Token | is |
Token ID | 318 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
ANE | +0.906 |
awan | +0.870 |
光 | +0.855 |
srf | +0.848 |
UA | +0.846 |
Neg logit contributions | |
ertodd | -0.812 |
ysis | -0.640 |
verts | -0.606 |
ered | -0.604 |
quo | -0.595 |
Token | one |
Token ID | 530 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
ANE | +0.612 |
awan | +0.587 |
光 | +0.581 |
srf | +0.576 |
UA | +0.571 |
Neg logit contributions | |
ertodd | -0.526 |
ysis | -0.416 |
verts | -0.396 |
ered | -0.396 |
quo | -0.392 |
Token | of |
Token ID | 286 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ertodd | +2.178 |
ysis | +1.717 |
ered | +1.628 |
verts | +1.625 |
quo | +1.600 |
Neg logit contributions | |
ANE | -2.397 |
awan | -2.305 |
光 | -2.263 |
UA | -2.238 |
女 | -2.234 |
Token | the |
Token ID | 262 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
ertodd | +2.648 |
ysis | +2.070 |
ered | +1.980 |
verts | +1.958 |
Jehovah | +1.952 |
Neg logit contributions | |
ANE | -3.410 |
awan | -3.274 |
光 | -3.240 |
srf | -3.210 |
女 | -3.201 |
Token | st |
Token ID | 336 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
ertodd | +1.401 |
ysis | +1.138 |
verts | +1.101 |
ered | +1.098 |
quo | +1.082 |
Neg logit contributions | |
ANE | -1.252 |
awan | -1.196 |
光 | -1.181 |
srf | -1.166 |
UA | -1.163 |
Token | aun |
Token ID | 1942 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
ertodd | +0.287 |
ysis | +0.203 |
verts | +0.186 |
ered | +0.185 |
quo | +0.180 |
Neg logit contributions | |
ANE | -0.552 |
awan | -0.535 |
光 | -0.527 |
UA | -0.523 |
女 | -0.523 |
Token | chest |
Token ID | 46713 |
Feature activation | -9.99e-01 |
Pos logit contributions | |
ertodd | +8.057 |
verts | +6.771 |
ered | +6.764 |
ysis | +6.579 |
quo | +6.488 |
Neg logit contributions | |
ANE | -10.008 |
女 | -9.340 |
senal | -9.227 |
UA | -9.208 |
awan | -9.151 |
Token | supporters |
Token ID | 5941 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
ANE | +3.069 |
awan | +2.951 |
光 | +2.896 |
UA | +2.877 |
女 | +2.865 |
Neg logit contributions | |
ertodd | -2.848 |
ysis | -2.231 |
ered | -2.099 |
verts | -2.096 |
quo | -2.057 |
Token | of |
Token ID | 286 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
ertodd | +0.279 |
ysis | +0.222 |
verts | +0.211 |
ered | +0.209 |
quo | +0.205 |
Neg logit contributions | |
ANE | -0.286 |
awan | -0.274 |
光 | -0.269 |
UA | -0.267 |
女 | -0.267 |
Token | Trump |
Token ID | 1301 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ANE | +0.752 |
awan | +0.726 |
光 | +0.713 |
UA | +0.708 |
女 | +0.706 |
Neg logit contributions | |
ertodd | -0.547 |
ysis | -0.416 |
verts | -0.389 |
ered | -0.386 |
quo | -0.378 |
Token | 's |
Token ID | 338 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
ANE | +0.425 |
awan | +0.406 |
光 | +0.397 |
UA | +0.394 |
srf | +0.393 |
Neg logit contributions | |
ertodd | -0.466 |
ysis | -0.377 |
verts | -0.360 |
ered | -0.359 |
quo | -0.355 |
Token | morning |
Token ID | 3329 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
ANE | +2.722 |
awan | +2.611 |
光 | +2.554 |
女 | +2.522 |
UA | +2.522 |
Neg logit contributions | |
ertodd | -3.016 |
ysis | -2.462 |
verts | -2.326 |
ered | -2.299 |
quo | -2.280 |
Token | 's |
Token ID | 338 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
ertodd | +0.140 |
ysis | +0.110 |
verts | +0.105 |
ered | +0.105 |
quo | +0.103 |
Neg logit contributions | |
ANE | -0.157 |
awan | -0.151 |
光 | -0.148 |
srf | -0.147 |
UA | -0.147 |
Token | prices |
Token ID | 4536 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
ertodd | +2.835 |
ysis | +2.218 |
ered | +2.130 |
verts | +2.130 |
quo | +2.116 |
Neg logit contributions | |
ANE | -3.034 |
awan | -2.952 |
srf | -2.912 |
光 | -2.887 |
女 | -2.873 |
Token | were |
Token ID | 547 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
ertodd | +4.638 |
ysis | +3.616 |
quo | +3.521 |
ered | +3.483 |
verts | +3.390 |
Neg logit contributions | |
ANE | -6.573 |
srf | -6.437 |
awan | -6.406 |
senal | -6.369 |
光 | -6.292 |
Token | a |
Token ID | 257 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ertodd | +1.105 |
ysis | +0.891 |
ered | +0.860 |
quo | +0.858 |
verts | +0.852 |
Neg logit contributions | |
ANE | -1.145 |
awan | -1.105 |
光 | -1.092 |
srf | -1.088 |
女 | -1.078 |
Token | bubble |
Token ID | 14310 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
ertodd | +2.935 |
ysis | +2.369 |
ered | +2.307 |
verts | +2.288 |
quo | +2.288 |
Neg logit contributions | |
ANE | -2.947 |
awan | -2.860 |
光 | -2.820 |
srf | -2.812 |
UA | -2.799 |
Token | is |
Token ID | 318 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
ertodd | +7.876 |
ered | +6.152 |
quo | +5.988 |
verts | +5.902 |
ysis | +5.800 |
Neg logit contributions | |
ANE | -9.843 |
senal | -9.533 |
srf | -9.519 |
awan | -9.450 |
光 | -9.276 |
Token | ultimately |
Token ID | 6165 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
ANE | +1.842 |
awan | +1.764 |
光 | +1.726 |
UA | +1.709 |
女 | +1.706 |
Neg logit contributions | |
ertodd | -2.029 |
ysis | -1.642 |
verts | -1.563 |
ered | -1.557 |
quo | -1.535 |
Token | a |
Token ID | 257 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
ANE | +1.433 |
awan | +1.368 |
光 | +1.335 |
UA | +1.321 |
srf | +1.321 |
Neg logit contributions | |
ertodd | -1.802 |
ysis | -1.482 |
verts | -1.417 |
ered | -1.415 |
quo | -1.395 |
Token | prediction |
Token ID | 17724 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
ertodd | +1.036 |
ysis | +0.854 |
ered | +0.829 |
verts | +0.828 |
quo | +0.818 |
Neg logit contributions | |
ANE | -0.831 |
awan | -0.793 |
srf | -0.774 |
光 | -0.773 |
UA | -0.770 |
Token | about |
Token ID | 546 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ertodd | +1.030 |
ysis | +0.833 |
ered | +0.811 |
quo | +0.798 |
verts | +0.798 |
Neg logit contributions | |
ANE | -1.049 |
awan | -1.004 |
srf | -0.990 |
光 | -0.982 |
女 | -0.975 |
Token | In |
Token ID | 818 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
ANE | +0.463 |
srf | +0.450 |
awan | +0.445 |
senal | +0.432 |
光 | +0.429 |
Neg logit contributions | |
ertodd | -0.738 |
ysis | -0.622 |
verts | -0.605 |
ered | -0.603 |
quo | -0.588 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
ertodd | +2.076 |
ysis | +1.612 |
verts | +1.555 |
ered | +1.526 |
quo | +1.491 |
Neg logit contributions | |
ANE | -2.552 |
awan | -2.465 |
光 | -2.433 |
srf | -2.417 |
女 | -2.409 |
Token | months |
Token ID | 1933 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
ertodd | +0.353 |
ysis | +0.286 |
verts | +0.274 |
ered | +0.272 |
quo | +0.268 |
Neg logit contributions | |
ANE | -0.334 |
awan | -0.320 |
光 | -0.315 |
女 | -0.312 |
UA | -0.311 |
Token | before |
Token ID | 878 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
ANE | +1.276 |
awan | +1.221 |
光 | +1.194 |
UA | +1.182 |
女 | +1.180 |
Neg logit contributions | |
ertodd | -1.495 |
ysis | -1.219 |
verts | -1.162 |
ered | -1.159 |
quo | -1.143 |
Token | the |
Token ID | 262 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
ANE | +2.491 |
awan | +2.396 |
光 | +2.347 |
UA | +2.334 |
EMENT | +2.321 |
Neg logit contributions | |
ertodd | -2.209 |
ysis | -1.725 |
verts | -1.627 |
ered | -1.620 |
quo | -1.595 |
Token | IPO |
Token ID | 41805 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
ertodd | +1.686 |
ysis | +1.370 |
verts | +1.310 |
ered | +1.297 |
Jehovah | +1.292 |
Neg logit contributions | |
ANE | -1.700 |
awan | -1.637 |
女 | -1.608 |
光 | -1.608 |
srf | -1.604 |
Token | , |
Token ID | 11 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
ertodd | +7.542 |
ered | +6.012 |
ysis | +5.952 |
verts | +5.835 |
Rupert | +5.821 |
Neg logit contributions | |
ANE | -8.619 |
srf | -8.571 |
awan | -8.347 |
女 | -8.278 |
adolesc | -8.183 |
Token | � |
Token ID | 564 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ANE | +0.522 |
awan | +0.501 |
光 | +0.490 |
女 | +0.485 |
UA | +0.485 |
Neg logit contributions | |
ertodd | -0.563 |
ysis | -0.455 |
verts | -0.433 |
ered | -0.431 |
quo | -0.425 |
Token | � |
Token ID | 250 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
ANE | +2.195 |
awan | +2.072 |
光 | +2.007 |
女 | +1.995 |
RAW | +1.976 |
Neg logit contributions | |
ertodd | -4.733 |
ysis | -4.030 |
verts | -3.902 |
ered | -3.857 |
quo | -3.833 |
Token | Black |
Token ID | 9915 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
ertodd | +0.097 |
ysis | +0.080 |
ered | +0.077 |
verts | +0.076 |
quo | +0.075 |
Neg logit contributions | |
ANE | -0.074 |
awan | -0.070 |
光 | -0.068 |
srf | -0.068 |
UA | -0.067 |
Token | fish |
Token ID | 11084 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
ANE | +0.844 |
awan | +0.800 |
光 | +0.778 |
srf | +0.769 |
UA | +0.766 |
Neg logit contributions | |
ertodd | -1.363 |
ysis | -1.143 |
verts | -1.098 |
ered | -1.097 |
quo | -1.081 |
Token | be |
Token ID | 307 |
Feature activation | +5.21e-02 |
Pos logit contributions | |
ertodd | +0.931 |
ysis | +0.718 |
ered | +0.685 |
verts | +0.677 |
quo | +0.665 |
Neg logit contributions | |
ANE | -1.216 |
awan | -1.172 |
光 | -1.157 |
UA | -1.150 |
srf | -1.144 |
Token | regarded |
Token ID | 11987 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ertodd | +0.143 |
ysis | +0.115 |
ered | +0.111 |
verts | +0.109 |
quo | +0.108 |
Neg logit contributions | |
ANE | -0.163 |
awan | -0.157 |
光 | -0.154 |
srf | -0.154 |
UA | -0.152 |
Token | as |
Token ID | 355 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
ertodd | +2.949 |
ysis | +2.383 |
ered | +2.291 |
verts | +2.240 |
quo | +2.238 |
Neg logit contributions | |
ANE | -3.242 |
awan | -3.105 |
srf | -3.064 |
光 | -3.062 |
UA | -3.039 |
Token | a |
Token ID | 257 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
ertodd | +1.563 |
ysis | +1.248 |
ered | +1.194 |
verts | +1.181 |
quo | +1.172 |
Neg logit contributions | |
ANE | -1.796 |
awan | -1.731 |
光 | -1.708 |
srf | -1.694 |
UA | -1.690 |
Token | pand |
Token ID | 19798 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
ertodd | +1.838 |
ysis | +1.494 |
ered | +1.435 |
verts | +1.420 |
quo | +1.401 |
Neg logit contributions | |
ANE | -1.897 |
awan | -1.826 |
光 | -1.804 |
UA | -1.791 |
srf | -1.782 |
Token | emic |
Token ID | 5314 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
ertodd | +3.636 |
ered | +2.599 |
ysis | +2.562 |
verts | +2.190 |
quo | +1.971 |
Neg logit contributions | |
srf | -8.550 |
ANE | -8.512 |
senal | -8.401 |
光 | -8.237 |
女 | -8.213 |
Token | but |
Token ID | 475 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
ertodd | +7.188 |
ysis | +6.198 |
ered | +6.155 |
quo | +5.924 |
verts | +5.877 |
Neg logit contributions | |
ANE | -7.850 |
srf | -7.769 |
awan | -7.699 |
光 | -7.680 |
senal | -7.627 |
Token | wanted |
Token ID | 2227 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
ANE | +0.441 |
awan | +0.425 |
光 | +0.417 |
UA | +0.413 |
女 | +0.413 |
Neg logit contributions | |
ertodd | -0.379 |
ysis | -0.297 |
verts | -0.280 |
ered | -0.279 |
quo | -0.274 |
Token | clear |
Token ID | 1598 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
ertodd | +1.598 |
ysis | +1.305 |
ered | +1.240 |
verts | +1.237 |
quo | +1.218 |
Neg logit contributions | |
ANE | -1.547 |
awan | -1.485 |
光 | -1.463 |
srf | -1.453 |
UA | -1.446 |
Token | evidence |
Token ID | 2370 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
ANE | +0.748 |
awan | +0.719 |
光 | +0.705 |
UA | +0.699 |
女 | +0.698 |
Neg logit contributions | |
ertodd | -0.700 |
ysis | -0.552 |
verts | -0.522 |
ered | -0.519 |
quo | -0.511 |
Token | before |
Token ID | 878 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
ertodd | +1.155 |
ysis | +0.943 |
ered | +0.898 |
verts | +0.891 |
quo | +0.883 |
Neg logit contributions | |
ANE | -1.205 |
awan | -1.162 |
光 | -1.138 |
srf | -1.135 |
UA | -1.126 |
Token | News |
Token ID | 3000 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
ertodd | +1.948 |
ysis | +1.629 |
verts | +1.571 |
ered | +1.559 |
Jehovah | +1.521 |
Neg logit contributions | |
ANE | -1.849 |
awan | -1.807 |
光 | -1.765 |
srf | -1.760 |
女 | -1.748 |
Token | 24 |
Token ID | 1987 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
ertodd | +0.959 |
ysis | +0.780 |
verts | +0.753 |
ered | +0.747 |
quo | +0.732 |
Neg logit contributions | |
ANE | -0.960 |
awan | -0.925 |
光 | -0.911 |
女 | -0.910 |
srf | -0.906 |
Token | . |
Token ID | 13 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
ertodd | +2.108 |
ysis | +1.757 |
verts | +1.707 |
ered | +1.691 |
Jehovah | +1.644 |
Neg logit contributions | |
ANE | -1.962 |
awan | -1.890 |
光 | -1.865 |
女 | -1.848 |
srf | -1.844 |
Token |
|
Token ID | 198 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
ertodd | +2.014 |
ysis | +1.583 |
verts | +1.522 |
ered | +1.498 |
quo | +1.466 |
Neg logit contributions | |
ANE | -2.529 |
awan | -2.455 |
光 | -2.415 |
srf | -2.415 |
女 | -2.391 |
Token |
|
Token ID | 198 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
ertodd | +1.040 |
ysis | +0.791 |
ered | +0.756 |
verts | +0.754 |
quo | +0.727 |
Neg logit contributions | |
ANE | -1.475 |
srf | -1.444 |
senal | -1.428 |
awan | -1.421 |
光 | -1.405 |
Token | Topics |
Token ID | 25902 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
ANE | +0.493 |
awan | +0.477 |
srf | +0.469 |
光 | +0.467 |
女 | +0.463 |
Neg logit contributions | |
ertodd | -0.450 |
ysis | -0.357 |
verts | -0.342 |
ered | -0.340 |
quo | -0.332 |
Token | : |
Token ID | 25 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
ertodd | +6.490 |
ered | +5.036 |
verts | +4.764 |
ysis | +4.720 |
Rupert | +4.659 |
Neg logit contributions | |
srf | -9.565 |
senal | -9.532 |
adolesc | -9.120 |
ANE | -9.097 |
awan | -8.802 |
Token | beef |
Token ID | 12023 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
ertodd | +1.409 |
ysis | +1.107 |
ered | +1.048 |
verts | +1.047 |
quo | +1.040 |
Neg logit contributions | |
ANE | -1.795 |
awan | -1.720 |
光 | -1.699 |
UA | -1.691 |
srf | -1.678 |
Token | - |
Token ID | 12 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
ANE | +0.089 |
awan | +0.086 |
光 | +0.084 |
UA | +0.083 |
EMENT | +0.083 |
Neg logit contributions | |
ertodd | -0.096 |
ysis | -0.078 |
verts | -0.074 |
ered | -0.073 |
quo | -0.073 |
Token | c |
Token ID | 66 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
ANE | +1.160 |
awan | +1.106 |
光 | +1.086 |
UA | +1.072 |
srf | +1.070 |
Neg logit contributions | |
ertodd | -1.370 |
ysis | -1.117 |
verts | -1.068 |
ered | -1.064 |
quo | -1.047 |
Token | attle |
Token ID | 1999 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
ANE | +2.324 |
awan | +2.270 |
UA | +2.176 |
RAW | +2.175 |
光 | +2.171 |
Neg logit contributions | |
ertodd | -2.218 |
ysis | -1.734 |
quo | -1.650 |
verts | -1.641 |
ered | -1.623 |
Token | so |
Token ID | 523 |
Feature activation | -9.37e-03 |
Pos logit contributions | |
ertodd | +2.884 |
ysis | +2.355 |
ered | +2.265 |
quo | +2.262 |
verts | +2.245 |
Neg logit contributions | |
ANE | -2.484 |
awan | -2.378 |
srf | -2.327 |
senal | -2.321 |
光 | -2.318 |
Token | rapidly |
Token ID | 8902 |
Feature activation | -1.72e-03 |
Pos logit contributions | |
ANE | +0.028 |
awan | +0.026 |
srf | +0.026 |
光 | +0.026 |
女 | +0.026 |
Neg logit contributions | |
ertodd | -0.028 |
ysis | -0.022 |
ered | -0.021 |
verts | -0.021 |
quo | -0.021 |
Token | ? |
Token ID | 30 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
ANE | +0.004 |
awan | +0.004 |
光 | +0.004 |
UA | +0.004 |
女 | +0.004 |
Neg logit contributions | |
ertodd | -0.006 |
ysis | -0.005 |
verts | -0.004 |
ered | -0.004 |
quo | -0.004 |
Token | Though |
Token ID | 7486 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
ertodd | +1.210 |
ysis | +0.952 |
verts | +0.909 |
ered | +0.908 |
quo | +0.888 |
Neg logit contributions | |
ANE | -1.428 |
awan | -1.381 |
srf | -1.372 |
光 | -1.349 |
女 | -1.340 |
Token | the |
Token ID | 262 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
ANE | +1.077 |
awan | +1.037 |
光 | +1.017 |
UA | +1.007 |
女 | +1.006 |
Neg logit contributions | |
ertodd | -0.961 |
ysis | -0.755 |
verts | -0.710 |
ered | -0.705 |
quo | -0.692 |
Token | boom |
Token ID | 14166 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
ertodd | +0.470 |
ysis | +0.377 |
verts | +0.357 |
ered | +0.356 |
quo | +0.352 |
Neg logit contributions | |
ANE | -0.482 |
awan | -0.462 |
光 | -0.453 |
UA | -0.449 |
女 | -0.449 |
Token | in |
Token ID | 287 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
ertodd | +7.098 |
ered | +5.858 |
ysis | +5.539 |
quo | +5.493 |
verts | +5.366 |
Neg logit contributions | |
ANE | -8.320 |
srf | -8.118 |
awan | -7.976 |
senal | -7.922 |
UA | -7.906 |
Token | global |
Token ID | 3298 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
ertodd | +1.933 |
ysis | +1.546 |
verts | +1.477 |
ered | +1.467 |
quo | +1.451 |
Neg logit contributions | |
ANE | -2.091 |
awan | -2.008 |
srf | -1.977 |
光 | -1.977 |
UA | -1.962 |
Token | commodity |
Token ID | 19464 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
ertodd | +1.450 |
ysis | +1.168 |
ered | +1.107 |
verts | +1.107 |
quo | +1.088 |
Neg logit contributions | |
ANE | -1.494 |
awan | -1.437 |
光 | -1.407 |
srf | -1.405 |
UA | -1.395 |
Token | prices |
Token ID | 4536 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
ertodd | +2.377 |
ysis | +1.886 |
verts | +1.818 |
ered | +1.810 |
quo | +1.784 |
Neg logit contributions | |
ANE | -2.842 |
awan | -2.740 |
srf | -2.688 |
光 | -2.659 |
女 | -2.646 |
Token | played |
Token ID | 2826 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ertodd | +5.424 |
ysis | +4.313 |
ered | +4.301 |
quo | +4.245 |
verts | +4.140 |
Neg logit contributions | |
ANE | -6.637 |
senal | -6.506 |
srf | -6.447 |
awan | -6.304 |
UA | -6.164 |
Token | Hay |
Token ID | 31306 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
ANE | +1.231 |
awan | +1.159 |
光 | +1.131 |
女 | +1.112 |
srf | +1.108 |
Neg logit contributions | |
ertodd | -2.363 |
ysis | -2.002 |
verts | -1.940 |
ered | -1.929 |
quo | -1.905 |
Token | es |
Token ID | 274 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
ertodd | +4.247 |
verts | +3.301 |
ered | +3.277 |
ysis | +3.243 |
quo | +3.163 |
Neg logit contributions | |
ANE | -5.066 |
srf | -4.910 |
光 | -4.819 |
senal | -4.805 |
awan | -4.749 |
Token | , |
Token ID | 11 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
ertodd | +1.896 |
ysis | +1.476 |
verts | +1.431 |
ered | +1.414 |
quo | +1.383 |
Neg logit contributions | |
ANE | -2.391 |
光 | -2.283 |
awan | -2.278 |
srf | -2.271 |
EMENT | -2.236 |
Token | at |
Token ID | 379 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
ertodd | +1.353 |
ysis | +1.081 |
verts | +1.027 |
ered | +1.021 |
quo | +1.008 |
Neg logit contributions | |
ANE | -1.453 |
awan | -1.391 |
光 | -1.374 |
女 | -1.355 |
UA | -1.355 |
Token | the |
Token ID | 262 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
ertodd | +1.113 |
ysis | +0.861 |
verts | +0.808 |
ered | +0.805 |
quo | +0.790 |
Neg logit contributions | |
ANE | -1.525 |
awan | -1.471 |
光 | -1.453 |
女 | -1.438 |
RAW | -1.437 |
Token | Sud |
Token ID | 14818 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
ertodd | +2.201 |
ysis | +1.785 |
verts | +1.710 |
ered | +1.707 |
Jehovah | +1.668 |
Neg logit contributions | |
ANE | -2.082 |
awan | -1.977 |
女 | -1.951 |
光 | -1.949 |
srf | -1.939 |
Token | z |
Token ID | 89 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
ertodd | +7.714 |
ered | +6.324 |
ysis | +6.274 |
verts | +6.112 |
quo | +5.801 |
Neg logit contributions | |
ANE | -7.636 |
srf | -7.587 |
senal | -7.425 |
光 | -7.365 |
女 | -7.209 |
Token | ha |
Token ID | 3099 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
ertodd | +1.010 |
ysis | +0.833 |
verts | +0.795 |
ered | +0.793 |
quo | +0.773 |
Neg logit contributions | |
ANE | -0.871 |
awan | -0.828 |
光 | -0.824 |
srf | -0.821 |
女 | -0.816 |
Token | pumping |
Token ID | 26916 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
ertodd | +1.713 |
ysis | +1.372 |
ered | +1.306 |
verts | +1.302 |
quo | +1.261 |
Neg logit contributions | |
ANE | -1.852 |
awan | -1.763 |
光 | -1.751 |
女 | -1.737 |
EMENT | -1.733 |
Token | station |
Token ID | 4429 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
ertodd | +1.202 |
ysis | +0.996 |
verts | +0.946 |
ered | +0.945 |
quo | +0.933 |
Neg logit contributions | |
ANE | -1.022 |
awan | -0.977 |
srf | -0.957 |
光 | -0.955 |
女 | -0.949 |
Token | on |
Token ID | 319 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
ANE | +0.572 |
awan | +0.547 |
光 | +0.535 |
UA | +0.530 |
女 | +0.528 |
Neg logit contributions | |
ertodd | -0.685 |
ysis | -0.558 |
verts | -0.532 |
ered | -0.530 |
quo | -0.523 |
Token | a |
Token ID | 257 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
ertodd | +4.779 |
ysis | +4.032 |
ered | +3.868 |
verts | +3.760 |
quo | +3.759 |
Neg logit contributions | |
ANE | -6.047 |
srf | -5.964 |
光 | -5.834 |
awan | -5.834 |
senal | -5.771 |
Token | full |
Token ID | 1336 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
ertodd | +2.050 |
ysis | +1.695 |
ered | +1.633 |
verts | +1.593 |
quo | +1.572 |
Neg logit contributions | |
ANE | -2.072 |
awan | -2.001 |
光 | -1.992 |
UA | -1.954 |
srf | -1.942 |
Token | - |
Token ID | 12 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
ertodd | +1.666 |
ysis | +1.286 |
ered | +1.193 |
verts | +1.191 |
quo | +1.166 |
Neg logit contributions | |
ANE | -2.499 |
awan | -2.420 |
光 | -2.377 |
女 | -2.365 |
UA | -2.357 |
Token | blown |
Token ID | 31290 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
ertodd | +2.740 |
ysis | +2.253 |
verts | +2.162 |
ered | +2.140 |
quo | +2.083 |
Neg logit contributions | |
ANE | -2.734 |
awan | -2.599 |
光 | -2.562 |
女 | -2.556 |
srf | -2.551 |
Token | pand |
Token ID | 19798 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
ertodd | +1.405 |
ysis | +1.150 |
ered | +1.097 |
verts | +1.071 |
Jehovah | +1.058 |
Neg logit contributions | |
ANE | -1.574 |
awan | -1.524 |
光 | -1.514 |
srf | -1.492 |
UA | -1.490 |
Token | emic |
Token ID | 5314 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
