.475 |
rer | +0.466 |
Mouth | +0.426 |
IPM | +0.407 |
ê | +0.406 |
Neg logit contributions | |
ilitarian | -0.619 |
>) | -0.600 |
xxxxxxxx | -0.545 |
romeda | -0.542 |
spot | -0.537 |
Token | onday |
Token ID | 3204 |
Feature activation | +8.34e-02 |
Pos logit contributions | |
ulf | +1.654 |
rer | +1.546 |
Mouth | +0.974 |
ê | +0.964 |
iner | +0.788 |
Neg logit contributions | |
ilitarian | -10.643 |
>) | -10.374 |
romeda | -9.795 |
Revival | -9.740 |
xxxxxxxx | -9.712 |
Token | � |
Token ID | 447 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ulf | +0.054 |
rer | +0.053 |
Mouth | +0.049 |
IPM | +0.047 |
ê | +0.047 |
Neg logit contributions | |
ilitarian | -0.062 |
>) | -0.060 |
xxxxxxxx | -0.054 |
romeda | -0.053 |
spot | -0.053 |
Token | � |
Token ID | 247 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
ilitarian | +0.813 |
>) | +0.788 |
xxxxxxxx | +0.691 |
spot | +0.684 |
romeda | +0.681 |
Neg logit contributions | |
ulf | -1.013 |
rer | -0.993 |
Mouth | -0.926 |
IPM | -0.907 |
ê | -0.895 |
Token | s |
Token ID | 82 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
ulf | +0.387 |
rer | +0.382 |
Mouth | +0.358 |
IPM | +0.347 |
ê | +0.346 |
Neg logit contributions | |
ilitarian | -0.269 |
>) | -0.256 |
xxxxxxxx | -0.224 |
romeda | -0.221 |
spot | -0.219 |
Token | d |
Token ID | 288 |
Feature activation | +1.98e+01 |
Pos logit contributions | |
ilitarian | +2.027 |
>) | +1.966 |
spot | +1.764 |
xxxxxxxx | +1.763 |
romeda | +1.736 |
Neg logit contributions | |
ulf | -1.838 |
rer | -1.790 |
Mouth | -1.622 |
IPM | -1.605 |
ê | -1.581 |
Token | ul |
Token ID | 377 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
ulf | +11.815 |
rer | +11.349 |
ê | +11.138 |
ashi | +10.261 |
azing | +10.226 |
Neg logit contributions | |
ilitarian | -12.372 |
>) | -12.051 |
Revival | -11.163 |
xxxxxxxx | -11.111 |
weighed | -10.812 |
Token | c |
Token ID | 66 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
ilitarian | +1.585 |
>) | +1.519 |
xxxxxxxx | +1.339 |
spot | +1.329 |
romeda | +1.305 |
Neg logit contributions | |
ulf | -1.988 |
rer | -1.960 |
Mouth | -1.838 |
IPM | -1.802 |
ê | -1.771 |
Token | et |
Token ID | 316 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
ulf | +2.590 |
rer | +2.540 |
Mouth | +2.292 |
ê | +2.287 |
IPM | +2.229 |
Neg logit contributions | |
ilitarian | -2.786 |
>) | -2.699 |
xxxxxxxx | -2.418 |
romeda | -2.418 |
spot | -2.406 |
Token | tones |
Token ID | 23755 |
Feature activation | +6.28e+00 |
Pos logit contributions | |
ulf | +0.223 |
rer | +0.219 |
Mouth | +0.201 |
IPM | +0.195 |
ê | +0.193 |
Neg logit contributions | |
ilitarian | -0.241 |
>) | -0.233 |
xxxxxxxx | -0.210 |
romeda | -0.207 |
spot | -0.207 |
Token | . |
Token ID | 13 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
ulf | +3.917 |
rer | +3.891 |
Mouth | +3.575 |
ê | +3.439 |
IPM | +3.268 |
Neg logit contributions | |
ilitarian | -4.767 |
>) | -4.592 |
romeda | -4.191 |
xxxxxxxx | -4.105 |
spot | -4.029 |
Token | ) |
Token ID | 1267 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
ulf | +1.436 |
rer | +1.426 |
Mouth | +1.313 |
ê | +1.261 |
IPM | +1.258 |
Neg logit contributions | |
ilitarian | -1.464 |
>) | -1.401 |
xxxxxxxx | -1.268 |
romeda | -1.255 |
spot | -1.252 |
Token |
|
Token ID | 198 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
ilitarian | +2.355 |
>) | +2.311 |
xxxxxxxx | +2.036 |
spot | +2.028 |
romeda | +1.995 |
Neg logit contributions | |
ulf | -2.374 |
rer | -2.323 |
Mouth | -2.130 |
IPM | -2.117 |
ê | -2.063 |
Token |
|
Token ID | 198 |
Feature activation | +8.68e+00 |
Pos logit contributions | |
ulf | +1.593 |
rer | +1.566 |
Mouth | +1.445 |
ê | +1.388 |
IPM | +1.382 |
Neg logit contributions | |
ilitarian | -1.728 |
>) | -1.628 |
romeda | -1.496 |
xxxxxxxx | -1.469 |
spot | -1.460 |
Token | ( |
Token ID | 7 |
Feature activation | +1.57e+01 |
Pos logit contributions | |
ulf | +5.649 |
rer | +5.532 |
Mouth | +5.105 |
ê | +4.838 |
IPM | +4.717 |
Neg logit contributions | |
ilitarian | -6.163 |
>) | -5.661 |
romeda | -5.449 |
xxxxxxxx | -5.343 |
Eliot | -5.309 |
Token | Example |
Token ID | 16281 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
rer | +7.091 |
ulf | +6.976 |
Mouth | +6.158 |
aver | +5.772 |
ê | +5.618 |
Neg logit contributions | |
ilitarian | -12.365 |
Eliot | -11.280 |
>) | -11.269 |
xxxxxxxx | -11.143 |
weighed | -11.096 |
Token | : |
Token ID | 25 |
Feature activation | +1.98e+01 |
Pos logit contributions | |
ulf | +1.608 |
rer | +1.582 |
Mouth | +1.458 |
IPM | +1.385 |
ê | +1.380 |
Neg logit contributions | |
ilitarian | -2.043 |
>) | -1.920 |
romeda | -1.778 |
xxxxxxxx | -1.755 |
spot | -1.746 |
Token | Your |
Token ID | 3406 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
ulf | +7.850 |
Mouth | +7.448 |
rer | +7.080 |
ê | +6.072 |
IPM | +5.767 |
Neg logit contributions | |
ilitarian | -15.709 |
romeda | -15.288 |
xxxxxxxx | -14.356 |
ozy | -14.151 |
>) | -14.138 |
Token | + |
Token ID | 1343 |
Feature activation | +9.41e+00 |
Pos logit contributions | |
ulf | +4.031 |
rer | +3.728 |
Mouth | +3.342 |
ê | +2.942 |
IPM | +2.851 |
Neg logit contributions | |
ilitarian | -10.757 |
>) | -10.199 |
romeda | -10.108 |
Eliot | -9.619 |
ozy | -9.548 |
Token | 1 |
Token ID | 16 |
Feature activation | +1.35e+01 |
Pos logit contributions | |
ulf | +3.902 |
rer | +3.619 |
Mouth | +3.005 |
ê | +2.925 |
aver | +2.837 |
Neg logit contributions | |
ilitarian | -9.268 |
romeda | -8.441 |
>) | -8.439 |
Revival | -8.111 |
Eliot | -8.072 |
Token | shield |
Token ID | 7614 |
Feature activation | -6.10e+00 |
Pos logit contributions | |
ulf | +1.836 |
rer | +1.274 |
Mouth | +0.626 |
IPM | +0.473 |
deserts | +0.470 |
Neg logit contributions | |
ilitarian | -16.243 |
>) | -15.197 |
romeda | -14.990 |
Eliot | -14.913 |
ozy | -14.708 |
Token | keeps |
Token ID | 7622 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
ilitarian | +3.648 |
>) | +3.596 |
xxxxxxxx | +3.230 |
spot | +3.225 |
weighed | +3.102 |
Neg logit contributions | |
ulf | -4.652 |
rer | -4.534 |
Mouth | -4.264 |
IPM | -4.196 |
ê | -4.132 |
Token | turned |
Token ID | 2900 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
ilitarian | +4.276 |
>) | +4.158 |
weighed | +3.846 |
xxxxxxxx | +3.801 |
spot | +3.760 |
Neg logit contributions | |
ulf | -5.069 |
rer | -4.905 |
Mouth | -4.581 |
IPM | -4.534 |
ê | -4.448 |
Token | out |
Token ID | 503 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
ulf | +4.195 |
rer | +4.129 |
Mouth | +3.819 |
IPM | +3.746 |
ê | +3.720 |
Neg logit contributions | |
ilitarian | -4.097 |
>) | -3.997 |
romeda | -3.445 |
spot | -3.402 |
xxxxxxxx | -3.392 |
Token | to |
Token ID | 284 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
ulf | +1.644 |
rer | +1.602 |
Mouth | +1.471 |
ê | +1.424 |
IPM | +1.415 |
Neg logit contributions | |
ilitarian | -1.859 |
>) | -1.797 |
romeda | -1.617 |
xxxxxxxx | -1.611 |
spot | -1.591 |
Token | be |
Token ID | 307 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
ulf | +1.650 |
rer | +1.617 |
Mouth | +1.488 |
ê | +1.440 |
IPM | +1.432 |
Neg logit contributions | |
ilitarian | -1.613 |
>) | -1.551 |
xxxxxxxx | -1.391 |
romeda | -1.382 |
spot | -1.366 |
Token | a |
Token ID | 257 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
ulf | +1.713 |
rer | +1.680 |
Mouth | +1.561 |
IPM | +1.509 |
ê | +1.499 |
Neg logit contributions | |
ilitarian | -1.743 |
>) | -1.674 |
xxxxxxxx | -1.491 |
romeda | -1.483 |
spot | -1.464 |
Token | turning |
Token ID | 6225 |
Feature activation | +1.96e+01 |
Pos logit contributions | |
ilitarian | +1.541 |
>) | +1.481 |
xxxxxxxx | +1.337 |
spot | +1.325 |
romeda | +1.315 |
Neg logit contributions | |
ulf | -1.535 |
rer | -1.500 |
Mouth | -1.382 |
IPM | -1.353 |
ê | -1.331 |
Token | point |
Token ID | 966 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ulf | +5.791 |
rer | +5.515 |
deserts | +4.881 |
Mouth | +4.841 |
ement | +4.585 |
Neg logit contributions | |
ilitarian | -18.071 |
>) | -17.532 |
romeda | -16.198 |
xxxxxxxx | -16.063 |
AIN | -15.902 |
Token | , |
Token ID | 11 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
ulf | +1.066 |
rer | +1.050 |
Mouth | +0.965 |
IPM | +0.928 |
ê | +0.925 |
Neg logit contributions | |
ilitarian | -1.166 |
>) | -1.128 |
romeda | -1.003 |
xxxxxxxx | -1.003 |
spot | -0.992 |
Token | although |
Token ID | 3584 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ilitarian | +0.065 |
>) | +0.062 |
xxxxxxxx | +0.056 |
romeda | +0.055 |
spot | +0.055 |
Neg logit contributions | |
ulf | -0.065 |
rer | -0.064 |
Mouth | -0.059 |
IPM | -0.057 |
ê | -0.057 |
Token | L |
Token ID | 406 |
Feature activation | +5.40e-02 |
Pos logit contributions | |
ilitarian | +1.162 |
>) | +1.121 |
xxxxxxxx | +1.005 |
spot | +0.990 |
romeda | +0.987 |
Neg logit contributions | |
ulf | -1.288 |
rer | -1.261 |
Mouth | -1.170 |
IPM | -1.138 |
ê | -1.130 |
Token | all |
Token ID | 439 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
ulf | +0.040 |
rer | +0.040 |
Mouth | +0.037 |
IPM | +0.036 |
ê | +0.035 |
Neg logit contributions | |
ilitarian | -0.035 |
>) | -0.034 |
xxxxxxxx | -0.030 |
romeda | -0.030 |
spot | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
ilitarian | +1.185 |
>) | +1.140 |
xxxxxxxx | +1.024 |
spot | +1.012 |
romeda | +1.004 |
Neg logit contributions | |
ulf | -1.216 |
rer | -1.188 |
Mouth | -1.106 |
IPM | -1.074 |
ê | -1.061 |
Token | marry |
Token ID | 12479 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
ilitarian | +1.282 |
>) | +1.223 |
xxxxxxxx | +1.085 |
spot | +1.072 |
romeda | +1.067 |
Neg logit contributions | |
ulf | -1.494 |
rer | -1.469 |
Mouth | -1.366 |
IPM | -1.326 |
ê | -1.317 |
Token | the |
Token ID | 262 |
Feature activation | +6.89e+00 |
Pos logit contributions | |
ilitarian | +1.243 |
>) | +1.198 |
xxxxxxxx | +1.072 |
spot | +1.058 |
romeda | +1.048 |
Neg logit contributions | |
ulf | -1.323 |
rer | -1.292 |
Mouth | -1.203 |
IPM | -1.172 |
ê | -1.160 |
Token | person |
Token ID | 1048 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
ulf | +4.712 |
rer | +4.611 |
Mouth | +4.329 |
IPM | +4.146 |
deserts | +4.102 |
Neg logit contributions | |
ilitarian | -4.667 |
>) | -4.538 |
romeda | -4.106 |
spot | -3.989 |
xxxxxxxx | -3.985 |
Token | of |
Token ID | 286 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
ulf | +3.251 |
rer | +3.209 |
Mouth | +2.880 |
IPM | +2.782 |
ê | +2.765 |
Neg logit contributions | |
ilitarian | -3.358 |
>) | -3.188 |
romeda | -2.883 |
xxxxxxxx | -2.835 |
spot | -2.815 |
Token | their |
Token ID | 511 |
Feature activation | +1.95e+01 |
Pos logit contributions | |
ulf | +3.357 |
rer | +3.280 |
Mouth | +2.980 |
IPM | +2.896 |
ê | +2.868 |
Neg logit contributions | |
ilitarian | -3.648 |
>) | -3.523 |
romeda | -3.214 |
xxxxxxxx | -3.167 |
spot | -3.139 |
Token | choice |
Token ID | 3572 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
ulf | +8.121 |
deserts | +8.001 |
rer | +7.849 |
Mouth | +7.800 |
IPM | +7.270 |
Neg logit contributions | |
ilitarian | -15.207 |
>) | -14.404 |
romeda | -14.007 |
ozy | -13.469 |
xxxxxxxx | -13.353 |
Token | is |
Token ID | 318 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ilitarian | +1.821 |
>) | +1.756 |
xxxxxxxx | +1.570 |
spot | +1.548 |
weighed | +1.532 |
Neg logit contributions | |
ulf | -1.969 |
rer | -1.918 |
Mouth | -1.792 |
IPM | -1.754 |
ê | -1.729 |
Token | any |
Token ID | 597 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
ulf | +0.882 |
rer | +0.871 |
Mouth | +0.802 |
IPM | +0.781 |
ê | +0.771 |
Neg logit contributions | |
ilitarian | -0.880 |
>) | -0.850 |
xxxxxxxx | -0.761 |
romeda | -0.755 |
spot | -0.750 |
Token | different |
Token ID | 1180 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ilitarian | +1.383 |
>) | +1.321 |
xxxxxxxx | +1.189 |
spot | +1.167 |
romeda | +1.164 |
Neg logit contributions | |
ulf | -1.392 |
rer | -1.356 |
Mouth | -1.265 |
IPM | -1.227 |
ê | -1.206 |
Token | now |
Token ID | 783 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
ilitarian | +0.752 |
>) | +0.722 |
xxxxxxxx | +0.646 |
spot | +0.635 |
romeda | +0.635 |
Neg logit contributions | |
ulf | -0.804 |
rer | -0.787 |
Mouth | -0.734 |
IPM | -0.713 |
ê | -0.705 |
Token | Photo |
Token ID | 5555 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
ilitarian | +0.902 |
>) | +0.867 |
xxxxxxxx | +0.771 |
spot | +0.764 |
romeda | +0.761 |
Neg logit contributions | |
ulf | -1.033 |
rer | -1.014 |
Mouth | -0.943 |
IPM | -0.916 |
ê | -0.912 |
Token | Pokemon |
Token ID | 14878 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ulf | +0.700 |
rer | +0.688 |
Mouth | +0.642 |
IPM | +0.620 |
ê | +0.611 |
Neg logit contributions | |
ilitarian | -0.692 |
>) | -0.663 |
xxxxxxxx | -0.595 |
romeda | -0.590 |
spot | -0.587 |
Token | Go |
Token ID | 1514 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
ilitarian | +1.351 |
>) | +1.310 |
xxxxxxxx | +1.177 |
spot | +1.169 |
romeda | +1.165 |
Neg logit contributions | |
ulf | -1.342 |
rer | -1.306 |
Mouth | -1.204 |
IPM | -1.175 |
ê | -1.167 |
Token | players |
Token ID | 1938 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
ilitarian | +1.794 |
>) | +1.734 |
xxxxxxxx | +1.556 |
spot | +1.549 |
romeda | +1.535 |
Neg logit contributions | |
ulf | -1.845 |
rer | -1.796 |
Mouth | -1.664 |
IPM | -1.624 |
ê | -1.605 |
Token | make |
Token ID | 787 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
ilitarian | +1.243 |
>) | +1.200 |
xxxxxxxx | +1.073 |
romeda | +1.071 |
spot | +1.070 |
Neg logit contributions | |
ulf | -1.269 |
rer | -1.239 |
Mouth | -1.145 |
IPM | -1.114 |
ê | -1.110 |
Token | their |
Token ID | 511 |
Feature activation | +1.95e+01 |
Pos logit contributions | |
rer | +6.435 |
ulf | +6.265 |
Mouth | +5.928 |
deserts | +5.876 |
IPM | +5.797 |
Neg logit contributions | |
ilitarian | -9.898 |
>) | -9.528 |
xxxxxxxx | -8.680 |
romeda | -8.498 |
AIN | -8.379 |
Token | way |
Token ID | 835 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
ulf | +6.384 |
deserts | +6.317 |
Mouth | +6.194 |
rer | +6.186 |
turns | +5.945 |
Neg logit contributions | |
ilitarian | -16.612 |
>) | -16.452 |
":[ | -14.974 |
ozy | -14.843 |
xxxxxxxx | -14.632 |
Token | through |
Token ID | 832 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ilitarian | +1.070 |
>) | +1.036 |
xxxxxxxx | +0.927 |
spot | +0.918 |
romeda | +0.916 |
Neg logit contributions | |
ulf | -1.151 |
rer | -1.125 |
Mouth | -1.044 |
IPM | -1.019 |
ê | -1.011 |
Token | Battery |
Token ID | 23490 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
ilitarian | +0.714 |
>) | +0.687 |
xxxxxxxx | +0.614 |
romeda | +0.608 |
spot | +0.608 |
Neg logit contributions | |
ulf | -0.751 |
rer | -0.736 |
Mouth | -0.681 |
IPM | -0.661 |
ê | -0.657 |
Token | Park |
Token ID | 3250 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ulf | +4.155 |
rer | +4.097 |
Mouth | +3.890 |
ê | +3.643 |
IPM | +3.617 |
Neg logit contributions | |
ilitarian | -4.419 |
>) | -4.277 |
xxxxxxxx | -3.886 |
romeda | -3.862 |
spot | -3.689 |
Token | as |
Token ID | 355 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ulf | +1.035 |
rer | +1.020 |
Mouth | +0.949 |
IPM | +0.915 |
ê | +0.904 |
Neg logit contributions | |
ilitarian | -1.022 |
>) | -0.985 |
xxxxxxxx | -0.882 |
romeda | -0.871 |
spot | -0.865 |
Token | before |
Token ID | 878 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
ulf | +2.996 |
rer | +2.952 |
Mouth | +2.648 |
ê | +2.564 |
deserts | +2.535 |
Neg logit contributions | |
ilitarian | -3.438 |
>) | -3.387 |
xxxxxxxx | -3.005 |
romeda | -2.973 |
spot | -2.919 |
Token | him |
Token ID | 683 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
ulf | +0.182 |
rer | +0.178 |
Mouth | +0.166 |
IPM | +0.161 |
ê | +0.159 |
Neg logit contributions | |
ilitarian | -0.173 |
>) | -0.166 |
xxxxxxxx | -0.149 |
romeda | -0.147 |
spot | -0.147 |
Token | , |
Token ID | 11 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
ilitarian | +0.249 |
>) | +0.239 |
xxxxxxxx | +0.215 |
spot | +0.212 |
romeda | +0.212 |
Neg logit contributions | |
ulf | -0.248 |
rer | -0.243 |
Mouth | -0.225 |
IPM | -0.219 |
ê | -0.216 |
Token | and |
Token ID | 290 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
ulf | +0.339 |
rer | +0.332 |
Mouth | +0.308 |
IPM | +0.297 |
ê | +0.295 |
Neg logit contributions | |
ilitarian | -0.345 |
>) | -0.333 |
xxxxxxxx | -0.299 |
romeda | -0.295 |
spot | -0.295 |
Token | made |
Token ID | 925 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
ulf | +0.033 |
rer | +0.032 |
Mouth | +0.030 |
IPM | +0.029 |
ê | +0.028 |
Neg logit contributions | |
ilitarian | -0.032 |
>) | -0.031 |
xxxxxxxx | -0.028 |
romeda | -0.027 |
spot | -0.027 |
Token | his |
Token ID | 465 |
Feature activation | +1.92e+01 |
Pos logit contributions | |
ilitarian | +1.969 |
>) | +1.875 |
xxxxxxxx | +1.678 |
spot | +1.665 |
romeda | +1.659 |
Neg logit contributions | |
ulf | -2.120 |
rer | -2.077 |
Mouth | -1.927 |
IPM | -1.873 |
ê | -1.867 |
Token | way |
Token ID | 835 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ulf | +9.771 |
rer | +9.653 |
deserts | +9.556 |
Mouth | +9.447 |
embassy | +8.773 |
Neg logit contributions | |
>) | -13.228 |
ilitarian | -12.911 |
xxxxxxxx | -11.936 |
romeda | -11.626 |
AIN | -11.299 |
Token | to |
Token ID | 284 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
ilitarian | +0.906 |
>) | +0.875 |
xxxxxxxx | +0.791 |
spot | +0.784 |
romeda | +0.783 |
Neg logit contributions | |
ulf | -0.822 |
rer | -0.804 |
Mouth | -0.744 |
IPM | -0.723 |
ê | -0.713 |
Token | York |
Token ID | 1971 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ilitarian | +3.699 |
>) | +3.460 |
Eliot | +3.126 |
spot | +3.073 |
xxxxxxxx | +3.063 |
