Token | brother |
Token ID | 3956 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
Lauder | +0.011 |
Loving | +0.010 |
Sioux | +0.010 |
Hots | +0.009 |
Subtle | +0.009 |
Neg logit contributions | |
obar | -0.012 |
rane | -0.012 |
minist | -0.011 |
oba | -0.011 |
ega | -0.010 |
Token | ." |
Token ID | 526 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
Lauder | +0.857 |
Loving | +0.780 |
Sioux | +0.771 |
Hots | +0.724 |
Subtle | +0.713 |
Neg logit contributions | |
obar | -0.836 |
rane | -0.807 |
minist | -0.738 |
oba | -0.723 |
ega | -0.713 |
Token |
|
Token ID | 198 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
obar | +0.642 |
rane | +0.617 |
minist | +0.570 |
oba | +0.561 |
ega | +0.556 |
Neg logit contributions | |
Lauder | -0.560 |
Loving | -0.504 |
Sioux | -0.499 |
Hots | -0.467 |
Subtle | -0.455 |
Token |
|
Token ID | 198 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
obar | +0.191 |
rane | +0.184 |
minist | +0.169 |
oba | +0.167 |
ega | +0.164 |
Neg logit contributions | |
Lauder | -0.179 |
Loving | -0.159 |
Sioux | -0.159 |
Hots | -0.148 |
Subtle | -0.146 |
Token | President |
Token ID | 10364 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
obar | +0.102 |
rane | +0.098 |
minist | +0.089 |
oba | +0.087 |
ega | +0.086 |
Neg logit contributions | |
Lauder | -0.122 |
Loving | -0.112 |
Sioux | -0.111 |
Hots | -0.104 |
Subtle | -0.103 |
Token | Rodrigo |
Token ID | 46198 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
obar | +0.121 |
rane | +0.115 |
minist | +0.104 |
oba | +0.101 |
ega | +0.099 |
Neg logit contributions | |
Lauder | -0.173 |
Loving | -0.160 |
Sioux | -0.159 |
Hots | -0.150 |
Subtle | -0.148 |
Token | Duterte |
Token ID | 25763 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
obar | +2.467 |
rane | +2.227 |
oba | +1.976 |
minist | +1.946 |
ega | +1.856 |
Neg logit contributions | |
Lauder | -4.687 |
Sioux | -4.367 |
Loving | -4.315 |
Hots | -4.160 |
Subtle | -4.120 |
Token | had |
Token ID | 550 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
obar | +2.494 |
rane | +2.380 |
ega | +2.208 |
minist | +2.188 |
oba | +2.152 |
Neg logit contributions | |
Lauder | -2.284 |
Loving | -2.074 |
Sioux | -2.056 |
Subtle | -1.926 |
Hots | -1.860 |
Token | nothing |
Token ID | 2147 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
obar | +0.460 |
rane | +0.442 |
minist | +0.408 |
ega | +0.403 |
oba | +0.402 |
Neg logit contributions | |
Lauder | -0.394 |
Loving | -0.358 |
Sioux | -0.350 |
Subtle | -0.327 |
Hots | -0.324 |
Token | but |
Token ID | 475 |
Feature activation | -9.97e-02 |
Pos logit contributions | |
Lauder | +0.159 |
Loving | +0.144 |
Sioux | +0.143 |
Hots | +0.134 |
Subtle | +0.132 |
Neg logit contributions | |
obar | -0.157 |
rane | -0.151 |
minist | -0.139 |
oba | -0.136 |
ega | -0.134 |
Token | kind |
Token ID | 1611 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Lauder | +0.186 |
Loving | +0.168 |
Sioux | +0.166 |
Hots | +0.158 |
Subtle | +0.157 |
Neg logit contributions | |
obar | -0.164 |
rane | -0.157 |
minist | -0.144 |
oba | -0.142 |
ega | -0.140 |
Token | 2016 |