ertodd | +3.283 |
ysis | +2.384 |
ered | +2.312 |
verts | +2.070 |
Rupert | +1.844 |
Neg logit contributions | |
ANE | -7.352 |
srf | -7.277 |
光 | -7.177 |
senal | -7.155 |
女 | -7.105 |
Token | . |
Token ID | 13 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
ertodd | +7.625 |
ysis | +6.423 |
ered | +6.193 |
quo | +6.058 |
verts | +6.029 |
Neg logit contributions | |
ANE | -7.353 |
srf | -7.237 |
awan | -7.170 |
光 | -7.138 |
senal | -7.118 |
Token | SW |
Token ID | 12672 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
ANE | +0.846 |
awan | +0.815 |
光 | +0.800 |
UA | +0.794 |
女 | +0.792 |
Neg logit contributions | |
ertodd | -0.695 |
ysis | -0.539 |
verts | -0.507 |
ered | -0.504 |
quo | -0.496 |
Token | INE |
Token ID | 8881 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
ANE | +1.629 |
awan | +1.523 |
光 | +1.475 |
UA | +1.462 |
RAW | +1.450 |
Neg logit contributions | |
ertodd | -3.116 |
ysis | -2.635 |
verts | -2.536 |
ered | -2.523 |
quo | -2.502 |
Token | FL |
Token ID | 9977 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
ertodd | +0.197 |
ysis | +0.158 |
verts | +0.150 |
ered | +0.150 |
quo | +0.146 |
Neg logit contributions | |
ANE | -0.205 |
awan | -0.198 |
光 | -0.194 |
女 | -0.192 |
srf | -0.192 |
Token | U |
Token ID | 52 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
ANE | +0.861 |
awan | +0.803 |
光 | +0.771 |
女 | +0.755 |
srf | +0.755 |
Neg logit contributions | |
ertodd | -2.334 |
ysis | -2.017 |
verts | -1.949 |
ered | -1.945 |
quo | -1.922 |
Token | and |
Token ID | 290 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
ANE | +2.264 |
awan | +2.185 |
光 | +2.142 |
UA | +2.128 |
女 | +2.122 |
Neg logit contributions | |
ertodd | -1.761 |
ysis | -1.358 |
verts | -1.262 |
ered | -1.257 |
quo | -1.233 |
Token | the |
Token ID | 262 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
ANE | +2.020 |
awan | +1.953 |
光 | +1.908 |
UA | +1.902 |
EMENT | +1.894 |
Neg logit contributions | |
ertodd | -1.704 |
ysis | -1.326 |
verts | -1.230 |
ered | -1.222 |
quo | -1.215 |
Token | Paradox |
Token ID | 37983 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ertodd | +0.502 |
ysis | +0.391 |
verts | +0.368 |
ered | +0.367 |
quo | +0.360 |
Neg logit contributions | |
ANE | -0.619 |
awan | -0.595 |
光 | -0.585 |
UA | -0.580 |
女 | -0.579 |
Token | of |
Token ID | 286 |
Feature activation | -8.89e-02 |
Pos logit contributions | |
ertodd | +3.123 |
ysis | +2.508 |
ered | +2.383 |
verts | +2.379 |
quo | +2.326 |
Neg logit contributions | |
ANE | -3.295 |
awan | -3.163 |
光 | -3.128 |
srf | -3.099 |
女 | -3.080 |
Token | Credit |
Token ID | 10504 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
ANE | +0.289 |
awan | +0.279 |
光 | +0.273 |
UA | +0.271 |
女 | +0.271 |
Neg logit contributions | |
ertodd | -0.238 |
ysis | -0.185 |
verts | -0.174 |
ered | -0.173 |
quo | -0.170 |
Token | Bub |
Token ID | 19645 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
ertodd | +2.188 |
ysis | +1.751 |
verts | +1.676 |
ered | +1.669 |
quo | +1.628 |
Neg logit contributions | |
ANE | -2.478 |
awan | -2.365 |
光 | -2.339 |
srf | -2.335 |
女 | -2.308 |
Token | bles |
Token ID | 7689 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ertodd | +5.806 |
verts | +4.368 |
ysis | +4.310 |
ered | +4.128 |
gencies | +3.914 |
Neg logit contributions | |
ANE | -9.437 |
srf | -9.405 |
senal | -9.392 |
光 | -9.356 |
女 | -9.169 |
Token | , |
Token ID | 11 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
ertodd | +4.635 |
ysis | +3.728 |
ered | +3.606 |
verts | +3.589 |
quo | +3.509 |
Neg logit contributions | |
ANE | -4.618 |
awan | -4.439 |
srf | -4.400 |
光 | -4.386 |
女 | -4.332 |
Token | Equity |
Token ID | 35659 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
ANE | +0.080 |
awan | +0.077 |
光 | +0.076 |
UA | +0.075 |
女 | +0.075 |
Neg logit contributions | |
ertodd | -0.073 |
ysis | -0.058 |
verts | -0.055 |
ered | -0.055 |
quo | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
ANE | +1.532 |
awan | +1.481 |
光 | +1.447 |
UA | +1.435 |
EMENT | +1.433 |
Neg logit contributions | |
ertodd | -1.392 |
ysis | -1.094 |
verts | -1.022 |
ered | -1.018 |
quo | -1.006 |
Token | Demand |
Token ID | 34479 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ANE | +1.937 |
awan | +1.875 |
光 | +1.828 |
UA | +1.822 |
EMENT | +1.819 |
Neg logit contributions | |
ertodd | -1.551 |
ysis | -1.190 |
verts | -1.096 |
ered | -1.091 |
quo | -1.083 |
Token | 45 |
Token ID | 2231 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
ertodd | +2.017 |
ysis | +1.678 |
verts | +1.624 |
ered | +1.602 |
Jehovah | +1.577 |
Neg logit contributions | |
srf | -1.948 |
awan | -1.920 |
ANE | -1.918 |
senal | -1.875 |
光 | -1.829 |
Token | 366 |
Token ID | 44856 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
ertodd | +2.002 |
ysis | +1.655 |
verts | +1.582 |
ered | +1.567 |
Jehovah | +1.547 |
Neg logit contributions | |
ANE | -2.018 |
awan | -1.988 |
srf | -1.927 |
光 | -1.905 |
女 | -1.891 |
Token | . |
Token ID | 13 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
ertodd | +2.132 |
ysis | +1.774 |
verts | +1.719 |
ered | +1.714 |
quo | +1.684 |
Neg logit contributions | |
ANE | -1.690 |
awan | -1.644 |
光 | -1.606 |
srf | -1.583 |
RAW | -1.577 |
Token |
|
Token ID | 198 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
ertodd | +0.076 |
ysis | +0.059 |
verts | +0.056 |
ered | +0.055 |
quo | +0.054 |
Neg logit contributions | |
ANE | -0.089 |
awan | -0.085 |
光 | -0.084 |
UA | -0.083 |
女 | -0.083 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
ertodd | +1.028 |
ysis | +0.784 |
ered | +0.747 |
verts | +0.745 |
quo | +0.721 |
Neg logit contributions | |
ANE | -1.445 |
srf | -1.406 |
awan | -1.392 |
senal | -1.390 |
光 | -1.375 |
Token | Topics |
Token ID | 25902 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
ANE | +0.379 |
awan | +0.365 |
srf | +0.361 |
光 | +0.358 |
女 | +0.354 |
Neg logit contributions | |
ertodd | -0.385 |
ysis | -0.311 |
verts | -0.298 |
ered | -0.297 |
quo | -0.290 |
Token | : |
Token ID | 25 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
ertodd | +6.301 |
ered | +4.874 |
verts | +4.694 |
ysis | +4.630 |
Rupert | +4.571 |
Neg logit contributions | |
srf | -9.265 |
senal | -9.230 |
adolesc | -8.807 |
ANE | -8.806 |
awan | -8.538 |
Token | community |
Token ID | 2055 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
ertodd | +1.727 |
ysis | +1.396 |
ered | +1.340 |
verts | +1.336 |
quo | +1.318 |
Neg logit contributions | |
ANE | -1.854 |
awan | -1.769 |
光 | -1.758 |
UA | -1.745 |
RAW | -1.739 |
Token | - |
Token ID | 12 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
ertodd | +1.713 |
ysis | +1.285 |
verts | +1.199 |
ered | +1.190 |
quo | +1.165 |
Neg logit contributions | |
ANE | -2.654 |
awan | -2.558 |
光 | -2.516 |
srf | -2.510 |
UA | -2.497 |
Token | and |
Token ID | 392 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
ANE | +0.266 |
awan | +0.260 |
光 | +0.250 |
UA | +0.247 |
女 | +0.246 |
Neg logit contributions | |
ertodd | -0.413 |
ysis | -0.342 |
ered | -0.325 |
verts | -0.324 |
quo | -0.323 |
Token | - |
Token ID | 12 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
ertodd | +0.882 |
ysis | +0.655 |
ered | +0.616 |
verts | +0.615 |
quo | +0.597 |
Neg logit contributions | |
ANE | -1.401 |
awan | -1.349 |
srf | -1.331 |
光 | -1.331 |
女 | -1.318 |
Token | activists |
Token ID | 7941 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
ertodd | +0.552 |
ysis | +0.445 |
ered | +0.425 |
verts | +0.425 |
quo | +0.417 |
Neg logit contributions | |
ANE | -0.567 |
awan | -0.543 |
光 | -0.534 |
srf | -0.532 |
女 | -0.529 |
Token | protesting |
Token ID | 23655 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
ANE | +1.408 |
awan | +1.357 |
光 | +1.333 |
UA | +1.322 |
女 | +1.320 |
Neg logit contributions | |
ertodd | -1.119 |
ysis | -0.867 |
verts | -0.815 |
ered | -0.812 |
quo | -0.798 |
Token | the |
Token ID | 262 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ANE | +0.278 |
awan | +0.266 |
光 | +0.261 |
srf | +0.261 |
女 | +0.259 |
Neg logit contributions | |
ertodd | -0.262 |
ysis | -0.213 |
verts | -0.202 |
ered | -0.201 |
quo | -0.199 |
Token | theft |
Token ID | 12402 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
ertodd | +0.436 |
ysis | +0.358 |
verts | +0.336 |
ered | +0.336 |
quo | +0.333 |
Neg logit contributions | |
ANE | -0.426 |
awan | -0.406 |
srf | -0.399 |
光 | -0.398 |
女 | -0.398 |
Token | of |
Token ID | 286 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
ertodd | +0.670 |
ysis | +0.532 |
verts | +0.504 |
ered | +0.500 |
quo | +0.492 |
Neg logit contributions | |
ANE | -0.701 |
awan | -0.674 |
光 | -0.661 |
UA | -0.654 |
女 | -0.653 |
Token | earthquake |
Token ID | 16295 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
ANE | +1.163 |
awan | +1.114 |
光 | +1.096 |
女 | +1.090 |
srf | +1.087 |
Neg logit contributions | |
ertodd | -1.098 |
ysis | -0.881 |
verts | -0.833 |
ered | -0.833 |
quo | -0.820 |
Token | aid |
Token ID | 6133 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
ertodd | +5.831 |
ysis | +4.767 |
ered | +4.613 |
quo | +4.408 |
verts | +4.292 |
Neg logit contributions | |
ANE | -9.085 |
awan | -8.809 |
srf | -8.788 |
女 | -8.690 |
RAW | -8.660 |
Token | & |
Token ID | 1222 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
ertodd | +0.088 |
ysis | +0.071 |
ered | +0.068 |
verts | +0.068 |
quo | +0.066 |
Neg logit contributions | |
ANE | -0.093 |
awan | -0.089 |
光 | -0.087 |
srf | -0.086 |
女 | -0.086 |
Token | pill |
Token ID | 9582 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
ANE | +0.482 |
awan | +0.462 |
光 | +0.453 |
UA | +0.449 |
女 | +0.449 |
Neg logit contributions | |
ertodd | -0.458 |
ysis | -0.366 |
verts | -0.346 |
ered | -0.346 |
quo | -0.340 |
Token | age |
Token ID | 496 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
ertodd | +1.255 |
ysis | +1.035 |
ered | +0.991 |
verts | +0.978 |
quo | +0.955 |
Neg logit contributions | |
ANE | -1.159 |
awan | -1.111 |
光 | -1.094 |
srf | -1.092 |
UA | -1.090 |
Token | of |
Token ID | 286 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
ertodd | +1.735 |
ysis | +1.415 |
ered | +1.365 |
quo | +1.338 |
verts | +1.337 |
Neg logit contributions | |
ANE | -1.789 |
awan | -1.699 |
srf | -1.679 |
光 | -1.656 |
RAW | -1.650 |
Token | T |
Token ID | 51 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
ertodd | +2.201 |
ysis | +1.853 |
verts | +1.788 |
ered | +1.784 |
quo | +1.752 |
Neg logit contributions | |
ANE | -1.270 |
awan | -1.203 |
光 | -1.168 |
srf | -1.154 |
女 | -1.153 |
Token | Secrets |
Token ID | 23561 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
ertodd | +2.117 |
ysis | +1.695 |
verts | +1.617 |
ered | +1.615 |
quo | +1.576 |
Neg logit contributions | |
ANE | -2.309 |
awan | -2.220 |
光 | -2.178 |
女 | -2.170 |
srf | -2.164 |
Token | St |
Token ID | 520 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
ANE | +1.200 |
awan | +1.152 |
光 | +1.128 |
UA | +1.117 |
女 | +1.116 |
Neg logit contributions | |
ertodd | -1.227 |
ysis | -0.985 |
verts | -0.935 |
ered | -0.932 |
quo | -0.917 |
Token | James |
Token ID | 3700 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ertodd | +0.890 |
ysis | +0.710 |
ered | +0.674 |
verts | +0.669 |
quo | +0.655 |
Neg logit contributions | |
ANE | -0.995 |
awan | -0.952 |
光 | -0.940 |
女 | -0.939 |
srf | -0.930 |
Token | in |
Token ID | 287 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
ertodd | +3.309 |
ysis | +2.714 |
verts | +2.593 |
ered | +2.585 |
Rupert | +2.517 |
Neg logit contributions | |
ANE | -3.417 |
awan | -3.244 |
女 | -3.228 |
光 | -3.222 |
srf | -3.221 |
Token | Monte |
Token ID | 22489 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
ertodd | +0.622 |
ysis | +0.490 |
verts | +0.465 |
ered | +0.462 |
quo | +0.454 |
Neg logit contributions | |
ANE | -0.705 |
awan | -0.678 |
光 | -0.665 |
女 | -0.659 |
UA | -0.659 |
Token | go |
Token ID | 2188 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ertodd | +8.068 |
verts | +6.791 |
ysis | +6.732 |
ered | +6.615 |
Rupert | +6.375 |
Neg logit contributions | |
ANE | -7.150 |
光 | -6.893 |
女 | -6.772 |
srf | -6.724 |
RAW | -6.689 |
Token | Bay |
Token ID | 4696 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
ertodd | +3.533 |
ered | +2.721 |
verts | +2.706 |
ysis | +2.700 |
Jehovah | +2.546 |
Neg logit contributions | |
ANE | -4.433 |
awan | -4.313 |
光 | -4.312 |
RAW | -4.278 |
EMENT | -4.260 |
Token | from |
Token ID | 422 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
ertodd | +1.838 |
ysis | +1.497 |
ered | +1.448 |
verts | +1.444 |
quo | +1.396 |
Neg logit contributions | |
ANE | -1.791 |
awan | -1.710 |
光 | -1.678 |
RAW | -1.678 |
EMENT | -1.677 |
Token | £ |
Token ID | 4248 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
ertodd | +1.036 |
ysis | +0.839 |
verts | +0.797 |
ered | +0.793 |
quo | +0.783 |
Neg logit contributions | |
ANE | -0.917 |
awan | -0.879 |
光 | -0.859 |
UA | -0.851 |
女 | -0.848 |
Token | 1 |
Token ID | 16 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
ANE | +0.063 |
awan | +0.060 |
srf | +0.058 |
光 | +0.058 |
UA | +0.057 |
Neg logit contributions | |
ertodd | -0.101 |
ysis | -0.085 |
verts | -0.082 |
ered | -0.082 |
quo | -0.080 |
Token | we |
Token ID | 356 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
ANE | +1.508 |
awan | +1.449 |
光 | +1.419 |
UA | +1.406 |
女 | +1.406 |
Neg logit contributions | |
ertodd | -1.432 |
ysis | -1.131 |
verts | -1.069 |
ered | -1.063 |
quo | -1.047 |
Token | are |
Token ID | 389 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
ertodd | +0.898 |
ysis | +0.694 |
ered | +0.670 |
verts | +0.654 |
quo | +0.649 |
Neg logit contributions | |
ANE | -1.187 |
awan | -1.142 |
srf | -1.137 |
光 | -1.135 |
UA | -1.126 |
Token | in |
Token ID | 287 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ertodd | +1.073 |
ysis | +0.875 |
ered | +0.841 |
verts | +0.830 |
quo | +0.822 |
Neg logit contributions | |
ANE | -1.084 |
awan | -1.043 |
光 | -1.026 |
srf | -1.022 |
UA | -1.015 |
Token | a |
Token ID | 257 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
ertodd | +3.219 |
ysis | +2.515 |
verts | +2.419 |
ered | +2.386 |
quo | +2.335 |
Neg logit contributions | |
ANE | -4.371 |
awan | -4.254 |
光 | -4.215 |
srf | -4.149 |
UA | -4.132 |
Token | pand |
Token ID | 19798 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
ertodd | +2.536 |
ysis | +2.096 |
verts | +2.014 |
ered | +2.009 |
quo | +1.987 |
Neg logit contributions | |
ANE | -2.310 |
awan | -2.223 |
光 | -2.206 |
UA | -2.170 |
srf | -2.162 |
Token | emic |
Token ID | 5314 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
ertodd | +3.296 |
ysis | +2.278 |
ered | +2.244 |
verts | +1.999 |
quo | +1.799 |
Neg logit contributions | |
ANE | -7.259 |
srf | -7.228 |
senal | -7.140 |
光 | -7.061 |
女 | -6.996 |
Token | situation |
Token ID | 3074 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ertodd | +7.179 |
ysis | +6.085 |
ered | +5.933 |
verts | +5.778 |
quo | +5.769 |
Neg logit contributions | |
ANE | -7.528 |
srf | -7.362 |
senal | -7.351 |
光 | -7.350 |
awan | -7.292 |
Token | ," |
Token ID | 553 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
ertodd | +3.192 |
ysis | +2.596 |
ered | +2.498 |
quo | +2.485 |
verts | +2.472 |
Neg logit contributions | |
ANE | -3.298 |
awan | -3.183 |
srf | -3.171 |
光 | -3.156 |
senal | -3.151 |
Token | he |
Token ID | 339 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ertodd | +2.145 |
ysis | +1.635 |
ered | +1.530 |
verts | +1.525 |
quo | +1.504 |
Neg logit contributions | |
ANE | -3.096 |
awan | -2.981 |
光 | -2.945 |
srf | -2.935 |
UA | -2.927 |
Token | said |
Token ID | 531 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
ertodd | +2.926 |
ysis | +2.310 |
ered | +2.216 |
verts | +2.204 |
quo | +2.183 |
Neg logit contributions | |
ANE | -3.281 |
awan | -3.127 |
srf | -3.117 |
光 | -3.091 |
女 | -3.063 |
Token | . |
Token ID | 13 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
ertodd | +1.068 |
ysis | +0.884 |
verts | +0.849 |
ered | +0.849 |
quo | +0.835 |
Neg logit contributions | |
ANE | -0.779 |
awan | -0.738 |
光 | -0.722 |
srf | -0.717 |
UA | -0.715 |
Token | tad |
Token ID | 36264 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
ertodd | +0.946 |
ysis | +0.774 |
verts | +0.740 |
ered | +0.738 |
quo | +0.730 |
Neg logit contributions | |
ANE | -0.860 |
awan | -0.823 |
光 | -0.808 |
srf | -0.803 |
女 | -0.803 |
Token | pole |
Token ID | 36869 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ertodd | +3.384 |
ysis | +2.807 |
verts | +2.697 |
ered | +2.683 |
quo | +2.663 |
Neg logit contributions | |
ANE | -2.350 |
awan | -2.213 |
光 | -2.184 |
UA | -2.156 |
srf | -2.151 |
Token | had |
Token ID | 550 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ertodd | +2.957 |
ysis | +2.315 |
ered | +2.243 |
verts | +2.216 |
quo | +2.199 |
Neg logit contributions | |
ANE | -3.484 |
srf | -3.356 |
光 | -3.316 |
awan | -3.311 |
senal | -3.308 |
Token | just |
Token ID | 655 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ertodd | +2.923 |
ysis | +2.325 |
ered | +2.272 |
verts | +2.199 |
Jehovah | +2.160 |
Neg logit contributions | |
ANE | -3.513 |
awan | -3.392 |
srf | -3.365 |
光 | -3.326 |
senal | -3.324 |
Token | a |
Token ID | 257 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ertodd | +2.968 |
ysis | +2.337 |
ered | +2.299 |
verts | +2.228 |
quo | +2.198 |
Neg logit contributions | |
ANE | -3.468 |
srf | -3.334 |
awan | -3.326 |
senal | -3.325 |
光 | -3.278 |
Token | tail |
Token ID | 7894 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
ertodd | +3.882 |
ysis | +3.216 |
ered | +3.167 |
verts | +3.121 |
quo | +3.101 |
Neg logit contributions | |
ANE | -3.428 |
awan | -3.303 |
光 | -3.251 |
srf | -3.242 |
UA | -3.237 |
Token | I |
Token ID | 314 |
Feature activation | +2.13e-03 |
Pos logit contributions | |
ertodd | +6.603 |
ysis | +5.398 |
ered | +5.397 |
quo | +5.225 |
verts | +5.060 |
Neg logit contributions | |
ANE | -7.920 |
srf | -7.863 |
senal | -7.769 |
光 | -7.730 |
女 | -7.649 |
Token | sold |
Token ID | 2702 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
ertodd | +0.005 |
ysis | +0.004 |
ered | +0.004 |
verts | +0.004 |
quo | +0.003 |
Neg logit contributions | |
ANE | -0.008 |
awan | -0.007 |
光 | -0.007 |
srf | -0.007 |
UA | -0.007 |
Token | ' |
Token ID | 705 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
ertodd | +0.463 |
ysis | +0.365 |
ered | +0.350 |
verts | +0.344 |
quo | +0.337 |
Neg logit contributions | |
ANE | -0.564 |
awan | -0.542 |
光 | -0.533 |
srf | -0.532 |
女 | -0.531 |
Token | em |
Token ID | 368 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ANE | +1.681 |
awan | +1.618 |
光 | +1.575 |
UA | +1.562 |
女 | +1.553 |
Neg logit contributions | |
ertodd | -1.984 |
ysis | -1.611 |
verts | -1.534 |
ered | -1.522 |
quo | -1.510 |
Token | for |
Token ID | 329 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
ANE | +0.689 |
awan | +0.659 |
光 | +0.646 |
UA | +0.641 |
女 | +0.640 |
Neg logit contributions | |
ertodd | -0.752 |
ysis | -0.613 |
ered | -0.583 |
verts | -0.582 |
quo | -0.573 |
Token | into |
Token ID | 656 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
ertodd | +0.350 |
ysis | +0.292 |
ered | +0.282 |
verts | +0.279 |
quo | +0.276 |
Neg logit contributions | |
ANE | -0.272 |
awan | -0.261 |
光 | -0.255 |
srf | -0.255 |
UA | -0.252 |
Token | them |
Token ID | 606 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
ANE | +0.318 |
awan | +0.307 |
光 | +0.301 |
UA | +0.298 |
女 | +0.298 |
Neg logit contributions | |
ertodd | -0.282 |
ysis | -0.222 |
verts | -0.210 |
ered | -0.209 |
quo | -0.205 |
Token | ". |
Token ID | 1911 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
ANE | +0.072 |
awan | +0.069 |
光 | +0.067 |
srf | +0.066 |
UA | +0.066 |
Neg logit contributions | |
ertodd | -0.083 |
ysis | -0.067 |
ered | -0.064 |
verts | -0.064 |
quo | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
ertodd | +2.114 |
ysis | +1.604 |
ered | +1.506 |
verts | +1.497 |
quo | +1.457 |
Neg logit contributions | |
ANE | -3.009 |
srf | -2.921 |
awan | -2.900 |
senal | -2.882 |
光 | -2.872 |
Token |
|
Token ID | 198 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
ertodd | +1.662 |
ysis | +1.260 |
ered | +1.211 |
verts | +1.203 |
quo | +1.157 |
Neg logit contributions | |
ANE | -2.443 |
srf | -2.426 |
senal | -2.405 |
awan | -2.352 |
光 | -2.331 |
Token | Topics |
Token ID | 25902 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
ertodd | +0.805 |
ysis | +0.664 |
ered | +0.642 |
verts | +0.641 |
quo | +0.624 |
Neg logit contributions | |
ANE | -0.652 |
srf | -0.633 |
awan | -0.628 |
senal | -0.615 |
光 | -0.615 |
Token | : |
Token ID | 25 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
ertodd | +6.171 |
ered | +4.789 |
verts | +4.625 |
ysis | +4.580 |
Rupert | +4.515 |
Neg logit contributions | |
srf | -9.048 |
senal | -8.972 |
adolesc | -8.589 |
ANE | -8.561 |
awan | -8.345 |
Token | marine |
Token ID | 16050 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ertodd | +1.912 |
ysis | +1.542 |
ered | +1.483 |
verts | +1.483 |
quo | +1.463 |
Neg logit contributions | |
ANE | -2.147 |
光 | -2.046 |
awan | -2.043 |
UA | -2.012 |
RAW | -2.007 |
Token | - |
Token ID | 12 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
ertodd | +3.795 |
ysis | +2.852 |
verts | +2.708 |
ered | +2.703 |
quo | +2.604 |
Neg logit contributions | |
ANE | -5.868 |
awan | -5.613 |
光 | -5.572 |
srf | -5.567 |
EMENT | -5.548 |
Token | biology |
Token ID | 43592 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ANE | +0.769 |
awan | +0.737 |
光 | +0.719 |
UA | +0.713 |
女 | +0.711 |
Neg logit contributions | |
ertodd | -0.917 |
ysis | -0.746 |
verts | -0.711 |
ered | -0.708 |
quo | -0.700 |
Token | , |
Token ID | 11 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
ertodd | +3.890 |
ysis | +3.140 |
verts | +3.022 |
ered | +3.009 |
quo | +2.922 |
Neg logit contributions | |
ANE | -3.975 |
srf | -3.839 |