Neg logit contributions | |
ulf | -4.232 |
rer | -4.228 |
IPM | -3.850 |
Mouth | -3.798 |
OTOS | -3.750 |
Token | , |
Token ID | 11 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
ilitarian | +0.988 |
>) | +0.947 |
xxxxxxxx | +0.849 |
spot | +0.846 |
romeda | +0.841 |
Neg logit contributions | |
ulf | -1.001 |
rer | -0.982 |
Mouth | -0.910 |
IPM | -0.887 |
ê | -0.873 |
Token | devastating |
Token ID | 14101 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
ulf | +1.063 |
rer | +1.040 |
Mouth | +0.963 |
IPM | +0.924 |
ê | +0.919 |
Neg logit contributions | |
ilitarian | -1.154 |
>) | -1.120 |
xxxxxxxx | -1.007 |
romeda | -0.993 |
spot | -0.986 |
Token | the |
Token ID | 262 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
ilitarian | +4.955 |
>) | +4.837 |
Revival | +4.360 |
xxxxxxxx | +4.311 |
spot | +4.248 |
Neg logit contributions | |
ulf | -6.091 |
rer | -6.069 |
Mouth | -5.652 |
OTOS | -5.524 |
ê | -5.384 |
Token | lake |
Token ID | 13546 |
Feature activation | -8.20e+00 |
Pos logit contributions | |
ilitarian | +7.318 |
>) | +7.153 |
Revival | +6.836 |
xxxxxxxx | +6.579 |
spot | +6.356 |
Neg logit contributions | |
ulf | -7.885 |
rer | -7.663 |
Mouth | -7.009 |
OTOS | -6.962 |
ê | -6.823 |
Token | � |
Token ID | 447 |
Feature activation | +6.45e+00 |
Pos logit contributions | |
ilitarian | +5.168 |
>) | +4.937 |
spot | +4.670 |
xxxxxxxx | +4.493 |
Revival | +4.375 |
Neg logit contributions | |
ulf | -5.819 |
rer | -5.517 |
Mouth | -5.302 |
IPM | -5.087 |
OTOS | -5.054 |
Token | � |
Token ID | 247 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
ulf | +4.179 |
rer | +4.119 |
Mouth | +3.773 |
ê | +3.603 |
IPM | +3.592 |
Neg logit contributions | |
ilitarian | -4.736 |
>) | -4.361 |
xxxxxxxx | -4.055 |
romeda | -4.042 |
Eliot | -4.039 |
Token | s |
Token ID | 82 |
Feature activation | -1.71e+01 |
Pos logit contributions | |
ilitarian | +1.187 |
>) | +1.143 |
spot | +0.986 |
xxxxxxxx | +0.982 |
romeda | +0.960 |
Neg logit contributions | |
ulf | -1.950 |
rer | -1.912 |
Mouth | -1.807 |
IPM | -1.772 |
ê | -1.743 |
Token | inf |
Token ID | 1167 |
Feature activation | -2.38e+01 |
Pos logit contributions | |
ilitarian | +9.657 |
>) | +9.541 |
Revival | +9.205 |
borrow | +8.621 |
Burnett | +8.578 |
Neg logit contributions | |
ulf | -10.809 |
rer | -10.470 |
OTOS | -10.001 |
Mouth | -9.354 |
ê | -9.144 |
Token | low |
Token ID | 9319 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
ilitarian | +10.992 |
spot | +9.726 |
uration | +9.349 |
ozy | +9.025 |
>) | +8.995 |
Neg logit contributions | |
OTOS | -16.460 |
Mouth | -16.430 |
� | -16.360 |
エル | -15.771 |
ulf | -15.073 |
Token | , |
Token ID | 11 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
ilitarian | +0.459 |
>) | +0.441 |
xxxxxxxx | +0.395 |
spot | +0.391 |
romeda | +0.390 |
Neg logit contributions | |
ulf | -0.486 |
rer | -0.476 |
Mouth | -0.443 |
IPM | -0.429 |
ê | -0.425 |
Token | limit |
Token ID | 4179 |
Feature activation | -6.65e+00 |
Pos logit contributions | |
ilitarian | +7.192 |
>) | +6.966 |
spot | +6.323 |
Revival | +6.296 |
weighed | +6.276 |
Neg logit contributions | |
ulf | -7.656 |
rer | -7.497 |
OTOS | -7.081 |
Mouth | -6.987 |
� | -6.724 |
Token | additional |
Token ID | 3224 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
ilitarian | +4.033 |
>) | +3.916 |
spot | +3.490 |
Revival | +3.444 |
weighed | +3.440 |
Neg logit contributions | |
ulf | -4.899 |
rer | -4.774 |
Mouth | -4.441 |
ê | -4.318 |
IPM | -4.306 |
Token | surface |
Token ID | 4417 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
ilitarian | +4.198 |
>) | +4.084 |
weighed | +3.625 |
spot | +3.614 |
romeda | +3.605 |
Neg logit contributions | |
ulf | -4.802 |
rer | -4.655 |
Mouth | -4.323 |
ê | -4.215 |
IPM | -4.200 |
Token | 7 |
Token ID | 22 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
ulf | +2.698 |
rer | +2.657 |
Mouth | +2.372 |
ê | +2.364 |
IPM | +2.260 |
Neg logit contributions | |
ilitarian | -3.253 |
>) | -3.088 |
romeda | -2.805 |
Eliot | -2.798 |
xxxxxxxx | -2.793 |
Token | { |
Token ID | 1391 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
ilitarian | +1.749 |
>) | +1.721 |
xxxxxxxx | +1.481 |
spot | +1.428 |
romeda | +1.394 |
Neg logit contributions | |
ulf | -3.257 |
rer | -3.204 |
Mouth | -2.989 |
IPM | -2.956 |
ê | -2.903 |
Token | ( |
Token ID | 7 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ilitarian | +1.855 |
>) | +1.832 |
xxxxxxxx | +1.685 |
spot | +1.657 |
romeda | +1.618 |
Neg logit contributions | |
ulf | -1.305 |
rer | -1.268 |
Mouth | -1.173 |
IPM | -1.130 |
ê | -1.102 |
Token | 150 |
Token ID | 8628 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
ulf | +0.911 |
rer | +0.893 |
Mouth | +0.822 |
IPM | +0.794 |
ê | +0.788 |
Neg logit contributions | |
ilitarian | -1.021 |
>) | -0.980 |
xxxxxxxx | -0.885 |
romeda | -0.883 |
spot | -0.877 |
Token | s |
Token ID | 82 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
ulf | +3.608 |
rer | +3.579 |
Mouth | +3.292 |
ê | +3.209 |
IPM | +3.206 |
Neg logit contributions | |
ilitarian | -2.896 |
>) | -2.663 |
romeda | -2.397 |
xxxxxxxx | -2.389 |
Eliot | -2.314 |
Token | )} |
Token ID | 38165 |
Feature activation | -2.27e+01 |
Pos logit contributions | |
ulf | +0.109 |
rer | +0.107 |
Mouth | +0.097 |
IPM | +0.093 |
ê | +0.092 |
Neg logit contributions | |
ilitarian | -0.161 |
>) | -0.156 |
xxxxxxxx | -0.143 |
romeda | -0.142 |
spot | -0.141 |
Token | 37 |
Token ID | 5214 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
>) | +7.802 |
xxxxxxxx | +6.592 |
ilitarian | +6.516 |
Revival | +6.376 |
spot | +6.303 |
Neg logit contributions | |
ulf | -18.323 |
rer | -17.955 |
Mouth | -17.074 |
stocks | -16.872 |
IPM | -16.477 |
Token | . |
Token ID | 13 |
Feature activation | -7.13e+00 |
Pos logit contributions | |
ilitarian | +1.845 |
>) | +1.801 |
xxxxxxxx | +1.618 |
spot | +1.584 |
romeda | +1.555 |
Neg logit contributions | |
ulf | -2.077 |
rer | -2.042 |
Mouth | -1.891 |
IPM | -1.850 |
ê | -1.820 |
Token | f |
Token ID | 277 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
>) | +4.395 |
ilitarian | +4.312 |
xxxxxxxx | +3.860 |
Revival | +3.776 |
Eliot | +3.776 |
Neg logit contributions | |
ulf | -5.189 |
rer | -5.112 |
Mouth | -4.649 |
ê | -4.573 |
エル | -4.559 |
Token | xe |
Token ID | 27705 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
ilitarian | +0.587 |
>) | +0.567 |
xxxxxxxx | +0.507 |
spot | +0.500 |
romeda | +0.498 |
Neg logit contributions | |
ulf | -0.625 |
rer | -0.613 |
Mouth | -0.573 |
IPM | -0.555 |
ê | -0.547 |
Token | 6 |
Token ID | 21 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
ilitarian | +0.539 |
>) | +0.522 |
xxxxxxxx | +0.470 |
spot | +0.464 |
romeda | +0.463 |
Neg logit contributions | |
ulf | -0.497 |
rer | -0.487 |
Mouth | -0.450 |
IPM | -0.436 |
ê | -0.430 |
Token | size |
Token ID | 2546 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
ulf | +3.791 |
rer | +3.776 |
Mouth | +3.544 |
IPM | +3.366 |
ê | +3.342 |
Neg logit contributions | |
ilitarian | -4.128 |
>) | -4.028 |
xxxxxxxx | -3.638 |
romeda | -3.589 |
Eliot | -3.548 |
Token | makes |
Token ID | 1838 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
ulf | +1.328 |
rer | +1.303 |
Mouth | +1.199 |
IPM | +1.152 |
ê | +1.150 |
Neg logit contributions | |
ilitarian | -1.494 |
>) | -1.445 |
xxxxxxxx | -1.303 |
romeda | -1.302 |
spot | -1.284 |
Token | a |
Token ID | 257 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ulf | +3.539 |
rer | +3.451 |
Mouth | +3.229 |
IPM | +3.079 |
ê | +3.006 |
Neg logit contributions | |
ilitarian | -4.038 |
>) | -3.889 |
xxxxxxxx | -3.552 |
romeda | -3.478 |
spot | -3.424 |
Token | traditional |
Token ID | 4569 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ulf | +1.080 |
rer | +1.063 |
Mouth | +0.989 |
IPM | +0.948 |
ê | +0.939 |
Neg logit contributions | |
ilitarian | -1.107 |
>) | -1.069 |
xxxxxxxx | -0.964 |
romeda | -0.953 |
spot | -0.946 |
Token | hi |
Token ID | 23105 |
Feature activation | -7.92e+00 |
Pos logit contributions | |
ilitarian | +1.017 |
>) | +0.979 |
xxxxxxxx | +0.878 |
spot | +0.871 |
romeda | +0.870 |
Neg logit contributions | |
ulf | -0.998 |
rer | -0.974 |
Mouth | -0.898 |
IPM | -0.869 |
ê | -0.867 |
Token | - |
Token ID | 12 |
Feature activation | -2.27e+01 |
Pos logit contributions | |
ilitarian | +4.795 |
>) | +4.749 |
xxxxxxxx | +4.236 |
spot | +4.196 |
romeda | +4.095 |
Neg logit contributions | |
ulf | -5.828 |
rer | -5.692 |
Mouth | -5.352 |
� | -5.183 |
IPM | -5.173 |
Token | fi |
Token ID | 12463 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
ilitarian | +11.355 |
spot | +11.205 |
>) | +10.521 |
xxxxxxxx | +9.470 |
hang | +9.469 |
Neg logit contributions | |
ulf | -14.380 |
Mouth | -13.776 |
rer | -13.396 |
IPM | -13.346 |
エル | -13.197 |
Token | system |
Token ID | 1080 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
ilitarian | +2.468 |
>) | +2.371 |
xxxxxxxx | +2.133 |
spot | +2.121 |
romeda | +2.106 |
Neg logit contributions | |
ulf | -2.480 |
rer | -2.371 |
Mouth | -2.204 |
IPM | -2.142 |
ê | -2.127 |
Token | , |
Token ID | 11 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
ulf | +1.455 |
rer | +1.434 |
Mouth | +1.318 |
IPM | +1.275 |
ê | +1.274 |
Neg logit contributions | |
ilitarian | -1.560 |
>) | -1.512 |
xxxxxxxx | -1.365 |
romeda | -1.344 |
spot | -1.328 |
Token | with |
Token ID | 351 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
ulf | +1.801 |
rer | +1.778 |
Mouth | +1.651 |
IPM | +1.612 |
ê | +1.581 |
Neg logit contributions | |
ilitarian | -1.947 |
>) | -1.895 |
xxxxxxxx | -1.706 |
romeda | -1.674 |
spot | -1.670 |
Token | its |
Token ID | 663 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ilitarian | +1.854 |
>) | +1.786 |
xxxxxxxx | +1.587 |
spot | +1.578 |
romeda | +1.578 |
Neg logit contributions | |
ulf | -2.070 |
rer | -2.009 |
Mouth | -1.852 |
ê | -1.806 |
IPM | -1.794 |
Token | , |
Token ID | 11 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
ilitarian | +3.026 |
>) | +2.910 |
spot | +2.611 |
xxxxxxxx | +2.604 |
romeda | +2.604 |
Neg logit contributions | |
ulf | -3.059 |
rer | -2.938 |
Mouth | -2.696 |
IPM | -2.635 |
ê | -2.603 |
Token | w |
Token ID | 266 |
Feature activation | +9.56e+00 |
Pos logit contributions | |
ilitarian | +2.724 |
>) | +2.601 |
spot | +2.344 |
xxxxxxxx | +2.334 |
romeda | +2.318 |
Neg logit contributions | |
ulf | -2.875 |
rer | -2.769 |
Mouth | -2.558 |
IPM | -2.480 |
ê | -2.468 |
Token | ann |
Token ID | 1236 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
ulf | +6.441 |
rer | +6.036 |
ê | +5.646 |
iner | +5.458 |
Mouth | +5.440 |
Neg logit contributions | |
ilitarian | -6.622 |
>) | -6.363 |
romeda | -6.066 |
Revival | -5.800 |
xxxxxxxx | -5.770 |
Token | abe |
Token ID | 11231 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ulf | +0.421 |
rer | +0.414 |
Mouth | +0.389 |
IPM | +0.380 |
ê | +0.378 |
Neg logit contributions | |
ilitarian | -0.238 |
>) | -0.227 |
xxxxxxxx | -0.195 |
romeda | -0.191 |
spot | -0.190 |
Token | hi |
Token ID | 23105 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
ilitarian | +1.017 |
>) | +0.978 |
xxxxxxxx | +0.879 |
spot | +0.871 |
romeda | +0.871 |
Neg logit contributions | |
ulf | -1.000 |
rer | -0.975 |
Mouth | -0.902 |
IPM | -0.875 |
ê | -0.867 |
Token | - |
Token ID | 12 |
Feature activation | -2.24e+01 |
Pos logit contributions | |
ilitarian | +5.955 |
>) | +5.920 |
spot | +5.273 |
xxxxxxxx | +5.149 |
Revival | +5.060 |
Neg logit contributions | |
ulf | -7.558 |
rer | -7.422 |
Mouth | -6.933 |
IPM | -6.832 |
OTOS | -6.671 |
Token | fi |
Token ID | 12463 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
spot | +11.896 |
ilitarian | +11.656 |
>) | +11.165 |
hang | +10.327 |
xxxxxxxx | +10.036 |
Neg logit contributions | |
ulf | -13.588 |
Mouth | -13.256 |
IPM | -13.017 |
rer | -12.777 |
� | -12.721 |
Token | pret |
Token ID | 2181 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ilitarian | +2.507 |
>) | +2.407 |
xxxxxxxx | +2.173 |
spot | +2.172 |
romeda | +2.163 |
Neg logit contributions | |
ulf | -2.424 |
rer | -2.326 |
Mouth | -2.157 |
IPM | -2.105 |
ê | -2.069 |
Token | ender |
Token ID | 2194 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
ilitarian | +1.213 |
>) | +1.172 |
xxxxxxxx | +1.064 |
spot | +1.054 |
romeda | +1.054 |
Neg logit contributions | |
ulf | -0.911 |
rer | -0.880 |
Mouth | -0.812 |
IPM | -0.788 |
ê | -0.763 |
Token | -- |
Token ID | 1377 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
ulf | +2.151 |
rer | +2.128 |
Mouth | +1.951 |
IPM | +1.881 |
ê | +1.877 |
Neg logit contributions | |
ilitarian | -2.364 |
>) | -2.314 |
xxxxxxxx | -2.066 |
romeda | -2.051 |
spot | -2.028 |
Token | an |
Token ID | 281 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
ilitarian | +2.343 |
>) | +2.249 |
spot | +2.008 |
xxxxxxxx | +2.006 |
romeda | +1.988 |
Neg logit contributions | |
ulf | -2.441 |
rer | -2.387 |
Mouth | -2.199 |
IPM | -2.143 |
ê | -2.120 |
Token | considered |
Token ID | 3177 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
ilitarian | +3.035 |
>) | +2.984 |
xxxxxxxx | +2.652 |
spot | +2.624 |
weighed | +2.593 |
Neg logit contributions | |
ulf | -3.467 |
rer | -3.433 |
Mouth | -3.190 |
IPM | -3.165 |
ê | -3.047 |
Token | the |
Token ID | 262 |
Feature activation | -9.47e+00 |
Pos logit contributions | |
ilitarian | +3.348 |
>) | +3.240 |
xxxxxxxx | +2.901 |
spot | +2.863 |
weighed | +2.824 |
Neg logit contributions | |
ulf | -3.549 |
rer | -3.493 |
Mouth | -3.231 |
IPM | -3.136 |
ê | -3.121 |
Token | best |
Token ID | 1266 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
ilitarian | +6.175 |
>) | +6.118 |
xxxxxxxx | +5.476 |
weighed | +5.370 |
spot | +5.359 |
Neg logit contributions | |
ulf | -6.381 |
rer | -6.253 |
ê | -5.679 |
Mouth | -5.656 |
IPM | -5.551 |
Token | spread |
Token ID | 4104 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
ilitarian | +7.134 |
>) | +7.126 |
spot | +6.442 |
weighed | +6.321 |
xxxxxxxx | +6.279 |
Neg logit contributions | |
ulf | -7.489 |
rer | -7.457 |
ê | -6.753 |
Mouth | -6.718 |
� | -6.637 |
Token | in |
Token ID | 287 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
ilitarian | +3.632 |
>) | +3.527 |
spot | +3.155 |
xxxxxxxx | +3.116 |
Eliot | +3.085 |
Neg logit contributions | |
ulf | -4.106 |
rer | -3.968 |
Mouth | -3.742 |
IPM | -3.669 |
ê | -3.644 |
Token | the |
Token ID | 262 |
Feature activation | -2.19e+01 |
Pos logit contributions | |
ilitarian | +2.277 |
>) | +2.218 |
xxxxxxxx | +1.984 |
spot | +1.959 |
Eliot | +1.947 |
Neg logit contributions | |
ulf | -2.127 |
rer | -2.097 |
Mouth | -1.920 |
ê | -1.866 |
IPM | -1.858 |
Token | International |
Token ID | 4037 |
Feature activation | -9.72e+00 |
Pos logit contributions | |
>) | +10.525 |
ilitarian | +10.262 |
majors | +10.008 |
Eliot | +9.580 |
Burnett | +9.229 |
Neg logit contributions | |
ulf | -14.152 |
rer | -13.989 |
ê | -13.559 |
� | -13.167 |
エル | -12.735 |
Token | League |
Token ID | 4041 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
>) | +4.740 |
ilitarian | +4.653 |
spot | +4.264 |
weighed | +4.103 |
xxxxxxxx | +3.999 |
Neg logit contributions | |
ulf | -8.046 |
rer | -7.926 |
Mouth | -7.330 |
IPM | -7.306 |
ê | -7.279 |
Token | , |
Token ID | 11 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ilitarian | +1.520 |
>) | +1.477 |
xxxxxxxx | +1.316 |
spot | +1.312 |
romeda | +1.295 |
Neg logit contributions | |
ulf | -1.611 |
rer | -1.570 |
Mouth | -1.461 |
IPM | -1.416 |
ê | -1.405 |
Token | on |
Token ID | 319 |
Feature activation | -9.89e+00 |
Pos logit contributions | |
ilitarian | +0.713 |
>) | +0.688 |
xxxxxxxx | +0.618 |
spot | +0.611 |
romeda | +0.609 |
Neg logit contributions | |
ulf | -0.720 |
rer | -0.705 |
Mouth | -0.651 |
IPM | -0.633 |
ê | -0.627 |
Token | this |
Token ID | 428 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
ilitarian | +6.120 |
>) | +5.818 |
spot | +5.355 |
xxxxxxxx | +5.312 |
Revival | +5.271 |
Neg logit contributions | |
ulf | -6.881 |
rer | -6.679 |
IPM | -6.279 |
Mouth | -6.238 |
ê | -6.111 |
Token | 4 |
Token ID | 19 |
Feature activation | -4.83e+00 |
Pos logit contributions | |
ilitarian | +0.107 |
>) | +0.103 |
xxxxxxxx | +0.093 |
romeda | +0.092 |
spot | +0.092 |
Neg logit contributions | |
ulf | -0.102 |
rer | -0.100 |
Mouth | -0.093 |
IPM | -0.090 |
ê | -0.089 |
Token | { |
Token ID | 1391 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
ilitarian | +2.317 |
>) | +2.310 |
xxxxxxxx | +2.010 |
spot | +1.928 |
romeda | +1.850 |
Neg logit contributions | |
ulf | -4.302 |
rer | -4.204 |
Mouth | -3.922 |
IPM | -3.902 |
� | -3.861 |
Token | ( |
Token ID | 7 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
>) | +3.200 |
ilitarian | +3.190 |
xxxxxxxx | +2.951 |
spot | +2.882 |
romeda | +2.758 |
Neg logit contributions | |
ulf | -2.471 |
rer | -2.399 |
Mouth | -2.254 |
IPM | -2.180 |
� | -2.128 |
Token | 99 |
Token ID | 2079 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
ilitarian | +0.426 |
>) | +0.412 |
xxxxxxxx | +0.371 |
spot | +0.367 |
romeda | +0.366 |
Neg logit contributions | |
ulf | -0.386 |
rer | -0.378 |
Mouth | -0.349 |
IPM | -0.337 |
ê | -0.334 |
Token | s |
Token ID | 82 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
ulf | +1.577 |
rer | +1.557 |
Mouth | +1.444 |
IPM | +1.403 |
ê | +1.396 |
Neg logit contributions | |
ilitarian | -1.324 |
>) | -1.261 |
xxxxxxxx | -1.128 |
romeda | -1.121 |
spot | -1.103 |
Token | )} |
Token ID | 38165 |
Feature activation | -2.17e+01 |
Pos logit contributions | |
ilitarian | +1.118 |
>) | +1.096 |
xxxxxxxx | +0.995 |
romeda | +0.980 |
spot | +0.979 |
Neg logit contributions | |
ulf | -0.813 |
rer | -0.791 |