Token ID | 5304 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
Lauder | +0.137 |
Loving | +0.126 |
Sioux | +0.125 |
Hots | +0.116 |
Sikh | +0.115 |
Neg logit contributions | |
obar | -0.124 |
rane | -0.119 |
minist | -0.109 |
oba | -0.107 |
ega | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
Lauder | +0.949 |
Loving | +0.848 |
Sioux | +0.839 |
Hots | +0.781 |
Subtle | +0.774 |
Neg logit contributions | |
obar | -0.954 |
rane | -0.926 |
minist | -0.847 |
oba | -0.836 |
ega | -0.821 |
Token | 01 |
Token ID | 486 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
Lauder | +0.076 |
Loving | +0.069 |
Sioux | +0.069 |
Hots | +0.065 |
Sikh | +0.064 |
Neg logit contributions | |
obar | -0.058 |
rane | -0.056 |
minist | -0.051 |
oba | -0.050 |
ega | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
obar | +0.108 |
rane | +0.104 |
minist | +0.094 |
oba | +0.094 |
ega | +0.092 |
Neg logit contributions | |
Lauder | -0.117 |
Sioux | -0.104 |
Loving | -0.103 |
Hots | -0.096 |
Subtle | -0.096 |
Token | 29 |
Token ID | 1959 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
obar | +0.084 |
rane | +0.082 |
minist | +0.075 |
oba | +0.072 |
ega | +0.071 |
Neg logit contributions | |
Lauder | -0.098 |
Loving | -0.089 |
Sioux | -0.088 |
Hots | -0.083 |
Sikh | -0.081 |
Token | "] |
Token ID | 8973 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
obar | +0.012 |
rane | +0.012 |
minist | +0.010 |
oba | +0.010 |
ega | +0.010 |
Neg logit contributions | |
Lauder | -0.025 |
Loving | -0.023 |
Sioux | -0.023 |
Subtle | -0.022 |
Sikh | -0.022 |
Token | [ |
Token ID | 685 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
obar | +2.562 |
rane | +2.546 |
ega | +2.291 |
oba | +2.229 |
minist | +2.200 |
Neg logit contributions | |
Lauder | -3.489 |
Sioux | -3.036 |
Loving | -3.016 |
etooth | -2.928 |
Sikh | -2.804 |
Token | Round |
Token ID | 22685 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
obar | +0.263 |
rane | +0.250 |
minist | +0.222 |
oba | +0.217 |
ega | +0.215 |
Neg logit contributions | |
Lauder | -0.452 |
Loving | -0.419 |
Sioux | -0.415 |
Hots | -0.392 |
Subtle | -0.391 |
Token | " |
Token ID | 366 |
Feature activation | +3.19e-03 |
Pos logit contributions | |
Lauder | +0.407 |
Loving | +0.352 |
Sioux | +0.351 |
Subtle | +0.311 |
Sikh | +0.301 |
Neg logit contributions | |
obar | -0.826 |
rane | -0.806 |
oba | -0.749 |
minist | -0.748 |
ega | -0.741 |
Token | 11 |
Token ID | 1157 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
obar | +0.006 |
rane | +0.006 |
minist | +0.005 |
oba | +0.005 |
ega | +0.005 |
Neg logit contributions | |
Lauder | -0.005 |
Loving | -0.005 |
Sioux | -0.005 |
Hots | -0.005 |
Subtle | -0.005 |
Token | "] |
Token ID | 8973 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Lauder | +0.529 |
Loving | +0.485 |
Sioux | +0.479 |
Hots | +0.451 |
Subtle | +0.444 |
Neg logit contributions | |
obar | -0.447 |
rane | -0.430 |
minist | -0.391 |
oba | -0.383 |
ega | -0.377 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Lauder | +0.089 |
Loving | +0.080 |
Sioux | +0.078 |
Subtle | +0.073 |
Hots | +0.072 |
Neg logit contributions | |