senal | -3.790 |
awan | -3.750 |
光 | -3.730 |
Token | support |
Token ID | 1104 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
ANE | +1.427 |
awan | +1.372 |
光 | +1.344 |
UA | +1.331 |
女 | +1.330 |
Neg logit contributions | |
ertodd | -1.186 |
ysis | -0.924 |
verts | -0.865 |
ered | -0.860 |
quo | -0.848 |
Token | the |
Token ID | 262 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
ANE | +0.781 |
awan | +0.744 |
UA | +0.729 |
光 | +0.728 |
女 | +0.724 |
Neg logit contributions | |
ertodd | -0.639 |
ysis | -0.491 |
verts | -0.459 |
ered | -0.455 |
quo | -0.447 |
Token | mission |
Token ID | 4365 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
ertodd | +0.071 |
ysis | +0.057 |
verts | +0.054 |
ered | +0.054 |
quo | +0.053 |
Neg logit contributions | |
ANE | -0.063 |
awan | -0.060 |
光 | -0.059 |
UA | -0.058 |
女 | -0.058 |
Token | of |
Token ID | 286 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
ertodd | +2.387 |
ysis | +1.873 |
ered | +1.777 |
verts | +1.771 |
quo | +1.769 |
Neg logit contributions | |
ANE | -2.981 |
awan | -2.835 |
srf | -2.830 |
光 | -2.823 |
senal | -2.804 |
Token | New |
Token ID | 968 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
ANE | +2.193 |
awan | +2.048 |
UA | +2.047 |
光 | +2.038 |
RAW | +2.032 |
Neg logit contributions | |
ertodd | -2.214 |
ysis | -1.712 |
ered | -1.592 |
verts | -1.585 |
quo | -1.568 |
Token | Advent |
Token ID | 33732 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
ertodd | +1.218 |
ysis | +0.902 |
ered | +0.836 |
verts | +0.824 |
Jehovah | +0.809 |
Neg logit contributions | |
ANE | -2.174 |
awan | -2.115 |
光 | -2.074 |
EMENT | -2.069 |
RAW | -2.065 |
Token | and |
Token ID | 290 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
ertodd | +6.008 |
ered | +4.649 |
ysis | +4.580 |
quo | +4.263 |
verts | +4.236 |
Neg logit contributions | |
srf | -9.085 |
ANE | -9.026 |
awan | -8.813 |
senal | -8.797 |
光 | -8.711 |
Token | get |
Token ID | 651 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
ANE | +1.359 |
awan | +1.322 |
女 | +1.278 |
RAW | +1.269 |
EMENT | +1.262 |
Neg logit contributions | |
ertodd | -1.860 |
ysis | -1.491 |
verts | -1.437 |
ered | -1.387 |
quo | -1.385 |
Token | the |
Token ID | 262 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
ANE | +1.600 |
awan | +1.563 |
女 | +1.535 |
EMENT | +1.532 |
UA | +1.518 |
Neg logit contributions | |
ertodd | -1.488 |
ysis | -1.175 |
verts | -1.088 |
ered | -1.080 |
quo | -1.035 |
Token | full |
Token ID | 1336 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
ANE | +1.019 |
awan | +0.990 |
UA | +0.946 |
女 | +0.943 |
光 | +0.938 |
Neg logit contributions | |
ertodd | -1.769 |
ysis | -1.482 |
verts | -1.419 |
ered | -1.399 |
Jehovah | -1.372 |
Token | contents |
Token ID | 10154 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
ertodd | +2.152 |
ysis | +1.816 |
verts | +1.760 |
quo | +1.736 |
ered | +1.735 |
Neg logit contributions | |
ANE | -1.474 |
awan | -1.366 |
光 | -1.350 |
女 | -1.337 |
RAW | -1.322 |
Token | problem |
Token ID | 1917 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ANE | +0.333 |
awan | +0.320 |
光 | +0.313 |
UA | +0.310 |
女 | +0.310 |
Neg logit contributions | |
ertodd | -0.297 |
ysis | -0.233 |
verts | -0.219 |
ered | -0.218 |
quo | -0.215 |
Token | is |
Token ID | 318 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
ertodd | +3.963 |
ysis | +3.064 |
verts | +2.951 |
ered | +2.937 |
quo | +2.913 |
Neg logit contributions | |
ANE | -5.373 |
srf | -5.219 |
awan | -5.205 |
光 | -5.196 |
senal | -5.092 |
Token | that |
Token ID | 326 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
ANE | +1.013 |
awan | +0.973 |
光 | +0.953 |
UA | +0.943 |
女 | +0.941 |
Neg logit contributions | |
ertodd | -1.060 |
ysis | -0.853 |
verts | -0.810 |
ered | -0.807 |
quo | -0.795 |
Token | the |
Token ID | 262 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
ANE | +0.803 |
awan | +0.773 |
光 | +0.757 |
UA | +0.750 |
女 | +0.750 |
Neg logit contributions | |
ertodd | -0.723 |
ysis | -0.567 |
verts | -0.535 |
ered | -0.531 |
quo | -0.523 |
Token | pand |
Token ID | 19798 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ANE | +0.095 |
awan | +0.091 |
光 | +0.089 |
UA | +0.089 |
女 | +0.089 |
Neg logit contributions | |
ertodd | -0.085 |
ysis | -0.067 |
verts | -0.063 |
ered | -0.063 |
quo | -0.062 |
Token | emic |
Token ID | 5314 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
ertodd | +2.656 |
ysis | +1.886 |
ered | +1.822 |
verts | +1.796 |
quo | +1.553 |
Neg logit contributions | |
ANE | -5.398 |
srf | -5.298 |
光 | -5.218 |
女 | -5.197 |
senal | -5.172 |
Token | phase |
Token ID | 7108 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ertodd | +6.100 |
ysis | +4.812 |
verts | +4.760 |
ered | +4.695 |
quo | +4.559 |
Neg logit contributions | |
ANE | -8.561 |
srf | -8.556 |
光 | -8.400 |
senal | -8.285 |
awan | -8.263 |
Token | system |
Token ID | 1080 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
ertodd | +3.145 |
ysis | +2.485 |
ered | +2.368 |
verts | +2.358 |
quo | +2.349 |
Neg logit contributions | |
ANE | -4.101 |
awan | -3.992 |
srf | -3.969 |
光 | -3.947 |
女 | -3.924 |
Token | is |
Token ID | 318 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
ertodd | +0.800 |
ysis | +0.629 |
verts | +0.595 |
ered | +0.593 |
quo | +0.583 |
Neg logit contributions | |
ANE | -0.957 |
awan | -0.921 |
光 | -0.910 |
srf | -0.903 |
女 | -0.899 |
Token | designed |
Token ID | 3562 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
ANE | +0.194 |
awan | +0.187 |
光 | +0.184 |
srf | +0.183 |
UA | +0.181 |
Neg logit contributions | |
ertodd | -0.203 |
ysis | -0.166 |
ered | -0.158 |
verts | -0.157 |
quo | -0.155 |
Token | for |
Token ID | 329 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
ANE | +0.126 |
awan | +0.121 |
光 | +0.118 |
UA | +0.117 |
女 | +0.117 |
Neg logit contributions | |
ertodd | -0.147 |
ysis | -0.119 |
verts | -0.114 |
ered | -0.113 |
quo | -0.112 |
Token | that |
Token ID | 326 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
ertodd | +0.845 |
ysis | +0.663 |
ered | +0.628 |
verts | +0.626 |
quo | +0.612 |
Neg logit contributions | |
ANE | -1.040 |
awan | -1.001 |
光 | -0.983 |
srf | -0.981 |
UA | -0.976 |
Token | she |
Token ID | 673 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
ANE | +0.062 |
awan | +0.060 |
光 | +0.059 |
UA | +0.058 |
女 | +0.058 |
Neg logit contributions | |
ertodd | -0.048 |
ysis | -0.037 |
verts | -0.035 |
ered | -0.034 |
quo | -0.034 |
Token | was |
Token ID | 373 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
ertodd | +0.140 |
ysis | +0.109 |
verts | +0.103 |
ered | +0.103 |
quo | +0.101 |
Neg logit contributions | |
ANE | -0.167 |
awan | -0.161 |
光 | -0.158 |
srf | -0.157 |
UA | -0.157 |
Token | pressing |
Token ID | 12273 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
ertodd | +1.672 |
ysis | +1.348 |
ered | +1.291 |
verts | +1.283 |
quo | +1.278 |
Neg logit contributions | |
ANE | -1.938 |
awan | -1.875 |
srf | -1.866 |
光 | -1.844 |
senal | -1.823 |
Token | for |
Token ID | 329 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
ANE | +0.311 |
awan | +0.299 |
光 | +0.293 |
UA | +0.290 |
女 | +0.290 |
Neg logit contributions | |
ertodd | -0.310 |
ysis | -0.248 |
verts | -0.235 |
ered | -0.234 |
quo | -0.231 |
Token | Jun |
Token ID | 7653 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
ertodd | +1.332 |
ysis | +1.029 |
verts | +0.967 |
ered | +0.963 |
quo | +0.950 |
Neg logit contributions | |
ANE | -1.777 |
awan | -1.716 |
光 | -1.690 |
srf | -1.674 |
UA | -1.670 |
Token | cker |
Token ID | 15280 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ertodd | +2.303 |
ered | +1.029 |
ysis | +0.966 |
verts | +0.916 |
quo | +0.842 |
Neg logit contributions | |
senal | -12.517 |
srf | -12.417 |
ANE | -12.278 |
光 | -12.005 |
adolesc | -11.969 |
Token | to |
Token ID | 284 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
ertodd | +5.110 |
ysis | +4.170 |
ered | +3.970 |
verts | +3.918 |
quo | +3.898 |
Neg logit contributions | |
ANE | -4.920 |
awan | -4.705 |
srf | -4.610 |
光 | -4.592 |
UA | -4.589 |
Token | take |
Token ID | 1011 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ertodd | +2.306 |
ysis | +1.855 |
ered | +1.831 |
quo | +1.766 |
verts | +1.756 |
Neg logit contributions | |
ANE | -2.676 |
srf | -2.584 |
senal | -2.579 |
awan | -2.553 |
光 | -2.546 |
Token | the |
Token ID | 262 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
ertodd | +3.494 |
ysis | +2.884 |
ered | +2.741 |
verts | +2.734 |
quo | +2.673 |
Neg logit contributions | |
ANE | -4.456 |
srf | -4.284 |
光 | -4.277 |
awan | -4.274 |
UA | -4.215 |
Token | reins |
Token ID | 35627 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
ertodd | +0.825 |
ysis | +0.667 |
verts | +0.640 |
ered | +0.639 |
quo | +0.631 |
Neg logit contributions | |
ANE | -0.838 |
awan | -0.802 |
光 | -0.793 |
srf | -0.788 |
女 | -0.785 |
Token | We |
Token ID | 1135 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
ANE | +0.439 |
srf | +0.427 |
awan | +0.423 |
senal | +0.410 |
光 | +0.409 |
Neg logit contributions | |
ertodd | -0.742 |
ysis | -0.632 |
verts | -0.611 |
ered | -0.609 |
quo | -0.598 |
Token | 're |
Token ID | 821 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
ertodd | +0.830 |
ysis | +0.648 |
ered | +0.624 |
verts | +0.608 |
quo | +0.606 |
Neg logit contributions | |
ANE | -1.027 |
awan | -0.981 |
光 | -0.978 |
srf | -0.976 |
UA | -0.972 |
Token | hoping |
Token ID | 7725 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
ertodd | +2.335 |
ysis | +1.900 |
ered | +1.826 |
verts | +1.823 |
Jehovah | +1.820 |
Neg logit contributions | |
ANE | -2.302 |
光 | -2.206 |
awan | -2.204 |
srf | -2.187 |
UA | -2.177 |
Token | that |
Token ID | 326 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
ertodd | +0.528 |
ysis | +0.418 |
ered | +0.396 |
verts | +0.394 |
quo | +0.391 |
Neg logit contributions | |
ANE | -0.639 |
awan | -0.616 |
光 | -0.611 |
srf | -0.607 |
女 | -0.604 |
Token | he |
Token ID | 339 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
ANE | +0.944 |
awan | +0.909 |
光 | +0.894 |
UA | +0.885 |
srf | +0.885 |
Neg logit contributions | |
ertodd | -0.820 |
ysis | -0.648 |
verts | -0.613 |
ered | -0.611 |
quo | -0.602 |
Token | sur |
Token ID | 969 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
ertodd | +1.089 |
ysis | +0.850 |
verts | +0.804 |
ered | +0.804 |
quo | +0.789 |
Neg logit contributions | |
ANE | -1.337 |
awan | -1.285 |
光 | -1.264 |
srf | -1.260 |
UA | -1.256 |
Token | rend |
Token ID | 10920 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ertodd | +6.401 |
ysis | +5.139 |
verts | +5.062 |
ered | +5.032 |
prises | +4.858 |
Neg logit contributions | |
ANE | -8.369 |
srf | -7.996 |
senal | -7.985 |
女 | -7.957 |
UA | -7.881 |
Token | ers |
Token ID | 364 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
ertodd | +3.340 |
ered | +2.436 |
ysis | +2.315 |
verts | +2.287 |
quo | +2.023 |
Neg logit contributions | |
ANE | -6.614 |
senal | -6.519 |
srf | -6.514 |
光 | -6.376 |
女 | -6.335 |
Token | ," |
Token ID | 553 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
ertodd | +1.842 |
ysis | +1.494 |
ered | +1.431 |
verts | +1.416 |
quo | +1.408 |
Neg logit contributions | |
ANE | -1.967 |
awan | -1.877 |
光 | -1.848 |
srf | -1.843 |
女 | -1.836 |
Token | the |
Token ID | 262 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
ertodd | +1.555 |
ysis | +1.166 |
ered | +1.082 |
verts | +1.081 |
quo | +1.068 |
Neg logit contributions | |
ANE | -2.398 |
awan | -2.310 |
光 | -2.289 |
女 | -2.267 |
UA | -2.262 |
Token | police |
Token ID | 1644 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
ertodd | +1.081 |
ysis | +0.849 |
ered | +0.794 |
verts | +0.791 |
quo | +0.785 |
Neg logit contributions | |
ANE | -1.360 |
awan | -1.309 |
光 | -1.294 |
女 | -1.283 |
UA | -1.282 |
Token | 5 |
Token ID | 642 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
ANE | +5.387 |
awan | +5.140 |
光 | +5.055 |
RAW | +4.985 |
UA | +4.966 |
Neg logit contributions | |
ertodd | -7.167 |
ysis | -5.840 |
verts | -5.453 |
ered | -5.426 |
quo | -5.369 |
Token | years |
Token ID | 812 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
ANE | +1.277 |
awan | +1.230 |
光 | +1.205 |
UA | +1.195 |
女 | +1.194 |
Neg logit contributions | |
ertodd | -1.091 |
ysis | -0.854 |
verts | -0.807 |
ered | -0.804 |
quo | -0.789 |
Token | on |
Token ID | 319 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
ANE | +2.200 |
awan | +2.109 |
光 | +2.063 |
UA | +2.041 |
女 | +2.039 |
Neg logit contributions | |
ertodd | -2.453 |
ysis | -1.986 |
verts | -1.890 |
ered | -1.880 |
quo | -1.853 |
Token | the |
Token ID | 262 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
ANE | +2.130 |
awan | +2.050 |
光 | +2.010 |
UA | +1.992 |
女 | +1.988 |
Neg logit contributions | |
ertodd | -1.972 |
ysis | -1.560 |
verts | -1.473 |
ered | -1.466 |
quo | -1.442 |
Token | housing |
Token ID | 5627 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
ANE | +0.726 |
awan | +0.695 |
光 | +0.681 |
UA | +0.675 |
女 | +0.674 |
Neg logit contributions | |
ertodd | -0.762 |
ysis | -0.615 |
verts | -0.584 |
ered | -0.582 |
quo | -0.574 |
Token | bubble |
Token ID | 14310 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
ANE | +2.364 |
awan | +2.275 |
光 | +2.231 |
UA | +2.212 |
女 | +2.207 |
Neg logit contributions | |
ertodd | -2.168 |
ysis | -1.713 |
verts | -1.618 |
ered | -1.609 |
quo | -1.581 |
Token | / |
Token ID | 14 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
ertodd | +7.144 |
ered | +5.722 |
ysis | +5.702 |
quo | +5.649 |
verts | +5.474 |
Neg logit contributions | |
ANE | -7.457 |
awan | -7.099 |
srf | -7.075 |
光 | -6.939 |
女 | -6.871 |
Token | b |
Token ID | 65 |
Feature activation | +7.85e-02 |
Pos logit contributions | |
ANE | +2.443 |
awan | +2.342 |
光 | +2.282 |
UA | +2.266 |
女 | +2.256 |
Neg logit contributions | |
ertodd | -3.230 |
ysis | -2.656 |
verts | -2.527 |
ered | -2.516 |
quo | -2.492 |
Token | ust |
Token ID | 436 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
ertodd | +0.251 |
ysis | +0.205 |
ered | +0.197 |
verts | +0.196 |
quo | +0.191 |
Neg logit contributions | |
ANE | -0.214 |
awan | -0.203 |
光 | -0.202 |
srf | -0.202 |
女 | -0.200 |
Token | : |
Token ID | 25 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
ertodd | +2.337 |
ysis | +1.898 |
ered | +1.853 |
quo | +1.797 |
verts | +1.795 |
Neg logit contributions | |
ANE | -2.199 |
awan | -2.118 |
光 | -2.073 |
srf | -2.050 |
女 | -2.042 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ANE | +2.256 |
awan | +2.178 |
光 | +2.136 |
女 | +2.120 |
UA | +2.118 |
Neg logit contributions | |
ertodd | -1.966 |
ysis | -1.548 |
verts | -1.459 |
ered | -1.442 |
quo | -1.403 |
Token | star |
Token ID | 3491 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
ANE | +2.467 |
awan | +2.375 |
光 | +2.317 |
UA | +2.299 |
女 | +2.287 |
Neg logit contributions | |
ertodd | -2.737 |
ysis | -2.207 |
verts | -2.095 |
ered | -2.082 |
quo | -2.061 |
Token | ( |
Token ID | 357 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ertodd | +0.886 |
ysis | +0.702 |
verts | +0.671 |
ered | +0.668 |
quo | +0.654 |
Neg logit contributions | |
ANE | -0.958 |
awan | -0.918 |
光 | -0.902 |
女 | -0.897 |
UA | -0.894 |
Token | Sh |
Token ID | 2484 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
ANE | +3.087 |
awan | +2.943 |
光 | +2.878 |
UA | +2.844 |
女 | +2.830 |
Neg logit contributions | |
ertodd | -4.473 |
ysis | -3.706 |
verts | -3.529 |
ered | -3.523 |
quo | -3.495 |
Token | rav |
Token ID | 4108 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
ANE | +0.431 |
awan | +0.409 |
光 | +0.401 |
srf | +0.397 |
女 | +0.397 |
Neg logit contributions | |
ertodd | -0.613 |
ysis | -0.510 |
ered | -0.488 |
verts | -0.487 |
quo | -0.478 |
Token | ana |
Token ID | 2271 |
Feature activation | -4.57e-03 |
Pos logit contributions | |
ANE | +1.320 |
awan | +1.268 |
光 | +1.229 |
UA | +1.219 |
女 | +1.212 |
Neg logit contributions | |
ertodd | -1.615 |
ysis | -1.311 |
verts | -1.254 |
ered | -1.247 |
quo | -1.234 |
Token | Nak |
Token ID | 22255 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
ANE | +0.012 |
awan | +0.012 |
光 | +0.011 |
UA | +0.011 |
女 | +0.011 |
Neg logit contributions | |
ertodd | -0.015 |
ysis | -0.012 |
verts | -0.012 |
ered | -0.012 |
quo | -0.011 |
Token | sh |
Token ID | 1477 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
awan | +6.988 |
ANE | +6.937 |
UA | +6.493 |
光 | +6.274 |
pull | +6.250 |
Neg logit contributions | |
ertodd | -8.990 |
ysis | -7.167 |
quo | -6.986 |
verts | -6.931 |
ered | -6.805 |
Token | tra |
Token ID | 9535 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
ANE | +2.097 |
awan | +2.017 |
光 | +1.933 |
UA | +1.933 |
RAW | +1.911 |
Neg logit contributions | |
ertodd | -2.940 |
ysis | -2.425 |
verts | -2.323 |
ered | -2.303 |
quo | -2.294 |
Token | ) |
Token ID | 8 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
ertodd | +0.710 |
ysis | +0.591 |
verts | +0.569 |
ered | +0.568 |
quo | +0.559 |
Neg logit contributions | |
ANE | -0.504 |
awan | -0.477 |
光 | -0.466 |
srf | -0.463 |
女 | -0.462 |
Token | these |
Token ID | 777 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
ertodd | +1.992 |
ysis | +1.584 |
verts | +1.507 |
ered | +1.503 |
quo | +1.493 |
Neg logit contributions | |
ANE | -2.285 |
awan | -2.183 |
srf | -2.149 |
EMENT | -2.141 |
光 | -2.137 |
Token | p |
Token ID | 279 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ertodd | +1.120 |
ysis | +0.890 |
verts | +0.844 |
ered | +0.842 |
quo | +0.829 |
Neg logit contributions | |
ANE | -1.242 |
awan | -1.198 |
光 | -1.173 |
UA | -1.161 |
srf | -1.160 |
Token | a |
Token ID | 257 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ANE | +0.038 |
awan | +0.037 |
光 | +0.036 |
srf | +0.036 |
UA | +0.036 |
Neg logit contributions | |
ertodd | -0.034 |
ysis | -0.027 |
ered | -0.026 |
verts | -0.026 |
quo | -0.025 |
Token | number |
Token ID | 1271 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ertodd | +0.402 |
ysis | +0.326 |
verts | +0.309 |
ered | +0.309 |
quo | +0.305 |
Neg logit contributions | |
ANE | -0.385 |
awan | -0.368 |
光 | -0.360 |
UA | -0.360 |
srf | -0.357 |
Token | of |
Token ID | 286 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
ertodd | +0.419 |
ysis | +0.333 |
verts | +0.317 |
ered | +0.315 |
quo | +0.307 |
Neg logit contributions | |
ANE | -0.425 |
awan | -0.408 |
光 | -0.401 |
女 | -0.397 |
UA | -0.397 |
Token | things |
Token ID | 1243 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
ANE | +1.923 |
awan | +1.847 |
光 | +1.809 |
UA | +1.792 |
女 | +1.789 |
Neg logit contributions | |
ertodd | -1.919 |
ysis | -1.533 |
verts | -1.453 |
ered | -1.447 |
quo | -1.424 |
Token | to |
Token ID | 284 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
ANE | +0.094 |
awan | +0.091 |
光 | +0.089 |
srf | +0.088 |
UA | +0.088 |
Neg logit contributions | |
ertodd | -0.085 |
ysis | -0.068 |
ered | -0.064 |
verts | -0.064 |
quo | -0.063 |
Token | argue |
Token ID | 7267 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
ANE | +1.636 |
awan | +1.575 |
光 | +1.543 |
女 | +1.528 |
UA | +1.527 |
Neg logit contributions | |
ertodd | -1.482 |
ysis | -1.170 |
verts | -1.104 |
ered | -1.094 |
quo | -1.078 |
Token | with |
Token ID | 351 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
ANE | +6.309 |
awan | +5.946 |
RAW | +5.803 |
女 | +5.775 |
EMENT | +5.772 |
Neg logit contributions | |
ertodd | -9.502 |
ysis | -7.779 |
verts | -7.476 |
ered | -7.291 |
gencies | -7.277 |
Token | in |
Token ID | 287 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
ANE | +1.784 |
awan | +1.705 |
光 | +1.666 |
UA | +1.648 |
女 | +1.645 |
Neg logit contributions | |
ertodd | -2.197 |
ysis | -1.799 |
verts | -1.717 |
ered | -1.710 |
quo | -1.687 |
Token | Reed |
Token ID | 16105 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
ANE | +0.918 |
awan | +0.884 |
光 | +0.868 |
UA | +0.861 |
女 | +0.859 |
Neg logit contributions | |
ertodd | -0.785 |
ysis | -0.614 |
verts | -0.581 |
ered | -0.577 |
quo | -0.568 |
Token | � |
Token ID | 447 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
ANE | +1.076 |
awan | +1.033 |
光 | +1.013 |
UA | +1.005 |
女 | +1.003 |
Neg logit contributions | |
ertodd | -1.054 |
ysis | -0.840 |
verts | -0.796 |
ered | -0.793 |
quo | -0.780 |
Token | � |
Token ID | 247 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
ertodd | +0.173 |
ysis | +0.145 |
ered | +0.139 |
verts | +0.139 |
quo | +0.137 |
Neg logit contributions | |
ANE | -0.110 |
awan | -0.105 |
光 | -0.101 |
UA | -0.100 |
女 | -0.100 |
Token | , |
Token ID | 837 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
ANE | +3.553 |
awan | +3.365 |
光 | +3.309 |
UA | +3.294 |
RAW | +3.283 |
Neg logit contributions | |
ertodd | -4.454 |
ysis | -3.605 |
verts | -3.441 |
ered | -3.437 |
quo | -3.416 |
Token | r |
Token ID | 374 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
ertodd | +1.583 |
ysis | +1.307 |
verts | +1.267 |
ered | +1.253 |
quo | +1.250 |
Neg logit contributions | |
ANE | -1.318 |
awan | -1.271 |
光 | -1.239 |
女 | -1.217 |
UA | -1.211 |
Token | ' |
Token ID | 705 |
Feature activation | +9.38e-02 |
Pos logit contributions | |
ANE | +0.587 |
awan | +0.561 |
光 | +0.548 |
女 | +0.541 |
UA | +0.538 |
Neg logit contributions | |
ertodd | -0.781 |
ysis | -0.646 |
verts | -0.620 |
ered | -0.616 |
quo | -0.607 |
Token | \ |
Token ID | 59 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
ertodd | +0.317 |
ysis | +0.264 |
verts | +0.253 |
ered | +0.252 |
quo | +0.248 |
Neg logit contributions | |
ANE | -0.237 |
awan | -0.227 |
光 | -0.220 |
srf | -0.219 |
女 | -0.218 |
Token | [ |
Token ID | 58 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ANE | +1.220 |
awan | +1.164 |
光 | +1.135 |
UA | +1.120 |
srf | +1.119 |
Neg logit contributions | |
ertodd | -1.608 |
ysis | -1.329 |
verts | -1.272 |
ered | -1.267 |
quo | -1.248 |
Token | +( |
Token ID | 33747 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
ANE | +2.855 |