Mouth | -0.727 |
IPM | -0.699 |
ê | -0.693 |
Token | 33 |
Token ID | 4747 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
>) | +8.958 |
ilitarian | +8.464 |
Eliot | +7.424 |
spot | +7.169 |
xxxxxxxx | +7.110 |
Neg logit contributions | |
ulf | -16.902 |
rer | -16.168 |
Mouth | -15.179 |
deserts | -15.083 |
azing | -14.852 |
Token | . |
Token ID | 13 |
Feature activation | -7.30e+00 |
Pos logit contributions | |
ilitarian | +1.172 |
>) | +1.139 |
xxxxxxxx | +1.023 |
spot | +1.004 |
romeda | +0.994 |
Neg logit contributions | |
ulf | -1.251 |
rer | -1.226 |
Mouth | -1.138 |
IPM | -1.110 |
ê | -1.093 |
Token | Q |
Token ID | 1195 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
>) | +4.467 |
ilitarian | +4.393 |
xxxxxxxx | +3.921 |
Eliot | +3.844 |
Revival | +3.837 |
Neg logit contributions | |
ulf | -5.333 |
rer | -5.249 |
Mouth | -4.766 |
ê | -4.692 |
エル | -4.676 |
Token | e |
Token ID | 68 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
ilitarian | +3.360 |
>) | +3.289 |
xxxxxxxx | +2.930 |
spot | +2.874 |
romeda | +2.756 |
Neg logit contributions | |
ulf | -4.466 |
rer | -4.369 |
Mouth | -4.257 |
IPM | -4.146 |
deserts | -4.000 |
Token | 2 |
Token ID | 17 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
ilitarian | +2.295 |
>) | +2.247 |
xxxxxxxx | +2.001 |
spot | +1.981 |
romeda | +1.942 |
Neg logit contributions | |
ulf | -2.321 |
rer | -2.277 |
Mouth | -2.142 |
IPM | -2.077 |
deserts | -1.999 |
Token | 21 |
Token ID | 2310 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
>) | +4.723 |
ilitarian | +4.723 |
xxxxxxxx | +4.148 |
spot | +4.003 |
AIN | +3.996 |
Neg logit contributions | |
ulf | -6.980 |
rer | -6.851 |
Mouth | -6.383 |
ê | -6.334 |
IPM | -6.270 |
Token | 22 |
Token ID | 2534 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
ilitarian | +2.270 |
>) | +2.202 |
spot | +1.898 |
romeda | +1.893 |
xxxxxxxx | +1.893 |
Neg logit contributions | |
ulf | -2.985 |
rer | -2.895 |
Mouth | -2.714 |
IPM | -2.650 |
ê | -2.639 |
Token | 23 |
Token ID | 2242 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
ilitarian | +5.680 |
>) | +5.662 |
xxxxxxxx | +4.878 |
spot | +4.863 |
Revival | +4.824 |
Neg logit contributions | |
ulf | -9.067 |
rer | -8.479 |
Mouth | -8.037 |
IPM | -7.901 |
エル | -7.899 |
Token | 24 |
Token ID | 1987 |
Feature activation | -7.08e+00 |
Pos logit contributions | |
ulf | +0.954 |
rer | +0.943 |
Mouth | +0.864 |
IPM | +0.831 |
ê | +0.815 |
Neg logit contributions | |
ilitarian | -1.247 |
>) | -1.201 |
xxxxxxxx | -1.096 |
romeda | -1.087 |
spot | -1.080 |
Token | 25 |
Token ID | 1679 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
ilitarian | +4.412 |
>) | +4.376 |
spot | +3.907 |
weighed | +3.872 |
romeda | +3.854 |
Neg logit contributions | |
ulf | -5.154 |
rer | -4.935 |
Mouth | -4.681 |
ê | -4.587 |
エル | -4.509 |
Token | 26 |
Token ID | 2608 |
Feature activation | -2.15e+01 |
Pos logit contributions | |
ulf | +1.424 |
rer | +1.386 |
Mouth | +1.279 |
IPM | +1.232 |
ê | +1.189 |
Neg logit contributions | |
ilitarian | -1.857 |
>) | -1.778 |
xxxxxxxx | -1.627 |
romeda | -1.607 |
spot | -1.600 |
Token | 27 |
Token ID | 2681 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
>) | +7.462 |
ilitarian | +6.433 |
Scan | +6.415 |
weighed | +6.268 |
borrow | +6.216 |
Neg logit contributions | |
ulf | -17.352 |
rer | -16.839 |
ê | -16.338 |
Mouth | -16.166 |
� | -15.929 |
Token | # |
Token ID | 1303 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
ilitarian | +2.456 |
>) | +2.408 |
spot | +2.125 |
xxxxxxxx | +2.098 |
romeda | +2.096 |
Neg logit contributions | |
ulf | -2.660 |
rer | -2.620 |
Mouth | -2.399 |
ê | -2.358 |
IPM | -2.353 |
Token | loop |
Token ID | 9052 |
Feature activation | -8.01e+00 |
Pos logit contributions | |
ilitarian | +2.525 |
>) | +2.474 |
xxxxxxxx | +2.204 |
spot | +2.184 |
romeda | +2.126 |
Neg logit contributions | |
ulf | -3.153 |
rer | -3.089 |
Mouth | -2.862 |
ê | -2.792 |
IPM | -2.777 |
Token | over |
Token ID | 625 |
Feature activation | -9.36e+00 |
Pos logit contributions | |
ilitarian | +3.904 |
>) | +3.891 |
xxxxxxxx | +3.453 |
spot | +3.324 |
Eliot | +3.231 |
Neg logit contributions | |
ulf | -6.626 |
rer | -6.457 |
Mouth | -6.125 |
IPM | -6.023 |
ê | -5.994 |
Token | the |
Token ID | 262 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
ilitarian | +5.118 |
>) | +4.919 |
xxxxxxxx | +4.435 |
spot | +4.298 |
Eliot | +4.292 |
Neg logit contributions | |
ulf | -7.183 |
rer | -7.024 |
Mouth | -6.527 |
ê | -6.388 |
IPM | -6.303 |
Token | bona |
Token ID | 41602 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
ilitarian | +3.694 |
>) | +3.537 |
spot | +3.211 |
xxxxxxxx | +3.175 |
romeda | +3.161 |
Neg logit contributions | |
ulf | -3.969 |
rer | -3.917 |
Mouth | -3.612 |
ê | -3.472 |
IPM | -3.470 |
Token | - |
Token ID | 12 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
ulf | +1.632 |
rer | +1.573 |
Mouth | +1.447 |
ê | +1.386 |
IPM | +1.361 |
Neg logit contributions | |
ilitarian | -2.474 |
>) | -2.374 |
romeda | -2.170 |
xxxxxxxx | -2.164 |
spot | -2.157 |
Token | f |
Token ID | 69 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
ulf | +1.576 |
rer | +1.535 |
Mouth | +1.396 |
ê | +1.361 |
IPM | +1.323 |
Neg logit contributions | |
ilitarian | -1.879 |
>) | -1.834 |
romeda | -1.634 |
xxxxxxxx | -1.634 |
Eliot | -1.606 |
Token | ide |
Token ID | 485 |
Feature activation | -8.03e+00 |
Pos logit contributions | |
ulf | +2.082 |
rer | +1.958 |
ê | +1.695 |
Mouth | +1.557 |
iner | +1.530 |
Neg logit contributions | |
ilitarian | -4.629 |
>) | -4.568 |
romeda | -4.205 |
Revival | -4.180 |
Eliot | -4.175 |
Token | hi |
Token ID | 23105 |
Feature activation | -6.80e+00 |
Pos logit contributions | |
ilitarian | +5.525 |
>) | +5.319 |
spot | +4.906 |
Revival | +4.884 |
xxxxxxxx | +4.859 |
Neg logit contributions | |
ulf | -5.244 |
rer | -5.111 |
Mouth | -4.685 |
ê | -4.485 |
IPM | -4.453 |
Token | - |
Token ID | 12 |
Feature activation | -2.14e+01 |
Pos logit contributions | |
ilitarian | +4.262 |
>) | +4.158 |
xxxxxxxx | +3.751 |
spot | +3.678 |
romeda | +3.632 |
Neg logit contributions | |
ulf | -4.932 |
rer | -4.864 |
Mouth | -4.548 |
IPM | -4.413 |
� | -4.344 |
Token | fi |
Token ID | 12463 |
Feature activation | -7.39e+00 |
Pos logit contributions | |
ilitarian | +11.020 |
spot | +10.796 |
>) | +10.200 |
xxxxxxxx | +9.537 |
hang | +9.115 |
Neg logit contributions | |
ulf | -13.600 |
Mouth | -13.255 |
IPM | -12.978 |
rer | -12.960 |
エル | -12.752 |
Token | sound |
Token ID | 2128 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
ilitarian | +5.043 |
>) | +4.810 |
spot | +4.451 |
xxxxxxxx | +4.450 |
Revival | +4.390 |
Neg logit contributions | |
ulf | -4.938 |
rer | -4.767 |
Mouth | -4.439 |
IPM | -4.266 |
エル | -4.228 |
Token | . |
Token ID | 13 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
ilitarian | +1.505 |
>) | +1.441 |
spot | +1.307 |
xxxxxxxx | +1.305 |
romeda | +1.291 |
Neg logit contributions | |
ulf | -1.436 |
rer | -1.405 |
Mouth | -1.306 |
IPM | -1.273 |
ê | -1.249 |
Token |
|
Token ID | 198 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
ulf | +0.667 |
rer | +0.655 |
Mouth | +0.611 |
IPM | +0.588 |
ê | +0.581 |
Neg logit contributions | |
ilitarian | -0.689 |
>) | -0.662 |
xxxxxxxx | -0.594 |
romeda | -0.590 |
spot | -0.586 |
Token |
|
Token ID | 198 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
ulf | +0.426 |
rer | +0.418 |
Mouth | +0.386 |
IPM | +0.375 |
ê | +0.371 |
Neg logit contributions | |
ilitarian | -0.425 |
>) | -0.407 |
xxxxxxxx | -0.364 |
romeda | -0.364 |
spot | -0.360 |
Token | lied |
Token ID | 19837 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
ilitarian | +5.562 |
>) | +5.413 |
weighed | +5.141 |
spot | +4.945 |
xxxxxxxx | +4.912 |
Neg logit contributions | |
ulf | -6.910 |
Mouth | -6.572 |
rer | -6.525 |
OTOS | -6.427 |
� | -6.238 |
Token | about |
Token ID | 546 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
ilitarian | +2.785 |
>) | +2.654 |
xxxxxxxx | +2.396 |
spot | +2.375 |
weighed | +2.348 |
Neg logit contributions | |
ulf | -3.314 |
rer | -3.175 |
Mouth | -3.046 |
IPM | -2.961 |
ê | -2.958 |
Token | my |
Token ID | 616 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
ilitarian | +1.243 |
>) | +1.193 |
xxxxxxxx | +1.071 |
spot | +1.059 |
romeda | +1.055 |
Neg logit contributions | |
ulf | -1.277 |
rer | -1.247 |
Mouth | -1.157 |
ê | -1.124 |
IPM | -1.120 |
Token | age |
Token ID | 2479 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
ulf | +2.443 |
rer | +2.432 |
Mouth | +2.232 |
IPM | +2.152 |
deserts | +2.135 |
Neg logit contributions | |
ilitarian | -2.860 |
>) | -2.746 |
xxxxxxxx | -2.479 |
romeda | -2.473 |
spot | -2.442 |
Token | and |
Token ID | 290 |
Feature activation | -7.16e+00 |
Pos logit contributions | |
ulf | +2.221 |
rer | +2.190 |
Mouth | +2.002 |
IPM | +1.916 |
ê | +1.905 |
Neg logit contributions | |
ilitarian | -2.532 |
>) | -2.461 |
romeda | -2.211 |
xxxxxxxx | -2.186 |
spot | -2.161 |
Token | got |
Token ID | 1392 |
Feature activation | -2.08e+01 |
Pos logit contributions | |
ilitarian | +4.334 |
>) | +4.193 |
weighed | +3.975 |
romeda | +3.794 |
xxxxxxxx | +3.784 |
Neg logit contributions | |
ulf | -5.289 |
rer | -5.056 |
Mouth | -4.718 |
ê | -4.701 |
IPM | -4.642 |
Token | jobs |
Token ID | 3946 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
weighed | +10.267 |
ilitarian | +9.717 |
>) | +9.599 |
borrow | +9.432 |
spot | +8.938 |
Neg logit contributions | |
ulf | -13.370 |
rer | -12.989 |
� | -12.739 |
Mouth | -12.554 |
ê | -12.436 |
Token | in |
Token ID | 287 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
ulf | +1.576 |
rer | +1.549 |
Mouth | +1.414 |
IPM | +1.367 |
ê | +1.356 |
Neg logit contributions | |
ilitarian | -1.654 |
>) | -1.599 |
xxxxxxxx | -1.431 |
romeda | -1.422 |
spot | -1.402 |
Token | a |
Token ID | 257 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
ulf | +2.836 |
rer | +2.805 |
Mouth | +2.624 |
IPM | +2.537 |
deserts | +2.492 |
Neg logit contributions | |
ilitarian | -3.073 |
>) | -2.937 |
romeda | -2.672 |
xxxxxxxx | -2.652 |
spot | -2.593 |
Token | salon |
Token ID | 46608 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
ilitarian | +1.142 |
>) | +1.102 |
xxxxxxxx | +0.989 |
spot | +0.979 |
romeda | +0.972 |
Neg logit contributions | |
ulf | -1.138 |
rer | -1.109 |
Mouth | -1.024 |
IPM | -0.996 |
ê | -0.993 |
Token | and |
Token ID | 290 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
ilitarian | +1.241 |
>) | +1.187 |
xxxxxxxx | +1.069 |
spot | +1.066 |
romeda | +1.052 |
Neg logit contributions | |
ulf | -1.284 |
rer | -1.250 |
Mouth | -1.164 |
IPM | -1.132 |
ê | -1.119 |
Token | number |
Token ID | 1271 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ilitarian | +5.606 |
>) | +5.430 |
spot | +4.865 |
Eliot | +4.844 |
Revival | +4.736 |
Neg logit contributions | |
ulf | -7.463 |
rer | -7.156 |
Mouth | -6.573 |
ê | -6.538 |
IPM | -6.510 |
Token | of |
Token ID | 286 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
ulf | +1.188 |
rer | +1.167 |
Mouth | +1.071 |
ê | +1.033 |
IPM | +1.030 |
Neg logit contributions | |
ilitarian | -1.278 |
>) | -1.232 |
xxxxxxxx | -1.106 |
romeda | -1.099 |
spot | -1.087 |
Token | people |
Token ID | 661 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ilitarian | +2.260 |
>) | +2.173 |
xxxxxxxx | +1.913 |
spot | +1.911 |
romeda | +1.907 |
Neg logit contributions | |
ulf | -2.863 |
rer | -2.791 |
Mouth | -2.594 |
IPM | -2.538 |
ê | -2.501 |
Token | travelling |
Token ID | 16574 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
ilitarian | +1.026 |
>) | +0.993 |
xxxxxxxx | +0.878 |
spot | +0.874 |
romeda | +0.874 |
Neg logit contributions | |
ulf | -1.166 |
rer | -1.140 |
Mouth | -1.065 |
IPM | -1.037 |
ê | -1.022 |
Token | off |
Token ID | 572 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
ilitarian | +2.404 |
>) | +2.341 |
xxxxxxxx | +2.065 |
weighed | +2.057 |
spot | +2.055 |
Neg logit contributions | |
ulf | -2.765 |
rer | -2.682 |
Mouth | -2.496 |
IPM | -2.424 |
ê | -2.406 |
Token | - |
Token ID | 12 |
Feature activation | -2.05e+01 |
Pos logit contributions | |
ilitarian | +5.886 |
>) | +5.680 |
weighed | +5.166 |
spot | +5.160 |
Eliot | +4.988 |
Neg logit contributions | |
ulf | -7.647 |
rer | -7.465 |
Mouth | -7.170 |
OTOS | -7.090 |
IPM | -7.070 |
Token | peak |
Token ID | 36729 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
peak | +10.019 |
spot | +9.962 |
ilitarian | +9.763 |
>) | +9.576 |
weighed | +8.676 |
Neg logit contributions | |
OTOS | -12.898 |
ulf | -12.878 |
Mouth | -12.859 |
IPM | -12.767 |
mosquit | -12.685 |
Token | has |
Token ID | 468 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ilitarian | +2.916 |
>) | +2.837 |
weighed | +2.561 |
spot | +2.518 |
xxxxxxxx | +2.503 |
Neg logit contributions | |
ulf | -3.442 |
rer | -3.331 |
Mouth | -3.139 |
IPM | -3.060 |
ê | -2.992 |
Token | almost |
Token ID | 2048 |
Feature activation | +6.45e+00 |
Pos logit contributions | |
ulf | +1.043 |
rer | +1.029 |
Mouth | +0.939 |
IPM | +0.914 |
ê | +0.899 |
Neg logit contributions | |
ilitarian | -1.273 |
>) | -1.222 |
xxxxxxxx | -1.114 |
romeda | -1.100 |
spot | -1.089 |
Token | doubled |
Token ID | 15229 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
rer | +3.890 |
ulf | +3.849 |
Mouth | +3.451 |
IPM | +3.407 |
ê | +3.379 |
Neg logit contributions | |
ilitarian | -5.006 |
>) | -4.761 |
romeda | -4.324 |
xxxxxxxx | -4.297 |
ozy | -4.175 |
Token | , |
Token ID | 11 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
ulf | +0.310 |
rer | +0.305 |
Mouth | +0.282 |
IPM | +0.273 |
ê | +0.271 |
Neg logit contributions | |
ilitarian | -0.317 |
>) | -0.306 |
xxxxxxxx | -0.274 |
romeda | -0.272 |
spot | -0.271 |
Token | the |
Token ID | 262 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
ilitarian | +3.737 |
>) | +3.620 |
Eliot | +3.213 |
xxxxxxxx | +3.201 |
romeda | +3.178 |
Neg logit contributions | |
ulf | -4.372 |
rer | -4.251 |
Mouth | -3.950 |
ê | -3.831 |
IPM | -3.829 |
Token | Spending |
Token ID | 43902 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
ilitarian | +3.573 |
>) | +3.445 |
xxxxxxxx | +3.075 |
Revival | +3.057 |
Eliot | +3.054 |
Neg logit contributions | |
ulf | -3.503 |
rer | -3.425 |
Mouth | -3.096 |
ê | -3.069 |
IPM | -3.009 |
Token | C |
Token ID | 327 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
ilitarian | +0.455 |
>) | +0.438 |
xxxxxxxx | +0.394 |
romeda | +0.389 |
spot | +0.389 |
Neg logit contributions | |
ulf | -0.440 |
rer | -0.432 |
Mouth | -0.399 |
IPM | -0.386 |
ê | -0.382 |
Token | uts |
Token ID | 5500 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
ilitarian | +2.759 |
>) | +2.656 |
xxxxxxxx | +2.379 |
spot | +2.368 |
Eliot | +2.322 |
Neg logit contributions | |
ulf | -2.526 |
rer | -2.488 |
Mouth | -2.335 |
IPM | -2.242 |
ê | -2.206 |
Token | and |
Token ID | 290 |
Feature activation | -6.60e+00 |
Pos logit contributions | |
ilitarian | +2.786 |
>) | +2.657 |
xxxxxxxx | +2.408 |
romeda | +2.368 |
spot | +2.359 |
Neg logit contributions | |
ulf | -2.863 |
rer | -2.800 |
Mouth | -2.601 |
IPM | -2.520 |
ê | -2.483 |
Token | Def |
Token ID | 2896 |
Feature activation | -2.04e+01 |
Pos logit contributions | |
ilitarian | +2.750 |
>) | +2.712 |
romeda | +2.232 |
xxxxxxxx | +2.227 |
Revival | +2.168 |
Neg logit contributions | |
ulf | -6.212 |
rer | -6.152 |
Mouth | -5.723 |
IPM | -5.713 |
エル | -5.629 |
Token | icit |
Token ID | 3628 |
Feature activation | -8.09e+00 |
Pos logit contributions | |
ilitarian | +9.491 |
eas | +8.309 |
>) | +8.306 |
ozy | +7.862 |
uration | +7.509 |
Neg logit contributions | |
エル | -15.157 |
IPM | -14.736 |
Mouth | -14.418 |
� | -14.241 |
embassy | -13.740 |
Token | Reduction |
Token ID | 33396 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
ilitarian | +5.104 |
>) | +4.813 |
Revival | +4.518 |
Eliot | +4.388 |
xxxxxxxx | +4.320 |
Neg logit contributions | |
ulf | -5.797 |
rer | -5.665 |
エル | -5.320 |
� | -5.183 |
Mouth | -5.177 |
Token | Working |
Token ID | 14594 |
Feature activation | +7.56e+00 |
Pos logit contributions | |
ilitarian | +2.756 |
>) | +2.635 |
xxxxxxxx | +2.363 |
Revival | +2.322 |
spot | +2.317 |
Neg logit contributions | |
ulf | -3.004 |
rer | -2.950 |
Mouth | -2.724 |
IPM | -2.655 |
ê | -2.639 |
Token | Group |
Token ID | 4912 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
ulf | +4.209 |
rer | +4.118 |
Mouth | +3.886 |
IPM | +3.721 |
ê | +3.621 |
Neg logit contributions | |
ilitarian | -6.230 |
>) | -5.888 |
romeda | -5.494 |
spot | -5.429 |
xxxxxxxx | -5.284 |
Token | . |
Token ID | 13 |
Feature activation | -5.24e+00 |
Pos logit contributions | |
ilitarian | +2.981 |
>) | +2.864 |
xxxxxxxx | +2.560 |
spot | +2.538 |
romeda | +2.512 |
Neg logit contributions | |
ulf | -3.316 |
rer | -3.265 |
Mouth | -3.053 |
IPM | -2.945 |
ê | -2.921 |
Token | shift |
Token ID | 6482 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
ilitarian | +4.139 |
>) | +4.016 |
Revival | +3.616 |
Eliot | +3.608 |
xxxxxxxx | +3.584 |
Neg logit contributions | |
ulf | -4.193 |
rer | -4.121 |
Mouth | -3.809 |
IPM | -3.667 |
ê | -3.662 |
Token | toward |
Token ID | 3812 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
ulf | +2.167 |
rer | +2.141 |
Mouth | +1.922 |
IPM | +1.869 |
ê | +1.866 |
Neg logit contributions | |
ilitarian | -2.337 |
>) | -2.259 |
xxxxxxxx | -2.027 |
romeda | -2.012 |
spot | -1.987 |
Token | progressive |
Token ID | 10393 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
ilitarian | +1.608 |
>) | +1.536 |
xxxxxxxx | +1.368 |
romeda | +1.363 |
spot | +1.352 |
Neg logit contributions | |
ulf | -1.765 |
rer | -1.730 |
Mouth | -1.618 |