obar | -0.101 |
rane | -0.097 |
minist | -0.090 |
oba | -0.088 |
ega | -0.087 |
Token | Future |
Token ID | 10898 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
obar | +0.187 |
rane | +0.177 |
minist | +0.165 |
oba | +0.162 |
ega | +0.160 |
Neg logit contributions | |
Lauder | -0.171 |
Loving | -0.151 |
Sioux | -0.150 |
Hots | -0.138 |
Sikh | -0.138 |
Token | Hall |
Token ID | 4789 |
Feature activation | +8.54e-01 |
Pos logit contributions | |
obar | +1.109 |
rane | +1.063 |
minist | +0.984 |
oba | +0.970 |
ega | +0.945 |
Neg logit contributions | |
Lauder | -1.060 |
Loving | -0.954 |
Sioux | -0.945 |
Subtle | -0.887 |
Hots | -0.882 |
Token | of |
Token ID | 286 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
obar | +1.801 |
rane | +1.743 |
minist | +1.628 |
oba | +1.599 |
ega | +1.581 |
Neg logit contributions | |
Lauder | -1.199 |
Loving | -1.060 |
Sioux | -1.038 |
Hots | -0.951 |
Sikh | -0.932 |
Token | Fame |
Token ID | 18864 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Lauder | +0.098 |
Loving | +0.089 |
Sioux | +0.088 |
Hots | +0.083 |
Subtle | +0.081 |
Neg logit contributions | |
obar | -0.101 |
rane | -0.097 |
minist | -0.089 |
oba | -0.088 |
ega | -0.086 |
Token | slug |
Token ID | 31065 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
obar | +0.222 |
rane | +0.215 |
minist | +0.199 |
oba | +0.194 |
ega | +0.191 |
Neg logit contributions | |
Lauder | -0.212 |
Loving | -0.192 |
Sioux | -0.187 |
Hots | -0.175 |
Subtle | -0.174 |
Token | ger |
Token ID | 1362 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
obar | +2.542 |
rane | +2.421 |
minist | +2.241 |
oba | +2.110 |
anders | +2.008 |
Neg logit contributions | |
Lauder | -3.374 |
Loving | -3.046 |
Sioux | -2.959 |
Sikh | -2.845 |
Subtle | -2.811 |
Token | Stan |
Token ID | 7299 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
Lauder | +0.078 |
Loving | +0.071 |
Sioux | +0.069 |
Hots | +0.064 |
Subtle | +0.064 |
Neg logit contributions | |
obar | -0.091 |
rane | -0.088 |
minist | -0.081 |
oba | -0.079 |
ega | -0.079 |
Token | Mus |
Token ID | 2629 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Lauder | +0.091 |
Sioux | +0.082 |
Loving | +0.081 |
Hots | +0.076 |
Subtle | +0.074 |
Neg logit contributions | |
obar | -0.121 |
rane | -0.116 |
oba | -0.107 |
minist | -0.107 |
ega | -0.105 |
Token | ial |
Token ID | 498 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Lauder | +0.491 |
Loving | +0.454 |
Sioux | +0.450 |
Hots | +0.430 |
Subtle | +0.427 |
Neg logit contributions | |
obar | -0.237 |
rane | -0.226 |
minist | -0.193 |
oba | -0.187 |
ega | -0.182 |
Token | , |
Token ID | 11 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
Lauder | +0.217 |
Loving | +0.195 |
Sioux | +0.193 |
Subtle | +0.178 |
Hots | +0.177 |
Neg logit contributions | |
obar | -0.269 |
rane | -0.257 |
minist | -0.237 |
oba | -0.234 |
ega | -0.234 |
Token | m |
Token ID | 76 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
obar | +0.027 |
rane | +0.027 |
minist | +0.025 |
oba | +0.024 |
ega | +0.023 |
Neg logit contributions | |
Lauder | -0.028 |
Loving | -0.025 |