awan | +2.715 |
光 | +2.652 |
UA | +2.651 |
女 | +2.625 |
Neg logit contributions | |
ertodd | -3.744 |
ysis | -3.069 |
verts | -2.917 |
ered | -2.907 |
quo | -2.880 |
Token | \ |
Token ID | 59 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ANE | +6.665 |
awan | +6.282 |
UA | +6.273 |
RAW | +6.194 |
EMENT | +6.179 |
Neg logit contributions | |
ertodd | -9.121 |
ysis | -7.472 |
quo | -7.028 |
ered | -7.028 |
verts | -6.981 |
Token | S |
Token ID | 50 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
ANE | +2.797 |
awan | +2.664 |
光 | +2.607 |
UA | +2.584 |
女 | +2.576 |
Neg logit contributions | |
ertodd | -3.672 |
ysis | -3.009 |
verts | -2.870 |
ered | -2.865 |
quo | -2.841 |
Token | + |
Token ID | 10 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
ANE | +1.393 |
awan | +1.325 |
光 | +1.291 |
UA | +1.271 |
女 | +1.270 |
Neg logit contributions | |
ertodd | -2.180 |
ysis | -1.826 |
verts | -1.753 |
ered | -1.747 |
quo | -1.725 |
Token | )\ |
Token ID | 19415 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
ANE | +1.370 |
awan | +1.287 |
光 | +1.247 |
UA | +1.234 |
女 | +1.229 |
Neg logit contributions | |
ertodd | -2.641 |
ysis | -2.240 |
verts | -2.153 |
ered | -2.146 |
quo | -2.128 |
Token | s |
Token ID | 82 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
ertodd | +0.613 |
ysis | +0.513 |
verts | +0.496 |
ered | +0.489 |
quo | +0.479 |
Neg logit contributions | |
ANE | -0.432 |
awan | -0.416 |
srf | -0.406 |
光 | -0.399 |
EMENT | -0.396 |
Token | ] |
Token ID | 60 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ANE | +3.181 |
awan | +3.040 |
光 | +2.974 |
UA | +2.944 |
RAW | +2.930 |
Neg logit contributions | |
ertodd | -3.809 |
ysis | -3.099 |
verts | -2.950 |
ered | -2.941 |
quo | -2.902 |
Token | :: |
Token ID | 3712 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ertodd | +0.380 |
ysis | +0.321 |
ered | +0.310 |
verts | +0.308 |
quo | +0.304 |
Neg logit contributions | |
ANE | -0.218 |
awan | -0.208 |
光 | -0.202 |
女 | -0.201 |
srf | -0.200 |
Token | From |
Token ID | 4863 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
ANE | +2.535 |
awan | +2.394 |
光 | +2.321 |
UA | +2.299 |
女 | +2.281 |
Neg logit contributions | |
ertodd | -4.594 |
ysis | -3.873 |
verts | -3.715 |
ered | -3.704 |
quo | -3.674 |
Token | Ar |
Token ID | 3163 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
ertodd | +0.170 |
ysis | +0.143 |
verts | +0.139 |
ered | +0.139 |
quo | +0.136 |
Neg logit contributions | |
ANE | -0.093 |
awan | -0.090 |
srf | -0.088 |
光 | -0.086 |
女 | -0.086 |
Token | gb |
Token ID | 22296 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ertodd | +0.137 |
ysis | +0.104 |
verts | +0.098 |
ered | +0.098 |
quo | +0.095 |
Neg logit contributions | |
ANE | -0.189 |
awan | -0.182 |
光 | -0.180 |
srf | -0.178 |
女 | -0.178 |
Token | ($ |
Token ID | 16763 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
ANE | +3.126 |
awan | +2.966 |
光 | +2.897 |
UA | +2.873 |
RAW | +2.866 |
Neg logit contributions | |
ertodd | -4.484 |
ysis | -3.709 |
verts | -3.562 |
ered | -3.542 |
quo | -3.505 |
Token | BG |
Token ID | 40469 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ANE | +5.978 |
UA | +5.782 |
RAW | +5.653 |
awan | +5.649 |
光 | +5.480 |
Neg logit contributions | |
ertodd | -9.607 |
ysis | -7.881 |
quo | -7.727 |
Jehovah | -7.475 |
ered | -7.423 |
Token | [ |
Token ID | 58 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ANE | +2.735 |
awan | +2.586 |
光 | +2.525 |
UA | +2.514 |
RAW | +2.493 |
Neg logit contributions | |
ertodd | -4.217 |
ysis | -3.514 |
verts | -3.372 |
ered | -3.361 |
quo | -3.337 |
Token | 0 |
Token ID | 15 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
ANE | +2.837 |
awan | +2.679 |
UA | +2.608 |
光 | +2.606 |
RAW | +2.575 |
Neg logit contributions | |
ertodd | -4.796 |
ysis | -4.011 |
verts | -3.839 |
ered | -3.826 |
quo | -3.817 |
Token | ], |
Token ID | 4357 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
ANE | +1.453 |
awan | +1.387 |
光 | +1.357 |
UA | +1.346 |
RAW | +1.337 |
Neg logit contributions | |
ertodd | -1.744 |
ysis | -1.419 |
verts | -1.352 |
ered | -1.343 |
quo | -1.332 |
Token | $ |
Token ID | 3 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ertodd | +0.219 |
ysis | +0.181 |
verts | +0.174 |
ered | +0.173 |
quo | +0.170 |
Neg logit contributions | |
ANE | -0.172 |
awan | -0.165 |
光 | -0.160 |
srf | -0.159 |
女 | -0.159 |
Token | look |
Token ID | 804 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
ANE | +1.660 |
awan | +1.594 |
光 | +1.569 |
UA | +1.550 |
srf | +1.549 |
Neg logit contributions | |
ertodd | -1.665 |
ysis | -1.335 |
ered | -1.274 |
verts | -1.271 |
quo | -1.248 |
Token | up |
Token ID | 510 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
ANE | +1.400 |
awan | +1.343 |
光 | +1.322 |
女 | +1.306 |
UA | +1.305 |
Neg logit contributions | |
ertodd | -1.456 |
ysis | -1.178 |
ered | -1.121 |
verts | -1.119 |
quo | -1.100 |
Token | from |
Token ID | 422 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
ertodd | +1.537 |
ysis | +1.241 |
verts | +1.186 |
ered | +1.180 |
quo | +1.161 |
Neg logit contributions | |
ANE | -1.645 |
awan | -1.575 |
光 | -1.558 |
女 | -1.539 |
srf | -1.536 |
Token | the |
Token ID | 262 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
ertodd | +2.363 |
ysis | +1.841 |
verts | +1.790 |
ered | +1.783 |
quo | +1.743 |
Neg logit contributions | |
ANE | -2.742 |
awan | -2.646 |
光 | -2.608 |
女 | -2.605 |
EMENT | -2.573 |
Token | bridge |
Token ID | 7696 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ertodd | +0.491 |
ysis | +0.401 |
verts | +0.386 |
ered | +0.384 |
quo | +0.378 |
Neg logit contributions | |
ANE | -0.421 |
awan | -0.402 |
光 | -0.395 |
女 | -0.392 |
srf | -0.389 |
Token | � |
Token ID | 30325 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
ANE | +3.322 |
awan | +3.178 |
光 | +3.097 |
UA | +3.072 |
女 | +3.059 |
Neg logit contributions | |
ertodd | -4.063 |
ysis | -3.315 |
verts | -3.162 |
ered | -3.146 |
quo | -3.103 |
Token | � |
Token ID | 231 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
ANE | +4.600 |
awan | +4.272 |
RAW | +4.206 |
UA | +4.199 |
光 | +4.178 |
Neg logit contributions | |
ertodd | -10.563 |
ysis | -9.019 |
verts | -8.636 |
quo | -8.579 |
ered | -8.575 |
Token | ) |
Token ID | 1267 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
ANE | +1.216 |
awan | +1.143 |
光 | +1.108 |
UA | +1.093 |
女 | +1.088 |
Neg logit contributions | |
ertodd | -2.462 |
ysis | -2.090 |
verts | -2.017 |
ered | -2.009 |
quo | -1.987 |
Token | I |
Token ID | 314 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
ertodd | +2.637 |
ysis | +2.145 |
ered | +2.004 |
verts | +1.987 |
quo | +1.979 |
Neg logit contributions | |
ANE | -3.003 |
awan | -2.861 |
女 | -2.820 |
srf | -2.819 |
光 | -2.804 |
Token | � |
Token ID | 447 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
ANE | +1.813 |
awan | +1.742 |
光 | +1.713 |
UA | +1.696 |
女 | +1.694 |
Neg logit contributions | |
ertodd | -1.584 |
ysis | -1.244 |
verts | -1.174 |
ered | -1.174 |
quo | -1.152 |
Token | � |
Token ID | 247 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
ANE | +0.289 |
awan | +0.274 |
光 | +0.267 |
女 | +0.262 |
UA | +0.262 |
Neg logit contributions | |
ertodd | -0.467 |
ysis | -0.392 |
ered | -0.377 |
verts | -0.376 |
quo | -0.371 |
Token | know |
Token ID | 760 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
ANE | +1.009 |
awan | +0.970 |
光 | +0.963 |
srf | +0.961 |
UA | +0.953 |
Neg logit contributions | |
ertodd | -0.791 |
ysis | -0.613 |
ered | -0.591 |
verts | -0.580 |
quo | -0.577 |
Token | this |
Token ID | 428 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
ANE | +1.493 |
awan | +1.437 |
光 | +1.411 |
srf | +1.406 |
女 | +1.398 |
Neg logit contributions | |
ertodd | -1.368 |
ysis | -1.092 |
ered | -1.040 |
verts | -1.038 |
quo | -1.022 |
Token | was |
Token ID | 373 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
ertodd | +0.336 |
ysis | +0.266 |
verts | +0.257 |
ered | +0.255 |
quo | +0.252 |
Neg logit contributions | |
ANE | -0.414 |
awan | -0.400 |
srf | -0.397 |
光 | -0.394 |
女 | -0.391 |
Token | a |
Token ID | 257 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
ANE | +1.390 |
awan | +1.341 |
光 | +1.307 |
srf | +1.299 |
女 | +1.296 |
Neg logit contributions | |
ertodd | -1.411 |
ysis | -1.140 |
verts | -1.087 |
ered | -1.086 |
quo | -1.070 |
Token | totally |
Token ID | 6635 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
ertodd | +1.010 |
ysis | +0.844 |
ered | +0.813 |
verts | +0.812 |
quo | +0.804 |
Neg logit contributions | |
ANE | -0.848 |
awan | -0.816 |
光 | -0.800 |
srf | -0.789 |
女 | -0.786 |
Token | biased |
Token ID | 21925 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
ANE | +1.827 |
awan | +1.745 |
光 | +1.703 |
女 | +1.684 |
UA | +1.683 |
Neg logit contributions | |
ertodd | -2.401 |
ysis | -1.985 |
verts | -1.899 |
ered | -1.896 |
quo | -1.870 |
Token | decision |
Token ID | 2551 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
ANE | +7.358 |
awan | +7.067 |
光 | +6.932 |
EMENT | +6.930 |
UA | +6.909 |
Neg logit contributions | |
ertodd | -8.138 |
ysis | -6.359 |
verts | -5.988 |
ered | -5.922 |
quo | -5.781 |
Token | , |
Token ID | 11 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
ANE | +0.785 |
awan | +0.755 |
光 | +0.742 |
srf | +0.737 |
女 | +0.736 |
Neg logit contributions | |
ertodd | -0.667 |
ysis | -0.524 |
verts | -0.497 |
ered | -0.494 |
quo | -0.488 |
Token | was |
Token ID | 373 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ANE | +0.472 |
awan | +0.455 |
光 | +0.448 |
srf | +0.446 |
女 | +0.445 |
Neg logit contributions | |
ertodd | -0.386 |
ysis | -0.304 |
verts | -0.288 |
ered | -0.285 |
quo | -0.284 |
Token | the |
Token ID | 262 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
ANE | +2.900 |
awan | +2.780 |
光 | +2.721 |
UA | +2.696 |
女 | +2.690 |
Neg logit contributions | |
ertodd | -3.061 |
ysis | -2.461 |
verts | -2.338 |
ered | -2.325 |
quo | -2.292 |
Token | fact |
Token ID | 1109 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
ANE | +1.853 |
awan | +1.780 |
光 | +1.743 |
女 | +1.725 |
UA | +1.724 |
Neg logit contributions | |
ertodd | -1.896 |
ysis | -1.526 |
verts | -1.452 |
ered | -1.443 |
quo | -1.423 |
Token |
|
Token ID | 198 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
ertodd | +0.554 |
ysis | +0.424 |
verts | +0.401 |
ered | +0.401 |
quo | +0.389 |
Neg logit contributions | |
ANE | -0.759 |
awan | -0.733 |
srf | -0.732 |
光 | -0.721 |
senal | -0.720 |
Token | Results |
Token ID | 25468 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
ANE | +0.199 |
srf | +0.193 |
awan | +0.191 |
senal | +0.186 |
女 | +0.184 |
Neg logit contributions | |
ertodd | -0.339 |
ysis | -0.290 |
verts | -0.282 |
ered | -0.281 |
quo | -0.273 |
Token | and |
Token ID | 290 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
ertodd | +0.657 |
ysis | +0.511 |
verts | +0.479 |
ered | +0.478 |
quo | +0.469 |
Neg logit contributions | |
ANE | -0.834 |
awan | -0.805 |
光 | -0.790 |
女 | -0.784 |
UA | -0.783 |
Token | achievements |
Token ID | 16970 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
ANE | +2.446 |
awan | +2.355 |
光 | +2.300 |
UA | +2.286 |
EMENT | +2.276 |
Neg logit contributions | |
ertodd | -2.290 |
ysis | -1.808 |
verts | -1.708 |
ered | -1.699 |
quo | -1.669 |
Token | [ |
Token ID | 685 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
ANE | +0.795 |
awan | +0.767 |
光 | +0.752 |
UA | +0.747 |
女 | +0.744 |
Neg logit contributions | |
ertodd | -0.633 |
ysis | -0.489 |
verts | -0.459 |
ered | -0.456 |
quo | -0.447 |
Token | edit |
Token ID | 4370 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
ANE | +1.186 |
awan | +1.086 |
光 | +1.033 |
UA | +1.016 |
女 | +1.008 |
Neg logit contributions | |
ertodd | -3.953 |
ysis | -3.433 |
verts | -3.322 |
ered | -3.315 |
quo | -3.288 |
Token | ] |
Token ID | 2361 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
ANE | +5.660 |
awan | +5.460 |
RAW | +5.364 |
pull | +5.336 |
UA | +5.329 |
Neg logit contributions | |
ertodd | -9.411 |
ysis | -7.793 |
ered | -7.335 |
verts | -7.295 |
quo | -7.281 |
Token |
|
Token ID | 198 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ANE | +1.487 |
awan | +1.435 |
光 | +1.409 |
UA | +1.398 |
女 | +1.395 |
Neg logit contributions | |
ertodd | -1.168 |
ysis | -0.902 |
verts | -0.847 |
ered | -0.842 |
quo | -0.827 |
Token |
|
Token ID | 198 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
ANE | +4.345 |
awan | +4.198 |
UA | +4.131 |
RAW | +4.069 |
女 | +4.064 |
Neg logit contributions | |
ertodd | -4.379 |
ysis | -3.460 |
quo | -3.167 |
verts | -3.150 |
gencies | -3.118 |
Token | The |
Token ID | 464 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
ANE | +3.624 |
awan | +3.428 |
UA | +3.341 |
光 | +3.339 |
RAW | +3.322 |
Neg logit contributions | |
ertodd | -6.016 |
ysis | -4.999 |
verts | -4.774 |
ered | -4.761 |
quo | -4.754 |
Token | ion |
Token ID | 22088 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
ANE | +1.466 |
awan | +1.407 |
光 | +1.378 |
UA | +1.365 |
女 | +1.363 |
Neg logit contributions | |
ertodd | -1.505 |
ysis | -1.208 |
verts | -1.146 |
ered | -1.141 |
quo | -1.124 |
Token | in |
Token ID | 287 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
ANE | +1.890 |
awan | +1.808 |
光 | +1.771 |
UA | +1.751 |
女 | +1.750 |
Neg logit contributions | |
ertodd | -2.134 |
ysis | -1.733 |
verts | -1.650 |
ered | -1.646 |
quo | -1.623 |
Token | the |
Token ID | 262 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
ertodd | +0.903 |
ysis | +0.725 |
verts | +0.691 |
ered | +0.686 |
quo | +0.677 |
Neg logit contributions | |
ANE | -0.919 |
awan | -0.880 |
光 | -0.869 |
女 | -0.862 |
srf | -0.860 |
Token | first |
Token ID | 717 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
ANE | +0.370 |
awan | +0.353 |
光 | +0.347 |
女 | +0.347 |
srf | +0.344 |
Neg logit contributions | |
ertodd | -0.425 |
ysis | -0.348 |
verts | -0.332 |
ered | -0.331 |
quo | -0.326 |
Token | quarter |
Token ID | 3860 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
ANE | +2.224 |
awan | +2.124 |
光 | +2.074 |
UA | +2.052 |
女 | +2.049 |
Neg logit contributions | |
ertodd | -2.804 |
ysis | -2.301 |
verts | -2.198 |
ered | -2.190 |
quo | -2.161 |
Token | to |
Token ID | 284 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
ertodd | +1.133 |
ysis | +0.915 |
ered | +0.882 |
verts | +0.865 |
quo | +0.860 |
Neg logit contributions | |
ANE | -1.199 |
awan | -1.147 |
srf | -1.139 |
光 | -1.123 |
女 | -1.118 |
Token | lobby |
Token ID | 10866 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
ANE | +1.517 |
awan | +1.450 |
光 | +1.427 |
UA | +1.415 |
女 | +1.413 |
Neg logit contributions | |
ertodd | -1.571 |
ysis | -1.268 |
ered | -1.207 |
verts | -1.205 |
quo | -1.187 |
Token | on |
Token ID | 319 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
ANE | +7.223 |
awan | +6.948 |
UA | +6.780 |
EMENT | +6.713 |
ARI | +6.538 |
Neg logit contributions | |
ertodd | -7.725 |
ysis | -6.118 |
verts | -5.717 |
gencies | -5.692 |
quo | -5.684 |
Token | domestic |
Token ID | 5928 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
ANE | +2.113 |
awan | +2.019 |
光 | +1.962 |
UA | +1.948 |
EMENT | +1.934 |
Neg logit contributions | |
ertodd | -2.840 |
ysis | -2.335 |
verts | -2.226 |
ered | -2.214 |
quo | -2.192 |
Token | spying |
Token ID | 23649 |
Feature activation | +5.78e-02 |
Pos logit contributions | |
ertodd | +2.685 |
ysis | +2.180 |
verts | +2.092 |
ered | +2.089 |
Jehovah | +2.039 |
Neg logit contributions | |
ANE | -2.954 |
srf | -2.816 |
awan | -2.813 |
光 | -2.768 |
女 | -2.761 |
Token | legislation |
Token ID | 5520 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
ertodd | +0.162 |
ysis | +0.130 |
verts | +0.125 |
ered | +0.124 |
quo | +0.122 |
Neg logit contributions | |
ANE | -0.179 |
awan | -0.171 |
srf | -0.168 |
光 | -0.168 |
女 | -0.167 |
Token | and |
Token ID | 290 |
Feature activation | +9.09e-02 |
Pos logit contributions | |
ANE | +1.119 |
awan | +1.069 |
光 | +1.047 |
srf | +1.041 |
女 | +1.037 |
Neg logit contributions | |
ertodd | -1.196 |
ysis | -0.969 |
verts | -0.926 |
ered | -0.925 |
quo | -0.910 |
Token |
|
Token ID | 198 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
ertodd | +0.104 |
ysis | +0.080 |
verts | +0.075 |
ered | +0.075 |
quo | +0.073 |
Neg logit contributions | |
ANE | -0.137 |
awan | -0.133 |
光 | -0.130 |
srf | -0.130 |
UA | -0.129 |
Token | Indeed |
Token ID | 17854 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
ANE | +1.106 |
awan | +1.057 |
srf | +1.035 |
光 | +1.031 |
女 | +1.020 |
Neg logit contributions | |
ertodd | -1.344 |
ysis | -1.101 |
verts | -1.052 |
ered | -1.051 |
quo | -1.033 |
Token | , |
Token ID | 11 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
ertodd | +0.556 |
ysis | +0.454 |
verts | +0.434 |
ered | +0.429 |
quo | +0.424 |
Neg logit contributions | |
ANE | -0.457 |
awan | -0.439 |
光 | -0.428 |
女 | -0.423 |
UA | -0.423 |
Token | about |
Token ID | 546 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
ANE | +1.705 |
awan | +1.641 |
光 | +1.609 |
UA | +1.594 |
女 | +1.592 |
Neg logit contributions | |
ertodd | -1.551 |
ysis | -1.224 |
verts | -1.157 |
ered | -1.151 |
quo | -1.132 |
Token | an |
Token ID | 281 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
ANE | +0.968 |
awan | +0.929 |
光 | +0.909 |
UA | +0.902 |
srf | +0.901 |
Neg logit contributions | |
ertodd | -0.927 |
ysis | -0.739 |
verts | -0.702 |
ered | -0.700 |
quo | -0.689 |
Token | hour |
Token ID | 1711 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
ANE | +1.391 |
awan | +1.335 |
光 | +1.305 |
UA | +1.296 |
女 | +1.293 |
Neg logit contributions | |
ertodd | -1.467 |
ysis | -1.179 |
verts | -1.120 |
ered | -1.119 |
quo | -1.102 |
Token | before |
Token ID | 878 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ANE | +5.797 |
awan | +5.644 |
光 | +5.407 |
RAW | +5.355 |
EMENT | +5.308 |
Neg logit contributions | |
ertodd | -9.128 |
ysis | -7.479 |
verts | -7.212 |
ered | -6.999 |
quo | -6.946 |
Token | the |
Token ID | 262 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
ANE | +4.438 |
awan | +4.307 |
光 | +4.222 |
RAW | +4.179 |
UA | +4.177 |
Neg logit contributions | |
ertodd | -3.754 |
ysis | -2.898 |
verts | -2.759 |
ered | -2.721 |
quo | -2.648 |
Token | festivities |
Token ID | 42735 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ertodd | +1.589 |
ysis | +1.321 |
ered | +1.261 |
verts | +1.252 |
quo | +1.251 |
Neg logit contributions | |
ANE | -1.323 |
awan | -1.262 |
srf | -1.236 |
光 | -1.230 |
女 | -1.228 |
Token | started |
Token ID | 2067 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
ertodd | +3.417 |
ysis | +2.652 |
ered | +2.584 |
quo | +2.542 |
verts | +2.516 |
Neg logit contributions | |
ANE | -4.377 |
srf | -4.145 |
awan | -4.127 |
senal | -4.126 |
UA | -4.101 |
Token | at |
Token ID | 379 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
ertodd | +1.345 |
ysis | +1.088 |
ered | +1.048 |
verts | +1.039 |
quo | +1.033 |
Neg logit contributions | |
ANE | -1.274 |
awan | -1.216 |
光 | -1.191 |
UA | -1.189 |
srf | -1.188 |
Token | string |
Token ID | 8841 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
ANE | +1.738 |
awan | +1.660 |
光 | +1.615 |
UA | +1.602 |
女 | +1.593 |
Neg logit contributions | |
ertodd | -2.407 |
ysis | -1.992 |
verts | -1.894 |
ered | -1.891 |
quo | -1.879 |
Token | format |
Token ID | 18982 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
ANE | +1.407 |
awan | +1.339 |
光 | +1.309 |
UA | +1.291 |
女 | +1.291 |
Neg logit contributions | |
ertodd | -1.957 |
ysis | -1.625 |
verts | -1.554 |
ered | -1.553 |
quo | -1.528 |
Token | Switch |
Token ID | 14645 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
ANE | +0.606 |
awan | +0.577 |
光 | +0.566 |
女 | +0.558 |
UA | +0.557 |
Neg logit contributions | |
ertodd | -0.784 |
ysis | -0.647 |
verts | -0.619 |
ered | -0.619 |
quo | -0.608 |
Token | ($ |
Token ID | 7198 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ertodd | +2.481 |
ysis | +2.007 |
ered | +1.956 |
verts | +1.931 |
quo | +1.888 |
Neg logit contributions | |
ANE | -2.313 |
awan | -2.204 |
光 | -2.183 |
女 | -2.178 |
EMENT | -2.129 |
Token | Al |
Token ID | 2348 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
ANE | +4.016 |
awan | +3.823 |
UA | +3.741 |
光 | +3.721 |
RAW | +3.707 |
Neg logit contributions | |
ertodd | -5.515 |
ysis | -4.516 |
quo | -4.288 |
ered | -4.275 |
verts | -4.263 |
Token | ign |
Token ID | 570 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
ANE | +1.514 |
awan | +1.462 |
光 | +1.443 |
女 | +1.427 |
UA | +1.424 |
Neg logit contributions | |
ertodd | -1.031 |
ysis | -0.779 |
verts | -0.729 |
ered | -0.726 |
quo | -0.707 |
Token | ) |
Token ID | 8 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
ANE | +5.634 |
EMENT | +5.627 |
awan | +5.423 |
UA | +5.344 |
MENT | +5.245 |
Neg logit contributions | |
ertodd | -9.116 |
ysis | -7.484 |
verts | -7.212 |
Jehovah | -7.181 |
quo | -7.105 |
Token | { |
Token ID | 1391 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
ertodd | +0.858 |
ysis | +0.694 |
ered | +0.658 |
verts | +0.656 |
quo | +0.645 |
Neg logit contributions | |
ANE | -0.885 |
awan | -0.851 |
光 | -0.838 |
女 | -0.832 |
UA | -0.827 |
Token | Center |
Token ID | 3337 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
ANE | +0.259 |
awan | +0.249 |
光 | +0.244 |
女 | +0.242 |
UA | +0.241 |
Neg logit contributions | |
ertodd | -0.260 |
ysis | -0.208 |
verts | -0.199 |
ered | -0.198 |
quo | -0.195 |
Token | { |
Token ID | 1391 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
ANE | +4.248 |
awan | +4.037 |
光 | +3.933 |
UA | +3.915 |
RAW | +3.898 |
Neg logit contributions | |
ertodd | -5.566 |
ysis | -4.555 |
verts | -4.325 |
ered | -4.280 |
quo | -4.233 |
Token | $ |
Token ID | 720 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
ertodd | +0.877 |
ysis | +0.713 |
verts | +0.689 |
ered | +0.682 |
quo | +0.673 |
Neg logit contributions | |
ANE | -0.838 |
awan | -0.804 |
光 | -0.789 |