IPM | -1.560 |
ê | -1.543 |
Token | policies |
Token ID | 4788 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
ilitarian | +6.588 |
>) | +6.213 |
Revival | +5.797 |
borrow | +5.748 |
weighed | +5.715 |
Neg logit contributions | |
ulf | -7.885 |
rer | -7.642 |
Mouth | -7.452 |
OTOS | -7.160 |
エル | -7.026 |
Token | and |
Token ID | 290 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
ilitarian | +1.241 |
>) | +1.196 |
xxxxxxxx | +1.067 |
spot | +1.063 |
romeda | +1.057 |
Neg logit contributions | |
ulf | -1.305 |
rer | -1.277 |
Mouth | -1.194 |
IPM | -1.156 |
ê | -1.141 |
Token | generous |
Token ID | 14431 |
Feature activation | -2.04e+01 |
Pos logit contributions | |
ilitarian | +3.230 |
>) | +3.112 |
romeda | +2.813 |
weighed | +2.765 |
xxxxxxxx | +2.759 |
Neg logit contributions | |
ulf | -3.547 |
rer | -3.429 |
Mouth | -3.248 |
IPM | -3.098 |
ê | -3.041 |
Token | social |
Token ID | 1919 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
borrow | +9.951 |
ilitarian | +9.683 |
>) | +9.459 |
Revival | +8.865 |
weighed | +8.722 |
Neg logit contributions | |
ulf | -13.381 |
rer | -13.113 |
エル | -12.752 |
Mouth | -12.537 |
� | -12.457 |
Token | spending |
Token ID | 4581 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
ilitarian | +2.248 |
>) | +2.171 |
xxxxxxxx | +1.911 |
romeda | +1.906 |
spot | +1.893 |
Neg logit contributions | |
ulf | -2.745 |
rer | -2.715 |
Mouth | -2.546 |
IPM | -2.454 |
ê | -2.385 |
Token | was |
Token ID | 373 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
ilitarian | +2.122 |
>) | +2.044 |
romeda | +1.818 |
weighed | +1.817 |
xxxxxxxx | +1.811 |
Neg logit contributions | |
ulf | -2.205 |
rer | -2.161 |
Mouth | -2.027 |
IPM | -1.964 |
ê | -1.922 |
Token | soon |
Token ID | 2582 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
ulf | +0.153 |
rer | +0.150 |
Mouth | +0.139 |
IPM | +0.135 |
ê | +0.134 |
Neg logit contributions | |
ilitarian | -0.150 |
>) | -0.145 |
xxxxxxxx | -0.130 |
romeda | -0.128 |
spot | -0.128 |
Token | followed |
Token ID | 3940 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
ulf | +1.743 |
rer | +1.705 |
Mouth | +1.561 |
ê | +1.514 |
IPM | +1.501 |
Neg logit contributions | |
ilitarian | -1.837 |
>) | -1.773 |
xxxxxxxx | -1.589 |
romeda | -1.566 |
spot | -1.546 |
Token | - |
Token ID | 12 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
ulf | +2.598 |
rer | +2.579 |
Mouth | +2.310 |
ê | +2.206 |
IPM | +2.183 |
Neg logit contributions | |
ilitarian | -3.306 |
>) | -3.187 |
xxxxxxxx | -2.898 |
spot | -2.847 |
romeda | -2.842 |
Token | Ali |
Token ID | 37893 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ulf | +1.220 |
rer | +1.202 |
Mouth | +1.061 |
ê | +1.014 |
IPM | +1.014 |
Neg logit contributions | |
ilitarian | -1.934 |
>) | -1.857 |
xxxxxxxx | -1.691 |
romeda | -1.687 |
spot | -1.679 |
Token | , |
Token ID | 11 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
ulf | +0.783 |
rer | +0.768 |
Mouth | +0.702 |
IPM | +0.676 |
ê | +0.673 |
Neg logit contributions | |
ilitarian | -0.918 |
>) | -0.887 |
xxxxxxxx | -0.804 |
romeda | -0.796 |
spot | -0.789 |
Token | who |
Token ID | 508 |
Feature activation | +6.92e+00 |
Pos logit contributions | |
rer | +3.655 |
ulf | +3.649 |
Mouth | +3.368 |
IPM | +3.209 |
ê | +3.167 |
Neg logit contributions | |
ilitarian | -3.827 |
>) | -3.690 |
xxxxxxxx | -3.337 |
romeda | -3.310 |
spot | -3.290 |
Token | holds |
Token ID | 6622 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
rer | +4.502 |
ulf | +4.374 |
Mouth | +3.992 |
deserts | +3.904 |
IPM | +3.852 |
Neg logit contributions | |
ilitarian | -5.024 |
>) | -4.821 |
xxxxxxxx | -4.359 |
romeda | -4.352 |
spot | -4.241 |
Token | dual |
Token ID | 10668 |
Feature activation | -2.04e+01 |
Pos logit contributions | |
ilitarian | +7.558 |
>) | +7.297 |
Eliot | +6.695 |
Revival | +6.609 |
spot | +6.490 |
Neg logit contributions | |
ulf | -10.830 |
rer | -10.589 |
OTOS | -10.107 |
ê | -9.796 |
Mouth | -9.730 |
Token | British |
Token ID | 3517 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
>) | +10.575 |
ilitarian | +10.246 |
Revival | +9.839 |
Bu | +9.413 |
Suzuki | +9.359 |
Neg logit contributions | |
ulf | -12.984 |
rer | -12.524 |
OTOS | -11.894 |
ê | -11.440 |
Mouth | -11.297 |
Token | and |
Token ID | 290 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
ilitarian | +2.851 |
>) | +2.786 |
xxxxxxxx | +2.533 |
spot | +2.485 |
Revival | +2.482 |
Neg logit contributions | |
ulf | -2.863 |
rer | -2.799 |
Mouth | -2.604 |
IPM | -2.529 |
ê | -2.499 |
Token | Pakistani |
Token ID | 17807 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
ilitarian | +1.718 |
>) | +1.654 |
xxxxxxxx | +1.482 |
romeda | +1.468 |
spot | +1.457 |
Neg logit contributions | |
ulf | -1.830 |
rer | -1.803 |
Mouth | -1.664 |
IPM | -1.622 |
ê | -1.606 |
Token | citizenship |
Token ID | 14218 |
Feature activation | +5.45e+00 |
Pos logit contributions | |
ilitarian | +4.417 |
>) | +4.395 |
xxxxxxxx | +3.998 |
Revival | +3.995 |
romeda | +3.944 |
Neg logit contributions | |
ulf | -3.573 |
rer | -3.481 |
Mouth | -3.222 |
IPM | -3.095 |
ê | -3.065 |
Token | , |
Token ID | 11 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
ulf | +3.399 |
rer | +3.391 |
Mouth | +3.031 |
ê | +2.934 |
IPM | +2.910 |
Neg logit contributions | |
ilitarian | -4.133 |
>) | -4.002 |
romeda | -3.613 |
xxxxxxxx | -3.569 |
spot | -3.468 |
Token | extreme |
Token ID | 3257 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
ilitarian | +7.720 |
>) | +7.629 |
Revival | +6.873 |
xxxxxxxx | +6.865 |
Eliot | +6.808 |
Neg logit contributions | |
ulf | -7.948 |
rer | -7.649 |
ê | -6.892 |
Mouth | -6.872 |
IPM | -6.684 |
Token | compression |
Token ID | 19794 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
ilitarian | +7.364 |
>) | +7.240 |
Revival | +6.501 |
Eliot | +6.411 |
weighed | +6.403 |
Neg logit contributions | |
ulf | -7.197 |
rer | -6.980 |
Mouth | -6.553 |
ê | -6.399 |
IPM | -6.342 |
Token | of |
Token ID | 286 |
Feature activation | -9.91e+00 |
Pos logit contributions | |
ilitarian | +6.740 |
>) | +6.484 |
weighed | +6.016 |
Revival | +5.775 |
Eliot | +5.762 |
Neg logit contributions | |
ulf | -6.861 |
rer | -6.477 |
Mouth | -6.182 |
IPM | -5.932 |
ê | -5.908 |
Token | the |
Token ID | 262 |
Feature activation | -9.38e+00 |
Pos logit contributions | |
ilitarian | +6.027 |
>) | +5.904 |
Revival | +5.268 |
xxxxxxxx | +5.266 |
Eliot | +5.264 |
Neg logit contributions | |
ulf | -7.058 |
rer | -6.869 |
Mouth | -6.175 |
ê | -6.140 |
エル | -6.013 |
Token | low |
Token ID | 1877 |
Feature activation | -1.70e+01 |
Pos logit contributions | |
ilitarian | +5.955 |
>) | +5.886 |
xxxxxxxx | +5.302 |
Revival | +5.258 |
Eliot | +5.236 |
Neg logit contributions | |
ulf | -6.582 |
rer | -6.245 |
ê | -5.658 |
Mouth | -5.617 |
エル | -5.517 |
Token | - |
Token ID | 12 |
Feature activation | -2.01e+01 |
Pos logit contributions | |
>) | +8.966 |
ilitarian | +8.856 |
spot | +8.404 |
weighed | +7.969 |
Revival | +7.607 |
Neg logit contributions | |
ulf | -11.407 |
rer | -10.885 |
� | -10.531 |
Mouth | -10.400 |
IPM | -10.380 |
Token | quality |
Token ID | 13237 |
Feature activation | -8.53e+00 |
Pos logit contributions | |
spot | +10.810 |
>) | +10.742 |
ilitarian | +10.642 |
xxxxxxxx | +9.683 |
hang | +9.625 |
Neg logit contributions | |
Mouth | -12.019 |
ulf | -11.945 |
� | -11.767 |
rer | -11.527 |
OTOS | -11.368 |
Token | MP |
Token ID | 4904 |
Feature activation | -8.17e+00 |
Pos logit contributions | |
ilitarian | +5.458 |
>) | +5.376 |
Revival | +4.856 |
Eliot | +4.822 |
weighed | +4.787 |
Neg logit contributions | |
ulf | -5.947 |
rer | -5.714 |
ê | -5.140 |
Mouth | -5.134 |
エル | -5.093 |
Token | 3 |
Token ID | 18 |
Feature activation | -7.16e+00 |
Pos logit contributions | |
>) | +4.239 |
ilitarian | +4.138 |
xxxxxxxx | +3.551 |
spot | +3.531 |
AIN | +3.393 |
Neg logit contributions | |
ulf | -6.865 |
rer | -6.566 |
Mouth | -6.278 |
IPM | -6.214 |
エル | -6.098 |
Token | � |
Token ID | 564 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
ilitarian | +4.125 |
>) | +4.029 |
spot | +3.578 |
xxxxxxxx | +3.530 |
weighed | +3.498 |
Neg logit contributions | |
ulf | -5.566 |
rer | -5.342 |
Mouth | -5.062 |
IPM | -5.006 |
ê | -4.831 |
Token | � |
Token ID | 250 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
ilitarian | +2.126 |
>) | +2.089 |
xxxxxxxx | +1.831 |
spot | +1.790 |
romeda | +1.771 |
Neg logit contributions | |
ulf | -2.836 |
rer | -2.767 |
Mouth | -2.608 |
IPM | -2.562 |
ê | -2.512 |
Token | the |
Token ID | 262 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
ilitarian | +1.973 |
>) | +1.903 |
xxxxxxxx | +1.686 |
spot | +1.661 |
romeda | +1.656 |
Neg logit contributions | |
ulf | -2.383 |
rer | -2.338 |
Mouth | -2.158 |
ê | -2.125 |
IPM | -2.112 |
Token | Chiefs |
Token ID | 18733 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
>) | +7.371 |
ilitarian | +7.326 |
Eliot | +6.567 |
Revival | +6.464 |
Burnett | +6.341 |
Neg logit contributions | |
ulf | -9.280 |
rer | -8.974 |
ê | -8.481 |
� | -8.389 |
IPM | -8.101 |
Token | called |
Token ID | 1444 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
ulf | +1.446 |
rer | +1.422 |
Mouth | +1.314 |
IPM | +1.266 |
ê | +1.253 |
Neg logit contributions | |
ilitarian | -1.505 |
>) | -1.443 |
xxxxxxxx | -1.298 |
romeda | -1.283 |
spot | -1.279 |
Token | up |
Token ID | 510 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
ulf | +1.892 |
rer | +1.870 |
Mouth | +1.727 |
IPM | +1.663 |
ê | +1.640 |
Neg logit contributions | |
ilitarian | -1.935 |
>) | -1.852 |
xxxxxxxx | -1.662 |
romeda | -1.654 |
spot | -1.642 |
Token | to |
Token ID | 284 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
ilitarian | +2.979 |
>) | +2.844 |
xxxxxxxx | +2.570 |
spot | +2.538 |
weighed | +2.511 |
Neg logit contributions | |
ulf | -3.378 |
rer | -3.278 |
Mouth | -3.084 |
IPM | -3.005 |
ê | -2.991 |
Token | the |
Token ID | 262 |
Feature activation | -1.99e+01 |
Pos logit contributions | |
ilitarian | +1.722 |
>) | +1.662 |
xxxxxxxx | +1.492 |
spot | +1.474 |
romeda | +1.464 |
Neg logit contributions | |
ulf | -1.711 |
rer | -1.674 |
Mouth | -1.545 |
IPM | -1.503 |
ê | -1.502 |
Token | Nationals |
Token ID | 26291 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
>) | +11.061 |
ilitarian | +10.831 |
Revival | +9.844 |
spot | +9.836 |
Eliot | +9.734 |
Neg logit contributions | |
ulf | -12.437 |
rer | -11.710 |
� | -11.524 |
ê | -11.407 |
エル | -10.766 |
Token | earlier |
Token ID | 2961 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
ilitarian | +3.440 |
>) | +3.309 |
xxxxxxxx | +2.978 |
spot | +2.950 |
weighed | +2.907 |
Neg logit contributions | |
ulf | -3.852 |
rer | -3.746 |
Mouth | -3.512 |
IPM | -3.414 |
ê | -3.405 |
Token | in |
Token ID | 287 |
Feature activation | -5.89e+00 |
Pos logit contributions | |
ilitarian | +1.419 |
>) | +1.369 |
xxxxxxxx | +1.226 |
spot | +1.202 |
romeda | +1.198 |
Neg logit contributions | |
ulf | -1.545 |
rer | -1.519 |
Mouth | -1.410 |
IPM | -1.369 |
ê | -1.355 |
Token | the |
Token ID | 262 |
Feature activation | -1.54e+01 |
Pos logit contributions | |
ilitarian | +3.375 |
>) | +3.325 |
xxxxxxxx | +2.916 |
spot | +2.875 |
Eliot | +2.851 |
Neg logit contributions | |
ulf | -4.614 |
rer | -4.526 |
Mouth | -4.191 |
IPM | -4.132 |
ê | -4.100 |
Token | month |
Token ID | 1227 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
>) | +6.474 |
ilitarian | +6.126 |
Eliot | +5.691 |
xxxxxxxx | +5.642 |
Revival | +5.429 |
Neg logit contributions | |
ulf | -12.531 |
rer | -12.085 |
� | -11.663 |
Mouth | -11.431 |
ê | -11.424 |
Token | waiting |
Token ID | 4953 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
ilitarian | +0.983 |
>) | +0.949 |
xxxxxxxx | +0.851 |
spot | +0.841 |
romeda | +0.839 |
Neg logit contributions | |
ulf | -1.048 |
rer | -1.022 |
Mouth | -0.948 |
IPM | -0.923 |
ê | -0.909 |
Token | in |
Token ID | 287 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ulf | +3.000 |
rer | +2.990 |
Mouth | +2.709 |
IPM | +2.625 |
ê | +2.603 |
Neg logit contributions | |
ilitarian | -3.694 |
>) | -3.566 |
romeda | -3.183 |
xxxxxxxx | -3.181 |
spot | -3.136 |
Token | the |
Token ID | 262 |
Feature activation | -6.57e+00 |
Pos logit contributions | |
ilitarian | +0.887 |
>) | +0.857 |
xxxxxxxx | +0.765 |
spot | +0.759 |
romeda | +0.757 |
Neg logit contributions | |
ulf | -0.906 |
rer | -0.885 |
Mouth | -0.819 |
IPM | -0.795 |
ê | -0.785 |
Token | back |
Token ID | 736 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
ilitarian | +4.509 |
>) | +4.445 |
xxxxxxxx | +3.966 |
Revival | +3.947 |
spot | +3.941 |
Neg logit contributions | |
ulf | -4.441 |
rer | -4.236 |
Mouth | -3.941 |
IPM | -3.845 |
ê | -3.792 |
Token | of |
Token ID | 286 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ilitarian | +2.966 |
>) | +2.836 |
spot | +2.565 |
xxxxxxxx | +2.533 |
romeda | +2.494 |
Neg logit contributions | |
ulf | -3.353 |
rer | -3.284 |
Mouth | -3.097 |
IPM | -3.004 |
ê | -2.928 |
Token | an |
Token ID | 281 |
Feature activation | -1.98e+01 |
Pos logit contributions | |
ilitarian | +1.351 |
>) | +1.299 |
xxxxxxxx | +1.158 |
spot | +1.143 |
romeda | +1.138 |
Neg logit contributions | |
ulf | -1.555 |
rer | -1.520 |
Mouth | -1.412 |
IPM | -1.376 |
ê | -1.362 |
Token | SUV |
Token ID | 26763 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
>) | +11.328 |
ilitarian | +10.471 |
Eliot | +10.064 |
Suzuki | +9.975 |
Revival | +9.878 |
Neg logit contributions | |
ulf | -12.001 |
rer | -11.336 |
Mouth | -11.296 |
� | -11.100 |
エル | -10.741 |
Token | , |
Token ID | 11 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
ulf | +0.018 |
rer | +0.018 |
Mouth | +0.016 |
IPM | +0.016 |
ê | +0.016 |
Neg logit contributions | |
ilitarian | -0.018 |
>) | -0.017 |
xxxxxxxx | -0.015 |
romeda | -0.015 |
spot | -0.015 |
Token | wearing |
Token ID | 5762 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
ulf | +1.199 |
rer | +1.184 |
Mouth | +1.098 |
IPM | +1.057 |
ê | +1.056 |
Neg logit contributions | |
ilitarian | -1.195 |
>) | -1.152 |
xxxxxxxx | -1.027 |
romeda | -1.019 |
spot | -1.013 |
Token | ripped |
Token ID | 19551 |
Feature activation | -8.78e+00 |
Pos logit contributions | |
ilitarian | +6.937 |
>) | +6.701 |
Revival | +6.148 |
Eliot | +6.083 |
weighed | +6.012 |
Neg logit contributions | |
ulf | -8.737 |
rer | -8.285 |
Mouth | -7.695 |
IPM | -7.559 |
� | -7.474 |
Token | jeans |
Token ID | 21029 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ilitarian | +4.724 |
>) | +4.671 |
Eliot | +4.121 |
Revival | +4.114 |
xxxxxxxx | +3.992 |
Neg logit contributions | |
ulf | -6.976 |
rer | -6.711 |
Mouth | -6.293 |
IPM | -6.203 |
OTOS | -6.108 |
Token | be |
Token ID | 307 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
ulf | +3.352 |
rer | +3.304 |
Mouth | +3.013 |
IPM | +2.931 |
ê | +2.922 |
Neg logit contributions | |
ilitarian | -3.627 |
>) | -3.471 |
xxxxxxxx | -3.125 |
romeda | -3.119 |
Eliot | -3.082 |
Token | an |
Token ID | 281 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
ulf | +2.663 |
rer | +2.614 |
Mouth | +2.427 |
IPM | +2.322 |
ê | +2.288 |
Neg logit contributions | |
ilitarian | -2.978 |
>) | -2.843 |
xxxxxxxx | -2.542 |
romeda | -2.512 |
spot | -2.477 |
Token | impact |
Token ID | 2928 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
ilitarian | +1.310 |
>) | +1.274 |
xxxxxxxx | +1.139 |
romeda | +1.125 |
spot | +1.121 |
Neg logit contributions | |
ulf | -1.336 |
rer | -1.315 |
Mouth | -1.218 |
IPM | -1.173 |
ê | -1.166 |
Token | player |
Token ID | 2137 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
ilitarian | +1.436 |
>) | +1.378 |
xxxxxxxx | +1.233 |
spot | +1.228 |
romeda | +1.211 |
Neg logit contributions | |
ulf | -1.533 |
rer | -1.481 |
Mouth | -1.389 |
IPM | -1.360 |
ê | -1.346 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
rer | +3.259 |
ulf | +3.243 |
Mouth | +2.910 |
IPM | +2.773 |
ê | +2.757 |
Neg logit contributions | |
ilitarian | -3.883 |
>) | -3.784 |
romeda | -3.357 |
xxxxxxxx | -3.354 |
spot | -3.309 |
Token | every |
Token ID | 790 |
Feature activation | -1.98e+01 |
Pos logit contributions | |
ilitarian | +0.940 |
>) | +0.908 |
xxxxxxxx | +0.812 |
spot | +0.807 |
romeda | +0.802 |
Neg logit contributions | |
ulf | -0.935 |
rer | -0.909 |
Mouth | -0.846 |
IPM | -0.818 |
ê | -0.816 |
Token | day |
Token ID | 1110 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
>) | +9.023 |
spot | +8.471 |
ilitarian | +8.338 |
Suzuki | +7.301 |
weighed | +7.271 |
Neg logit contributions | |
ulf | -15.060 |
rer | -13.900 |
� | -13.769 |
ê | -13.543 |
Mouth | -13.522 |
Token | for |
Token ID | 329 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
ilitarian | +1.628 |
>) | +1.565 |
xxxxxxxx | +1.402 |
spot | +1.393 |
romeda | +1.381 |
Neg logit contributions | |
ulf | -1.742 |
rer | -1.694 |
Mouth | -1.581 |
IPM | -1.539 |
ê | -1.530 |
Token | somebody |
Token ID | 8276 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
ilitarian | +2.400 |
>) | +2.331 |
xxxxxxxx | +2.078 |
spot | +2.031 |
Eliot | +2.018 |
Neg logit contributions | |
ulf | -2.871 |
rer | -2.800 |
Mouth | -2.616 |
ê | -2.559 |
IPM | -2.526 |
Token | . |
Token ID | 13 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
ulf | +2.209 |
rer | +2.197 |
Mouth | +2.003 |
IPM | +1.930 |
ê | +1.915 |
Neg logit contributions | |
ilitarian | -2.421 |
>) | -2.343 |
xxxxxxxx | -2.087 |
romeda | -2.062 |
spot | -2.056 |
Token | It |
Token ID | 632 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
ulf | +2.155 |
rer | +2.128 |
Mouth | +2.008 |
IPM | +1.901 |
ê | +1.877 |
Neg logit contributions | |
ilitarian | -2.232 |
>) | -2.123 |
romeda | -1.897 |