Sioux | -0.025 |
Hots | -0.024 |
Subtle | -0.023 |
Token | going |
Token ID | 1016 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
obar | +1.010 |
rane | +0.961 |
minist | +0.897 |
oba | +0.870 |
ega | +0.854 |
Neg logit contributions | |
Lauder | -0.983 |
Loving | -0.868 |
Sioux | -0.867 |
Hots | -0.815 |
Subtle | -0.811 |
Token | to |
Token ID | 284 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
obar | +0.213 |
rane | +0.207 |
minist | +0.192 |
oba | +0.188 |
ega | +0.186 |
Neg logit contributions | |
Lauder | -0.157 |
Loving | -0.140 |
Sioux | -0.138 |
Hots | -0.127 |
Sikh | -0.125 |
Token | have |
Token ID | 423 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
obar | +0.198 |
rane | +0.191 |
minist | +0.175 |
oba | +0.171 |
ega | +0.169 |
Neg logit contributions | |
Lauder | -0.217 |
Loving | -0.196 |
Sioux | -0.193 |
Hots | -0.182 |
Subtle | -0.181 |
Token | to |
Token ID | 284 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
obar | +0.257 |
rane | +0.247 |
minist | +0.229 |
oba | +0.223 |
ega | +0.222 |
Neg logit contributions | |
Lauder | -0.215 |
Loving | -0.192 |
Sioux | -0.189 |
Hots | -0.177 |
Subtle | -0.176 |
Token | paraph |
Token ID | 38624 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
obar | +0.200 |
rane | +0.193 |
minist | +0.175 |
oba | +0.173 |
ega | +0.169 |
Neg logit contributions | |
Lauder | -0.230 |
Loving | -0.209 |
Sioux | -0.205 |
Hots | -0.194 |
Subtle | -0.192 |
Token | rase |
Token ID | 22789 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
obar | +3.091 |
rane | +3.025 |
oba | +2.704 |
ega | +2.682 |
minist | +2.677 |
Neg logit contributions | |
Lauder | -2.896 |
Loving | -2.600 |
Sioux | -2.589 |
Hots | -2.400 |
Sikh | -2.346 |
Token | here |
Token ID | 994 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
Lauder | +0.590 |
Loving | +0.529 |
Sioux | +0.522 |
Hots | +0.486 |
Subtle | +0.477 |
Neg logit contributions | |
obar | -0.702 |
rane | -0.679 |
minist | -0.632 |
oba | -0.613 |
ega | -0.608 |
Token | — |
Token ID | 851 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
obar | +1.069 |
rane | +1.026 |
minist | +0.964 |
oba | +0.933 |
ega | +0.918 |
Neg logit contributions | |
Lauder | -0.881 |
Loving | -0.785 |
Sioux | -0.772 |
Hots | -0.723 |
Subtle | -0.707 |
Token | that |
Token ID | 326 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
Lauder | +0.345 |
Loving | +0.309 |
Sioux | +0.306 |
Hots | +0.287 |
Subtle | +0.279 |
Neg logit contributions | |
obar | -0.398 |
rane | -0.382 |
minist | -0.355 |
oba | -0.345 |
ega | -0.342 |
Token | the |
Token ID | 262 |
Feature activation | -4.28e-02 |
Pos logit contributions | |
Lauder | +0.146 |
Loving | +0.131 |
Sioux | +0.130 |
Hots | +0.121 |
Subtle | +0.120 |
Neg logit contributions | |
obar | -0.172 |
rane | -0.165 |
minist | -0.153 |
oba | -0.149 |
ega | -0.149 |
Token | Kills |
Token ID | 23478 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
Lauder | +0.819 |
Loving | +0.735 |
Sioux | +0.726 |
Hots | +0.674 |
Subtle | +0.660 |
Neg logit contributions | |
obar | -1.040 |
rane | -1.010 |
minist | -0.927 |
oba | -0.916 |