女 | -0.783 |
UA | -0.778 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ertodd | +0.490 |
ysis | +0.380 |
verts | +0.359 |
ered | +0.357 |
quo | +0.348 |
Neg logit contributions | |
ANE | -0.641 |
awan | -0.621 |
srf | -0.617 |
光 | -0.610 |
女 | -0.603 |
Token |
|
Token ID | 198 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
ertodd | +0.368 |
ysis | +0.282 |
verts | +0.267 |
ered | +0.266 |
quo | +0.258 |
Neg logit contributions | |
ANE | -0.500 |
awan | -0.483 |
srf | -0.481 |
光 | -0.475 |
senal | -0.473 |
Token | More |
Token ID | 5167 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ANE | +0.744 |
srf | +0.730 |
awan | +0.720 |
senal | +0.700 |
光 | +0.693 |
Neg logit contributions | |
ertodd | -1.114 |
ysis | -0.938 |
verts | -0.911 |
ered | -0.906 |
quo | -0.881 |
Token | than |
Token ID | 621 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
ertodd | +0.392 |
ysis | +0.320 |
verts | +0.309 |
ered | +0.307 |
quo | +0.301 |
Neg logit contributions | |
ANE | -0.376 |
awan | -0.361 |
光 | -0.355 |
srf | -0.351 |
女 | -0.349 |
Token | an |
Token ID | 281 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
ANE | +0.334 |
awan | +0.321 |
光 | +0.316 |
srf | +0.314 |
女 | +0.313 |
Neg logit contributions | |
ertodd | -0.318 |
ysis | -0.257 |
ered | -0.243 |
verts | -0.243 |
quo | -0.239 |
Token | hour |
Token ID | 1711 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
ANE | +0.163 |
awan | +0.156 |
srf | +0.154 |
光 | +0.153 |
UA | +0.153 |
Neg logit contributions | |
ertodd | -0.177 |
ysis | -0.143 |
ered | -0.138 |
verts | -0.137 |
quo | -0.136 |
Token | before |
Token ID | 878 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ANE | +6.060 |
awan | +5.925 |
UA | +5.577 |
光 | +5.565 |
EMENT | +5.565 |
Neg logit contributions | |
ertodd | -8.656 |
ysis | -7.023 |
verts | -6.692 |
Jehovah | -6.495 |
quo | -6.478 |
Token | kick |
Token ID | 4829 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
ANE | +3.579 |
awan | +3.452 |
光 | +3.366 |
UA | +3.358 |
EMENT | +3.331 |
Neg logit contributions | |
ertodd | -3.268 |
ysis | -2.553 |
verts | -2.401 |
ered | -2.400 |
quo | -2.354 |
Token | - |
Token ID | 12 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
ertodd | +0.754 |
ysis | +0.574 |
verts | +0.537 |
ered | +0.534 |
quo | +0.524 |
Neg logit contributions | |
ANE | -1.045 |
awan | -1.009 |
光 | -0.992 |
UA | -0.984 |
女 | -0.983 |
Token | off |
Token ID | 2364 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
ANE | +1.116 |
awan | +1.075 |
光 | +1.053 |
UA | +1.044 |
女 | +1.042 |
Neg logit contributions | |
ertodd | -1.020 |
ysis | -0.805 |
verts | -0.760 |
ered | -0.757 |
quo | -0.745 |
Token | Bruce |
Token ID | 11088 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
ertodd | +1.861 |
ysis | +1.514 |
verts | +1.452 |
ered | +1.449 |
quo | +1.418 |
Neg logit contributions | |
ANE | -1.915 |
awan | -1.838 |
srf | -1.822 |
光 | -1.822 |
女 | -1.792 |
Token | miles |
Token ID | 4608 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ertodd | +0.331 |
ysis | +0.279 |
verts | +0.269 |
ered | +0.268 |
quo | +0.265 |
Neg logit contributions | |
ANE | -0.186 |
awan | -0.175 |
光 | -0.171 |
UA | -0.168 |
女 | -0.168 |
Token | . |
Token ID | 13 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
ANE | +2.865 |
awan | +2.729 |
光 | +2.660 |
UA | +2.624 |
EMENT | +2.610 |
Neg logit contributions | |
ertodd | -4.162 |
ysis | -3.455 |
verts | -3.304 |
ered | -3.263 |
quo | -3.241 |
Token | Eas |
Token ID | 38647 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ANE | +1.678 |
awan | +1.617 |
光 | +1.585 |
UA | +1.571 |
女 | +1.570 |
Neg logit contributions | |
ertodd | -1.463 |
ysis | -1.149 |
verts | -1.086 |
ered | -1.084 |
quo | -1.063 |
Token | ily |
Token ID | 813 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
ANE | +2.971 |
awan | +2.878 |
光 | +2.785 |
女 | +2.772 |
EMENT | +2.753 |
Neg logit contributions | |
ertodd | -3.365 |
ysis | -2.762 |
verts | -2.605 |
quo | -2.540 |
Jehovah | -2.533 |
Token | the |
Token ID | 262 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
ANE | +1.775 |
awan | +1.708 |
光 | +1.676 |
UA | +1.665 |
女 | +1.660 |
Neg logit contributions | |
ertodd | -1.509 |
ysis | -1.183 |
verts | -1.127 |
ered | -1.127 |
quo | -1.107 |
Token | hardest |
Token ID | 17612 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
ANE | +0.561 |
awan | +0.536 |
光 | +0.521 |
srf | +0.517 |
女 | +0.516 |
Neg logit contributions | |
ertodd | -0.813 |
ysis | -0.680 |
verts | -0.659 |
ered | -0.657 |
quo | -0.651 |
Token | day |
Token ID | 1110 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
ANE | +6.618 |
awan | +6.222 |
光 | +6.179 |
RAW | +6.086 |
UA | +6.069 |
Neg logit contributions | |
ertodd | -8.229 |
ysis | -6.633 |
verts | -6.248 |
gencies | -6.078 |
ered | -6.069 |
Token | of |
Token ID | 286 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
ANE | +1.395 |
awan | +1.341 |
光 | +1.313 |
UA | +1.304 |
女 | +1.300 |
Neg logit contributions | |
ertodd | -1.343 |
ysis | -1.071 |
verts | -1.015 |
ered | -1.015 |
quo | -0.997 |
Token | the |
Token ID | 262 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
ANE | +1.829 |
awan | +1.762 |
光 | +1.729 |
UA | +1.715 |
女 | +1.712 |
Neg logit contributions | |
ertodd | -1.521 |
ysis | -1.185 |
verts | -1.115 |
ered | -1.109 |
quo | -1.090 |
Token | trip |
Token ID | 5296 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
ANE | +1.494 |
awan | +1.430 |
光 | +1.397 |
UA | +1.386 |
女 | +1.385 |
Neg logit contributions | |
ertodd | -1.633 |
ysis | -1.323 |
verts | -1.262 |
ered | -1.257 |
quo | -1.240 |
Token | , |
Token ID | 11 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
ANE | +2.036 |
awan | +1.948 |
光 | +1.904 |
UA | +1.886 |
女 | +1.881 |
Neg logit contributions | |
ertodd | -2.411 |
ysis | -1.967 |
verts | -1.876 |
ered | -1.871 |
quo | -1.844 |
Token | a |
Token ID | 257 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
ANE | +1.726 |
awan | +1.662 |
光 | +1.630 |
UA | +1.616 |
女 | +1.614 |
Neg logit contributions | |
ertodd | -1.471 |
ysis | -1.152 |
verts | -1.086 |
ered | -1.081 |
quo | -1.063 |
Token | chief |
Token ID | 4039 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
ANE | +0.578 |
awan | +0.551 |
光 | +0.544 |
UA | +0.537 |
女 | +0.536 |
Neg logit contributions | |
ertodd | -0.603 |
ysis | -0.488 |
verts | -0.465 |
ered | -0.464 |
quo | -0.457 |
Token | of |
Token ID | 286 |
Feature activation | +3.72e-03 |
Pos logit contributions | |
ANE | +0.178 |
awan | +0.170 |
光 | +0.168 |
srf | +0.166 |
UA | +0.166 |
Neg logit contributions | |
ertodd | -0.170 |
ysis | -0.137 |
ered | -0.130 |
verts | -0.129 |
quo | -0.127 |
Token | B |
Token ID | 347 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
ertodd | +0.010 |
ysis | +0.007 |
verts | +0.007 |
ered | +0.007 |
quo | +0.007 |
Neg logit contributions | |
ANE | -0.013 |
awan | -0.012 |
光 | -0.012 |
UA | -0.012 |
女 | -0.012 |
Token | ani |
Token ID | 3216 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
ertodd | +0.757 |
ysis | +0.634 |
verts | +0.608 |
ered | +0.607 |
quo | +0.600 |
Neg logit contributions | |
ANE | -0.476 |
awan | -0.451 |
光 | -0.440 |
UA | -0.435 |
女 | -0.434 |
Token | Nad |
Token ID | 21877 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
ANE | +0.869 |
awan | +0.836 |
光 | +0.822 |
UA | +0.814 |
女 | +0.813 |
Neg logit contributions | |
ertodd | -0.731 |
ysis | -0.571 |
verts | -0.538 |
ered | -0.536 |
quo | -0.527 |
Token | ir |
Token ID | 343 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
awan | +6.658 |
ANE | +6.584 |
UA | +6.237 |
RAW | +6.126 |
光 | +6.073 |
Neg logit contributions | |
ertodd | -7.988 |
ysis | -6.205 |
verts | -5.959 |
ered | -5.830 |
quo | -5.787 |
Token | and |
Token ID | 290 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
ANE | +3.394 |
awan | +3.311 |
光 | +3.190 |
UA | +3.182 |
RAW | +3.167 |
Neg logit contributions | |
ertodd | -3.745 |
ysis | -2.980 |
verts | -2.838 |
ered | -2.812 |
quo | -2.766 |
Token | Saf |
Token ID | 6895 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ANE | +1.163 |
awan | +1.118 |
光 | +1.099 |
UA | +1.088 |
女 | +1.087 |
Neg logit contributions | |
ertodd | -0.997 |
ysis | -0.783 |
verts | -0.738 |
ered | -0.736 |
quo | -0.724 |
Token | iyah |
Token ID | 46398 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ANE | +2.720 |
awan | +2.656 |
UA | +2.527 |
光 | +2.526 |
RAW | +2.503 |
Neg logit contributions | |
ertodd | -3.426 |
ysis | -2.790 |
verts | -2.655 |
ered | -2.610 |
quo | -2.601 |
Token | � |
Token ID | 447 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
ANE | +0.340 |
awan | +0.325 |
光 | +0.319 |
UA | +0.316 |
srf | +0.316 |
Neg logit contributions | |
ertodd | -0.352 |
ysis | -0.284 |
verts | -0.270 |
ered | -0.269 |
quo | -0.266 |
Token | Soviets |
Token ID | 31062 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
ANE | +0.106 |
awan | +0.102 |
光 | +0.100 |
UA | +0.099 |
女 | +0.099 |
Neg logit contributions | |
ertodd | -0.100 |
ysis | -0.080 |
verts | -0.076 |
ered | -0.075 |
quo | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
ANE | +0.640 |
awan | +0.615 |
光 | +0.603 |
UA | +0.598 |
女 | +0.596 |
Neg logit contributions | |
ertodd | -0.594 |
ysis | -0.471 |
verts | -0.446 |
ered | -0.444 |
quo | -0.437 |
Token | � |
Token ID | 447 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
ANE | +0.804 |
awan | +0.774 |
光 | +0.759 |
UA | +0.753 |
女 | +0.752 |
Neg logit contributions | |
ertodd | -0.682 |
ysis | -0.533 |
verts | -0.503 |
ered | -0.501 |
quo | -0.493 |
Token | � |
Token ID | 251 |
Feature activation | -9.14e-01 |
Pos logit contributions | |
ANE | +0.584 |
awan | +0.555 |
光 | +0.542 |
UA | +0.536 |
女 | +0.534 |
Neg logit contributions | |
ertodd | -0.837 |
ysis | -0.693 |
verts | -0.665 |
ered | -0.662 |
quo | -0.653 |
Token | Lad |
Token ID | 12862 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
ANE | +2.844 |
awan | +2.752 |
光 | +2.707 |
UA | +2.672 |
女 | +2.667 |
Neg logit contributions | |
ertodd | -2.559 |
ysis | -2.002 |
verts | -1.884 |
ered | -1.860 |
quo | -1.812 |
Token | isl |
Token ID | 3044 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
ertodd | +0.153 |
ysis | +0.127 |
verts | +0.122 |
ered | +0.122 |
quo | +0.119 |
Neg logit contributions | |
ANE | -0.107 |
awan | -0.101 |
光 | -0.100 |
女 | -0.098 |
srf | -0.098 |
Token | av |
Token ID | 615 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ANE | +5.120 |
awan | +5.034 |
UA | +4.659 |
RAW | +4.591 |
光 | +4.509 |
Neg logit contributions | |
ertodd | -9.749 |
ysis | -8.145 |
verts | -7.850 |
quo | -7.773 |
ered | -7.689 |
Token | Sm |
Token ID | 2439 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
ANE | +3.799 |
awan | +3.679 |
光 | +3.604 |
UA | +3.586 |
女 | +3.576 |
Neg logit contributions | |
ertodd | -3.579 |
ysis | -2.791 |
verts | -2.637 |
ered | -2.595 |
quo | -2.579 |
Token | ol |
Token ID | 349 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
ANE | +1.805 |
awan | +1.751 |
UA | +1.666 |
RAW | +1.657 |
EMENT | +1.655 |
Neg logit contributions | |
ertodd | -2.337 |
ysis | -1.905 |
verts | -1.815 |
quo | -1.805 |
ered | -1.792 |
Token | j |
Token ID | 73 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
ertodd | +2.715 |
ysis | +2.225 |
verts | +2.149 |
ered | +2.142 |
quo | +2.088 |
Neg logit contributions | |
ANE | -2.176 |
光 | -2.060 |
srf | -2.039 |
awan | -2.038 |
女 | -2.028 |
Token | ak |
Token ID | 461 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
ANE | +0.089 |
awan | +0.085 |
光 | +0.084 |
srf | +0.083 |
UA | +0.083 |
Neg logit contributions | |
ertodd | -0.109 |
ysis | -0.090 |
ered | -0.086 |
verts | -0.086 |
quo | -0.084 |
Token | cancer |
Token ID | 4890 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
ANE | +0.552 |
awan | +0.530 |
光 | +0.519 |
UA | +0.513 |
女 | +0.512 |
Neg logit contributions | |
ertodd | -0.608 |
ysis | -0.495 |
verts | -0.470 |
ered | -0.469 |
quo | -0.462 |
Token | and |
Token ID | 290 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
ertodd | +2.860 |
ysis | +2.358 |
ered | +2.230 |
verts | +2.215 |
quo | +2.202 |
Neg logit contributions | |
ANE | -2.447 |
awan | -2.352 |
光 | -2.292 |
UA | -2.286 |
srf | -2.284 |
Token | one |
Token ID | 530 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
ertodd | +0.032 |
ysis | +0.026 |
ered | +0.025 |
verts | +0.024 |
Jehovah | +0.024 |
Neg logit contributions | |
ANE | -0.035 |
awan | -0.034 |
光 | -0.033 |
srf | -0.033 |
UA | -0.033 |
Token | of |
Token ID | 286 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
ANE | +0.910 |
awan | +0.873 |
光 | +0.855 |
UA | +0.848 |
女 | +0.846 |
Neg logit contributions | |
ertodd | -0.912 |
ysis | -0.730 |
verts | -0.692 |
ered | -0.689 |
quo | -0.679 |
Token | the |
Token ID | 262 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
ertodd | +0.078 |
ysis | +0.061 |
verts | +0.057 |
ered | +0.057 |
quo | +0.056 |
Neg logit contributions | |
ANE | -0.097 |
awan | -0.093 |
光 | -0.091 |
UA | -0.091 |
女 | -0.091 |
Token | hardest |
Token ID | 17612 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
ANE | +0.818 |
awan | +0.782 |
光 | +0.764 |
UA | +0.755 |
女 | +0.753 |
Neg logit contributions | |
ertodd | -1.083 |
ysis | -0.899 |
verts | -0.860 |
ered | -0.857 |
quo | -0.846 |
Token | things |
Token ID | 1243 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
ANE | +5.862 |
女 | +5.415 |
awan | +5.403 |
EMENT | +5.401 |
光 | +5.341 |
Neg logit contributions | |
ertodd | -8.872 |
ysis | -7.127 |
verts | -6.872 |
ered | -6.763 |
quo | -6.703 |
Token | I |
Token ID | 314 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
ANE | +0.520 |
awan | +0.501 |
光 | +0.491 |
UA | +0.488 |
srf | +0.487 |
Neg logit contributions | |
ertodd | -0.469 |
ysis | -0.372 |
verts | -0.350 |
ered | -0.350 |
quo | -0.344 |
Token | have |
Token ID | 423 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
ANE | +2.797 |
awan | +2.691 |
光 | +2.632 |
女 | +2.611 |
UA | +2.601 |
Neg logit contributions | |
ertodd | -2.794 |
ysis | -2.237 |
verts | -2.122 |
ered | -2.095 |
quo | -2.068 |
Token | dealt |
Token ID | 11829 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
ANE | +0.963 |
awan | +0.924 |
光 | +0.905 |
srf | +0.898 |
UA | +0.898 |
Neg logit contributions | |
ertodd | -0.993 |
ysis | -0.798 |
ered | -0.761 |
verts | -0.757 |
quo | -0.747 |
Token | with |
Token ID | 351 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ANE | +0.713 |
awan | +0.682 |
光 | +0.662 |
女 | +0.661 |
UA | +0.659 |
Neg logit contributions | |
ertodd | -0.841 |
ysis | -0.680 |
verts | -0.656 |
ered | -0.641 |
quo | -0.637 |
Token | ! |
Token ID | 0 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
ertodd | +3.013 |
ysis | +2.393 |
verts | +2.291 |
ered | +2.289 |
Jehovah | +2.240 |
Neg logit contributions | |
ANE | -3.224 |
awan | -3.159 |
光 | -3.092 |
srf | -3.055 |
女 | -3.042 |
Token |
|
Token ID | 198 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
ertodd | +2.444 |
ysis | +1.878 |
verts | +1.781 |
ered | +1.778 |
Jehovah | +1.727 |
Neg logit contributions | |
ANE | -3.178 |
awan | -3.110 |
光 | -3.028 |
srf | -3.012 |
女 | -2.995 |
Token |
|
Token ID | 198 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
ANE | +0.078 |
awan | +0.075 |
光 | +0.074 |
srf | +0.073 |
UA | +0.073 |
Neg logit contributions | |
ertodd | -0.060 |
ysis | -0.046 |
verts | -0.043 |
ered | -0.043 |
quo | -0.042 |
Token | Bob |
Token ID | 18861 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
ANE | +1.138 |
awan | +1.084 |
光 | +1.058 |
UA | +1.047 |
女 | +1.044 |
Neg logit contributions | |
ertodd | -1.572 |
ysis | -1.300 |
verts | -1.243 |
ered | -1.238 |
quo | -1.224 |
Token | bi |
Token ID | 8482 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
ertodd | +0.369 |
ysis | +0.294 |
verts | +0.279 |
ered | +0.277 |
quo | +0.271 |
Neg logit contributions | |
ANE | -0.397 |
awan | -0.382 |
光 | -0.376 |
女 | -0.372 |
UA | -0.371 |
Token | Krist |
Token ID | 14912 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
ANE | +1.365 |
awan | +1.308 |
光 | +1.294 |
srf | +1.273 |
女 | +1.269 |
Neg logit contributions | |
ertodd | -1.323 |
ysis | -1.087 |
ered | -1.021 |
verts | -1.020 |
quo | -1.001 |
Token | ina |
Token ID | 1437 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
ANE | +6.413 |
awan | +6.359 |
RAW | +5.928 |
UA | +5.814 |
pull | +5.752 |
Neg logit contributions | |
ertodd | -8.046 |
ysis | -6.416 |
verts | -6.106 |
quo | -6.095 |
Jehovah | -6.043 |
Token | celebrates |
Token ID | 24538 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ANE | +2.812 |
awan | +2.716 |
光 | +2.653 |
UA | +2.638 |
女 | +2.627 |
Neg logit contributions | |
ertodd | -2.543 |
ysis | -1.994 |
verts | -1.874 |
ered | -1.865 |
quo | -1.843 |
Token | Whitney |
Token ID | 34701 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
ANE | +1.137 |
awan | +1.092 |
光 | +1.071 |
UA | +1.061 |
女 | +1.059 |
Neg logit contributions | |
ertodd | -1.116 |
ysis | -0.894 |
verts | -0.848 |
ered | -0.845 |
quo | -0.831 |
Token | Houston |
Token ID | 6995 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
ANE | +1.189 |
awan | +1.135 |
光 | +1.111 |
UA | +1.100 |
女 | +1.098 |
Neg logit contributions | |
ertodd | -1.415 |
ysis | -1.153 |
verts | -1.093 |
ered | -1.091 |
quo | -1.078 |
Token | 's |
Token ID | 338 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
ANE | +1.193 |
awan | +1.144 |
光 | +1.120 |
UA | +1.109 |
女 | +1.107 |
Neg logit contributions | |
ertodd | -1.292 |
ysis | -1.044 |
verts | -0.992 |
ered | -0.988 |
quo | -0.974 |
Token | 1 |
Token ID | 352 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
ertodd | +2.293 |
ysis | +1.864 |
ered | +1.767 |
quo | +1.749 |
verts | +1.735 |
Neg logit contributions | |
ANE | -2.703 |
awan | -2.583 |
光 | -2.561 |
女 | -2.548 |
srf | -2.539 |
Token | - |
Token ID | 12 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
ertodd | +0.609 |
ysis | +0.497 |
ered | +0.475 |
verts | +0.470 |
quo | +0.462 |
Neg logit contributions | |
ANE | -0.577 |
awan | -0.555 |
光 | -0.544 |
女 | -0.543 |
srf | -0.541 |
Token | 0 |
Token ID | 15 |
Feature activation | -6.80e-02 |
Pos logit contributions | |
ANE | +1.039 |
awan | +0.976 |
光 | +0.956 |
srf | +0.953 |
女 | +0.944 |
Neg logit contributions | |
ertodd | -1.842 |
ysis | -1.575 |
ered | -1.525 |
verts | -1.523 |
quo | -1.497 |
Token | [ |
Token ID | 685 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
ANE | +0.212 |
awan | +0.203 |
光 | +0.199 |
女 | +0.198 |
UA | +0.198 |
Neg logit contributions | |
ertodd | -0.191 |
ysis | -0.151 |
verts | -0.143 |
ered | -0.143 |
quo | -0.140 |
Token | Event |
Token ID | 9237 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
ANE | +0.132 |
awan | +0.125 |
光 | +0.120 |
srf | +0.120 |
女 | +0.119 |
Neg logit contributions | |
ertodd | -0.233 |
ysis | -0.198 |
verts | -0.192 |
ered | -0.191 |
quo | -0.189 |
Token | " |
Token ID | 366 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
ertodd | +0.546 |
ysis | +0.433 |
verts | +0.413 |
ered | +0.408 |
quo | +0.402 |
Neg logit contributions | |
ANE | -0.653 |
awan | -0.627 |
光 | -0.616 |
UA | -0.610 |
女 | -0.609 |
Token | 78 |
Token ID | 3695 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
ANE | +5.527 |
awan | +5.274 |
光 | +5.256 |
UA | +5.244 |
RAW | +5.241 |
Neg logit contributions | |
ertodd | -9.081 |
ysis | -7.505 |
verts | -7.107 |
quo | -7.106 |
ered | -7.056 |
Token | th |
Token ID | 400 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ANE | +0.788 |
awan | +0.756 |
光 | +0.740 |
UA | +0.732 |
女 | +0.731 |
Neg logit contributions | |
ertodd | -0.848 |
ysis | -0.685 |
verts | -0.651 |
ered | -0.648 |
quo | -0.639 |
Token | Tata |
Token ID | 49963 |
Feature activation | -9.97e-02 |
Pos logit contributions | |
ANE | +3.542 |
awan | +3.385 |
光 | +3.328 |
UA | +3.309 |
RAW | +3.296 |
Neg logit contributions | |
ertodd | -3.371 |
ysis | -2.656 |
verts | -2.511 |
ered | -2.496 |
quo | -2.462 |
Token | Steel |
Token ID | 7851 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
ANE | +0.298 |
awan | +0.287 |
光 | +0.281 |
UA | +0.278 |
女 | +0.278 |
Neg logit contributions | |
ertodd | -0.293 |
ysis | -0.234 |
verts | -0.221 |
ered | -0.220 |
quo | -0.217 |
Token | Chess |
Token ID | 25774 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
ANE | +2.270 |
awan | +2.185 |
光 | +2.139 |
UA | +2.120 |
女 | +2.108 |
Neg logit contributions | |
ertodd | -2.205 |
ysis | -1.754 |
verts | -1.658 |
ered | -1.642 |
quo | -1.626 |
Token | ( |
Token ID | 7 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ANE | +1.227 |
awan | +1.176 |
光 | +1.142 |
UA | +1.134 |
RAW | +1.131 |
Neg logit contributions | |
ertodd | -1.578 |
ysis | -1.290 |
verts | -1.231 |
ered | -1.223 |
quo | -1.214 |
Token | 0 |
Token ID | 15 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
ANE | +3.679 |
awan | +3.537 |
光 | +3.468 |
UA | +3.459 |
RAW | +3.441 |
Neg logit contributions | |
ertodd | -3.628 |
ysis | -2.881 |
verts | -2.719 |
ered | -2.708 |
quo | -2.686 |
Token | , |
Token ID | 11 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ANE | +1.562 |
awan | +1.492 |
光 | +1.455 |
UA | +1.442 |
女 | +1.437 |
Neg logit contributions | |
ertodd | -1.972 |
ysis | -1.616 |
verts | -1.542 |
ered | -1.534 |
quo | -1.518 |
Token | 0 |
Token ID | 15 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
ertodd | +0.556 |
ysis | +0.471 |
verts | +0.455 |
ered | +0.452 |
quo | +0.444 |
Neg logit contributions | |
ANE | -0.342 |
awan | -0.324 |
光 | -0.314 |
srf | -0.311 |
女 | -0.309 |
Token | , |
Token ID | 11 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
ANE | +1.491 |
awan | +1.426 |
光 | +1.387 |
UA | +1.377 |
女 | +1.368 |
Neg logit contributions | |
ertodd | -1.927 |
ysis | -1.583 |
verts | -1.511 |
ered | -1.504 |
quo | -1.490 |
Token | ($ |
Token ID | 16763 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
ANE | +0.584 |
awan | +0.552 |
光 | +0.536 |
srf | +0.529 |
女 | +0.528 |
Neg logit contributions | |
ertodd | -1.025 |
ysis | -0.867 |