xxxxxxxx | -1.888 |
spot | -1.882 |
Token | 7 |
Token ID | 767 |
Feature activation | -7.70e+00 |
Pos logit contributions | |
>) | +8.737 |
ilitarian | +7.749 |
spot | +7.745 |
xxxxxxxx | +7.261 |
borrow | +7.216 |
Neg logit contributions | |
ulf | -13.396 |
rer | -12.646 |
Mouth | -12.005 |
IPM | -11.965 |
ê | -11.934 |
Token | 8 |
Token ID | 807 |
Feature activation | -1.69e+01 |
Pos logit contributions | |
>) | +4.063 |
ilitarian | +3.997 |
spot | +3.465 |
xxxxxxxx | +3.316 |
weighed | +3.241 |
Neg logit contributions | |
ulf | -6.355 |
rer | -6.172 |
IPM | -5.763 |
Mouth | -5.761 |
ê | -5.651 |
Token | 9 |
Token ID | 860 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
>) | +8.369 |
ilitarian | +7.573 |
spot | +7.341 |
weighed | +6.762 |
Eliot | +6.614 |
Neg logit contributions | |
ulf | -12.880 |
IPM | -11.667 |
Mouth | -11.649 |
rer | -11.625 |
ê | -11.244 |
Token | 10 |
Token ID | 838 |
Feature activation | -1.42e+01 |
Pos logit contributions | |
ilitarian | +2.964 |
>) | +2.908 |
spot | +2.621 |
xxxxxxxx | +2.598 |
romeda | +2.592 |
Neg logit contributions | |
ulf | -2.499 |
rer | -2.427 |
Mouth | -2.249 |
IPM | -2.169 |
ê | -2.151 |
Token | 11 |
Token ID | 1367 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
>) | +7.183 |
ilitarian | +6.575 |
spot | +6.208 |
AIN | +6.027 |
xxxxxxxx | +5.981 |
Neg logit contributions | |
ulf | -10.624 |
rer | -10.355 |
Mouth | -9.877 |
IPM | -9.855 |
ê | -9.714 |
Token | 12 |
Token ID | 1105 |
Feature activation | -1.98e+01 |
Pos logit contributions | |
>) | +6.111 |
ilitarian | +5.895 |
spot | +5.210 |
romeda | +4.990 |
Eliot | +4.954 |
Neg logit contributions | |
ulf | -9.547 |
rer | -9.027 |
IPM | -8.519 |
Mouth | -8.401 |
ê | -8.387 |
Token | 13 |
Token ID | 1511 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
>) | +8.905 |
ilitarian | +7.717 |
spot | +7.611 |
xxxxxxxx | +7.333 |
borrow | +7.080 |
Neg logit contributions | |
ulf | -15.129 |
rer | -13.950 |
エル | -13.772 |
IPM | -13.619 |
Mouth | -13.174 |
Token | 14 |
Token ID | 1478 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
ilitarian | +1.574 |
>) | +1.539 |
xxxxxxxx | +1.366 |
spot | +1.362 |
romeda | +1.346 |
Neg logit contributions | |
ulf | -1.553 |
rer | -1.512 |
Mouth | -1.390 |
IPM | -1.368 |
ê | -1.345 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.22e+01 |
Pos logit contributions | |
>) | +7.268 |
ilitarian | +6.938 |
spot | +6.053 |
xxxxxxxx | +5.808 |
weighed | +5.798 |
Neg logit contributions | |
ulf | -11.959 |
rer | -11.539 |
Mouth | -10.691 |
IPM | -10.516 |
エル | -10.363 |
Token | -- |
Token ID | 1377 |
Feature activation | -6.57e+00 |
Pos logit contributions | |
>) | +5.662 |
ilitarian | +5.475 |
spot | +4.702 |
Eliot | +4.589 |
xxxxxxxx | +4.511 |
Neg logit contributions | |
ulf | -10.146 |
rer | -10.063 |
IPM | -9.331 |
Mouth | -9.260 |
ê | -8.988 |
Token | Save |
Token ID | 12793 |
Feature activation | -9.31e+00 |
Pos logit contributions | |
>) | +4.525 |
ilitarian | +4.460 |
spot | +4.049 |
xxxxxxxx | +4.006 |
romeda | +3.913 |
Neg logit contributions | |
ulf | -4.435 |
rer | -4.182 |
Mouth | -3.959 |
IPM | -3.852 |
ê | -3.787 |
Token | to |
Token ID | 284 |
Feature activation | -8.28e+00 |
Pos logit contributions | |
ulf | +0.902 |
rer | +0.888 |
Mouth | +0.813 |
IPM | +0.788 |
ê | +0.782 |
Neg logit contributions | |
ilitarian | -0.955 |
>) | -0.924 |
xxxxxxxx | -0.828 |
romeda | -0.825 |
spot | -0.814 |
Token | 300 |
Token ID | 5867 |
Feature activation | -7.97e+00 |
Pos logit contributions | |
ilitarian | +5.118 |
>) | +5.112 |
spot | +4.522 |
weighed | +4.468 |
Eliot | +4.445 |
Neg logit contributions | |
ulf | -5.752 |
rer | -5.620 |
Mouth | -5.338 |
OTOS | -5.292 |
IPM | -5.257 |
Token | , |
Token ID | 11 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
ilitarian | +4.866 |
>) | +4.742 |
spot | +4.258 |
weighed | +4.202 |
Eliot | +4.182 |
Neg logit contributions | |
rer | -5.580 |
ulf | -5.571 |
Mouth | -5.231 |
IPM | -5.200 |
OTOS | -5.026 |
Token | 000 |
Token ID | 830 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
ilitarian | +1.635 |
>) | +1.579 |
xxxxxxxx | +1.426 |
spot | +1.418 |
romeda | +1.410 |
Neg logit contributions | |
ulf | -1.390 |
rer | -1.368 |
Mouth | -1.261 |
IPM | -1.222 |
ê | -1.197 |
Token | barrels |
Token ID | 17907 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
ilitarian | +2.685 |
>) | +2.611 |
spot | +2.371 |
xxxxxxxx | +2.364 |
romeda | +2.356 |
Neg logit contributions | |
ulf | -2.024 |
rer | -1.989 |
Mouth | -1.814 |
IPM | -1.779 |
ê | -1.726 |
Token | a |
Token ID | 257 |
Feature activation | -1.97e+01 |
Pos logit contributions | |
ilitarian | +5.208 |
>) | +4.995 |
weighed | +4.711 |
Eliot | +4.476 |
spot | +4.360 |
Neg logit contributions | |
rer | -9.704 |
ulf | -9.659 |
Mouth | -9.262 |
IPM | -9.233 |
OTOS | -8.998 |
Token | day |
Token ID | 1110 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
>) | +4.433 |
weighed | +4.362 |
spot | +3.707 |
loaded | +3.560 |
borrow | +3.512 |
Neg logit contributions | |
ulf | -18.639 |
rer | -18.309 |
OTOS | -17.771 |
IPM | -17.508 |
azing | -17.316 |
Token | . |
Token ID | 13 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
ilitarian | +3.423 |
>) | +3.269 |
spot | +2.950 |
weighed | +2.922 |
xxxxxxxx | +2.905 |
Neg logit contributions | |
ulf | -3.979 |
rer | -3.879 |
Mouth | -3.702 |
IPM | -3.626 |
ê | -3.554 |
Token | Virt |
Token ID | 11285 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
ilitarian | +1.857 |
>) | +1.795 |
xxxxxxxx | +1.606 |
spot | +1.586 |
romeda | +1.558 |
Neg logit contributions | |
ulf | -1.982 |
rer | -1.935 |
Mouth | -1.781 |
IPM | -1.748 |
ê | -1.730 |
Token | ually |
Token ID | 935 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
ilitarian | +2.880 |
>) | +2.775 |
xxxxxxxx | +2.526 |
spot | +2.490 |
romeda | +2.460 |
Neg logit contributions | |
ulf | -2.437 |
rer | -2.428 |
Mouth | -2.212 |
IPM | -2.167 |
ê | -2.079 |
Token | all |
Token ID | 477 |
Feature activation | -9.89e-02 |
Pos logit contributions | |
ulf | +0.298 |
rer | +0.293 |
Mouth | +0.273 |
IPM | +0.265 |
ê | +0.262 |
Neg logit contributions | |
ilitarian | -0.261 |
>) | -0.251 |
xxxxxxxx | -0.223 |
romeda | -0.220 |
spot | -0.220 |
Token | over |
Token ID | 625 |
Feature activation | -5.68e+00 |
Pos logit contributions | |
ilitarian | +5.361 |
>) | +5.137 |
spot | +4.687 |
Eliot | +4.653 |
xxxxxxxx | +4.639 |
Neg logit contributions | |
ulf | -6.471 |
rer | -6.363 |
Mouth | -5.954 |
IPM | -5.765 |
OTOS | -5.704 |
Token | a |
Token ID | 257 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
ilitarian | +3.606 |
>) | +3.476 |
xxxxxxxx | +3.102 |
Eliot | +3.071 |
spot | +3.068 |
Neg logit contributions | |
ulf | -4.089 |
rer | -4.033 |
Mouth | -3.683 |
IPM | -3.599 |
ê | -3.565 |
Token | mont |
Token ID | 40689 |
Feature activation | -6.21e+00 |
Pos logit contributions | |
ilitarian | +8.196 |
>) | +8.173 |
Revival | +7.503 |
weighed | +7.396 |
Eliot | +7.357 |
Neg logit contributions | |
ulf | -8.309 |
rer | -8.048 |
OTOS | -7.482 |
エル | -7.128 |
� | -7.082 |
Token | age |
Token ID | 496 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
ilitarian | +3.788 |
>) | +3.589 |
spot | +3.133 |
romeda | +3.086 |
xxxxxxxx | +3.059 |
Neg logit contributions | |
ulf | -4.658 |
rer | -4.623 |
Mouth | -4.569 |
IPM | -4.393 |
� | -4.341 |
Token | on |
Token ID | 319 |
Feature activation | -1.36e+01 |
Pos logit contributions | |
ilitarian | +1.888 |
>) | +1.814 |
xxxxxxxx | +1.623 |
spot | +1.613 |
romeda | +1.606 |
Neg logit contributions | |
ulf | -2.077 |
rer | -2.032 |
Mouth | -1.894 |
IPM | -1.841 |
ê | -1.812 |
Token | a |
Token ID | 257 |
Feature activation | -1.96e+01 |
Pos logit contributions | |
ilitarian | +8.091 |
>) | +7.617 |
Revival | +7.243 |
Eliot | +7.168 |
weighed | +6.960 |
Neg logit contributions | |
ulf | -9.152 |
rer | -8.984 |
IPM | -8.222 |
Mouth | -8.045 |
エル | -7.972 |
Token | monitor |
Token ID | 5671 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
>) | +10.597 |
ilitarian | +10.590 |
Revival | +10.046 |
weighed | +9.675 |
spot | +9.623 |
Neg logit contributions | |
ulf | -12.138 |
rer | -11.687 |
� | -10.810 |
ê | -10.676 |
OTOS | -10.628 |
Token | — |
Token ID | 960 |
Feature activation | -5.80e+00 |
Pos logit contributions | |
ilitarian | +1.477 |
>) | +1.420 |
xxxxxxxx | +1.278 |
spot | +1.264 |
romeda | +1.264 |
Neg logit contributions | |
ulf | -1.583 |
rer | -1.550 |
Mouth | -1.436 |
IPM | -1.391 |
ê | -1.380 |
Token | one |
Token ID | 505 |
Feature activation | -9.46e+00 |
Pos logit contributions | |
ilitarian | +3.800 |
>) | +3.750 |
spot | +3.394 |
xxxxxxxx | +3.380 |
romeda | +3.235 |
Neg logit contributions | |
ulf | -4.047 |
rer | -3.964 |
Mouth | -3.708 |
IPM | -3.665 |
deserts | -3.501 |
Token | take |
Token ID | 1011 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
ilitarian | +5.603 |
>) | +5.559 |
Eliot | +5.049 |
xxxxxxxx | +5.016 |
weighed | +4.995 |
Neg logit contributions | |
ulf | -6.822 |
rer | -6.609 |
Mouth | -6.082 |
IPM | -5.940 |
ê | -5.889 |
Token | and |
Token ID | 290 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
ulf | +1.295 |
rer | +1.272 |
Mouth | +1.173 |
IPM | +1.136 |
ê | +1.131 |
Neg logit contributions | |
ilitarian | -1.298 |
>) | -1.251 |
xxxxxxxx | -1.120 |
romeda | -1.114 |
spot | -1.100 |
Token | power |
Token ID | 1176 |
Feature activation | +5.96e+00 |
Pos logit contributions | |
ulf | +3.217 |
rer | +3.209 |
Mouth | +2.972 |
IPM | +2.881 |
ê | +2.809 |
Neg logit contributions | |
ilitarian | -3.457 |
>) | -3.379 |
romeda | -3.040 |
xxxxxxxx | -3.031 |
spot | -2.975 |
Token | to |
Token ID | 284 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
rer | +3.615 |
ulf | +3.612 |
Mouth | +3.166 |
ê | +3.107 |
IPM | +3.036 |
Neg logit contributions | |
ilitarian | -4.575 |
>) | -4.488 |
romeda | -4.135 |
xxxxxxxx | -4.024 |
spot | -3.947 |
Token | legisl |
Token ID | 3560 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ulf | +1.196 |
rer | +1.179 |
Mouth | +1.075 |
IPM | +1.041 |
ê | +1.030 |
Neg logit contributions | |
ilitarian | -1.439 |
>) | -1.382 |
xxxxxxxx | -1.253 |
romeda | -1.245 |
spot | -1.237 |
Token | ate |
Token ID | 378 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
ulf | +0.589 |
rer | +0.574 |
Mouth | +0.515 |
ê | +0.494 |
IPM | +0.488 |
Neg logit contributions | |
ilitarian | -0.942 |
>) | -0.913 |
xxxxxxxx | -0.834 |
romeda | -0.832 |
spot | -0.827 |
Token | with |
Token ID | 351 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
ilitarian | +0.547 |
>) | +0.526 |
xxxxxxxx | +0.471 |
spot | +0.465 |
romeda | +0.465 |
Neg logit contributions | |
ulf | -0.579 |
rer | -0.567 |
Mouth | -0.526 |
IPM | -0.510 |
ê | -0.505 |
Token | respect |
Token ID | 2461 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
ulf | +0.420 |
rer | +0.413 |
Mouth | +0.388 |
IPM | +0.377 |
ê | +0.374 |
Neg logit contributions | |
ilitarian | -0.298 |
>) | -0.285 |
xxxxxxxx | -0.249 |
romeda | -0.246 |
spot | -0.245 |
Token | to |
Token ID | 284 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
rer | +6.159 |
ulf | +6.071 |
Mouth | +5.215 |
ê | +5.132 |
ement | +4.974 |
Neg logit contributions | |
ilitarian | -10.087 |
>) | -9.880 |
romeda | -9.116 |
spot | -8.916 |
xxxxxxxx | -8.768 |
Token | education |
Token ID | 3707 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
ulf | +0.276 |
rer | +0.271 |
Mouth | +0.252 |
IPM | +0.244 |
ê | +0.241 |
Neg logit contributions | |
ilitarian | -0.271 |
>) | -0.261 |
xxxxxxxx | -0.234 |
romeda | -0.232 |
spot | -0.231 |
Token | , |
Token ID | 11 |
Feature activation | -6.13e+00 |
Pos logit contributions | |
ilitarian | +1.279 |
>) | +1.226 |
xxxxxxxx | +1.104 |
spot | +1.091 |
romeda | +1.082 |
Neg logit contributions | |
ulf | -1.305 |
rer | -1.274 |
Mouth | -1.183 |
IPM | -1.147 |
ê | -1.130 |
Token | criminal |
Token ID | 4301 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
ilitarian | +3.972 |
>) | +3.876 |
spot | +3.432 |
xxxxxxxx | +3.406 |
weighed | +3.401 |
Neg logit contributions | |
ulf | -4.458 |
rer | -4.306 |
Mouth | -3.972 |
IPM | -3.832 |
ê | -3.788 |
Token | law |
Token ID | 1099 |
Feature activation | -9.07e+00 |
Pos logit contributions | |
ilitarian | +0.268 |
>) | +0.256 |
xxxxxxxx | +0.224 |
spot | +0.220 |
romeda | +0.220 |
Neg logit contributions | |
ulf | -0.382 |
rer | -0.375 |
Mouth | -0.353 |
IPM | -0.343 |
ê | -0.340 |
Token | of |
Token ID | 286 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
ulf | +0.072 |
rer | +0.070 |
Mouth | +0.065 |
IPM | +0.063 |
ê | +0.062 |
Neg logit contributions | |
ilitarian | -0.072 |
>) | -0.070 |
xxxxxxxx | -0.063 |
romeda | -0.062 |
spot | -0.062 |
Token | 100 |
Token ID | 1802 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
ulf | +0.174 |
rer | +0.170 |
Mouth | +0.158 |
IPM | +0.153 |
ê | +0.151 |
Neg logit contributions | |
ilitarian | -0.178 |
>) | -0.171 |
xxxxxxxx | -0.154 |
romeda | -0.152 |
spot | -0.152 |
Token | Greatest |
Token ID | 33575 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
ulf | +0.107 |
rer | +0.105 |
Mouth | +0.098 |
IPM | +0.095 |
ê | +0.094 |
Neg logit contributions | |
ilitarian | -0.102 |
>) | -0.098 |
xxxxxxxx | -0.088 |
romeda | -0.087 |
spot | -0.087 |
Token | African |
Token ID | 5510 |
Feature activation | +7.46e+00 |
Pos logit contributions | |
ilitarian | +0.622 |
>) | +0.598 |
xxxxxxxx | +0.536 |
spot | +0.530 |
romeda | +0.529 |
Neg logit contributions | |
ulf | -0.656 |
rer | -0.646 |
Mouth | -0.595 |
IPM | -0.582 |
ê | -0.573 |
Token | Americans |
Token ID | 3399 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ulf | +4.684 |
rer | +4.356 |
Mouth | +4.203 |
ê | +4.002 |
iner | +3.809 |
Neg logit contributions | |
ilitarian | -5.704 |
>) | -5.424 |
xxxxxxxx | -4.933 |
romeda | -4.887 |
spot | -4.852 |
Token | .[ |
Token ID | 3693 |
Feature activation | +1.26e+01 |
Pos logit contributions | |
ulf | +1.012 |
rer | +0.985 |
Mouth | +0.913 |
ê | +0.875 |
IPM | +0.874 |
Neg logit contributions | |
ilitarian | -1.080 |
>) | -1.044 |
xxxxxxxx | -0.936 |
romeda | -0.930 |
spot | -0.927 |
Token | 58 |
Token ID | 3365 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
rer | +4.291 |
ulf | +4.272 |
Mouth | +3.590 |
OTOS | +3.115 |
ê | +3.061 |
Neg logit contributions | |
ilitarian | -12.127 |
>) | -11.418 |
romeda | -11.132 |
Eliot | -10.856 |
xxxxxxxx | -10.827 |
Token | ] |
Token ID | 60 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ilitarian | +0.955 |
>) | +0.911 |
xxxxxxxx | +0.743 |
spot | +0.732 |
romeda | +0.721 |
Neg logit contributions | |
ulf | -2.186 |
rer | -2.150 |
Mouth | -2.039 |
IPM | -1.998 |
ê | -1.980 |
Token |
|
Token ID | 198 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
ilitarian | +0.726 |
>) | +0.700 |
xxxxxxxx | +0.627 |
romeda | +0.620 |
spot | +0.619 |
Neg logit contributions | |
ulf | -0.765 |
rer | -0.748 |
Mouth | -0.690 |
IPM | -0.672 |
ê | -0.667 |
Token |
|
Token ID | 198 |
Feature activation | -6.01e+00 |
Pos logit contributions | |
ulf | +1.447 |
rer | +1.424 |
Mouth | +1.304 |
IPM | +1.263 |
ê | +1.257 |
Neg logit contributions | |
ilitarian | -1.585 |
>) | -1.499 |
romeda | -1.373 |
xxxxxxxx | -1.344 |
spot | -1.335 |
Token | In |
Token ID | 818 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
>) | +3.845 |
ilitarian | +3.840 |
xxxxxxxx | +3.461 |
spot | +3.461 |
romeda | +3.260 |
Neg logit contributions | |
ulf | -4.263 |
rer | -4.142 |
Mouth | -3.971 |
IPM | -3.880 |
deserts | -3.828 |
Token | completed |
Token ID | 5668 |
Feature activation | +7.96e+00 |
Pos logit contributions | |
ulf | +1.239 |
rer | +1.220 |
Mouth | +1.133 |
IPM | +1.103 |
ê | +1.086 |
Neg logit contributions | |
ilitarian | -1.209 |
>) | -1.161 |
xxxxxxxx | -1.041 |
romeda | -1.035 |
spot | -1.019 |
Token | in |
Token ID | 287 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
ulf | +4.753 |
rer | +4.678 |
Mouth | +4.172 |
IPM | +4.090 |
deserts | +4.021 |
Neg logit contributions | |
ilitarian | -6.044 |
>) | -5.935 |
xxxxxxxx | -5.318 |
romeda | -5.317 |
spot | -5.186 |
Token | 2012 |
Token ID | 2321 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ilitarian | +0.251 |
>) | +0.241 |
xxxxxxxx | +0.212 |
romeda | +0.209 |
spot | +0.209 |
Neg logit contributions | |
ulf | -0.320 |
rer | -0.314 |
Mouth | -0.293 |
IPM | -0.285 |
ê | -0.283 |
Token | . |
Token ID | 13 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
ilitarian | +1.158 |
>) | +1.109 |
xxxxxxxx | +0.995 |
spot | +0.991 |
romeda | +0.980 |
Neg logit contributions | |
ulf | -1.202 |
rer | -1.179 |
Mouth | -1.098 |
IPM | -1.063 |
ê | -1.051 |
Token | The |
Token ID | 383 |
Feature activation | +5.92e+00 |
Pos logit contributions | |
ulf | +2.983 |
rer | +2.932 |
Mouth | +2.772 |
IPM | +2.652 |
ê | +2.583 |
Neg logit contributions | |
ilitarian | -3.296 |
>) | -3.173 |
romeda | -2.890 |
xxxxxxxx | -2.850 |
spot | -2.816 |
Token | old |
Token ID | 1468 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
rer | +4.019 |
ulf | +4.016 |
Mouth | +3.757 |
IPM | +3.658 |
deserts | +3.540 |
Neg logit contributions | |
ilitarian | -4.036 |
>) | -3.914 |
xxxxxxxx | -3.516 |
romeda | -3.479 |
spot | -3.423 |
Token | bridge |
Token ID | 7696 |
Feature activation | +5.41e+00 |
Pos logit contributions | |
ulf | +6.619 |
rer | +6.569 |
Mouth | +6.238 |
IPM | +6.030 |
deserts | +5.875 |
Neg logit contributions | |
ilitarian | -7.431 |
>) | -7.329 |
xxxxxxxx | -6.661 |
romeda | -6.520 |
ozy | -6.384 |
Token | had |
Token ID | 550 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ulf | +3.522 |
rer | +3.512 |
Mouth | +3.201 |
IPM | +3.101 |
ê | +3.039 |
Neg logit contributions | |