ega | -0.906 |
Token | , |
Token ID | 11 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
Lauder | +0.546 |
Loving | +0.489 |
Sioux | +0.485 |
Hots | +0.450 |
Subtle | +0.442 |
Neg logit contributions | |
obar | -0.634 |
rane | -0.615 |
minist | -0.562 |
oba | -0.556 |
ega | -0.548 |
Token | Will |
Token ID | 2561 |
Feature activation | +4.52e-04 |
Pos logit contributions | |
obar | +0.061 |
rane | +0.059 |
minist | +0.054 |
oba | +0.053 |
ega | +0.053 |
Neg logit contributions | |
Lauder | -0.051 |
Loving | -0.046 |
Sioux | -0.045 |
Hots | -0.042 |
Subtle | -0.041 |
Token | y |
Token ID | 88 |
Feature activation | +8.92e-02 |
Pos logit contributions | |
obar | +0.001 |
rane | +0.001 |
minist | +0.001 |
oba | +0.001 |
ega | +0.001 |
Neg logit contributions | |
Lauder | -0.001 |
Loving | -0.001 |
Sioux | -0.001 |
Hots | -0.001 |
Subtle | -0.001 |
Token | Moon |
Token ID | 6869 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
obar | +0.176 |
rane | +0.171 |
minist | +0.157 |
oba | +0.155 |
ega | +0.153 |
Neg logit contributions | |
Lauder | -0.136 |
Loving | -0.121 |
Sioux | -0.120 |
Hots | -0.111 |
Subtle | -0.110 |
Token | sacked |
Token ID | 32564 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
obar | +0.400 |
rane | +0.388 |
minist | +0.358 |
oba | +0.349 |
ega | +0.348 |
Neg logit contributions | |
Lauder | -0.331 |
Loving | -0.297 |
Sioux | -0.293 |
Hots | -0.272 |
Subtle | -0.268 |
Token |
|
Token ID | 198 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
obar | +2.923 |
rane | +2.843 |
minist | +2.619 |
ega | +2.555 |
oba | +2.540 |
Neg logit contributions | |
Lauder | -2.699 |
Loving | -2.431 |
Sioux | -2.413 |
Hots | -2.255 |
Subtle | -2.208 |
Token |
|
Token ID | 198 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Lauder | +0.316 |
Loving | +0.280 |
Sioux | +0.279 |
Hots | +0.258 |
Subtle | +0.256 |
Neg logit contributions | |
obar | -0.335 |
rane | -0.324 |
minist | -0.298 |
oba | -0.292 |
ega | -0.287 |
Token | * |
Token ID | 9 |
Feature activation | -9.89e-02 |
Pos logit contributions | |
Lauder | +0.236 |
Loving | +0.210 |
Sioux | +0.206 |
Hots | +0.189 |
Subtle | +0.185 |
Neg logit contributions | |
obar | -0.358 |
rane | -0.348 |
minist | -0.324 |
oba | -0.318 |
ega | -0.314 |
Token | Low |
Token ID | 7754 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
Lauder | +0.160 |
Loving | +0.143 |
Sioux | +0.142 |
Hots | +0.132 |
Sikh | +0.129 |
Neg logit contributions | |
obar | -0.186 |
rane | -0.180 |
minist | -0.166 |
oba | -0.163 |
ega | -0.161 |
Token | ratings |
Token ID | 10109 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
Lauder | +1.176 |
Loving | +1.065 |
Sioux | +1.049 |
Hots | +0.979 |
Subtle | +0.960 |
Neg logit contributions | |
obar | -1.281 |
rane | -1.241 |
minist | -1.141 |
oba | -1.118 |
ega | -1.101 |
Token | exact |
Token ID | 2748 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
obar | +0.560 |
rane | +0.548 |
minist | +0.504 |
oba | +0.489 |
ega | +0.480 |
Neg logit contributions | |
Lauder | -0.488 |
Loving | -0.438 |
Sioux | -0.428 |
Hots | -0.397 |
Subtle | -0.397 |
Token | mechanism |