verts | -0.837 |
ered | -0.833 |
quo | -0.820 |
Token | SR |
Token ID | 12562 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ANE | +4.959 |
UA | +4.706 |
awan | +4.562 |
RAW | +4.529 |
光 | +4.407 |
Neg logit contributions | |
ertodd | -9.707 |
ysis | -8.044 |
quo | -7.875 |
Jehovah | -7.770 |
ered | -7.668 |
Token | . |
Token ID | 13 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ANE | +2.718 |
awan | +2.592 |
UA | +2.499 |
光 | +2.496 |
RAW | +2.485 |
Neg logit contributions | |
ertodd | -4.367 |
ysis | -3.661 |
ered | -3.513 |
verts | -3.511 |
quo | -3.479 |
Token | Width |
Token ID | 30916 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ANE | +2.142 |
awan | +1.982 |
UA | +1.922 |
光 | +1.916 |
RAW | +1.902 |
Neg logit contributions | |
ertodd | -5.199 |
ysis | -4.427 |
ered | -4.243 |
quo | -4.238 |
verts | -4.231 |
Token | ), |
Token ID | 828 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
ANE | +2.632 |
awan | +2.507 |
光 | +2.444 |
UA | +2.430 |
RAW | +2.420 |
Neg logit contributions | |
ertodd | -3.592 |
ysis | -2.960 |
verts | -2.812 |
ered | -2.806 |
quo | -2.780 |
Token | ($ |
Token ID | 16763 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
ertodd | +1.365 |
ysis | +1.151 |
verts | +1.109 |
ered | +1.106 |
quo | +1.090 |
Neg logit contributions | |
ANE | -0.821 |
awan | -0.779 |
光 | -0.754 |
srf | -0.743 |
女 | -0.743 |
Token | the |
Token ID | 262 |
Feature activation | -9.06e-02 |
Pos logit contributions | |
ertodd | +2.092 |
ysis | +1.650 |
ered | +1.583 |
verts | +1.547 |
quo | +1.532 |
Neg logit contributions | |
ANE | -2.642 |
awan | -2.474 |
光 | -2.468 |
UA | -2.463 |
srf | -2.460 |
Token | bye |
Token ID | 33847 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
ANE | +0.257 |
awan | +0.245 |
光 | +0.240 |
UA | +0.239 |
女 | +0.238 |
Neg logit contributions | |
ertodd | -0.280 |
ysis | -0.228 |
verts | -0.217 |
ered | -0.217 |
quo | -0.214 |
Token | week |
Token ID | 1285 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
ANE | +0.416 |
awan | +0.394 |
光 | +0.390 |
srf | +0.385 |
女 | +0.384 |
Neg logit contributions | |
ertodd | -0.510 |
ysis | -0.418 |
verts | -0.405 |
ered | -0.401 |
quo | -0.397 |
Token | , |
Token ID | 11 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
ANE | +0.999 |
awan | +0.951 |
光 | +0.938 |
srf | +0.927 |
UA | +0.925 |
Neg logit contributions | |
ertodd | -1.100 |
ysis | -0.896 |
ered | -0.855 |
verts | -0.855 |
quo | -0.845 |
Token | because |
Token ID | 780 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
ertodd | +0.523 |
ysis | +0.424 |
verts | +0.401 |
ered | +0.400 |
quo | +0.400 |
Neg logit contributions | |
ANE | -0.540 |
awan | -0.513 |
光 | -0.507 |
RAW | -0.502 |
srf | -0.502 |
Token | Jord |
Token ID | 38317 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
ANE | +0.299 |
awan | +0.287 |
光 | +0.283 |
srf | +0.280 |
UA | +0.280 |
Neg logit contributions | |
ertodd | -0.251 |
ysis | -0.197 |
ered | -0.186 |
verts | -0.186 |
quo | -0.183 |
Token | y |
Token ID | 88 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
ANE | +6.162 |
awan | +5.959 |
UA | +5.607 |
女 | +5.522 |
EMENT | +5.476 |
Neg logit contributions | |
ertodd | -8.568 |
ysis | -6.994 |
verts | -6.757 |
quo | -6.592 |
Jehovah | -6.559 |
Token | Nelson |
Token ID | 12996 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
ANE | +1.766 |
awan | +1.677 |
光 | +1.638 |
女 | +1.619 |
UA | +1.614 |
Neg logit contributions | |
ertodd | -2.648 |
ysis | -2.209 |
verts | -2.121 |
ered | -2.117 |
quo | -2.092 |
Token | awaits |
Token ID | 37180 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
ANE | +4.170 |
awan | +4.081 |
光 | +3.957 |
女 | +3.930 |
UA | +3.923 |
Neg logit contributions | |
ertodd | -3.806 |
ysis | -2.942 |
verts | -2.771 |
ered | -2.721 |
quo | -2.656 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
ANE | +0.064 |
awan | +0.061 |
光 | +0.060 |
srf | +0.060 |
女 | +0.059 |
Neg logit contributions | |
ertodd | -0.059 |
ysis | -0.048 |
ered | -0.045 |
verts | -0.045 |
quo | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
ANE | +0.476 |
awan | +0.459 |
光 | +0.450 |
UA | +0.446 |
女 | +0.446 |
Neg logit contributions | |
ertodd | -0.397 |
ysis | -0.310 |
verts | -0.292 |
ered | -0.290 |
quo | -0.285 |
Token | neurons |
Token ID | 16890 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
ANE | +0.202 |
awan | +0.194 |
光 | +0.190 |
UA | +0.188 |
女 | +0.188 |
Neg logit contributions | |
ertodd | -0.206 |
ysis | -0.165 |
verts | -0.157 |
ered | -0.156 |
quo | -0.154 |
Token | activated |
Token ID | 13906 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
ertodd | +0.760 |
ysis | +0.596 |
ered | +0.567 |
verts | +0.562 |
quo | +0.550 |
Neg logit contributions | |
ANE | -0.917 |
awan | -0.879 |
光 | -0.865 |
srf | -0.861 |
UA | -0.860 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
ertodd | +1.904 |
ysis | +1.552 |
verts | +1.501 |
ered | +1.499 |
quo | +1.482 |
Neg logit contributions | |
ANE | -1.625 |
awan | -1.552 |
光 | -1.512 |
UA | -1.496 |
RAW | -1.494 |
Token |
|
Token ID | 198 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ANE | +0.595 |
awan | +0.573 |
光 | +0.563 |
UA | +0.559 |
女 | +0.557 |
Neg logit contributions | |
ertodd | -0.511 |
ysis | -0.399 |
verts | -0.375 |
ered | -0.373 |
quo | -0.369 |
Token |
|
Token ID | 198 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
ertodd | +0.270 |
ysis | +0.207 |
verts | +0.195 |
ered | +0.195 |
quo | +0.190 |
Neg logit contributions | |
ANE | -0.358 |
awan | -0.345 |
光 | -0.339 |
srf | -0.339 |
女 | -0.336 |
Token | Krist |
Token ID | 40756 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
ANE | +0.954 |
awan | +0.912 |
光 | +0.889 |
srf | +0.882 |
女 | +0.878 |
Neg logit contributions | |
ertodd | -1.226 |
ysis | -1.008 |
verts | -0.965 |
ered | -0.961 |
quo | -0.946 |
Token | ofer |
Token ID | 30288 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ANE | +6.821 |
awan | +6.766 |
UA | +6.371 |
pull | +6.239 |
RAW | +6.223 |
Neg logit contributions | |
ertodd | -7.475 |
ysis | -5.839 |
quo | -5.699 |
verts | -5.614 |
Jehovah | -5.454 |
Token | B |
Token ID | 347 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
ANE | +3.426 |
awan | +3.328 |
UA | +3.240 |
光 | +3.231 |
EMENT | +3.208 |
Neg logit contributions | |
ertodd | -2.983 |
ysis | -2.285 |
verts | -2.139 |
quo | -2.127 |
ered | -2.121 |
Token | ouch |
Token ID | 7673 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
ANE | +1.187 |
awan | +1.139 |
光 | +1.104 |
UA | +1.099 |
EMENT | +1.092 |
Neg logit contributions | |
ertodd | -1.318 |
ysis | -1.063 |
verts | -1.013 |
ered | -1.003 |
quo | -0.995 |
Token | ard |
Token ID | 446 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
ertodd | +1.252 |
ysis | +1.046 |
ered | +1.011 |
verts | +1.005 |
quo | +0.978 |
Neg logit contributions | |
ANE | -0.911 |
光 | -0.857 |
srf | -0.854 |
女 | -0.848 |
awan | -0.843 |
Token | , |
Token ID | 11 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
ertodd | +1.691 |
ysis | +1.373 |
ered | +1.310 |
verts | +1.304 |
quo | +1.276 |
Neg logit contributions | |
ANE | -1.630 |
awan | -1.551 |
光 | -1.535 |
srf | -1.516 |
女 | -1.513 |
Token | a |
Token ID | 257 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
ANE | +0.506 |
awan | +0.486 |
光 | +0.479 |
UA | +0.476 |
srf | +0.474 |
Neg logit contributions | |
ertodd | -0.411 |
ysis | -0.320 |
verts | -0.306 |
ered | -0.302 |
quo | -0.298 |
Token | premiere |
Token ID | 19245 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
ertodd | +0.096 |
ysis | +0.079 |
verts | +0.075 |
ered | +0.075 |
quo | +0.074 |
Neg logit contributions | |
ANE | -0.086 |
awan | -0.082 |
光 | -0.081 |
UA | -0.080 |
EMENT | -0.079 |
Token | ninja |
Token ID | 37049 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
ertodd | +1.900 |
ysis | +1.573 |
ered | +1.481 |
verts | +1.469 |
quo | +1.467 |
Neg logit contributions | |
ANE | -2.072 |
awan | -1.967 |
光 | -1.964 |
srf | -1.943 |
UA | -1.941 |
Token | in |
Token ID | 287 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
ertodd | +1.441 |
ysis | +1.181 |
ered | +1.129 |
verts | +1.125 |
quo | +1.114 |
Neg logit contributions | |
ANE | -1.331 |
光 | -1.254 |
awan | -1.252 |
UA | -1.239 |
srf | -1.238 |
Token | the |
Token ID | 262 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
ertodd | +1.181 |
ysis | +0.920 |
verts | +0.875 |
ered | +0.865 |
quo | +0.852 |
Neg logit contributions | |
ANE | -1.491 |
awan | -1.434 |
光 | -1.409 |
UA | -1.405 |
女 | -1.403 |
Token | Foot |
Token ID | 7870 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
ertodd | +0.503 |
ysis | +0.407 |
ered | +0.385 |
verts | +0.384 |
quo | +0.381 |
Neg logit contributions | |
ANE | -0.516 |
awan | -0.493 |
光 | -0.487 |
UA | -0.483 |
srf | -0.483 |
Token | , |
Token ID | 11 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
ertodd | +3.387 |
ysis | +2.289 |
ered | +2.239 |
verts | +2.096 |
quo | +2.020 |
Neg logit contributions | |
ANE | -8.025 |
srf | -7.781 |
光 | -7.734 |
awan | -7.691 |
女 | -7.660 |
Token | and |
Token ID | 290 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ertodd | +0.082 |
ysis | +0.066 |
verts | +0.063 |
ered | +0.062 |
quo | +0.062 |
Neg logit contributions | |
ANE | -0.091 |
awan | -0.087 |
光 | -0.086 |
UA | -0.085 |
EMENT | -0.085 |
Token | as |
Token ID | 355 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
ertodd | +0.353 |
ysis | +0.279 |
ered | +0.267 |
verts | +0.265 |
quo | +0.262 |
Neg logit contributions | |
ANE | -0.420 |
awan | -0.401 |
光 | -0.395 |
UA | -0.393 |
srf | -0.393 |
Token | a |
Token ID | 257 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
ertodd | +0.898 |
ysis | +0.699 |
verts | +0.659 |
ered | +0.656 |
quo | +0.648 |
Neg logit contributions | |
ANE | -1.156 |
awan | -1.107 |
光 | -1.093 |
UA | -1.088 |
srf | -1.087 |
Token | reward |
Token ID | 6721 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
ertodd | +0.169 |
ysis | +0.137 |
verts | +0.131 |
ered | +0.131 |
quo | +0.130 |
Neg logit contributions | |
ANE | -0.156 |
awan | -0.148 |
光 | -0.147 |
UA | -0.145 |
srf | -0.144 |
Token | option |
Token ID | 3038 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
ertodd | +1.332 |
ysis | +1.076 |
ered | +1.019 |
verts | +1.016 |
quo | +1.001 |
Neg logit contributions | |
ANE | -1.458 |
awan | -1.402 |
光 | -1.378 |
srf | -1.361 |
UA | -1.355 |
Token | � |
Token ID | 447 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
ANE | +0.473 |
awan | +0.457 |
光 | +0.448 |
UA | +0.445 |
女 | +0.445 |
Neg logit contributions | |
ertodd | -0.353 |
ysis | -0.270 |
verts | -0.253 |
ered | -0.251 |
quo | -0.246 |
Token | � |
Token ID | 247 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
ertodd | +0.112 |
ysis | +0.094 |
verts | +0.091 |
ered | +0.090 |
quo | +0.089 |
Neg logit contributions | |
ANE | -0.067 |
awan | -0.063 |
光 | -0.061 |
UA | -0.061 |
女 | -0.061 |
Token | adopted |
Token ID | 8197 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
ertodd | +0.629 |
ysis | +0.497 |
verts | +0.471 |
ered | +0.469 |
quo | +0.462 |
Neg logit contributions | |
ANE | -0.710 |
awan | -0.681 |
光 | -0.669 |
srf | -0.662 |
UA | -0.662 |
Token | by |
Token ID | 416 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
ertodd | +2.200 |
ysis | +1.762 |
verts | +1.697 |
ered | +1.696 |
quo | +1.679 |
Neg logit contributions | |
ANE | -2.212 |
awan | -2.092 |
srf | -2.062 |
光 | -2.060 |
UA | -2.046 |
Token | Pu |
Token ID | 11634 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
ANE | +0.123 |
awan | +0.119 |
光 | +0.116 |
UA | +0.115 |
女 | +0.115 |
Neg logit contributions | |
ertodd | -0.110 |
ysis | -0.087 |
verts | -0.082 |
ered | -0.081 |
quo | -0.080 |
Token | ig |
Token ID | 328 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
ertodd | +4.738 |
ysis | +3.766 |
ered | +3.693 |
verts | +3.661 |
quo | +3.497 |
Neg logit contributions | |
ANE | -5.458 |
senal | -5.408 |
srf | -5.384 |
光 | -5.269 |
女 | -5.142 |
Token | dem |
Token ID | 9536 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
ANE | +1.333 |
awan | +1.266 |
光 | +1.219 |
UA | +1.206 |
女 | +1.201 |
Neg logit contributions | |
ertodd | -2.587 |
ysis | -2.193 |
verts | -2.108 |
ered | -2.102 |
quo | -2.083 |
Token | ont |
Token ID | 756 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
ANE | +1.527 |
awan | +1.478 |
光 | +1.439 |
UA | +1.427 |
女 | +1.423 |
Neg logit contributions | |
ertodd | -1.433 |
ysis | -1.137 |
verts | -1.074 |
ered | -1.065 |
quo | -1.053 |
Token | and |
Token ID | 290 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
ANE | +2.195 |
awan | +2.136 |
光 | +2.091 |
UA | +2.075 |
女 | +2.071 |
Neg logit contributions | |
ertodd | -2.008 |
ysis | -1.586 |
verts | -1.486 |
ered | -1.480 |
quo | -1.452 |
Token | his |
Token ID | 465 |
Feature activation | +8.26e-02 |
Pos logit contributions | |
ertodd | +1.044 |
ysis | +0.807 |
verts | +0.767 |
ered | +0.767 |
quo | +0.750 |
Neg logit contributions | |
ANE | -1.311 |
awan | -1.257 |
光 | -1.242 |
srf | -1.224 |
女 | -1.224 |
Token | insofar |
Token ID | 44061 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
ertodd | +0.464 |
ysis | +0.379 |
ered | +0.364 |
verts | +0.358 |
quo | +0.354 |
Neg logit contributions | |
ANE | -0.444 |
awan | -0.424 |
光 | -0.421 |
srf | -0.418 |
女 | -0.413 |
Token | as |
Token ID | 355 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
ertodd | +0.795 |
ysis | +0.636 |
ered | +0.612 |
verts | +0.605 |
quo | +0.596 |
Neg logit contributions | |
ANE | -0.862 |
awan | -0.823 |
光 | -0.815 |
srf | -0.814 |
女 | -0.805 |
Token | mobile |
Token ID | 5175 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
ertodd | +1.729 |
ysis | +1.361 |
ered | +1.293 |
verts | +1.292 |
quo | +1.285 |
Neg logit contributions | |
ANE | -2.241 |
awan | -2.164 |
srf | -2.156 |
光 | -2.154 |
女 | -2.118 |
Token | teachers |
Token ID | 7799 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
ertodd | +0.937 |
ysis | +0.759 |
verts | +0.716 |
ered | +0.716 |
quo | +0.702 |
Neg logit contributions | |
ANE | -1.014 |
awan | -0.977 |
光 | -0.966 |
srf | -0.958 |
女 | -0.958 |
Token | are |
Token ID | 389 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
ertodd | +0.640 |
ysis | +0.500 |
ered | +0.478 |
verts | +0.475 |
quo | +0.468 |
Neg logit contributions | |
ANE | -0.781 |
awan | -0.753 |
光 | -0.749 |
srf | -0.742 |
UA | -0.735 |
Token | short |
Token ID | 1790 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
ertodd | +1.019 |
ysis | +0.825 |
ered | +0.794 |
verts | +0.793 |
quo | +0.788 |
Neg logit contributions | |
ANE | -1.073 |
awan | -1.039 |
光 | -1.029 |
srf | -1.025 |
女 | -1.004 |
Token | changed |
Token ID | 40985 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
ertodd | +4.737 |
ered | +3.833 |
ysis | +3.798 |
verts | +3.728 |
quo | +3.636 |
Neg logit contributions | |
ANE | -5.867 |
awan | -5.712 |
光 | -5.609 |
女 | -5.567 |
srf | -5.565 |
Token | by |
Token ID | 416 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
ertodd | +1.427 |
ysis | +1.167 |
ered | +1.122 |
verts | +1.111 |
quo | +1.110 |
Neg logit contributions | |
ANE | -1.301 |
awan | -1.243 |
srf | -1.230 |
光 | -1.229 |
senal | -1.211 |
Token | teacher |
Token ID | 4701 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ertodd | +0.851 |
ysis | +0.686 |
verts | +0.656 |
ered | +0.651 |
quo | +0.644 |
Neg logit contributions | |
ANE | -0.897 |
awan | -0.863 |
光 | -0.857 |
srf | -0.851 |
女 | -0.850 |
Token | pensions |
Token ID | 27581 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
ANE | +1.175 |
awan | +1.130 |
光 | +1.108 |
UA | +1.098 |
女 | +1.096 |
Neg logit contributions | |
ertodd | -1.084 |
ysis | -0.858 |
verts | -0.812 |
ered | -0.808 |
quo | -0.795 |
Token | . |
Token ID | 13 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
ertodd | +0.537 |
ysis | +0.442 |
verts | +0.424 |
ered | +0.423 |
quo | +0.420 |
Neg logit contributions | |
ANE | -0.418 |
awan | -0.398 |
光 | -0.389 |
srf | -0.386 |
UA | -0.385 |
Token | In |
Token ID | 554 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
ANE | +0.653 |
awan | +0.628 |
光 | +0.619 |
srf | +0.613 |
女 | +0.612 |
Neg logit contributions | |
ertodd | -0.505 |
ysis | -0.392 |
verts | -0.370 |
ered | -0.367 |
quo | -0.358 |
Token | Public |
Token ID | 5094 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
ertodd | +0.885 |
ysis | +0.705 |
verts | +0.678 |
ered | +0.670 |
Jehovah | +0.649 |
Neg logit contributions | |
ANE | -0.968 |
awan | -0.933 |
光 | -0.920 |
srf | -0.914 |
EMENT | -0.910 |
Token | - |
Token ID | 12 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
ertodd | +1.886 |
ysis | +1.485 |
verts | +1.392 |
ered | +1.390 |
quo | +1.347 |
Neg logit contributions | |
ANE | -2.371 |
awan | -2.282 |
光 | -2.242 |
srf | -2.235 |
女 | -2.222 |
Token | Writ |
Token ID | 20257 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
ertodd | +1.878 |
ysis | +1.594 |
verts | +1.553 |
ered | +1.548 |
Jehovah | +1.511 |
Neg logit contributions | |
ANE | -1.061 |
srf | -1.034 |
awan | -1.022 |
senal | -0.977 |
光 | -0.976 |
Token | ters |
Token ID | 1010 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ANE | +2.523 |
awan | +2.435 |
光 | +2.389 |
UA | +2.369 |
女 | +2.365 |
Neg logit contributions | |
ertodd | -1.989 |
ysis | -1.535 |
verts | -1.440 |
ered | -1.431 |
quo | -1.410 |
Token | Strike |
Token ID | 12282 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
ertodd | +4.178 |
ysis | +3.439 |
ered | +3.268 |
verts | +3.245 |
quo | +3.161 |
Neg logit contributions | |
ANE | -4.405 |
srf | -4.222 |
awan | -4.216 |
光 | -4.172 |
女 | -4.159 |
Token | 2008 |
Token ID | 3648 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
ertodd | +4.578 |
ysis | +3.682 |
ered | +3.617 |
verts | +3.503 |
Jehovah | +3.462 |
Neg logit contributions | |
ANE | -5.725 |
srf | -5.583 |
光 | -5.517 |
awan | -5.491 |
女 | -5.458 |
Token | 01 |
Token ID | 486 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
ANE | +0.352 |
awan | +0.335 |
光 | +0.327 |
UA | +0.323 |
女 | +0.323 |
Neg logit contributions | |
ertodd | -0.456 |
ysis | -0.375 |
verts | -0.358 |
ered | -0.357 |
quo | -0.352 |
Token | 04 |
Token ID | 3023 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ertodd | +0.617 |
ysis | +0.486 |
verts | +0.460 |
ered | +0.459 |
quo | +0.450 |
Neg logit contributions | |
ANE | -0.714 |
awan | -0.689 |
srf | -0.681 |
光 | -0.672 |
女 | -0.666 |
Token | O |
Token ID | 440 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ertodd | +4.069 |
ysis | +3.295 |
verts | +3.115 |
ered | +3.108 |
quo | +3.068 |
Neg logit contributions | |
ANE | -4.211 |
awan | -4.075 |
srf | -3.999 |
光 | -3.966 |
女 | -3.936 |
Token | & |
Token ID | 5 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
ertodd | +0.417 |
ysis | +0.336 |
verts | +0.320 |
ered | +0.320 |
quo | +0.312 |
Neg logit contributions | |
ANE | -0.407 |
srf | -0.394 |
awan | -0.393 |
光 | -0.388 |
senal | -0.385 |
Token | electing |
Token ID | 46913 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
ANE | +0.629 |
awan | +0.602 |
光 | +0.592 |
UA | +0.587 |
srf | +0.586 |
Neg logit contributions | |
ertodd | -0.622 |
ysis | -0.500 |
verts | -0.475 |
ered | -0.472 |
quo | -0.469 |
Token | a |
Token ID | 257 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
ANE | +2.514 |
awan | +2.425 |
光 | +2.369 |
UA | +2.351 |
女 | +2.345 |
Neg logit contributions | |
ertodd | -2.283 |
ysis | -1.786 |
verts | -1.686 |
ered | -1.676 |
quo | -1.637 |
Token | president |
Token ID | 1893 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
ANE | +1.118 |
awan | +1.071 |
光 | +1.049 |
UA | +1.039 |
女 | +1.037 |
Neg logit contributions | |
ertodd | -1.194 |
ysis | -0.963 |
verts | -0.916 |
ered | -0.912 |
quo | -0.900 |
Token | would |
Token ID | 561 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
ertodd | +0.772 |
ysis | +0.608 |
verts | +0.576 |
ered | +0.575 |
quo | +0.569 |
Neg logit contributions | |
ANE | -0.883 |
awan | -0.846 |
光 | -0.830 |
srf | -0.829 |
UA | -0.825 |
Token | be |
Token ID | 307 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
ertodd | +0.503 |
ysis | +0.393 |
ered | +0.376 |
verts | +0.372 |
quo | +0.366 |
Neg logit contributions | |
ANE | -0.590 |
awan | -0.566 |
光 | -0.557 |
UA | -0.556 |
srf | -0.553 |
Token | indul |
Token ID | 19441 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
ANE | +0.068 |
awan | +0.065 |
光 | +0.064 |
srf | +0.064 |
UA | +0.063 |
Neg logit contributions | |
ertodd | -0.070 |
ysis | -0.057 |
ered | -0.054 |
verts | -0.054 |
quo | -0.053 |
Token | ging |
Token ID | 2667 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
ertodd | +5.563 |
ysis | +4.467 |
ered | +4.361 |
verts | +4.334 |
quo | +4.127 |
Neg logit contributions | |
ANE | -5.387 |
srf | -5.098 |
光 | -5.097 |
女 | -5.079 |
awan | -5.070 |
Token | in |
Token ID | 287 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
ertodd | +1.963 |
ysis | +1.585 |
ered | +1.526 |
verts | +1.519 |
quo | +1.502 |
Neg logit contributions | |
ANE | -1.948 |
awan | -1.857 |
光 | -1.830 |
srf | -1.820 |
UA | -1.817 |
Token | the |
Token ID | 262 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
ANE | +0.102 |
awan | +0.097 |
光 | +0.096 |
UA | +0.095 |
srf | +0.095 |
Neg logit contributions | |
ertodd | -0.097 |
ysis | -0.078 |
verts | -0.074 |
ered | -0.073 |
quo | -0.073 |
Token | very |
Token ID | 845 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
ANE | +0.072 |
awan | +0.069 |
光 | +0.067 |
srf | +0.067 |
UA | +0.067 |
Neg logit contributions | |
ertodd | -0.085 |
ysis | -0.069 |
verts | -0.066 |
ered | -0.066 |
quo | -0.066 |
Token | reflex |
Token ID | 24133 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ANE | +2.053 |
awan | +1.966 |
光 | +1.922 |
UA | +1.902 |
女 | +1.900 |
Neg logit contributions | |
ertodd | -2.363 |
ysis | -1.919 |
verts | -1.827 |
ered | -1.819 |
quo | -1.792 |
Token | from |
Token ID | 422 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
ANE | +1.351 |
awan | +1.289 |
光 | +1.262 |
UA | +1.247 |