ilitarian | -3.935 |
>) | -3.818 |
xxxxxxxx | -3.409 |
romeda | -3.395 |
spot | -3.312 |
Token | a |
Token ID | 257 |
Feature activation | +9.30e+00 |
Pos logit contributions | |
ulf | +0.843 |
rer | +0.831 |
Mouth | +0.771 |
IPM | +0.749 |
ê | +0.737 |
Neg logit contributions | |
ilitarian | -0.835 |
>) | -0.805 |
xxxxxxxx | -0.722 |
romeda | -0.712 |
spot | -0.710 |
Token | much |
Token ID | 881 |
Feature activation | +5.01e+00 |
Pos logit contributions | |
rer | +5.912 |
ulf | +5.823 |
Mouth | +5.576 |
IPM | +5.278 |
deserts | +5.210 |
Neg logit contributions | |
>) | -6.224 |
ilitarian | -6.220 |
xxxxxxxx | -5.641 |
romeda | -5.523 |
spot | -5.338 |
Token | narrower |
Token ID | 40369 |
Feature activation | +8.35e+00 |
Pos logit contributions | |
rer | +3.045 |
ulf | +3.017 |
Mouth | +2.762 |
ê | +2.620 |
IPM | +2.612 |
Neg logit contributions | |
ilitarian | -3.845 |
>) | -3.714 |
xxxxxxxx | -3.429 |
romeda | -3.350 |
spot | -3.303 |
Token | M |
Token ID | 44 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
ulf | +3.379 |
rer | +3.286 |
Mouth | +3.022 |
ê | +2.941 |
IPM | +2.868 |
Neg logit contributions | |
ilitarian | -3.523 |
>) | -3.285 |
romeda | -3.024 |
spot | -2.903 |
xxxxxxxx | -2.894 |
Token | ord |
Token ID | 585 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
ulf | +1.340 |
rer | +1.278 |
Mouth | +1.032 |
ê | +1.000 |
iner | +0.959 |
Neg logit contributions | |
ilitarian | -3.772 |
>) | -3.664 |
spot | -3.399 |
xxxxxxxx | -3.399 |
romeda | -3.384 |
Token | ica |
Token ID | 3970 |
Feature activation | +6.19e+00 |
Pos logit contributions | |
ulf | +1.725 |
rer | +1.690 |
Mouth | +1.531 |
ê | +1.459 |
IPM | +1.435 |
Neg logit contributions | |
ilitarian | -2.270 |
>) | -2.166 |
xxxxxxxx | -1.969 |
spot | -1.954 |
Eliot | -1.941 |
Token | is |
Token ID | 318 |
Feature activation | +6.21e+00 |
Pos logit contributions | |
ulf | +3.977 |
rer | +3.964 |
Mouth | +3.615 |
ê | +3.450 |
IPM | +3.393 |
Neg logit contributions | |
ilitarian | -4.566 |
>) | -4.369 |
romeda | -3.927 |
xxxxxxxx | -3.890 |
spot | -3.863 |
Token | the |
Token ID | 262 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
ulf | +3.963 |
rer | +3.900 |
Mouth | +3.640 |
ê | +3.451 |
IPM | +3.411 |
Neg logit contributions | |
ilitarian | -4.621 |
>) | -4.394 |
xxxxxxxx | -3.946 |
romeda | -3.944 |
spot | -3.846 |
Token | fastest |
Token ID | 14162 |
Feature activation | +1.26e+01 |
Pos logit contributions | |
ulf | +2.356 |
rer | +2.315 |
Mouth | +2.163 |
IPM | +2.056 |
ê | +2.020 |
Neg logit contributions | |
ilitarian | -2.617 |
>) | -2.492 |
xxxxxxxx | -2.269 |
romeda | -2.244 |
spot | -2.220 |
Token | back |
Token ID | 736 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
ulf | +7.775 |
rer | +7.522 |
Mouth | +6.988 |
iner | +6.617 |
ê | +6.586 |
Neg logit contributions | |
ilitarian | -8.985 |
>) | -8.486 |
xxxxxxxx | -7.740 |
romeda | -7.530 |
ozy | -7.494 |
Token | we |
Token ID | 356 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ilitarian | +1.454 |
>) | +1.398 |
xxxxxxxx | +1.251 |
spot | +1.243 |
romeda | +1.235 |
Neg logit contributions | |
ulf | -1.569 |
rer | -1.547 |
Mouth | -1.440 |
IPM | -1.398 |
ê | -1.380 |
Token | � |
Token ID | 447 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
ilitarian | +1.136 |
>) | +1.102 |
xxxxxxxx | +0.985 |
spot | +0.974 |
romeda | +0.974 |
Neg logit contributions | |
ulf | -1.163 |
rer | -1.134 |
Mouth | -1.060 |
IPM | -1.027 |
ê | -1.008 |
Token | � |
Token ID | 247 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
ulf | +0.384 |
rer | +0.378 |
Mouth | +0.352 |
IPM | +0.341 |
ê | +0.338 |
Neg logit contributions | |
ilitarian | -0.332 |
>) | -0.318 |
xxxxxxxx | -0.283 |
romeda | -0.280 |
spot | -0.279 |
Token | ve |
Token ID | 303 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
rer | +2.138 |
ulf | +2.137 |
Mouth | +1.928 |
ê | +1.868 |
IPM | +1.836 |
Neg logit contributions | |
ilitarian | -2.375 |
>) | -2.286 |
xxxxxxxx | -2.041 |
romeda | -2.039 |
spot | -2.005 |
Token | had |
Token ID | 550 |
Feature activation | -6.27e+00 |
Pos logit contributions | |
ilitarian | +1.922 |
>) | +1.852 |
xxxxxxxx | +1.668 |
spot | +1.657 |
weighed | +1.644 |
Neg logit contributions | |
ulf | -2.060 |
rer | -2.006 |
Mouth | -1.888 |
IPM | -1.816 |
ê | -1.799 |
Token | , |
Token ID | 11 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
ilitarian | +3.936 |
>) | +3.801 |
Eliot | +3.435 |
weighed | +3.435 |
xxxxxxxx | +3.419 |
Neg logit contributions | |
ulf | -4.590 |
rer | -4.473 |
Mouth | -4.119 |
ê | -4.052 |
IPM | -3.999 |
Token | as |
Token ID | 355 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
ulf | +1.649 |
rer | +1.623 |
Mouth | +1.498 |
IPM | +1.446 |
ê | +1.425 |
Neg logit contributions | |
ilitarian | -1.780 |
>) | -1.709 |
xxxxxxxx | -1.544 |
romeda | -1.519 |
spot | -1.511 |
Token | New |
Token ID | 968 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
ilitarian | +1.014 |
>) | +0.977 |
xxxxxxxx | +0.875 |
romeda | +0.867 |
spot | +0.866 |
Neg logit contributions | |
ulf | -1.068 |
rer | -1.049 |
Mouth | -0.973 |
IPM | -0.945 |
ê | -0.938 |
Token | York |
Token ID | 1971 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ilitarian | +1.862 |
>) | +1.763 |
spot | +1.541 |
xxxxxxxx | +1.540 |
romeda | +1.512 |
Neg logit contributions | |
ulf | -2.613 |
rer | -2.588 |
Mouth | -2.423 |
IPM | -2.385 |
ê | -2.357 |
Token | social |
Token ID | 1919 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
ilitarian | +0.731 |
>) | +0.698 |
xxxxxxxx | +0.616 |
spot | +0.610 |
romeda | +0.607 |
Neg logit contributions | |
ulf | -0.919 |
rer | -0.901 |
Mouth | -0.841 |
IPM | -0.818 |
ê | -0.811 |
Token | democrat |
Token ID | 43268 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
ulf | +8.319 |
rer | +8.010 |
ê | +7.374 |
Mouth | +7.222 |
deserts | +7.153 |
Neg logit contributions | |
ilitarian | -10.890 |
>) | -10.503 |
romeda | -9.902 |
xxxxxxxx | -9.560 |
":[ | -9.039 |
Token | Louis |
Token ID | 5593 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ilitarian | +1.850 |
>) | +1.778 |
Eliot | +1.601 |
spot | +1.597 |
xxxxxxxx | +1.589 |
Neg logit contributions | |
ulf | -1.971 |
rer | -1.925 |
Mouth | -1.793 |
IPM | -1.750 |
ê | -1.724 |
Token | Wald |
Token ID | 24261 |
Feature activation | -5.52e+00 |
Pos logit contributions | |
ilitarian | +0.771 |
>) | +0.743 |
xxxxxxxx | +0.670 |
spot | +0.661 |
romeda | +0.660 |
Neg logit contributions | |
ulf | -0.704 |
rer | -0.689 |
Mouth | -0.634 |
IPM | -0.617 |
ê | -0.608 |
Token | man |
Token ID | 805 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
ilitarian | +4.174 |
>) | +3.925 |
spot | +3.617 |
xxxxxxxx | +3.594 |
romeda | +3.574 |
Neg logit contributions | |
ulf | -3.362 |
rer | -3.290 |
Mouth | -3.136 |
IPM | -3.053 |
ê | -2.932 |
Token | later |
Token ID | 1568 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
ulf | +0.129 |
rer | +0.126 |
Mouth | +0.117 |
IPM | +0.113 |
ê | +0.112 |
Neg logit contributions | |
ilitarian | -0.134 |
>) | -0.130 |
xxxxxxxx | -0.116 |
romeda | -0.115 |
spot | -0.115 |
Token | our |
Token ID | 674 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
ulf | +0.130 |
rer | +0.127 |
Mouth | +0.118 |
IPM | +0.114 |
ê | +0.113 |
Neg logit contributions | |
ilitarian | -0.122 |
>) | -0.117 |
xxxxxxxx | -0.105 |
spot | -0.103 |
romeda | -0.103 |
Token | hope |
Token ID | 2911 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
ilitarian | +0.200 |
>) | +0.193 |
xxxxxxxx | +0.174 |
romeda | +0.172 |
spot | +0.172 |
Neg logit contributions | |
ulf | -0.186 |
rer | -0.182 |
Mouth | -0.168 |
IPM | -0.162 |
ê | -0.161 |
Token | that |
Token ID | 326 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
ulf | +3.176 |
rer | +3.129 |
Mouth | +2.874 |
IPM | +2.743 |
ê | +2.740 |
Neg logit contributions | |
ilitarian | -3.769 |
>) | -3.637 |
romeda | -3.248 |
xxxxxxxx | -3.239 |
spot | -3.213 |
Token | the |
Token ID | 262 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ulf | +1.758 |
rer | +1.726 |
Mouth | +1.616 |
IPM | +1.561 |
ê | +1.546 |
Neg logit contributions | |
ilitarian | -1.634 |
>) | -1.567 |
xxxxxxxx | -1.390 |
spot | -1.377 |
romeda | -1.367 |
Token | plan |
Token ID | 1410 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
ulf | +0.843 |
rer | +0.827 |
Mouth | +0.768 |
IPM | +0.741 |
ê | +0.731 |
Neg logit contributions | |
ilitarian | -0.919 |
>) | -0.886 |
xxxxxxxx | -0.797 |
romeda | -0.789 |
spot | -0.787 |
Token | we |
Token ID | 356 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
ulf | +2.903 |
rer | +2.871 |
Mouth | +2.623 |
ê | +2.558 |
IPM | +2.490 |
Neg logit contributions | |
ilitarian | -3.431 |
>) | -3.309 |
romeda | -2.937 |
xxxxxxxx | -2.930 |
spot | -2.889 |
Token | put |
Token ID | 1234 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
ilitarian | +0.429 |
>) | +0.415 |
xxxxxxxx | +0.375 |
romeda | +0.371 |
spot | +0.371 |
Neg logit contributions | |
ulf | -0.382 |
rer | -0.374 |
Mouth | -0.345 |
IPM | -0.333 |
ê | -0.329 |
Token | together |
Token ID | 1978 |
Feature activation | +8.79e+00 |
Pos logit contributions | |
ulf | +1.624 |
rer | +1.586 |
Mouth | +1.450 |
IPM | +1.392 |
ê | +1.383 |
Neg logit contributions | |
ilitarian | -2.096 |
>) | -2.021 |
xxxxxxxx | -1.832 |
spot | -1.814 |
romeda | -1.807 |
Token | of |
Token ID | 286 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
ulf | +5.159 |
rer | +5.018 |
Mouth | +4.590 |
ê | +4.351 |
IPM | +4.319 |
Neg logit contributions | |
ilitarian | -6.892 |
>) | -6.527 |
xxxxxxxx | -5.851 |
romeda | -5.834 |
ozy | -5.721 |
Token | building |
Token ID | 2615 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
ulf | +2.991 |
rer | +2.914 |
Mouth | +2.726 |
IPM | +2.604 |
ê | +2.586 |
Neg logit contributions | |
ilitarian | -3.372 |
>) | -3.266 |
xxxxxxxx | -2.937 |
spot | -2.915 |
romeda | -2.875 |
Token | great |
Token ID | 1049 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
ulf | +1.964 |
rer | +1.931 |
Mouth | +1.807 |
IPM | +1.734 |
ê | +1.710 |
Neg logit contributions | |
ilitarian | -1.978 |
>) | -1.901 |
xxxxxxxx | -1.701 |
spot | -1.689 |
romeda | -1.676 |
Token | s |
Token ID | 82 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
ilitarian | +0.403 |
>) | +0.384 |
xxxxxxxx | +0.335 |
spot | +0.331 |
romeda | +0.329 |
Neg logit contributions | |
ulf | -0.595 |
rer | -0.584 |
Mouth | -0.550 |
IPM | -0.537 |
ê | -0.530 |
Token | prestige |
Token ID | 29063 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
ulf | +2.352 |
rer | +2.329 |
Mouth | +2.144 |
IPM | +2.076 |
ê | +2.075 |
Neg logit contributions | |
ilitarian | -2.285 |
>) | -2.200 |
xxxxxxxx | -1.968 |
romeda | -1.959 |
spot | -1.927 |
Token | to |
Token ID | 284 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
rer | +3.301 |
ulf | +3.277 |
Mouth | +2.939 |
ê | +2.891 |
deserts | +2.802 |
Neg logit contributions | |
ilitarian | -3.890 |
>) | -3.797 |
romeda | -3.452 |
xxxxxxxx | -3.385 |
spot | -3.340 |
Token | new |
Token ID | 649 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
ulf | +2.128 |
rer | +2.097 |
Mouth | +1.935 |
ê | +1.878 |
IPM | +1.865 |
Neg logit contributions | |
ilitarian | -2.117 |
>) | -2.068 |
xxxxxxxx | -1.846 |
romeda | -1.828 |
spot | -1.805 |
Token | heights |
Token ID | 23245 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
ilitarian | +0.067 |
>) | +0.064 |
xxxxxxxx | +0.056 |
romeda | +0.055 |
spot | +0.055 |
Neg logit contributions | |
ulf | -0.099 |
rer | -0.098 |
Mouth | -0.092 |
IPM | -0.089 |
ê | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
ulf | +3.056 |
rer | +3.025 |
Mouth | +2.716 |
ê | +2.635 |
IPM | +2.573 |
Neg logit contributions | |
ilitarian | -3.648 |
>) | -3.549 |
romeda | -3.190 |
xxxxxxxx | -3.161 |
spot | -3.126 |
Token |
|
Token ID | 198 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
ulf | +2.140 |
rer | +2.120 |
Mouth | +1.987 |
IPM | +1.887 |
ê | +1.881 |
Neg logit contributions | |
ilitarian | -2.398 |
>) | -2.292 |
romeda | -2.079 |
xxxxxxxx | -2.055 |
spot | -2.053 |
Token |
|
Token ID | 198 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
ulf | +1.541 |
rer | +1.517 |
Mouth | +1.385 |
ê | +1.339 |
IPM | +1.338 |
Neg logit contributions | |
ilitarian | -1.699 |
>) | -1.611 |
romeda | -1.475 |
xxxxxxxx | -1.437 |
spot | -1.434 |
Token | And |
Token ID | 1870 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
ulf | +1.799 |
rer | +1.776 |
Mouth | +1.607 |
ê | +1.568 |
IPM | +1.548 |
Neg logit contributions | |
ilitarian | -2.003 |
>) | -1.894 |
romeda | -1.741 |
xxxxxxxx | -1.688 |
spot | -1.686 |
Token | it |
Token ID | 340 |
Feature activation | +5.98e+00 |
Pos logit contributions | |
rer | +3.061 |
ulf | +3.052 |
Mouth | +2.796 |
IPM | +2.679 |
ê | +2.665 |
Neg logit contributions | |
ilitarian | -3.175 |
>) | -3.060 |
xxxxxxxx | -2.720 |
spot | -2.715 |
romeda | -2.610 |
Token | is |
Token ID | 318 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
rer | +3.791 |
ulf | +3.742 |
Mouth | +3.291 |
ê | +3.289 |
iner | +3.259 |
Neg logit contributions | |
ilitarian | -4.481 |
>) | -4.311 |
xxxxxxxx | -3.885 |
romeda | -3.877 |
Revival | -3.815 |
Token |
|
Token ID | 198 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
ulf | +1.992 |
rer | +1.967 |
Mouth | +1.789 |
ê | +1.728 |
IPM | +1.724 |
Neg logit contributions | |
ilitarian | -2.294 |
>) | -2.160 |
romeda | -1.997 |
xxxxxxxx | -1.928 |
spot | -1.926 |
Token | He |
Token ID | 1544 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
ilitarian | +3.129 |
>) | +3.076 |
xxxxxxxx | +2.813 |
spot | +2.744 |
romeda | +2.645 |
Neg logit contributions | |
ulf | -3.328 |
rer | -3.213 |
Mouth | -3.095 |
IPM | -2.996 |
deserts | -2.971 |
Token | added |
Token ID | 2087 |
Feature activation | +8.35e+00 |
Pos logit contributions | |
ulf | +1.516 |
rer | +1.488 |
Mouth | +1.343 |
ê | +1.308 |
IPM | +1.288 |
Neg logit contributions | |
ilitarian | -1.821 |
>) | -1.763 |
xxxxxxxx | -1.592 |
romeda | -1.575 |
spot | -1.563 |
Token | : |
Token ID | 25 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ulf | +4.737 |
rer | +4.727 |
Mouth | +4.196 |
ê | +4.029 |
IPM | +3.879 |
Neg logit contributions | |
ilitarian | -6.539 |
>) | -6.419 |
romeda | -5.797 |
xxxxxxxx | -5.777 |
spot | -5.731 |
Token | � |
Token ID | 564 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
ilitarian | +0.164 |
>) | +0.159 |
xxxxxxxx | +0.146 |
romeda | +0.145 |
spot | +0.144 |
Neg logit contributions | |
ulf | -0.108 |
rer | -0.105 |
Mouth | -0.095 |
IPM | -0.091 |
ê | -0.090 |
Token | � |
Token ID | 250 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ilitarian | +1.103 |
>) | +1.070 |
xxxxxxxx | +0.938 |
spot | +0.918 |
romeda | +0.906 |
Neg logit contributions | |
ulf | -1.596 |
rer | -1.569 |
Mouth | -1.478 |
IPM | -1.447 |
ê | -1.419 |
Token | Next |
Token ID | 10019 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
ulf | +0.919 |
rer | +0.902 |
Mouth | +0.828 |
ê | +0.802 |
IPM | +0.800 |
Neg logit contributions | |
ilitarian | -0.960 |
>) | -0.919 |
romeda | -0.825 |
xxxxxxxx | -0.822 |
spot | -0.813 |
Token | year |
Token ID | 614 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ilitarian | +2.492 |
>) | +2.444 |
xxxxxxxx | +2.182 |
spot | +2.129 |
Revival | +2.102 |
Neg logit contributions | |
ulf | -3.056 |
rer | -2.962 |
Mouth | -2.774 |
IPM | -2.718 |
ê | -2.667 |
Token | will |
Token ID | 481 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ilitarian | +0.764 |
>) | +0.737 |
xxxxxxxx | +0.662 |
spot | +0.654 |
romeda | +0.651 |
Neg logit contributions | |
ulf | -0.791 |
rer | -0.772 |
Mouth | -0.718 |
IPM | -0.698 |
ê | -0.688 |
Token | defin |
Token ID | 2730 |
Feature activation | +7.76e+00 |
Pos logit contributions | |
ilitarian | +0.678 |
>) | +0.654 |
xxxxxxxx | +0.583 |
spot | +0.577 |
romeda | +0.574 |
Neg logit contributions | |
ulf | -0.768 |
rer | -0.752 |
Mouth | -0.702 |
IPM | -0.682 |
ê | -0.674 |
Token | - |
Token ID | 12 |
Feature activation | -7.52e+00 |
Pos logit contributions | |
ulf | +4.958 |
rer | +4.899 |
ê | +4.412 |
Mouth | +4.409 |
ement | +4.206 |
Neg logit contributions | |
ilitarian | -5.736 |
>) | -5.381 |
romeda | -4.919 |
xxxxxxxx | -4.870 |
spot | -4.835 |
Token | a |
Token ID | 257 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
ulf | +1.868 |
rer | +1.837 |
Mouth | +1.704 |
IPM | +1.643 |
ê | +1.635 |
Neg logit contributions | |
ilitarian | -1.824 |
>) | -1.756 |
xxxxxxxx | -1.573 |
romeda | -1.563 |
spot | -1.539 |
Token | guide |
Token ID | 5698 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
ulf | +1.492 |
rer | +1.466 |
Mouth | +1.350 |
IPM | +1.292 |
ê | +1.285 |
Neg logit contributions | |
ilitarian | -1.788 |
>) | -1.739 |
xxxxxxxx | -1.576 |
romeda | -1.568 |
spot | -1.543 |
Token | book |
Token ID | 2070 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
ulf | +2.078 |
rer | +2.069 |
Mouth | +1.855 |
ê | +1.820 |
IPM | +1.793 |
Neg logit contributions | |
ilitarian | -2.308 |
>) | -2.247 |
xxxxxxxx | -2.019 |
romeda | -2.009 |
spot | -1.951 |
Token | about |
Token ID | 546 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ilitarian | +0.444 |
>) | +0.426 |
xxxxxxxx | +0.380 |
spot | +0.376 |
romeda | +0.376 |
Neg logit contributions | |
ulf | -0.484 |
rer | -0.475 |
Mouth | -0.442 |
IPM | -0.429 |
ê | -0.424 |
Token | public |
Token ID | 1171 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
ulf | +0.947 |
rer | +0.931 |
Mouth | +0.866 |
IPM | +0.842 |
ê | +0.835 |
Neg logit contributions | |
ilitarian | -0.848 |
>) | -0.819 |
xxxxxxxx | -0.729 |
romeda | -0.721 |
spot | -0.719 |
Token | stair |
Token ID | 18761 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