Token ID | 9030 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
obar | +1.580 |
rane | +1.555 |
minist | +1.421 |
oba | +1.375 |
ega | +1.357 |
Neg logit contributions | |
Lauder | -1.430 |
Loving | -1.281 |
Sioux | -1.248 |
Subtle | -1.172 |
Hots | -1.160 |
Token | that |
Token ID | 326 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
obar | +0.972 |
rane | +0.954 |
minist | +0.867 |
oba | +0.847 |
ega | +0.833 |
Neg logit contributions | |
Lauder | -0.869 |
Loving | -0.776 |
Sioux | -0.768 |
Hots | -0.714 |
Subtle | -0.708 |
Token | triggered |
Token ID | 13973 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
obar | +0.601 |
rane | +0.589 |
minist | +0.538 |
oba | +0.525 |
ega | +0.522 |
Neg logit contributions | |
Lauder | -0.476 |
Loving | -0.427 |
Sioux | -0.414 |
Subtle | -0.382 |
Hots | -0.381 |
Token | the |
Token ID | 262 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
obar | +0.028 |
rane | +0.027 |
minist | +0.025 |
oba | +0.025 |
ega | +0.024 |
Neg logit contributions | |
Lauder | -0.023 |
Loving | -0.021 |
Sioux | -0.021 |
Hots | -0.019 |
Subtle | -0.019 |
Token | stream |
Token ID | 4269 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
obar | +0.348 |
rane | +0.340 |
minist | +0.311 |
oba | +0.303 |
ega | +0.297 |
Neg logit contributions | |
Lauder | -0.331 |
Loving | -0.298 |
Sioux | -0.293 |
Hots | -0.274 |
Subtle | -0.270 |
Token | of |
Token ID | 286 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
obar | +3.358 |
rane | +3.244 |
minist | +3.034 |
oba | +2.959 |
ega | +2.920 |
Neg logit contributions | |
Lauder | -2.340 |
Loving | -2.092 |
Sioux | -2.036 |
Hots | -1.903 |
Subtle | -1.848 |
Token | incorrect |
Token ID | 11491 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
obar | +0.305 |
rane | +0.294 |
minist | +0.269 |
oba | +0.261 |
ega | +0.257 |
Neg logit contributions | |
Lauder | -0.323 |
Loving | -0.292 |
Sioux | -0.287 |
Hots | -0.270 |
Subtle | -0.267 |
Token | data |
Token ID | 1366 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
Lauder | +0.583 |
Loving | +0.531 |
Sioux | +0.524 |
Hots | +0.492 |
Subtle | +0.486 |
Neg logit contributions | |
obar | -0.535 |
rane | -0.517 |
minist | -0.469 |
oba | -0.459 |
ega | -0.450 |
Token | . |
Token ID | 13 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
obar | +0.682 |
rane | +0.660 |
minist | +0.611 |
oba | +0.593 |
ega | +0.585 |
Neg logit contributions | |
Lauder | -0.644 |
Loving | -0.583 |
Sioux | -0.574 |
Hots | -0.536 |
Subtle | -0.531 |
Token | They |
Token ID | 1119 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
obar | +0.128 |
rane | +0.124 |
minist | +0.114 |
oba | +0.113 |
ega | +0.110 |
Neg logit contributions | |
Lauder | -0.107 |
Loving | -0.096 |
Sioux | -0.095 |
Hots | -0.088 |
Sikh | -0.086 |
Token | ijk |
Token ID | 45961 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
Lauder | +0.220 |
Loving | +0.201 |
Sioux | +0.196 |
Hots | +0.184 |
Subtle | +0.183 |
Neg logit contributions | |
obar | -0.217 |
rane | -0.210 |
minist | -0.191 |
oba | -0.189 |
ega | -0.186 |
Token | a |