女 | +1.246 |
Neg logit contributions | |
ertodd | -1.721 |
ysis | -1.410 |
verts | -1.346 |
ered | -1.335 |
quo | -1.318 |
Token | an |
Token ID | 281 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
ertodd | +0.036 |
ysis | +0.028 |
verts | +0.026 |
ered | +0.026 |
quo | +0.026 |
Neg logit contributions | |
ANE | -0.041 |
awan | -0.039 |
光 | -0.038 |
女 | -0.038 |
UA | -0.038 |
Token | interpretation |
Token ID | 10794 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
ANE | +0.308 |
awan | +0.293 |
女 | +0.288 |
光 | +0.287 |
srf | +0.287 |
Neg logit contributions | |
ertodd | -0.369 |
ysis | -0.303 |
ered | -0.290 |
verts | -0.286 |
quo | -0.285 |
Token | of |
Token ID | 286 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
ANE | +2.376 |
awan | +2.286 |
光 | +2.242 |
UA | +2.224 |
女 | +2.212 |
Neg logit contributions | |
ertodd | -2.325 |
ysis | -1.837 |
verts | -1.738 |
ered | -1.721 |
quo | -1.686 |
Token | the |
Token ID | 262 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
ANE | +1.285 |
awan | +1.241 |
光 | +1.218 |
UA | +1.206 |
女 | +1.204 |
Neg logit contributions | |
ertodd | -1.039 |
ysis | -0.805 |
verts | -0.756 |
ered | -0.752 |
quo | -0.737 |
Token | word |
Token ID | 1573 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
ANE | +1.201 |
awan | +1.147 |
光 | +1.121 |
UA | +1.113 |
女 | +1.111 |
Neg logit contributions | |
ertodd | -1.343 |
ysis | -1.093 |
verts | -1.041 |
ered | -1.037 |
quo | -1.027 |
Token | � |
Token ID | 564 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
ertodd | +1.623 |
ysis | +1.318 |
ered | +1.249 |
verts | +1.248 |
quo | +1.245 |
Neg logit contributions | |
ANE | -1.758 |
awan | -1.666 |
光 | -1.637 |
UA | -1.634 |
srf | -1.629 |
Token | � |
Token ID | 250 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
ANE | +1.140 |
awan | +1.083 |
光 | +1.058 |
女 | +1.046 |
UA | +1.044 |
Neg logit contributions | |
ertodd | -1.692 |
ysis | -1.403 |
verts | -1.350 |
ered | -1.337 |
quo | -1.323 |
Token | d |
Token ID | 67 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
ertodd | +0.769 |
ysis | +0.647 |
ered | +0.624 |
verts | +0.621 |
quo | +0.611 |
Neg logit contributions | |
ANE | -0.530 |
awan | -0.501 |
srf | -0.488 |
光 | -0.488 |
UA | -0.484 |
Token | isson |
Token ID | 30927 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
ertodd | +1.127 |
ysis | +0.934 |
ered | +0.890 |
verts | +0.881 |
quo | +0.875 |
Neg logit contributions | |
ANE | -0.989 |
awan | -0.935 |
光 | -0.933 |
srf | -0.928 |
女 | -0.924 |
Token | ant |
Token ID | 415 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
ANE | +1.989 |
awan | +1.912 |
光 | +1.870 |
UA | +1.852 |
女 | +1.851 |
Neg logit contributions | |
ertodd | -1.978 |
ysis | -1.578 |
verts | -1.498 |
ered | -1.489 |
quo | -1.468 |
Token | trade |
Token ID | 3292 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
ertodd | +1.517 |
ysis | +1.242 |
verts | +1.171 |
ered | +1.168 |
quo | +1.168 |
Neg logit contributions | |
ANE | -1.637 |
awan | -1.578 |
光 | -1.539 |
RAW | -1.538 |
srf | -1.527 |
Token | asset |
Token ID | 11171 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ertodd | +0.843 |
ysis | +0.689 |
verts | +0.666 |
ered | +0.665 |
quo | +0.660 |
Neg logit contributions | |
ANE | -0.677 |
awan | -0.645 |
光 | -0.632 |
女 | -0.622 |
RAW | -0.621 |
Token | . |
Token ID | 13 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
ANE | +2.754 |
awan | +2.643 |
光 | +2.575 |
女 | +2.551 |
UA | +2.547 |
Neg logit contributions | |
ertodd | -3.278 |
ysis | -2.674 |
verts | -2.535 |
ered | -2.525 |
quo | -2.483 |
Token | And |
Token ID | 843 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
ANE | +0.603 |
awan | +0.582 |
光 | +0.571 |
UA | +0.566 |
女 | +0.565 |
Neg logit contributions | |
ertodd | -0.492 |
ysis | -0.382 |
verts | -0.360 |
ered | -0.358 |
quo | -0.351 |
Token | the |
Token ID | 262 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
ertodd | +1.248 |
ysis | +0.993 |
ered | +0.952 |
verts | +0.945 |
quo | +0.940 |
Neg logit contributions | |
ANE | -1.381 |
awan | -1.321 |
光 | -1.310 |
srf | -1.297 |
UA | -1.289 |
Token | Padres |
Token ID | 40188 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
ertodd | +0.405 |
ysis | +0.326 |
verts | +0.311 |
ered | +0.309 |
quo | +0.306 |
Neg logit contributions | |
ANE | -0.413 |
awan | -0.397 |
光 | -0.391 |
女 | -0.387 |
UA | -0.386 |
Token | should |
Token ID | 815 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
ertodd | +0.694 |
ysis | +0.547 |
ered | +0.524 |
verts | +0.515 |
quo | +0.513 |
Neg logit contributions | |
ANE | -0.804 |
awan | -0.774 |
光 | -0.760 |
女 | -0.755 |
srf | -0.753 |
Token | have |
Token ID | 423 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
ertodd | +0.905 |
ysis | +0.709 |
ered | +0.702 |
verts | +0.666 |
quo | +0.664 |
Neg logit contributions | |
ANE | -1.084 |
awan | -1.035 |
UA | -1.027 |
光 | -1.019 |
srf | -1.016 |
Token | left |
Token ID | 1364 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
ertodd | +0.811 |
ysis | +0.650 |
ered | +0.629 |
verts | +0.614 |
quo | +0.611 |
Neg logit contributions | |
ANE | -0.886 |
awan | -0.846 |
光 | -0.831 |
srf | -0.829 |
UA | -0.822 |
Token | him |
Token ID | 683 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
ANE | +1.540 |
awan | +1.485 |
光 | +1.455 |
UA | +1.443 |
女 | +1.441 |
Neg logit contributions | |
ertodd | -1.297 |
ysis | -1.010 |
verts | -0.952 |
ered | -0.946 |
quo | -0.930 |
Token | alone |
Token ID | 3436 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
ertodd | +1.427 |
ysis | +1.170 |
ered | +1.130 |
quo | +1.114 |
verts | +1.110 |
Neg logit contributions | |
ANE | -1.359 |
awan | -1.277 |
光 | -1.269 |
UA | -1.265 |
srf | -1.258 |
Token | rates |
Token ID | 3965 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
ertodd | +2.069 |
ysis | +1.408 |
verts | +1.388 |
ered | +1.334 |
quo | +1.250 |
Neg logit contributions | |
ANE | -5.807 |
awan | -5.645 |
光 | -5.531 |
srf | -5.511 |
senal | -5.483 |
Token | , |
Token ID | 11 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
ertodd | +4.860 |
ered | +3.992 |
ysis | +3.971 |
quo | +3.952 |
verts | +3.900 |
Neg logit contributions | |
ANE | -6.050 |
srf | -5.887 |
awan | -5.852 |
senal | -5.735 |
光 | -5.705 |
Token | or |
Token ID | 393 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
ertodd | +0.665 |
ysis | +0.519 |
verts | +0.492 |
ered | +0.491 |
quo | +0.483 |
Neg logit contributions | |
ANE | -0.861 |
awan | -0.832 |
光 | -0.818 |
女 | -0.812 |
srf | -0.810 |
Token | at |
Token ID | 379 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
ANE | +0.991 |
awan | +0.950 |
光 | +0.932 |
srf | +0.923 |
女 | +0.922 |
Neg logit contributions | |
ertodd | -1.033 |
ysis | -0.843 |
verts | -0.803 |
ered | -0.801 |
quo | -0.789 |
Token | a |
Token ID | 257 |
Feature activation | -1.26e-03 |
Pos logit contributions | |
ANE | +1.001 |
awan | +0.962 |
光 | +0.945 |
女 | +0.938 |
srf | +0.934 |
Neg logit contributions | |
ertodd | -0.896 |
ysis | -0.713 |
verts | -0.677 |
ered | -0.674 |
quo | -0.662 |
Token | refresh |
Token ID | 14976 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
ANE | +0.004 |
awan | +0.004 |
光 | +0.004 |
女 | +0.003 |
srf | +0.003 |
Neg logit contributions | |
ertodd | -0.004 |
ysis | -0.003 |
ered | -0.003 |
verts | -0.003 |
quo | -0.003 |
Token | rate |
Token ID | 2494 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ertodd | +0.933 |
ysis | +0.678 |
ered | +0.648 |
verts | +0.631 |
quo | +0.625 |
Neg logit contributions | |
ANE | -1.809 |
awan | -1.751 |
光 | -1.725 |
女 | -1.714 |
srf | -1.708 |
Token | more |
Token ID | 517 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
ertodd | +2.876 |
ysis | +2.341 |
ered | +2.304 |
quo | +2.279 |
verts | +2.232 |
Neg logit contributions | |
ANE | -3.461 |
awan | -3.346 |
srf | -3.317 |
女 | -3.305 |
senal | -3.302 |
Token | likely |
Token ID | 1884 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
ertodd | +0.634 |
ysis | +0.511 |
verts | +0.504 |
ered | +0.503 |
quo | +0.495 |
Neg logit contributions | |
ANE | -0.607 |
awan | -0.580 |
光 | -0.570 |
srf | -0.566 |
女 | -0.564 |
Token | achieved |
Token ID | 8793 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
ertodd | +0.993 |
ysis | +0.805 |
ered | +0.787 |
verts | +0.774 |
quo | +0.768 |
Neg logit contributions | |
ANE | -0.934 |
awan | -0.897 |
光 | -0.872 |
srf | -0.871 |
女 | -0.865 |
Token | during |
Token ID | 1141 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
ANE | +1.199 |
awan | +1.149 |
光 | +1.125 |
UA | +1.111 |
女 | +1.110 |
Neg logit contributions | |
ertodd | -1.312 |
ysis | -1.062 |
verts | -1.013 |
ered | -1.011 |
quo | -0.996 |
Token | Why |
Token ID | 4162 |
Feature activation | +3.27e-03 |
Pos logit contributions | |
ertodd | +0.358 |
ysis | +0.279 |
verts | +0.263 |
ered | +0.261 |
quo | +0.257 |
Neg logit contributions | |
ANE | -0.447 |
awan | -0.432 |
srf | -0.425 |
光 | -0.423 |
UA | -0.419 |
Token | don |
Token ID | 836 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
ertodd | +0.009 |
ysis | +0.007 |
verts | +0.007 |
ered | +0.007 |
quo | +0.007 |
Neg logit contributions | |
ANE | -0.010 |
awan | -0.010 |
光 | -0.010 |
srf | -0.010 |
UA | -0.010 |
Token | � |
Token ID | 447 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
ANE | +2.267 |
awan | +2.183 |
光 | +2.146 |
女 | +2.130 |
UA | +2.128 |
Neg logit contributions | |
ertodd | -1.989 |
ysis | -1.559 |
verts | -1.459 |
ered | -1.449 |
quo | -1.440 |
Token | � |
Token ID | 247 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
ertodd | +1.583 |
ysis | +1.326 |
ered | +1.278 |
verts | +1.266 |
quo | +1.249 |
Neg logit contributions | |
ANE | -1.171 |
awan | -1.126 |
srf | -1.088 |
光 | -1.083 |
senal | -1.064 |
Token | t |
Token ID | 83 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
ertodd | +1.489 |
ysis | +1.203 |
verts | +1.142 |
ered | +1.138 |
quo | +1.113 |
Neg logit contributions | |
ANE | -1.516 |
awan | -1.454 |
光 | -1.426 |
srf | -1.418 |
UA | -1.402 |
Token | you |
Token ID | 345 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ertodd | +1.047 |
ysis | +0.823 |
verts | +0.780 |
ered | +0.777 |
quo | +0.768 |
Neg logit contributions | |
ANE | -1.295 |
awan | -1.250 |
光 | -1.231 |
srf | -1.226 |
UA | -1.214 |
Token | trust |
Token ID | 3774 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
ertodd | +2.883 |
ysis | +2.339 |
ered | +2.259 |
verts | +2.225 |
quo | +2.206 |
Neg logit contributions | |
ANE | -3.205 |
srf | -3.104 |
senal | -3.065 |
awan | -3.049 |
UA | -3.017 |
Token | women |
Token ID | 1466 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
ertodd | +0.533 |
ysis | +0.421 |
verts | +0.400 |
ered | +0.398 |
quo | +0.392 |
Neg logit contributions | |
ANE | -0.602 |
awan | -0.580 |
光 | -0.571 |
srf | -0.566 |
女 | -0.564 |
Token | to |
Token ID | 284 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
ertodd | +0.038 |
ysis | +0.030 |
verts | +0.029 |
ered | +0.029 |
quo | +0.028 |
Neg logit contributions | |
ANE | -0.040 |
awan | -0.038 |
光 | -0.038 |
srf | -0.037 |
UA | -0.037 |
Token | make |
Token ID | 787 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ertodd | +1.031 |
ysis | +0.823 |
ered | +0.800 |
verts | +0.782 |
quo | +0.775 |
Neg logit contributions | |
ANE | -1.153 |
awan | -1.114 |
senal | -1.108 |
srf | -1.102 |
光 | -1.099 |
Token | this |
Token ID | 428 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
ertodd | +0.383 |
ysis | +0.306 |
ered | +0.291 |
verts | +0.289 |
quo | +0.285 |
Neg logit contributions | |
ANE | -0.416 |
awan | -0.401 |
光 | -0.395 |
srf | -0.391 |
UA | -0.390 |
Token | , |
Token ID | 11 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
ANE | +2.515 |
awan | +2.421 |
光 | +2.368 |
UA | +2.362 |
女 | +2.347 |
Neg logit contributions | |
ertodd | -2.602 |
ysis | -2.071 |
verts | -1.960 |
ered | -1.946 |
quo | -1.915 |
Token | transparency |
Token ID | 13902 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
ANE | +0.273 |
awan | +0.262 |
光 | +0.257 |
女 | +0.254 |
UA | +0.254 |
Neg logit contributions | |
ertodd | -0.282 |
ysis | -0.227 |
verts | -0.216 |
ered | -0.215 |
quo | -0.212 |
Token | , |
Token ID | 11 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
ANE | +2.144 |
awan | +2.053 |
光 | +2.009 |
UA | +2.000 |
女 | +1.990 |
Neg logit contributions | |
ertodd | -2.834 |
ysis | -2.335 |
verts | -2.211 |
ered | -2.195 |
quo | -2.155 |
Token | sound |
Token ID | 2128 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
ertodd | +1.062 |
ysis | +0.846 |
verts | +0.801 |
ered | +0.799 |
quo | +0.791 |
Neg logit contributions | |
ANE | -1.160 |
awan | -1.113 |
光 | -1.095 |
女 | -1.083 |
UA | -1.082 |
Token | st |
Token ID | 301 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
ertodd | +1.264 |
ysis | +1.072 |
verts | +1.032 |
ered | +1.030 |
quo | +1.018 |
Neg logit contributions | |
ANE | -0.720 |
awan | -0.672 |
光 | -0.656 |
UA | -0.644 |
srf | -0.643 |
Token | aging |
Token ID | 3039 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
ANE | +0.812 |
awan | +0.785 |
光 | +0.759 |
UA | +0.756 |
女 | +0.753 |
Neg logit contributions | |
ertodd | -0.843 |
ysis | -0.676 |
verts | -0.642 |
ered | -0.636 |
quo | -0.631 |
Token | , |
Token ID | 11 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
ertodd | +2.159 |
ysis | +1.737 |
verts | +1.654 |
ered | +1.654 |
quo | +1.630 |
Neg logit contributions | |
ANE | -2.061 |
awan | -1.969 |
光 | -1.932 |
srf | -1.909 |
UA | -1.905 |
Token | and |
Token ID | 290 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ertodd | +0.557 |
ysis | +0.442 |
verts | +0.418 |
ered | +0.416 |
quo | +0.410 |
Neg logit contributions | |
ANE | -0.621 |
awan | -0.595 |
光 | -0.586 |
女 | -0.579 |
UA | -0.579 |
Token | surprising |
Token ID | 6452 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
ANE | +0.318 |
awan | +0.304 |
光 | +0.298 |
UA | +0.294 |
女 | +0.294 |
Neg logit contributions | |
ertodd | -0.357 |
ysis | -0.291 |
verts | -0.277 |
ered | -0.276 |
quo | -0.272 |
Token | bass |
Token ID | 12702 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
ertodd | +0.683 |
ysis | +0.556 |
verts | +0.530 |
ered | +0.529 |
quo | +0.519 |
Neg logit contributions | |
ANE | -0.642 |
awan | -0.617 |
光 | -0.603 |
srf | -0.597 |
女 | -0.594 |
Token | response |
Token ID | 2882 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
ANE | +0.730 |
awan | +0.700 |
光 | +0.685 |
srf | +0.677 |
UA | +0.677 |
Neg logit contributions | |
ertodd | -0.734 |
ysis | -0.591 |
verts | -0.561 |
ered | -0.558 |
quo | -0.550 |
Token | of |
Token ID | 286 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
ANE | +3.649 |
awan | +3.502 |
光 | +3.429 |
UA | +3.413 |
女 | +3.380 |
Neg logit contributions | |
ertodd | -3.962 |
ysis | -3.156 |
verts | -3.009 |
ered | -2.967 |
quo | -2.905 |
Token | the |
Token ID | 262 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
ANE | +0.184 |
awan | +0.178 |
光 | +0.175 |
女 | +0.174 |
UA | +0.173 |
Neg logit contributions | |
ertodd | -0.138 |
ysis | -0.106 |
verts | -0.100 |
ered | -0.099 |
quo | -0.098 |
Token | galaxy |
Token ID | 16161 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
ertodd | +0.067 |
ysis | +0.055 |
verts | +0.053 |
ered | +0.052 |
quo | +0.052 |
Neg logit contributions | |
ANE | -0.058 |
awan | -0.056 |
光 | -0.054 |
女 | -0.054 |
UA | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
ANE | +1.398 |
awan | +1.335 |
光 | +1.305 |
UA | +1.290 |
女 | +1.290 |
Neg logit contributions | |
ertodd | -1.708 |
ysis | -1.401 |
verts | -1.336 |
ered | -1.335 |
quo | -1.317 |
Token | and |
Token ID | 290 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
ANE | +0.721 |
awan | +0.691 |
光 | +0.676 |
女 | +0.675 |
UA | +0.674 |
Neg logit contributions | |
ertodd | -0.658 |
ysis | -0.527 |
verts | -0.499 |
ered | -0.498 |
quo | -0.492 |
Token | the |
Token ID | 262 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
ANE | +0.095 |
awan | +0.092 |
光 | +0.090 |
女 | +0.090 |
srf | +0.090 |
Neg logit contributions | |
ertodd | -0.077 |
ysis | -0.061 |
verts | -0.058 |
ered | -0.057 |
quo | -0.056 |
Token | Milky |
Token ID | 34822 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
ANE | +0.620 |
awan | +0.591 |
光 | +0.577 |
UA | +0.572 |
女 | +0.572 |
Neg logit contributions | |
ertodd | -0.776 |
ysis | -0.638 |
verts | -0.610 |
ered | -0.608 |
quo | -0.600 |
Token | Way |
Token ID | 6378 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
ertodd | +1.689 |
ysis | +1.427 |
verts | +1.374 |
ered | +1.367 |
quo | +1.341 |
Neg logit contributions | |
ANE | -1.048 |
awan | -0.981 |
srf | -0.980 |
光 | -0.970 |
senal | -0.967 |
Token | is |
Token ID | 318 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
ertodd | +0.233 |
ysis | +0.182 |
verts | +0.173 |
ered | +0.172 |
quo | +0.168 |
Neg logit contributions | |
ANE | -0.299 |
awan | -0.288 |
光 | -0.284 |
srf | -0.283 |
女 | -0.283 |
Token | at |
Token ID | 379 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
ANE | +1.453 |
awan | +1.389 |
光 | +1.358 |
UA | +1.349 |
srf | +1.349 |
Neg logit contributions | |
ertodd | -1.592 |
ysis | -1.308 |
ered | -1.248 |
verts | -1.241 |
quo | -1.224 |
Token | least |
Token ID | 1551 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
ANE | +0.116 |
awan | +0.110 |
光 | +0.109 |
女 | +0.109 |
UA | +0.108 |
Neg logit contributions | |
ertodd | -0.114 |
ysis | -0.094 |
ered | -0.089 |
verts | -0.089 |
quo | -0.087 |
Token | your |
Token ID | 534 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
ANE | +2.697 |
awan | +2.598 |
光 | +2.550 |
女 | +2.532 |
UA | +2.529 |
Neg logit contributions | |
ertodd | -2.226 |
ysis | -1.726 |
verts | -1.624 |
ered | -1.598 |
quo | -1.578 |
Token | wife |
Token ID | 3656 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ANE | +1.064 |
awan | +1.021 |
光 | +1.000 |
srf | +0.991 |
女 | +0.989 |
Neg logit contributions | |
ertodd | -1.109 |
ysis | -0.898 |
verts | -0.852 |
ered | -0.851 |
quo | -0.836 |
Token | is |
Token ID | 318 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
ANE | +3.352 |
awan | +3.237 |
光 | +3.168 |
女 | +3.155 |
UA | +3.145 |
Neg logit contributions | |
ertodd | -2.936 |
ysis | -2.285 |
verts | -2.150 |
ered | -2.130 |
quo | -2.098 |
Token | the |
Token ID | 262 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
ANE | +2.625 |
awan | +2.523 |
光 | +2.471 |
UA | +2.447 |
女 | +2.439 |
Neg logit contributions | |
ertodd | -2.660 |
ysis | -2.135 |
verts | -2.027 |
ered | -2.020 |
quo | -1.988 |
Token | kind |
Token ID | 1611 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ertodd | +1.156 |
ysis | +0.933 |
ered | +0.896 |
verts | +0.892 |
Jehovah | +0.883 |
Neg logit contributions | |
ANE | -1.224 |
awan | -1.179 |
光 | -1.169 |
srf | -1.153 |
EMENT | -1.152 |
Token | of |
Token ID | 286 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
ertodd | +3.578 |
ysis | +2.881 |
ered | +2.809 |
verts | +2.754 |
quo | +2.727 |
Neg logit contributions | |
ANE | -4.073 |
awan | -3.934 |
光 | -3.894 |
srf | -3.878 |
UA | -3.832 |
Token | sweet |
Token ID | 6029 |
Feature activation | -9.95e-02 |
Pos logit contributions | |
ANE | +0.074 |
awan | +0.071 |
光 | +0.069 |
UA | +0.068 |
srf | +0.068 |
Neg logit contributions | |
ertodd | -0.098 |
ysis | -0.081 |
verts | -0.078 |
ered | -0.078 |
quo | -0.077 |
Token | heart |
Token ID | 11499 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
ANE | +0.271 |
awan | +0.259 |
光 | +0.254 |
UA | +0.252 |
srf | +0.250 |
Neg logit contributions | |
ertodd | -0.317 |
ysis | -0.259 |
verts | -0.250 |
ered | -0.248 |
quo | -0.244 |
Token | who |
Token ID | 508 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
ertodd | +1.394 |
ysis | +1.065 |
verts | +1.015 |
ered | +1.014 |
quo | +0.990 |
Neg logit contributions | |
ANE | -2.067 |
awan | -1.999 |
srf | -1.974 |
光 | -1.969 |
UA | -1.954 |
Token | loves |
Token ID | 10408 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
ertodd | +1.212 |
ysis | +0.947 |
verts | +0.899 |
ered | +0.896 |
quo | +0.879 |
Neg logit contributions | |
ANE | -1.552 |
awan | -1.495 |
srf | -1.472 |
光 | -1.466 |
UA | -1.457 |
Token | you |
Token ID | 345 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
ertodd | +2.004 |
ysis | +1.582 |
verts | +1.509 |
ered | +1.496 |
Jehovah | +1.471 |
Neg logit contributions | |
ANE | -2.620 |
awan | -2.528 |
srf | -2.483 |
光 | -2.474 |
UA | -2.473 |
Token | established |
Token ID | 4920 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
ertodd | +0.421 |
ysis | +0.336 |
verts | +0.321 |
ered | +0.318 |
quo | +0.315 |
Neg logit contributions | |
ANE | -0.458 |
awan | -0.436 |
光 | -0.428 |
srf | -0.428 |
UA | -0.426 |
Token | notions |
Token ID | 26226 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
ANE | +1.343 |
awan | +1.289 |
光 | +1.264 |
UA | +1.252 |
女 | +1.249 |
Neg logit contributions | |
ertodd | -1.316 |
ysis | -1.052 |
verts | -0.999 |
ered | -0.995 |
quo | -0.982 |
Token | of |
Token ID | 286 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
ertodd | +1.612 |
ysis | +1.280 |
verts | +1.212 |
ered | +1.207 |
quo | +1.189 |
Neg logit contributions | |
ANE | -1.699 |
awan | -1.633 |
光 | -1.600 |
UA | -1.586 |
女 | -1.583 |
Token | what |
Token ID | 644 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
ertodd | +0.807 |
ysis | +0.646 |
verts | +0.618 |
ered | +0.614 |
quo | +0.608 |
Neg logit contributions | |
ANE | -0.819 |
awan | -0.781 |
光 | -0.768 |
UA | -0.765 |
srf | -0.760 |
Token | constitutes |
Token ID | 19300 |
Feature activation | +9.08e-02 |
Pos logit contributions | |
ertodd | +1.570 |
ysis | +1.212 |
verts | +1.163 |
ered | +1.148 |
quo | +1.142 |
Neg logit contributions | |
ANE | -2.053 |
awan | -1.960 |
光 | -1.949 |
srf | -1.940 |
UA | -1.929 |
Token | the |
Token ID | 262 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
ertodd | +0.270 |
ysis | +0.217 |
verts | +0.206 |
ered | +0.206 |
quo | +0.203 |
Neg logit contributions | |
ANE | -0.267 |
awan | -0.255 |
光 | -0.251 |
UA | -0.249 |