ilitarian | +1.552 |
>) | +1.491 |
xxxxxxxx | +1.334 |
spot | +1.315 |
romeda | +1.311 |
Neg logit contributions | |
ulf | -1.753 |
rer | -1.716 |
Mouth | -1.602 |
IPM | -1.558 |
ê | -1.527 |
Token | ways |
Token ID | 1322 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
ulf | +0.117 |
rer | +0.115 |
Mouth | +0.105 |
IPM | +0.101 |
ê | +0.100 |
Neg logit contributions | |
ilitarian | -0.144 |
>) | -0.140 |
xxxxxxxx | -0.127 |
romeda | -0.125 |
spot | -0.125 |
Token | in |
Token ID | 287 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
ulf | +1.599 |
rer | +1.571 |
Mouth | +1.437 |
ê | +1.394 |
IPM | +1.394 |
Neg logit contributions | |
ilitarian | -1.680 |
>) | -1.631 |
romeda | -1.460 |
xxxxxxxx | -1.460 |
spot | -1.435 |
Token | Los |
Token ID | 5401 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
ulf | +3.656 |
rer | +3.615 |
Mouth | +3.415 |
deserts | +3.280 |
IPM | +3.259 |
Neg logit contributions | |
ilitarian | -3.777 |
>) | -3.627 |
romeda | -3.319 |
xxxxxxxx | -3.269 |
spot | -3.250 |
Token | Angeles |
Token ID | 5652 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
ulf | +2.963 |
rer | +2.841 |
Mouth | +2.648 |
ê | +2.548 |
IPM | +2.507 |
Neg logit contributions | |
ilitarian | -3.427 |
>) | -3.224 |
romeda | -2.922 |
spot | -2.915 |
xxxxxxxx | -2.898 |
Token | and |
Token ID | 290 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
ulf | +0.574 |
rer | +0.563 |
Mouth | +0.521 |
IPM | +0.504 |
ê | +0.501 |
Neg logit contributions | |
ilitarian | -0.579 |
>) | -0.559 |
xxxxxxxx | -0.501 |
romeda | -0.497 |
spot | -0.493 |
Token | said |
Token ID | 531 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
ilitarian | +3.342 |
>) | +3.248 |
weighed | +2.937 |
xxxxxxxx | +2.912 |
romeda | +2.911 |
Neg logit contributions | |
ulf | -3.253 |
rer | -3.156 |
Mouth | -2.928 |
IPM | -2.880 |
ê | -2.828 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ulf | +0.414 |
rer | +0.406 |
Mouth | +0.375 |
IPM | +0.362 |
ê | +0.359 |
Neg logit contributions | |
ilitarian | -0.429 |
>) | -0.414 |
xxxxxxxx | -0.371 |
romeda | -0.367 |
spot | -0.366 |
Token |
|
Token ID | 198 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
ulf | +0.085 |
rer | +0.083 |
Mouth | +0.077 |
IPM | +0.075 |
ê | +0.074 |
Neg logit contributions | |
ilitarian | -0.085 |
>) | -0.082 |
xxxxxxxx | -0.073 |
romeda | -0.072 |
spot | -0.072 |
Token |
|
Token ID | 198 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ulf | +0.538 |
rer | +0.528 |
Mouth | +0.487 |
IPM | +0.472 |
ê | +0.469 |
Neg logit contributions | |
ilitarian | -0.542 |
>) | -0.518 |
romeda | -0.464 |
xxxxxxxx | -0.464 |
spot | -0.459 |
Token | Council |
Token ID | 40940 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
ulf | +1.005 |
rer | +0.986 |
Mouth | +0.905 |
ê | +0.879 |
IPM | +0.874 |
Neg logit contributions | |
ilitarian | -0.984 |
>) | -0.936 |
romeda | -0.841 |
xxxxxxxx | -0.831 |
spot | -0.824 |
Token | member |
Token ID | 2888 |
Feature activation | +6.30e+00 |
Pos logit contributions | |
ilitarian | +0.451 |
>) | +0.435 |
xxxxxxxx | +0.386 |
spot | +0.382 |
romeda | +0.381 |
Neg logit contributions | |
ulf | -0.516 |
rer | -0.506 |
Mouth | -0.471 |
IPM | -0.458 |
ê | -0.454 |
Token | John |
Token ID | 1757 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
rer | +4.462 |
ulf | +4.462 |
Mouth | +4.189 |
IPM | +4.015 |
ê | +3.886 |
Neg logit contributions | |
ilitarian | -4.229 |
>) | -4.016 |
xxxxxxxx | -3.576 |
romeda | -3.552 |
spot | -3.471 |
Token | Elder |
Token ID | 15624 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ilitarian | +2.147 |
>) | +2.062 |
xxxxxxxx | +1.861 |
spot | +1.847 |
Eliot | +1.836 |
Neg logit contributions | |
ulf | -2.224 |
rer | -2.161 |
Mouth | -1.993 |
IPM | -1.975 |
ê | -1.930 |
Token | , |
Token ID | 11 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
ilitarian | +0.857 |
>) | +0.825 |
xxxxxxxx | +0.739 |
spot | +0.735 |
romeda | +0.732 |
Neg logit contributions | |
ulf | -0.856 |
rer | -0.838 |
Mouth | -0.778 |
IPM | -0.758 |
ê | -0.748 |
Token | who |
Token ID | 508 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
rer | +3.015 |
ulf | +3.014 |
Mouth | +2.792 |
IPM | +2.664 |
ê | +2.614 |
Neg logit contributions | |
ilitarian | -3.127 |
>) | -2.997 |
xxxxxxxx | -2.703 |
spot | -2.658 |
romeda | -2.641 |
Token | is |
Token ID | 318 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ulf | +2.060 |
rer | +2.054 |
Mouth | +1.879 |
IPM | +1.822 |
ê | +1.802 |
Neg logit contributions | |
ilitarian | -2.054 |
>) | -1.961 |
xxxxxxxx | -1.753 |
romeda | -1.749 |
spot | -1.722 |
Token | overall |
Token ID | 4045 |
Feature activation | +4.98e+00 |
Pos logit contributions | |
rer | +4.264 |
ulf | +4.233 |
Mouth | +4.075 |
deserts | +3.835 |
IPM | +3.820 |
Neg logit contributions | |
ilitarian | -5.207 |
>) | -5.047 |
xxxxxxxx | -4.485 |
romeda | -4.453 |
spot | -4.431 |
Token | . |
Token ID | 13 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
rer | +3.242 |
ulf | +3.231 |
Mouth | +2.983 |
ê | +2.879 |
IPM | +2.867 |
Neg logit contributions | |
ilitarian | -3.618 |
>) | -3.501 |
xxxxxxxx | -3.113 |
romeda | -3.088 |
spot | -3.040 |
Token | � |
Token ID | 447 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
ilitarian | +1.330 |
>) | +1.286 |
xxxxxxxx | +1.163 |
spot | +1.140 |
romeda | +1.136 |
Neg logit contributions | |
ulf | -1.413 |
rer | -1.383 |
Mouth | -1.271 |
IPM | -1.244 |
ê | -1.230 |
Token | � |
Token ID | 251 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
ulf | +0.702 |
rer | +0.688 |
Mouth | +0.639 |
IPM | +0.620 |
ê | +0.616 |
Neg logit contributions | |
ilitarian | -0.646 |
>) | -0.618 |
xxxxxxxx | -0.551 |
romeda | -0.546 |
spot | -0.545 |
Token |
|
Token ID | 198 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
ilitarian | +0.396 |
>) | +0.382 |
xxxxxxxx | +0.343 |
spot | +0.338 |
romeda | +0.338 |
Neg logit contributions | |
ulf | -0.414 |
rer | -0.406 |
Mouth | -0.376 |
IPM | -0.365 |
ê | -0.361 |
Token |
|
Token ID | 198 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
ulf | +0.457 |
rer | +0.449 |
Mouth | +0.415 |
IPM | +0.402 |
ê | +0.399 |
Neg logit contributions | |
ilitarian | -0.458 |
>) | -0.439 |
xxxxxxxx | -0.392 |
romeda | -0.392 |
spot | -0.388 |
Token | The |
Token ID | 464 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
ilitarian | +1.524 |
>) | +1.490 |
xxxxxxxx | +1.356 |
spot | +1.328 |
romeda | +1.300 |
Neg logit contributions | |
ulf | -1.603 |
rer | -1.568 |
Mouth | -1.465 |
IPM | -1.429 |
ê | -1.392 |
Token | same |
Token ID | 976 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
ulf | +3.486 |
rer | +3.467 |
Mouth | +3.286 |
IPM | +3.125 |
ê | +3.088 |
Neg logit contributions | |
ilitarian | -3.631 |
>) | -3.495 |
xxxxxxxx | -3.085 |
spot | -3.057 |
romeda | -3.055 |
Token | applies |
Token ID | 8991 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
ilitarian | +1.080 |
>) | +1.045 |
xxxxxxxx | +0.939 |
spot | +0.927 |
romeda | +0.923 |
Neg logit contributions | |
ulf | -1.142 |
rer | -1.125 |
Mouth | -1.039 |
IPM | -1.010 |
ê | -1.001 |
Token | to |
Token ID | 284 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
ulf | +1.482 |
rer | +1.462 |
Mouth | +1.336 |
IPM | +1.280 |
ê | +1.277 |
Neg logit contributions | |
ilitarian | -1.671 |
>) | -1.619 |
xxxxxxxx | -1.451 |
romeda | -1.438 |
spot | -1.433 |
Token | De |
Token ID | 1024 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
ulf | +0.379 |
rer | +0.372 |
Mouth | +0.346 |
IPM | +0.335 |
ê | +0.332 |
Neg logit contributions | |
ilitarian | -0.367 |
>) | -0.354 |
xxxxxxxx | -0.316 |
romeda | -0.313 |
spot | -0.312 |
Token | latest |
Token ID | 3452 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
ulf | +0.920 |
rer | +0.908 |
Mouth | +0.842 |
IPM | +0.810 |
ê | +0.796 |
Neg logit contributions | |
ilitarian | -0.998 |
>) | -0.960 |
xxxxxxxx | -0.865 |
romeda | -0.854 |
spot | -0.851 |
Token | C |
Token ID | 327 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
ulf | +3.503 |
rer | +3.429 |
Mouth | +3.233 |
IPM | +3.112 |
ê | +3.034 |
Neg logit contributions | |
ilitarian | -3.667 |
>) | -3.486 |
xxxxxxxx | -3.122 |
romeda | -3.091 |
spot | -3.042 |
Token | rave |
Token ID | 5758 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
ilitarian | +0.847 |
>) | +0.816 |
xxxxxxxx | +0.729 |
spot | +0.720 |
romeda | +0.719 |
Neg logit contributions | |
ulf | -0.955 |
rer | -0.938 |
Mouth | -0.881 |
IPM | -0.856 |
ê | -0.840 |
Token | Cast |
Token ID | 19248 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ilitarian | +3.950 |
>) | +3.826 |
spot | +3.484 |
xxxxxxxx | +3.456 |
weighed | +3.408 |
Neg logit contributions | |
ulf | -3.803 |
rer | -3.717 |
Mouth | -3.400 |
IPM | -3.347 |
ê | -3.301 |
Token | podcast |
Token ID | 9905 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
ilitarian | +0.937 |
>) | +0.904 |
xxxxxxxx | +0.814 |
spot | +0.810 |
romeda | +0.804 |
Neg logit contributions | |
ulf | -0.904 |
rer | -0.884 |
Mouth | -0.819 |
IPM | -0.794 |
ê | -0.785 |
Token | here |
Token ID | 994 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
ilitarian | +0.556 |
>) | +0.536 |
xxxxxxxx | +0.482 |
spot | +0.477 |
romeda | +0.475 |
Neg logit contributions | |
ulf | -0.559 |
rer | -0.548 |
Mouth | -0.508 |
IPM | -0.492 |
ê | -0.488 |
Token | ! |
Token ID | 0 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
ilitarian | +2.940 |
>) | +2.853 |
spot | +2.596 |
xxxxxxxx | +2.570 |
romeda | +2.502 |
Neg logit contributions | |
ulf | -3.235 |
rer | -3.181 |
Mouth | -2.969 |
IPM | -2.903 |
ê | -2.849 |
Token |
|
Token ID | 198 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
ilitarian | +0.536 |
>) | +0.519 |
xxxxxxxx | +0.467 |
spot | +0.461 |
romeda | +0.461 |
Neg logit contributions | |
ulf | -0.518 |
rer | -0.507 |
Mouth | -0.468 |
IPM | -0.454 |
ê | -0.450 |
Token |
|
Token ID | 198 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ilitarian | +2.007 |
>) | +1.995 |
xxxxxxxx | +1.794 |
spot | +1.747 |
Eliot | +1.673 |
Neg logit contributions | |
ulf | -2.585 |
rer | -2.517 |
Mouth | -2.377 |
� | -2.322 |
IPM | -2.313 |
Token | C |
Token ID | 34 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
ulf | +0.112 |
rer | +0.109 |
Mouth | +0.101 |
IPM | +0.097 |
ê | +0.097 |
Neg logit contributions | |
ilitarian | -0.124 |
>) | -0.119 |
xxxxxxxx | -0.107 |
romeda | -0.106 |
spot | -0.106 |
Token | rave |
Token ID | 5758 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
ilitarian | +3.052 |
>) | +2.938 |
xxxxxxxx | +2.655 |
spot | +2.610 |
romeda | +2.593 |
Neg logit contributions | |
ulf | -3.565 |
rer | -3.489 |
Mouth | -3.359 |
IPM | -3.273 |
deserts | -3.163 |
Token | oms |
Token ID | 3150 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
ilitarian | +0.386 |
>) | +0.371 |
xxxxxxxx | +0.332 |
romeda | +0.328 |
spot | +0.327 |
Neg logit contributions | |
ulf | -0.416 |
rer | -0.409 |
Mouth | -0.380 |
IPM | -0.368 |
ê | -0.365 |
Token | be |
Token ID | 307 |
Feature activation | -6.42e+00 |
Pos logit contributions | |
ilitarian | +2.315 |
>) | +2.255 |
xxxxxxxx | +2.014 |
spot | +2.004 |
romeda | +1.984 |
Neg logit contributions | |
ulf | -2.201 |
rer | -2.141 |
Mouth | -1.970 |
IPM | -1.926 |
ê | -1.886 |
Token | taken |
Token ID | 2077 |
Feature activation | -5.19e+00 |
Pos logit contributions | |
ilitarian | +4.146 |
>) | +4.014 |
weighed | +3.660 |
spot | +3.649 |
romeda | +3.567 |
Neg logit contributions | |
ulf | -4.558 |
rer | -4.456 |
Mouth | -4.108 |
IPM | -3.982 |
OTOS | -3.956 |
Token | seriously |
Token ID | 6411 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
ilitarian | +3.328 |
>) | +3.259 |
spot | +2.905 |
xxxxxxxx | +2.887 |
romeda | +2.858 |
Neg logit contributions | |
ulf | -3.736 |
rer | -3.655 |
Mouth | -3.414 |
IPM | -3.344 |
ê | -3.291 |
Token | by |
Token ID | 416 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
ilitarian | +1.189 |
>) | +1.142 |
xxxxxxxx | +1.013 |
spot | +1.001 |
romeda | +0.996 |
Neg logit contributions | |
ulf | -1.366 |
rer | -1.344 |
Mouth | -1.250 |
IPM | -1.214 |
ê | -1.204 |
Token | audi |
Token ID | 40504 |
Feature activation | -8.53e+00 |
Pos logit contributions | |
ulf | +0.150 |
rer | +0.147 |
Mouth | +0.137 |
IPM | +0.132 |
ê | +0.131 |
Neg logit contributions | |
ilitarian | -0.156 |
>) | -0.150 |
xxxxxxxx | -0.135 |
romeda | -0.134 |
spot | -0.133 |
Token | oph |
Token ID | 2522 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ilitarian | +3.214 |
>) | +3.048 |
spot | +2.580 |
xxxxxxxx | +2.503 |
weighed | +2.425 |
Neg logit contributions | |
ulf | -8.214 |
rer | -8.124 |
Mouth | -7.640 |
IPM | -7.479 |
OTOS | -7.466 |
Token | iles |
Token ID | 2915 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
ilitarian | +0.775 |
>) | +0.745 |
xxxxxxxx | +0.670 |
romeda | +0.664 |
spot | +0.662 |
Neg logit contributions | |
ulf | -0.761 |
rer | -0.747 |
Mouth | -0.693 |
IPM | -0.670 |
ê | -0.660 |
Token | ? |
Token ID | 30 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
ulf | +1.202 |
rer | +1.180 |
Mouth | +1.096 |
IPM | +1.056 |
ê | +1.050 |
Neg logit contributions | |
ilitarian | -1.159 |
>) | -1.116 |
xxxxxxxx | -0.999 |
romeda | -0.992 |
spot | -0.981 |
Token | For |
Token ID | 1114 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
ulf | +0.270 |
rer | +0.265 |
Mouth | +0.247 |
IPM | +0.238 |
ê | +0.236 |
Neg logit contributions | |
ilitarian | -0.268 |
>) | -0.258 |
xxxxxxxx | -0.231 |
romeda | -0.229 |
spot | -0.228 |
Token | their |
Token ID | 511 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
ulf | +1.298 |
rer | +1.280 |
Mouth | +1.184 |
IPM | +1.149 |
ê | +1.133 |
Neg logit contributions | |
ilitarian | -1.340 |
>) | -1.297 |
xxxxxxxx | -1.167 |
romeda | -1.156 |
spot | -1.145 |
Token | percent |
Token ID | 1411 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
ulf | +1.521 |
rer | +1.495 |
Mouth | +1.362 |
ê | +1.315 |
IPM | +1.310 |
Neg logit contributions | |
ilitarian | -1.755 |
>) | -1.700 |
xxxxxxxx | -1.535 |
romeda | -1.526 |
spot | -1.495 |
Token | drop |
Token ID | 4268 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
ilitarian | +2.706 |
>) | +2.621 |
spot | +2.345 |
xxxxxxxx | +2.302 |
weighed | +2.284 |
Neg logit contributions | |
ulf | -3.101 |
rer | -2.990 |
Mouth | -2.787 |
IPM | -2.719 |
ê | -2.679 |
Token | in |
Token ID | 287 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
ilitarian | +3.112 |
>) | +2.932 |
spot | +2.686 |
xxxxxxxx | +2.632 |
weighed | +2.595 |
Neg logit contributions | |
ulf | -3.519 |
rer | -3.419 |
Mouth | -3.236 |
IPM | -3.175 |
ê | -3.070 |
Token | enrollment |
Token ID | 20753 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
ilitarian | +2.466 |
>) | +2.384 |
xxxxxxxx | +2.101 |
spot | +2.083 |
Eliot | +2.073 |
Neg logit contributions | |
ulf | -3.190 |
rer | -3.075 |
Mouth | -2.883 |
ê | -2.792 |
IPM | -2.790 |
Token | . |
Token ID | 13 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
ilitarian | +2.607 |
>) | +2.513 |
spot | +2.249 |
xxxxxxxx | +2.241 |
weighed | +2.216 |
Neg logit contributions | |
ulf | -3.022 |
rer | -2.941 |
Mouth | -2.773 |
IPM | -2.729 |
ê | -2.650 |
Token | Students |
Token ID | 14882 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
ulf | +0.410 |
rer | +0.403 |
Mouth | +0.374 |
IPM | +0.362 |
ê | +0.358 |
Neg logit contributions | |
ilitarian | -0.408 |
>) | -0.392 |
xxxxxxxx | -0.352 |
romeda | -0.349 |
spot | -0.348 |
Token | who |
Token ID | 508 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
ilitarian | +2.075 |
>) | +2.006 |
xxxxxxxx | +1.767 |
spot | +1.764 |
weighed | +1.761 |
Neg logit contributions | |
ulf | -2.400 |
rer | -2.334 |
Mouth | -2.202 |
IPM | -2.145 |
ê | -2.134 |
Token | were |
Token ID | 547 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
ilitarian | +0.103 |
>) | +0.099 |
xxxxxxxx | +0.088 |
romeda | +0.087 |
spot | +0.087 |
Neg logit contributions | |
ulf | -0.111 |
rer | -0.108 |
Mouth | -0.101 |
IPM | -0.098 |
ê | -0.097 |
Token | no |
Token ID | 645 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ilitarian | +2.503 |
>) | +2.422 |
spot | +2.141 |
weighed | +2.136 |
Eliot | +2.116 |
Neg logit contributions | |
ulf | -2.710 |
rer | -2.651 |
Mouth | -2.468 |
ê | -2.393 |
IPM | -2.381 |
Token | longer |
Token ID | 2392 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
ilitarian | +0.982 |
>) | +0.955 |
xxxxxxxx | +0.879 |
spot | +0.872 |
romeda | +0.869 |
Neg logit contributions | |
ulf | -0.534 |
rer | -0.519 |
Mouth | -0.465 |
IPM | -0.446 |
ê | -0.435 |
Token | eligible |
Token ID | 8867 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
ilitarian | +4.164 |
>) | +4.049 |
weighed | +3.672 |
spot | +3.604 |
Eliot | +3.575 |
Neg logit contributions | |
ulf | -4.875 |
rer | -4.795 |
Mouth | -4.534 |
ê | -4.402 |
IPM | -4.375 |
Token | Britain |
Token ID | 5491 |
Feature activation | +4.32e+00 |
Pos logit contributions | |
ilitarian | +0.168 |
>) | +0.161 |
xxxxxxxx | +0.145 |
romeda | +0.143 |
spot | +0.143 |
Neg logit contributions | |
ulf | -0.170 |
rer | -0.167 |
Mouth | -0.154 |
IPM | -0.150 |
ê | -0.148 |
Token | should |
Token ID | 815 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
ulf | +2.748 |
rer | +2.710 |
Mouth | +2.452 |
ê | +2.349 |
IPM | +2.327 |
Neg logit contributions | |
ilitarian | -3.262 |
>) | -3.161 |
romeda | -2.856 |
xxxxxxxx | -2.845 |
Eliot | -2.776 |
Token | rival |
Token ID | 8976 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
ilitarian | +1.415 |
>) | +1.367 |
xxxxxxxx | +1.223 |
spot | +1.216 |
romeda | +1.210 |
Neg logit contributions | |
ulf | -1.392 |
rer | -1.361 |
Mouth | -1.278 |
IPM | -1.226 |