srf | -0.248 |
Token | middle |
Token ID | 3504 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
ANE | +0.259 |
awan | +0.246 |
光 | +0.242 |
UA | +0.240 |
srf | +0.238 |
Neg logit contributions | |
ertodd | -0.312 |
ysis | -0.255 |
verts | -0.244 |
ered | -0.243 |
quo | -0.240 |
Token | class |
Token ID | 1398 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
ANE | +1.883 |
awan | +1.799 |
光 | +1.742 |
女 | +1.728 |
UA | +1.706 |
Neg logit contributions | |
ertodd | -3.198 |
ysis | -2.686 |
verts | -2.579 |
ered | -2.533 |
Jehovah | -2.510 |
Token | , |
Token ID | 11 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
ertodd | +1.166 |
ysis | +0.961 |
ered | +0.928 |
verts | +0.924 |
quo | +0.923 |
Neg logit contributions | |
ANE | -0.877 |
awan | -0.829 |
光 | -0.813 |
srf | -0.809 |
UA | -0.802 |
Token | rather |
Token ID | 2138 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
ANE | +0.937 |
awan | +0.899 |
光 | +0.882 |
UA | +0.874 |
女 | +0.872 |
Neg logit contributions | |
ertodd | -0.894 |
ysis | -0.712 |
verts | -0.675 |
ered | -0.672 |
quo | -0.664 |
Token | than |
Token ID | 621 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
ANE | +0.991 |
awan | +0.948 |
光 | +0.930 |
srf | +0.919 |
UA | +0.919 |
Neg logit contributions | |
ertodd | -1.055 |
ysis | -0.850 |
verts | -0.810 |
ered | -0.807 |
quo | -0.796 |
Token | with |
Token ID | 351 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ertodd | +0.546 |
ysis | +0.443 |
verts | +0.421 |
ered | +0.419 |
quo | +0.413 |
Neg logit contributions | |
ANE | -0.487 |
awan | -0.467 |
光 | -0.456 |
UA | -0.452 |
女 | -0.451 |
Token | homelessness |
Token ID | 28822 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
ANE | +0.439 |
awan | +0.422 |
光 | +0.414 |
UA | +0.410 |
srf | +0.409 |
Neg logit contributions | |
ertodd | -0.434 |
ysis | -0.349 |
verts | -0.330 |
ered | -0.330 |
quo | -0.324 |
Token | . |
Token ID | 13 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
ertodd | +1.207 |
ysis | +0.987 |
verts | +0.941 |
ered | +0.939 |
quo | +0.928 |
Neg logit contributions | |
ANE | -1.072 |
awan | -1.029 |
光 | -1.007 |
srf | -0.999 |
UA | -0.993 |
Token |
|
Token ID | 198 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
ertodd | +0.079 |
ysis | +0.062 |
ered | +0.058 |
verts | +0.058 |
quo | +0.057 |
Neg logit contributions | |
ANE | -0.094 |
awan | -0.091 |
srf | -0.090 |
光 | -0.089 |
女 | -0.088 |
Token |
|
Token ID | 198 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
ertodd | +0.831 |
ysis | +0.627 |
ered | +0.604 |
verts | +0.598 |
quo | +0.572 |
Neg logit contributions | |
srf | -1.229 |
ANE | -1.225 |
senal | -1.215 |
awan | -1.185 |
光 | -1.165 |
Token | No |
Token ID | 2949 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
ANE | +0.339 |
srf | +0.327 |
awan | +0.325 |
senal | +0.316 |
光 | +0.315 |
Neg logit contributions | |
ertodd | -0.557 |
ysis | -0.470 |
ered | -0.454 |
verts | -0.454 |
quo | -0.445 |
Token | single |
Token ID | 2060 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ANE | +0.988 |
awan | +0.947 |
光 | +0.931 |
女 | +0.920 |
UA | +0.920 |
Neg logit contributions | |
ertodd | -0.992 |
ysis | -0.800 |
verts | -0.758 |
ered | -0.758 |
quo | -0.744 |
Token | system |
Token ID | 1080 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
ertodd | +0.496 |
ysis | +0.402 |
ered | +0.385 |
verts | +0.381 |
quo | +0.380 |
Neg logit contributions | |
ANE | -0.494 |
awan | -0.473 |
光 | -0.468 |
srf | -0.466 |
女 | -0.461 |
Token | tracks |
Token ID | 8339 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
ertodd | +0.252 |
ysis | +0.197 |
ered | +0.186 |
verts | +0.185 |
quo | +0.182 |
Neg logit contributions | |
ANE | -0.308 |
awan | -0.295 |
光 | -0.291 |
srf | -0.289 |
UA | -0.288 |
Token | street |
Token ID | 4675 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
ertodd | +1.845 |
ysis | +1.506 |
ered | +1.438 |
verts | +1.420 |
quo | +1.399 |
Neg logit contributions | |
ANE | -2.039 |
srf | -1.955 |
awan | -1.955 |
光 | -1.936 |
senal | -1.919 |
Token | people |
Token ID | 661 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
ertodd | +0.592 |
ysis | +0.473 |
verts | +0.449 |
ered | +0.446 |
quo | +0.439 |
Neg logit contributions | |
ANE | -0.662 |
awan | -0.639 |
光 | -0.627 |
srf | -0.624 |
UA | -0.623 |
Token | were |
Token ID | 547 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
ertodd | +0.475 |
ysis | +0.369 |
ered | +0.355 |
verts | +0.349 |
quo | +0.346 |
Neg logit contributions | |
ANE | -0.601 |
srf | -0.576 |
awan | -0.576 |
光 | -0.574 |
senal | -0.572 |
Token | going |
Token ID | 1016 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ertodd | +0.957 |
ysis | +0.769 |
verts | +0.730 |
ered | +0.728 |
quo | +0.723 |
Neg logit contributions | |
ANE | -1.020 |
awan | -0.985 |
光 | -0.971 |
srf | -0.971 |
女 | -0.954 |
Token | to |
Token ID | 284 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
ertodd | +5.191 |
ysis | +4.160 |
ered | +4.082 |
quo | +3.980 |
verts | +3.970 |
Neg logit contributions | |
ANE | -5.111 |
awan | -4.882 |
光 | -4.821 |
UA | -4.798 |
RAW | -4.779 |
Token | pit |
Token ID | 6028 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
ertodd | +2.761 |
ered | +2.190 |
ysis | +2.188 |
quo | +2.130 |
Jehovah | +2.118 |
Neg logit contributions | |
ANE | -3.076 |
senal | -2.974 |
srf | -2.955 |
awan | -2.924 |
光 | -2.906 |
Token | a |
Token ID | 257 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
ANE | +1.369 |
awan | +1.318 |
光 | +1.294 |
UA | +1.281 |
女 | +1.280 |
Neg logit contributions | |
ertodd | -1.252 |
ysis | -0.990 |
verts | -0.938 |
ered | -0.933 |
quo | -0.918 |
Token | city |
Token ID | 1748 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
ertodd | +0.467 |
ysis | +0.382 |
verts | +0.367 |
ered | +0.366 |
quo | +0.364 |
Neg logit contributions | |
ANE | -0.421 |
awan | -0.404 |
光 | -0.400 |
srf | -0.397 |
UA | -0.395 |
Token | ordinance |
Token ID | 19784 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
ANE | +0.058 |
awan | +0.054 |
光 | +0.054 |
srf | +0.053 |
女 | +0.053 |
Neg logit contributions | |
ertodd | -0.107 |
ysis | -0.091 |
ered | -0.088 |
verts | -0.088 |
quo | -0.087 |
Token | against |
Token ID | 1028 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
ertodd | +1.405 |
ysis | +1.216 |
ered | +1.180 |
verts | +1.176 |
quo | +1.168 |
Neg logit contributions | |
ANE | -0.585 |
awan | -0.539 |
光 | -0.536 |
srf | -0.529 |
女 | -0.520 |
Token | human |
Token ID | 1692 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
ertodd | +0.873 |
ysis | +0.682 |
verts | +0.648 |
ered | +0.645 |
quo | +0.636 |
Neg logit contributions | |
ANE | -1.070 |
awan | -1.031 |
光 | -1.019 |
srf | -1.012 |
UA | -1.005 |
Token | rights |
Token ID | 2489 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
ertodd | +1.740 |
ysis | +1.273 |
verts | +1.171 |
ered | +1.169 |
quo | +1.146 |
Neg logit contributions | |
ANE | -3.044 |
awan | -2.943 |
光 | -2.898 |
UA | -2.881 |
srf | -2.877 |
Token | , |
Token ID | 11 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
ertodd | +1.384 |
ysis | +1.119 |
verts | +1.066 |
ered | +1.065 |
quo | +1.059 |
Neg logit contributions | |
ANE | -1.360 |
awan | -1.301 |
光 | -1.279 |
srf | -1.270 |
女 | -1.259 |
Token | which |
Token ID | 543 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
ANE | +0.309 |
awan | +0.298 |
光 | +0.292 |
女 | +0.290 |
UA | +0.290 |
Neg logit contributions | |
ertodd | -0.271 |
ysis | -0.215 |
verts | -0.204 |
ered | -0.203 |
quo | -0.201 |
Token | includes |
Token ID | 3407 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
ertodd | +1.813 |
ysis | +1.424 |
verts | +1.369 |
ered | +1.367 |
quo | +1.336 |
Neg logit contributions | |
ANE | -2.361 |
awan | -2.266 |
srf | -2.258 |
光 | -2.242 |
女 | -2.233 |
Token | additional |
Token ID | 3224 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
ertodd | +1.542 |
ysis | +1.238 |
ered | +1.185 |
verts | +1.179 |
quo | +1.149 |
Neg logit contributions | |
ANE | -1.789 |
awan | -1.736 |
光 | -1.712 |
女 | -1.697 |
srf | -1.696 |
Token | instructions |
Token ID | 7729 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
ANE | +2.578 |
awan | +2.470 |
光 | +2.416 |
UA | +2.395 |
女 | +2.389 |
Neg logit contributions | |
ertodd | -2.794 |
ysis | -2.253 |
verts | -2.141 |
ered | -2.132 |
quo | -2.102 |
Token | for |
Token ID | 329 |
Feature activation | -4.23e-03 |
Pos logit contributions | |
ANE | +0.870 |
awan | +0.832 |
光 | +0.817 |
女 | +0.809 |
srf | +0.809 |
Neg logit contributions | |
ertodd | -0.958 |
ysis | -0.782 |
verts | -0.748 |
ered | -0.747 |
quo | -0.736 |
Token | ensuring |
Token ID | 13359 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ANE | +0.012 |
awan | +0.012 |
光 | +0.012 |
女 | +0.012 |
srf | +0.011 |
Neg logit contributions | |
ertodd | -0.013 |
ysis | -0.010 |
verts | -0.010 |
ered | -0.010 |
quo | -0.010 |
Token | compatibility |
Token ID | 17764 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
ANE | +4.490 |
awan | +4.299 |
UA | +4.187 |
RAW | +4.168 |
光 | +4.129 |
Neg logit contributions | |
ertodd | -4.410 |
ysis | -3.386 |
verts | -3.220 |
ered | -3.150 |
quo | -3.123 |
Token | with |
Token ID | 351 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
ertodd | +1.996 |
ysis | +1.634 |
ered | +1.557 |
verts | +1.553 |
quo | +1.550 |
Neg logit contributions | |
ANE | -1.958 |
awan | -1.884 |
光 | -1.859 |
srf | -1.857 |
女 | -1.827 |
Token | V |
Token ID | 569 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
ertodd | +0.593 |
ysis | +0.473 |
verts | +0.450 |
ered | +0.447 |
quo | +0.441 |
Neg logit contributions | |
ANE | -0.631 |
awan | -0.606 |
光 | -0.596 |
女 | -0.591 |
UA | -0.589 |
Token | OD |
Token ID | 3727 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
ertodd | +2.021 |
ysis | +1.725 |
ered | +1.667 |
verts | +1.654 |
quo | +1.618 |
Neg logit contributions | |
ANE | -1.227 |
awan | -1.186 |
光 | -1.166 |
srf | -1.157 |
女 | -1.150 |
Token | services |
Token ID | 2594 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
ANE | +0.214 |
awan | +0.206 |
光 | +0.201 |
女 | +0.200 |
srf | +0.199 |
Neg logit contributions | |
ertodd | -0.240 |
ysis | -0.198 |
verts | -0.188 |
ered | -0.188 |
quo | -0.184 |
Token | stri |
Token ID | 33565 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
ertodd | +1.002 |
ysis | +0.798 |
verts | +0.760 |
ered | +0.760 |
quo | +0.742 |
Neg logit contributions | |
ANE | -1.065 |
awan | -1.021 |
光 | -0.999 |
srf | -0.992 |
女 | -0.992 |
Token | ps |
Token ID | 862 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ANE | +1.381 |
awan | +1.355 |
光 | +1.327 |
UA | +1.322 |
EMENT | +1.322 |
Neg logit contributions | |
ertodd | -0.416 |
ysis | -0.228 |
quo | -0.180 |
verts | -0.180 |
ered | -0.172 |
Token | runner |
Token ID | 17490 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
ANE | +0.552 |
awan | +0.533 |
光 | +0.523 |
UA | +0.518 |
女 | +0.517 |
Neg logit contributions | |
ertodd | -0.447 |
ysis | -0.346 |
verts | -0.325 |
ered | -0.323 |
quo | -0.318 |
Token | - |
Token ID | 12 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
ertodd | +0.759 |
ysis | +0.571 |
verts | +0.533 |
ered | +0.531 |
quo | +0.520 |
Neg logit contributions | |
ANE | -1.137 |
awan | -1.097 |
光 | -1.079 |
女 | -1.072 |
UA | -1.070 |
Token | up |
Token ID | 929 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
ANE | +1.722 |
awan | +1.672 |
光 | +1.637 |
UA | +1.626 |
EMENT | +1.613 |
Neg logit contributions | |
ertodd | -1.406 |
ysis | -1.089 |
verts | -1.013 |
ered | -1.008 |
quo | -0.994 |
Token | Israel |
Token ID | 2692 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
ertodd | +0.681 |
ysis | +0.523 |
verts | +0.491 |
ered | +0.490 |
quo | +0.479 |
Neg logit contributions | |
ANE | -0.932 |
awan | -0.900 |
光 | -0.886 |
女 | -0.880 |
srf | -0.878 |
Token | ( |
Token ID | 357 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ANE | +4.606 |
awan | +4.421 |
光 | +4.325 |
UA | +4.253 |
RAW | +4.231 |
Neg logit contributions | |
ertodd | -5.819 |
ysis | -4.686 |
verts | -4.504 |
quo | -4.399 |
ered | -4.396 |
Token | at |
Token ID | 265 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ANE | +2.877 |
awan | +2.736 |
光 | +2.671 |
UA | +2.648 |
女 | +2.628 |
Neg logit contributions | |
ertodd | -4.156 |
ysis | -3.438 |
verts | -3.284 |
ered | -3.271 |
quo | -3.247 |
Token | 4 |
Token ID | 604 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
ANE | +2.969 |
awan | +2.866 |
光 | +2.796 |
UA | +2.776 |
EMENT | +2.756 |
Neg logit contributions | |
ertodd | -3.043 |
ysis | -2.389 |
verts | -2.278 |
ered | -2.262 |
quo | -2.228 |
Token | . |
Token ID | 13 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
ertodd | +2.193 |
ysis | +1.829 |
ered | +1.755 |
verts | +1.752 |
quo | +1.709 |
Neg logit contributions | |
ANE | -1.624 |
awan | -1.537 |
srf | -1.517 |
光 | -1.501 |
女 | -1.493 |
Token | 11 |
Token ID | 1157 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
ertodd | +1.681 |
ysis | +1.382 |
ered | +1.337 |
verts | +1.336 |
Jehovah | +1.292 |
Neg logit contributions | |
srf | -1.512 |
ANE | -1.505 |
senal | -1.477 |
awan | -1.449 |
光 | -1.418 |
Token | rounds |
Token ID | 9196 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
ertodd | +0.969 |
ysis | +0.776 |
ered | +0.745 |
verts | +0.744 |
quo | +0.724 |
Neg logit contributions | |
ANE | -0.996 |
awan | -0.962 |
女 | -0.941 |
光 | -0.941 |
srf | -0.938 |
Token | of |
Token ID | 286 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
ertodd | +1.216 |
ysis | +0.963 |
ered | +0.919 |
verts | +0.906 |
quo | +0.893 |
Neg logit contributions | |
ANE | -1.365 |
awan | -1.319 |
女 | -1.289 |
光 | -1.287 |
UA | -1.282 |
Token | ammunition |
Token ID | 14271 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
ertodd | +1.353 |
ysis | +1.099 |
verts | +1.044 |
ered | +1.044 |
quo | +1.029 |
Neg logit contributions | |
ANE | -1.322 |
awan | -1.269 |
女 | -1.246 |
光 | -1.246 |
UA | -1.239 |
Token | that |
Token ID | 326 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
ANE | +1.432 |
awan | +1.381 |
光 | +1.361 |
女 | +1.350 |
UA | +1.349 |
Neg logit contributions | |
ertodd | -1.102 |
ysis | -0.852 |
verts | -0.802 |
ered | -0.801 |
quo | -0.783 |
Token | disappeared |
Token ID | 12120 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
ertodd | +0.102 |
ysis | +0.079 |
ered | +0.075 |
verts | +0.074 |
quo | +0.073 |
Neg logit contributions | |
ANE | -0.125 |
awan | -0.121 |
光 | -0.119 |
女 | -0.118 |
UA | -0.118 |
Token | last |
Token ID | 938 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ANE | +0.828 |
awan | +0.792 |
光 | +0.774 |
UA | +0.767 |
女 | +0.766 |
Neg logit contributions | |
ertodd | -0.965 |
ysis | -0.786 |
verts | -0.749 |
ered | -0.747 |
quo | -0.736 |
Token | week |
Token ID | 1285 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
ANE | +3.704 |
awan | +3.546 |
光 | +3.438 |
UA | +3.403 |
女 | +3.389 |
Neg logit contributions | |
ertodd | -5.239 |
ysis | -4.349 |
verts | -4.067 |
ered | -4.057 |
quo | -4.027 |
Token | have |
Token ID | 423 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
ANE | +1.945 |
awan | +1.872 |
光 | +1.831 |
女 | +1.815 |
UA | +1.815 |
Neg logit contributions | |
ertodd | -1.795 |
ysis | -1.420 |
verts | -1.334 |
ered | -1.325 |
quo | -1.310 |
Token | been |
Token ID | 587 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
ertodd | +1.294 |
ysis | +0.997 |
ered | +0.945 |
verts | +0.939 |
quo | +0.917 |
Neg logit contributions | |
ANE | -1.667 |
awan | -1.609 |
光 | -1.580 |
UA | -1.571 |
srf | -1.570 |
Token | located |
Token ID | 5140 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
ANE | +0.568 |
awan | +0.548 |
光 | +0.542 |
UA | +0.537 |
srf | +0.537 |
Neg logit contributions | |
ertodd | -0.411 |
ysis | -0.313 |
ered | -0.298 |
verts | -0.296 |
quo | -0.289 |
Token | . |
Token ID | 13 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
ANE | +0.960 |
awan | +0.917 |
光 | +0.897 |
UA | +0.888 |
女 | +0.885 |
Neg logit contributions | |
ertodd | -1.190 |
ysis | -0.975 |
verts | -0.932 |
ered | -0.931 |
quo | -0.917 |
Token | that |
Token ID | 326 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
ertodd | +0.113 |
ysis | +0.090 |
ered | +0.086 |
verts | +0.085 |
quo | +0.083 |
Neg logit contributions | |
ANE | -0.127 |
awan | -0.123 |
光 | -0.121 |
srf | -0.120 |
女 | -0.119 |
Token | this |
Token ID | 428 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ANE | +0.520 |
awan | +0.500 |
光 | +0.493 |
srf | +0.488 |
UA | +0.486 |
Neg logit contributions | |
ertodd | -0.454 |
ysis | -0.358 |
verts | -0.340 |
ered | -0.339 |
quo | -0.333 |
Token | has |
Token ID | 468 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
ertodd | +0.350 |
ysis | +0.273 |
verts | +0.259 |
ered | +0.258 |
quo | +0.255 |
Neg logit contributions | |
ANE | -0.450 |
awan | -0.433 |
光 | -0.427 |
srf | -0.425 |
UA | -0.421 |
Token | made |
Token ID | 925 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
ertodd | +1.196 |
ysis | +0.949 |
ered | +0.916 |
verts | +0.903 |
quo | +0.890 |
Neg logit contributions | |
ANE | -1.346 |
awan | -1.297 |
srf | -1.274 |
光 | -1.273 |
senal | -1.258 |
Token | it |
Token ID | 340 |
Feature activation | -7.71e-02 |
Pos logit contributions | |
ertodd | +1.064 |
ysis | +0.857 |
ered | +0.829 |
verts | +0.813 |
quo | +0.807 |
Neg logit contributions | |
ANE | -1.209 |
光 | -1.165 |
awan | -1.157 |
srf | -1.146 |
女 | -1.142 |
Token | harder |
Token ID | 7069 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
ANE | +0.194 |
awan | +0.186 |
光 | +0.182 |
srf | +0.180 |
UA | +0.179 |
Neg logit contributions | |
ertodd | -0.260 |
ysis | -0.216 |
ered | -0.208 |
verts | -0.208 |
quo | -0.206 |
Token | for |
Token ID | 329 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
ANE | +3.846 |
awan | +3.650 |
女 | +3.563 |
光 | +3.521 |
UA | +3.503 |
Neg logit contributions | |
ertodd | -5.436 |
ysis | -4.484 |
verts | -4.317 |
Jehovah | -4.170 |
ered | -4.124 |
Token | screen |
Token ID | 3159 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
ANE | +0.545 |
awan | +0.525 |
光 | +0.519 |
srf | +0.513 |
女 | +0.512 |
Neg logit contributions | |
ertodd | -0.482 |
ysis | -0.383 |
ered | -0.363 |
verts | -0.363 |
quo | -0.356 |
Token | ers |
Token ID | 364 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ertodd | +1.238 |
ysis | +0.929 |
ered | +0.867 |
verts | +0.865 |
quo | +0.831 |
Neg logit contributions | |
ANE | -2.244 |
awan | -2.159 |
光 | -2.150 |
srf | -2.136 |
senal | -2.134 |
Token | to |
Token ID | 284 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
ertodd | +4.732 |
ysis | +3.856 |
ered | +3.700 |
verts | +3.612 |
quo | +3.591 |
Neg logit contributions | |
ANE | -4.879 |
awan | -4.680 |
光 | -4.615 |
EMENT | -4.559 |
srf | -4.540 |
Token | identify |
Token ID | 5911 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
ertodd | +0.509 |
ysis | +0.415 |
ered | +0.402 |
verts | +0.394 |
quo | +0.391 |
Neg logit contributions | |
ANE | -0.520 |
awan | -0.497 |
光 | -0.496 |
senal | -0.492 |
srf | -0.492 |
Token | . |
Token ID | 13 |
Feature activation | -3.96e-03 |
Pos logit contributions | |
ertodd | +0.479 |
ysis | +0.395 |
ered | +0.378 |
verts | +0.377 |
quo | +0.373 |
Neg logit contributions | |
ANE | -0.405 |
awan | -0.387 |
光 | -0.380 |
srf | -0.374 |
UA | -0.374 |
Token | An |
Token ID | 1052 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
ANE | +0.013 |
awan | +0.013 |
光 | +0.012 |
srf | +0.012 |
女 | +0.012 |
Neg logit contributions | |
ertodd | -0.010 |
ysis | -0.008 |
verts | -0.008 |
ered | -0.008 |
quo | -0.007 |
Token | example |
Token ID | 1672 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ANE | +0.409 |
awan | +0.393 |
光 | +0.386 |
女 | +0.382 |
srf | +0.381 |
Neg logit contributions | |
ertodd | -0.454 |
ysis | -0.368 |
ered | -0.353 |
verts | -0.351 |
quo | -0.345 |
Token | is |
Token ID | 318 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ANE | +0.375 |
awan | +0.361 |
光 | +0.355 |
srf | +0.351 |
女 | +0.351 |
Neg logit contributions | |
ertodd | -0.326 |
ysis | -0.257 |
verts | -0.244 |
ered | -0.243 |
quo | -0.239 |
Token | below |
Token ID | 2174 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
ANE | +3.923 |
awan | +3.761 |
光 | +3.691 |
UA | +3.671 |
女 | +3.662 |
Neg logit contributions | |
ertodd | -3.656 |
ysis | -2.869 |
verts | -2.691 |
ered | -2.674 |
quo | -2.654 |
Token | ( |
Token ID | 357 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
ANE | +3.528 |
awan | +3.378 |
光 | +3.295 |
UA | +3.291 |
EMENT | +3.268 |
Neg logit contributions | |
ertodd | -4.131 |
ysis | -3.329 |
verts | -3.159 |
ered | -3.132 |
quo | -3.093 |
Token | select |
Token ID | 19738 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
ANE | +3.960 |
awan | +3.762 |
光 | +3.674 |
UA | +3.668 |
RAW | +3.635 |
Neg logit contributions | |
ertodd | -5.754 |
ysis | -4.751 |
ered | -4.504 |
verts | -4.498 |
quo | -4.489 |
Token | category |
Token ID | 6536 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
ANE | +4.974 |
awan | +4.775 |
UA | +4.699 |
光 | +4.698 |
EMENT | +4.658 |
Neg logit contributions | |
ertodd | -4.127 |
ysis | -3.172 |
verts | -2.949 |
ered | -2.903 |
quo | -2.899 |
Token | --> |
Token ID | 14610 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
ANE | +1.758 |
awan | +1.685 |
光 | +1.649 |
UA | +1.632 |
女 | +1.629 |
Neg logit contributions | |
ertodd | -1.942 |
ysis | -1.573 |
verts | -1.497 |
ered | -1.491 |
quo | -1.470 |
Token | drill |
Token ID | 16007 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
ANE | +1.190 |
awan | +1.143 |
光 | +1.118 |
UA | +1.104 |
女 | +1.103 |
Neg logit contributions | |
ertodd | -1.272 |
ysis | -1.028 |
verts | -0.980 |
ered | -0.975 |
quo | -0.961 |
Token | through |
Token ID | 9579 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
ANE | +0.055 |
awan | +0.053 |
光 | +0.051 |
srf | +0.050 |
女 | +0.050 |
Neg logit contributions | |
ertodd | -0.083 |
ysis | -0.070 |
ered | -0.067 |
verts | -0.067 |
quo | -0.066 |