ê | -1.213 |
Token | Dubai |
Token ID | 24520 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
ulf | +2.027 |
rer | +1.985 |
Mouth | +1.842 |
IPM | +1.773 |
ê | +1.767 |
Neg logit contributions | |
ilitarian | -1.856 |
>) | -1.799 |
xxxxxxxx | -1.600 |
romeda | -1.594 |
spot | -1.570 |
Token | as |
Token ID | 355 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
ilitarian | +1.966 |
>) | +1.882 |
xxxxxxxx | +1.688 |
spot | +1.675 |
romeda | +1.661 |
Neg logit contributions | |
ulf | -2.089 |
rer | -2.054 |
Mouth | -1.901 |
IPM | -1.871 |
ê | -1.833 |
Token | one |
Token ID | 530 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
ilitarian | +1.263 |
>) | +1.213 |
xxxxxxxx | +1.083 |
spot | +1.076 |
romeda | +1.065 |
Neg logit contributions | |
ulf | -1.395 |
rer | -1.372 |
Mouth | -1.278 |
IPM | -1.248 |
ê | -1.229 |
Token | of |
Token ID | 286 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
ilitarian | +1.937 |
>) | +1.849 |
xxxxxxxx | +1.661 |
spot | +1.657 |
romeda | +1.622 |
Neg logit contributions | |
ulf | -2.121 |
rer | -2.085 |
Mouth | -1.952 |
IPM | -1.901 |
ê | -1.878 |
Token | the |
Token ID | 262 |
Feature activation | -7.17e+00 |
Pos logit contributions | |
ulf | +0.321 |
rer | +0.314 |
Mouth | +0.292 |
IPM | +0.283 |
ê | +0.281 |
Neg logit contributions | |
ilitarian | -0.296 |
>) | -0.285 |
xxxxxxxx | -0.254 |
romeda | -0.251 |
spot | -0.251 |
Token | � |
Token ID | 564 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
ilitarian | +3.899 |
>) | +3.701 |
spot | +3.271 |
xxxxxxxx | +3.254 |
Revival | +3.218 |
Neg logit contributions | |
ulf | -5.693 |
rer | -5.655 |
Mouth | -5.308 |
IPM | -5.218 |
ê | -5.189 |
Token | � |
Token ID | 250 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ulf | +3.273 |
rer | +3.210 |
Mouth | +2.940 |
ê | +2.884 |
IPM | +2.838 |
Neg logit contributions | |
ilitarian | -2.696 |
>) | -2.533 |
xxxxxxxx | -2.287 |
romeda | -2.284 |
spot | -2.213 |
Token | great |
Token ID | 18223 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
ilitarian | +0.782 |
>) | +0.751 |
xxxxxxxx | +0.663 |
spot | +0.658 |
romeda | +0.650 |
Neg logit contributions | |
ulf | -0.988 |
rer | -0.973 |
Mouth | -0.917 |
IPM | -0.892 |
ê | -0.877 |
Token | major |
Token ID | 1688 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
ilitarian | +1.695 |
>) | +1.631 |
xxxxxxxx | +1.460 |
spot | +1.454 |
romeda | +1.439 |
Neg logit contributions | |
ulf | -1.640 |
rer | -1.602 |
Mouth | -1.467 |
IPM | -1.428 |
ê | -1.420 |
Token | North |
Token ID | 2258 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
ilitarian | +1.833 |
>) | +1.773 |
xxxxxxxx | +1.582 |
spot | +1.581 |
romeda | +1.553 |
Neg logit contributions | |
ulf | -1.770 |
rer | -1.730 |
Mouth | -1.588 |
IPM | -1.539 |
ê | -1.536 |
Token | Sea |
Token ID | 6896 |
Feature activation | -5.39e+00 |
Pos logit contributions | |
ilitarian | +1.902 |
>) | +1.863 |
spot | +1.615 |
xxxxxxxx | +1.609 |
romeda | +1.591 |
Neg logit contributions | |
ulf | -2.508 |
rer | -2.486 |
Mouth | -2.289 |
IPM | -2.256 |
ê | -2.226 |
Token | oil |
Token ID | 3056 |
Feature activation | -9.98e+00 |
Pos logit contributions | |
ilitarian | +3.380 |
>) | +3.310 |
spot | +2.915 |
xxxxxxxx | +2.877 |
Revival | +2.873 |
Neg logit contributions | |
ulf | -4.013 |
rer | -3.892 |
Mouth | -3.608 |
IPM | -3.515 |
ê | -3.508 |
Token | field |
Token ID | 2214 |
Feature activation | -9.09e+00 |
Pos logit contributions | |
ilitarian | +5.682 |
>) | +5.622 |
spot | +5.314 |
weighed | +4.968 |
Revival | +4.931 |
Neg logit contributions | |
ulf | -7.318 |
rer | -6.997 |
Mouth | -6.763 |
IPM | -6.731 |
エル | -6.560 |
Token | coming |
Token ID | 2406 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
ilitarian | +5.471 |
>) | +5.294 |
spot | +4.989 |
weighed | +4.873 |
Revival | +4.731 |
Neg logit contributions | |
ulf | -6.597 |
rer | -6.219 |
Mouth | -5.931 |
ê | -5.756 |
IPM | -5.753 |
Token | back |
Token ID | 736 |
Feature activation | -1.54e+01 |
Pos logit contributions | |
>) | +7.433 |
ilitarian | +7.337 |
weighed | +6.925 |
spot | +6.903 |
Burnett | +6.611 |
Neg logit contributions | |
ulf | -10.127 |
IPM | -9.716 |
rer | -9.558 |
Mouth | -9.472 |
OTOS | -9.329 |
Token | on |
Token ID | 319 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
ilitarian | +6.995 |
>) | +6.790 |
weighed | +6.625 |
spot | +6.260 |
Burnett | +6.010 |
Neg logit contributions | |
ulf | -11.470 |
rer | -11.280 |
Mouth | -11.003 |
IPM | -10.848 |
OTOS | -10.626 |
Token | stream |
Token ID | 4269 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
ilitarian | +7.889 |
>) | +7.340 |
weighed | +7.222 |
Revival | +7.020 |
spot | +6.981 |
Neg logit contributions | |
ulf | -10.804 |
rer | -10.354 |
OTOS | -9.774 |
IPM | -9.745 |
Mouth | -9.744 |
Token | and |
Token ID | 290 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
ilitarian | +2.778 |
>) | +2.643 |
spot | +2.398 |
xxxxxxxx | +2.371 |
weighed | +2.364 |
Neg logit contributions | |
ulf | -3.178 |
rer | -3.098 |
Mouth | -2.923 |
IPM | -2.835 |
ê | -2.815 |
Token | a |
Token ID | 257 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
ilitarian | +3.837 |
>) | +3.776 |
weighed | +3.421 |
spot | +3.359 |
Eliot | +3.325 |
Neg logit contributions | |
ulf | -4.273 |
rer | -4.145 |
Mouth | -3.833 |
ê | -3.727 |
IPM | -3.692 |
Token | . |
Token ID | 13 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
ilitarian | +2.052 |
>) | +1.982 |
xxxxxxxx | +1.777 |
spot | +1.761 |
romeda | +1.748 |
Neg logit contributions | |
ulf | -2.306 |
rer | -2.248 |
Mouth | -2.104 |
IPM | -2.074 |
ê | -2.037 |
Token | I |
Token ID | 314 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
ilitarian | +1.524 |
>) | +1.481 |
xxxxxxxx | +1.329 |
spot | +1.307 |
Eliot | +1.300 |
Neg logit contributions | |
ulf | -1.671 |
rer | -1.637 |
Mouth | -1.493 |
IPM | -1.466 |
ê | -1.461 |
Token | was |
Token ID | 373 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ilitarian | +2.439 |
>) | +2.364 |
weighed | +2.135 |
xxxxxxxx | +2.131 |
spot | +2.118 |
Neg logit contributions | |
ulf | -2.603 |
rer | -2.541 |
Mouth | -2.386 |
IPM | -2.301 |
OTOS | -2.301 |
Token | so |
Token ID | 523 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ilitarian | +1.337 |
>) | +1.290 |
xxxxxxxx | +1.159 |
spot | +1.156 |
romeda | +1.151 |
Neg logit contributions | |
ulf | -1.352 |
rer | -1.327 |
Mouth | -1.221 |
IPM | -1.186 |
ê | -1.180 |
Token | desp |
Token ID | 11267 |
Feature activation | +6.90e+00 |
Pos logit contributions | |
ilitarian | +1.194 |
>) | +1.154 |
xxxxxxxx | +1.039 |
spot | +1.032 |
romeda | +1.028 |
Neg logit contributions | |
ulf | -1.198 |
rer | -1.172 |
Mouth | -1.083 |
IPM | -1.054 |
ê | -1.046 |
Token | ond |
Token ID | 623 |
Feature activation | -1.25e+01 |
Pos logit contributions | |
ulf | +2.133 |
rer | +1.934 |
ê | +1.488 |
Mouth | +1.424 |
iner | +1.402 |
Neg logit contributions | |
ilitarian | -7.417 |
>) | -7.383 |
xxxxxxxx | -6.943 |
Revival | -6.851 |
romeda | -6.844 |
Token | ent |
Token ID | 298 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
ilitarian | +5.865 |
>) | +5.694 |
weighed | +5.085 |
uration | +5.020 |
spot | +4.898 |
Neg logit contributions | |
ulf | -9.737 |
IPM | -9.707 |
rer | -9.595 |
OTOS | -9.537 |
Mouth | -9.520 |
Token | and |
Token ID | 290 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
ilitarian | +0.407 |
>) | +0.391 |
xxxxxxxx | +0.350 |
romeda | +0.346 |
spot | +0.346 |
Neg logit contributions | |
ulf | -0.431 |
rer | -0.423 |
Mouth | -0.392 |
IPM | -0.381 |
ê | -0.377 |
Token | depressed |
Token ID | 19095 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
ulf | +2.909 |
rer | +2.850 |
Mouth | +2.658 |
IPM | +2.526 |
deserts | +2.514 |
Neg logit contributions | |
ilitarian | -3.253 |
>) | -3.116 |
xxxxxxxx | -2.793 |
romeda | -2.744 |
spot | -2.721 |
Token | that |
Token ID | 326 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
ilitarian | +2.432 |
>) | +2.325 |
xxxxxxxx | +2.097 |
spot | +2.091 |
romeda | +2.080 |
Neg logit contributions | |
ulf | -2.802 |
rer | -2.764 |
Mouth | -2.557 |
IPM | -2.511 |
ê | -2.491 |
Token | I |
Token ID | 314 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ilitarian | +2.475 |
>) | +2.397 |
xxxxxxxx | +2.151 |
Eliot | +2.127 |
spot | +2.116 |
Neg logit contributions | |
ulf | -3.003 |
rer | -2.943 |
Mouth | -2.739 |
ê | -2.670 |
IPM | -2.666 |
Token | v |
Token ID | 85 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
ilitarian | +4.449 |
>) | +4.324 |
spot | +4.010 |
xxxxxxxx | +3.911 |
romeda | +3.710 |
Neg logit contributions | |
Mouth | -4.982 |
ulf | -4.963 |
� | -4.878 |
rer | -4.876 |
IPM | -4.735 |
Token | 2 |
Token ID | 17 |
Feature activation | -8.45e+00 |
Pos logit contributions | |
ilitarian | +1.914 |
>) | +1.885 |
xxxxxxxx | +1.668 |
spot | +1.661 |
romeda | +1.619 |
Neg logit contributions | |
ulf | -2.237 |
rer | -2.200 |
Mouth | -2.098 |
IPM | -2.036 |
ê | -1.994 |
Token | # |
Token ID | 1303 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ilitarian | +3.951 |
>) | +3.767 |
spot | +3.373 |
xxxxxxxx | +3.201 |
weighed | +3.189 |
Neg logit contributions | |
ulf | -7.288 |
rer | -7.036 |
Mouth | -6.745 |
ê | -6.728 |
エル | -6.620 |
Token | construct |
Token ID | 5678 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
ilitarian | +1.477 |
>) | +1.441 |
xxxxxxxx | +1.332 |
spot | +1.312 |
romeda | +1.303 |
Neg logit contributions | |
ulf | -0.860 |
rer | -0.832 |
Mouth | -0.754 |
IPM | -0.719 |
ê | -0.710 |
Token | the |
Token ID | 262 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
ulf | +1.375 |
rer | +1.351 |
Mouth | +1.247 |
IPM | +1.206 |
ê | +1.196 |
Neg logit contributions | |
ilitarian | -1.377 |
>) | -1.322 |
romeda | -1.183 |
xxxxxxxx | -1.177 |
spot | -1.172 |
Token | argument |
Token ID | 4578 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
rer | +3.022 |
ulf | +2.970 |
IPM | +2.630 |
Mouth | +2.624 |
ê | +2.513 |
Neg logit contributions | |
ilitarian | -4.370 |
>) | -4.184 |
romeda | -3.846 |
spot | -3.831 |
xxxxxxxx | -3.799 |
Token | parse |
Token ID | 21136 |
Feature activation | -6.15e+00 |
Pos logit contributions | |
ilitarian | +6.070 |
>) | +6.002 |
xxxxxxxx | +5.683 |
borrow | +5.310 |
Eliot | +5.174 |
Neg logit contributions | |
ulf | -9.717 |
rer | -9.345 |
Mouth | -9.141 |
� | -9.136 |
エル | -9.105 |
Token | and |
Token ID | 290 |
Feature activation | -8.27e+00 |
Pos logit contributions | |
ilitarian | +3.492 |
>) | +3.418 |
xxxxxxxx | +3.112 |
spot | +2.974 |
Eliot | +2.970 |
Neg logit contributions | |
ulf | -4.722 |
rer | -4.582 |
Mouth | -4.367 |
� | -4.343 |
IPM | -4.298 |
Token | parse |
Token ID | 21136 |
Feature activation | -7.76e+00 |
Pos logit contributions | |
ilitarian | +4.681 |
>) | +4.593 |
xxxxxxxx | +4.173 |
romeda | +4.004 |
spot | +3.994 |
Neg logit contributions | |
ulf | -6.404 |
rer | -6.198 |
Mouth | -5.984 |
� | -5.773 |
エル | -5.772 |
Token | the |
Token ID | 262 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
ilitarian | +3.829 |
>) | +3.780 |
xxxxxxxx | +3.325 |
weighed | +3.194 |
Eliot | +3.172 |
Neg logit contributions | |
ulf | -6.429 |
rer | -6.276 |
� | -5.989 |
Mouth | -5.929 |
エル | -5.862 |
Token | arguments |
Token ID | 7159 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
ulf | +2.043 |
rer | +2.016 |
Mouth | +1.837 |
IPM | +1.797 |
deserts | +1.750 |
Neg logit contributions | |
ilitarian | -2.712 |
>) | -2.585 |
spot | -2.365 |
xxxxxxxx | -2.345 |
romeda | -2.341 |
Token | able |
Token ID | 1498 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
ulf | +3.015 |
rer | +2.979 |
Mouth | +2.779 |
IPM | +2.646 |
deserts | +2.625 |
Neg logit contributions | |
ilitarian | -3.240 |
>) | -3.102 |
xxxxxxxx | -2.777 |
romeda | -2.719 |
spot | -2.680 |
Token | to |
Token ID | 284 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
ulf | +0.253 |
rer | +0.248 |
Mouth | +0.229 |
IPM | +0.221 |
ê | +0.219 |
Neg logit contributions | |
ilitarian | -0.267 |
>) | -0.257 |
xxxxxxxx | -0.230 |
romeda | -0.229 |
spot | -0.228 |
Token | get |
Token ID | 651 |
Feature activation | -7.15e+00 |
Pos logit contributions | |
ulf | +0.315 |
rer | +0.308 |
Mouth | +0.284 |
IPM | +0.275 |
ê | +0.271 |
Neg logit contributions | |
ilitarian | -0.360 |
>) | -0.348 |
xxxxxxxx | -0.314 |
romeda | -0.311 |
spot | -0.310 |
Token | back |
Token ID | 736 |
Feature activation | -6.86e+00 |
Pos logit contributions | |
ilitarian | +4.409 |
>) | +4.328 |
weighed | +3.992 |
Revival | +3.921 |
xxxxxxxx | +3.919 |
Neg logit contributions | |
ulf | -5.161 |
rer | -4.972 |
Mouth | -4.637 |
ê | -4.612 |
IPM | -4.542 |
Token | on |
Token ID | 319 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
ilitarian | +4.048 |
>) | +3.922 |
xxxxxxxx | +3.599 |
weighed | +3.575 |
spot | +3.546 |
Neg logit contributions | |
ulf | -5.177 |
rer | -5.053 |
Mouth | -4.750 |
IPM | -4.689 |
ê | -4.628 |
Token | the |
Token ID | 262 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
ilitarian | +5.771 |
>) | +5.470 |
spot | +5.261 |
weighed | +5.071 |
Eliot | +5.067 |
Neg logit contributions | |
ulf | -9.073 |
rer | -8.734 |
Mouth | -8.293 |
IPM | -8.229 |
ê | -8.168 |
Token | court |
Token ID | 2184 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
ilitarian | +6.464 |
>) | +6.302 |
spot | +6.057 |
Eliot | +5.858 |
Revival | +5.774 |
Neg logit contributions | |
ulf | -12.201 |
rer | -11.667 |
Mouth | -11.102 |
� | -11.084 |
ê | -10.916 |
Token | at |
Token ID | 379 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
ilitarian | +1.873 |
>) | +1.795 |
xxxxxxxx | +1.638 |
romeda | +1.610 |
spot | +1.610 |
Neg logit contributions | |
ulf | -2.041 |
rer | -2.003 |
Mouth | -1.852 |
IPM | -1.813 |
ê | -1.806 |
Token | the |
Token ID | 262 |
Feature activation | -6.61e+00 |
Pos logit contributions | |
ulf | +0.674 |
rer | +0.661 |
Mouth | +0.615 |
IPM | +0.597 |
ê | +0.588 |
Neg logit contributions | |
ilitarian | -0.658 |
>) | -0.634 |
xxxxxxxx | -0.566 |
romeda | -0.560 |
spot | -0.557 |
Token | beginning |
Token ID | 3726 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
ilitarian | +3.954 |
>) | +3.908 |
xxxxxxxx | +3.511 |
spot | +3.456 |
Revival | +3.429 |
Neg logit contributions | |
ulf | -5.066 |
rer | -4.988 |
Mouth | -4.500 |
ê | -4.477 |
� | -4.415 |
Token | of |
Token ID | 286 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ilitarian | +1.346 |
>) | +1.291 |
xxxxxxxx | +1.173 |
spot | +1.158 |
romeda | +1.143 |
Neg logit contributions | |
ulf | -1.438 |
rer | -1.412 |
Mouth | -1.308 |
IPM | -1.275 |
ê | -1.265 |
Token | also |
Token ID | 635 |
Feature activation | -6.62e+00 |
Pos logit contributions | |
ilitarian | +3.416 |
>) | +3.344 |
weighed | +3.024 |
spot | +2.979 |
xxxxxxxx | +2.969 |
Neg logit contributions | |
ulf | -3.834 |
rer | -3.718 |
Mouth | -3.506 |
OTOS | -3.481 |
IPM | -3.410 |
Token | had |
Token ID | 550 |
Feature activation | -1.46e+01 |
Pos logit contributions | |
ilitarian | +4.331 |
>) | +4.191 |
weighed | +3.908 |
spot | +3.802 |
xxxxxxxx | +3.732 |
Neg logit contributions | |
ulf | -4.597 |
rer | -4.464 |
OTOS | -4.268 |
Mouth | -4.193 |
IPM | -4.097 |
Token | a |
Token ID | 257 |
Feature activation | -7.71e+00 |
Pos logit contributions | |
>) | +7.705 |
ilitarian | +7.413 |
weighed | +7.127 |
Eliot | +7.064 |
Revival | +6.964 |
Neg logit contributions | |
ulf | -10.337 |
rer | -10.290 |
OTOS | -9.398 |
ê | -9.390 |
エル | -9.211 |
Token | couple |
Token ID | 3155 |
Feature activation | -7.75e+00 |
Pos logit contributions | |
ilitarian | +5.139 |
>) | +4.994 |
spot | +4.452 |
romeda | +4.432 |
Eliot | +4.409 |
Neg logit contributions | |
ulf | -5.357 |
rer | -5.196 |
IPM | -4.720 |
ê | -4.716 |
OTOS | -4.710 |
Token | glasses |
Token ID | 15232 |
Feature activation | -6.36e+00 |
Pos logit contributions | |
ilitarian | +4.635 |
>) | +4.498 |
romeda | +4.069 |
Eliot | +4.039 |
spot | +4.018 |
Neg logit contributions | |
ulf | -5.737 |
rer | -5.636 |
ê | -5.121 |
IPM | -5.076 |
OTOS | -5.026 |
Token | of |
Token ID | 286 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
ilitarian | +3.921 |
>) | +3.734 |
weighed | +3.367 |
spot | +3.359 |
xxxxxxxx | +3.355 |
Neg logit contributions | |
ulf | -4.690 |
rer | -4.582 |
Mouth | -4.310 |
IPM | -4.269 |
OTOS | -4.188 |
Token | Vampire |
Token ID | 21463 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
ilitarian | +9.554 |
>) | +9.219 |
Revival | +8.997 |
Eliot | +8.834 |
spot | +8.543 |
Neg logit contributions | |
ulf | -9.834 |
rer | -9.636 |
OTOS | -9.090 |
ê | -8.803 |
エル | -8.729 |
Token | for |
Token ID | 329 |
Feature activation | -4.59e+00 |
Pos logit contributions | |
ulf | +0.518 |
rer | +0.508 |
Mouth | +0.472 |
IPM | +0.454 |
ê | +0.452 |
Neg logit contributions | |
ilitarian | -0.520 |
>) | -0.501 |
xxxxxxxx | -0.451 |
romeda | -0.445 |
spot | -0.441 |
Token | Your |
Token ID | 3406 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
ilitarian | +3.090 |
>) | +2.967 |
romeda | +2.649 |
xxxxxxxx | +2.636 |
Revival | +2.633 |
Neg logit contributions | |
ulf | -3.235 |
rer | -3.150 |
Mouth | -2.866 |
IPM | -2.846 |
ê | -2.801 |
Token | Love |
Token ID | 5896 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
ulf | +0.346 |
rer | +0.338 |
Mouth | +0.314 |
IPM | +0.301 |
ê | +0.298 |
Neg logit contributions | |
ilitarian | -0.415 |
>) | -0.402 |
xxxxxxxx | -0.364 |
romeda | -0.360 |
spot | -0.359 |
Token | , |
Token ID | 11 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
rer | +2.474 |
ulf | +2.474 |
Mouth | +2.308 |
IPM | +2.168 |
ê | +2.163 |
Neg logit contributions | |
ilitarian | -2.615 |
>) | -2.551 |
xxxxxxxx | -2.317 |
romeda | -2.269 |
spot | -2.221 |