Token ID | 257 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Lauder | +0.073 |
Loving | +0.065 |
Sioux | +0.064 |
Sikh | +0.058 |
Hots | +0.058 |
Neg logit contributions | |
obar | -0.094 |
rane | -0.090 |
minist | -0.083 |
oba | -0.082 |
ega | -0.082 |
Token | an |
Token ID | 272 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
obar | +0.305 |
rane | +0.293 |
minist | +0.264 |
oba | +0.260 |
ega | +0.257 |
Neg logit contributions | |
Lauder | -0.367 |
Loving | -0.336 |
Sioux | -0.331 |
Hots | -0.312 |
Sikh | -0.308 |
Token | Z |
Token ID | 1168 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
obar | +0.892 |
rane | +0.850 |
oba | +0.747 |
ega | +0.746 |
minist | +0.740 |
Neg logit contributions | |
Lauder | -1.212 |
Loving | -1.122 |
Sioux | -1.119 |
Sikh | -1.041 |
Hots | -1.036 |
Token | ee |
Token ID | 1453 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Lauder | +0.515 |
Loving | +0.464 |
Sioux | +0.455 |
Sikh | +0.419 |
Hots | +0.417 |
Neg logit contributions | |
obar | -0.686 |
rane | -0.665 |
minist | -0.614 |
oba | -0.612 |
ega | -0.603 |
Token | "] |
Token ID | 8973 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
obar | +0.268 |
rane | +0.260 |
minist | +0.236 |
oba | +0.235 |
ega | +0.231 |
Neg logit contributions | |
Lauder | -0.245 |
Loving | -0.224 |
Sioux | -0.223 |
Hots | -0.206 |
Sikh | -0.204 |
Token | [ |
Token ID | 685 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
rane | +2.328 |
obar | +2.323 |
ega | +2.059 |
minist | +2.045 |
oba | +2.035 |
Neg logit contributions | |
Lauder | -3.339 |
Sioux | -2.842 |
Loving | -2.792 |
etooth | -2.713 |
cks | -2.612 |
Token | Date |
Token ID | 10430 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
obar | +0.209 |
rane | +0.203 |
minist | +0.185 |
oba | +0.180 |
ega | +0.175 |
Neg logit contributions | |
Lauder | -0.276 |
Loving | -0.255 |
Sioux | -0.253 |
Hots | -0.236 |
Subtle | -0.235 |
Token | " |
Token ID | 366 |
Feature activation | -7.43e-02 |
Pos logit contributions | |
Lauder | +0.229 |
Loving | +0.191 |
Sioux | +0.191 |
Sikh | +0.164 |
Subtle | +0.163 |
Neg logit contributions | |
obar | -0.495 |
rane | -0.487 |
oba | -0.453 |
minist | -0.450 |
ega | -0.446 |
Token | 2016 |
Token ID | 5304 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
Lauder | +0.137 |
Loving | +0.126 |
Sioux | +0.125 |
Hots | +0.116 |
Sikh | +0.115 |
Neg logit contributions | |
obar | -0.124 |
rane | -0.119 |
minist | -0.109 |
oba | -0.107 |
ega | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
Lauder | +0.949 |
Loving | +0.848 |
Sioux | +0.839 |
Hots | +0.781 |
Subtle | +0.774 |
Neg logit contributions | |
obar | -0.954 |
rane | -0.926 |
minist | -0.847 |
oba | -0.836 |
ega | -0.821 |
Token | Big |
Token ID | 4403 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
obar | +0.139 |
rane | +0.135 |
minist | +0.124 |
oba | +0.123 |
ega | +0.120 |
Neg logit contributions | |
Lauder | -0.108 |
Loving | -0.096 |
Sioux | -0.095 |
Hots | -0.088 |
Sikh | -0.086 |
Token | Bang |
Token ID | 9801 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
obar | +0.062 |
rane | +0.058 |
minist | +0.053 |
oba | +0.051 |
ega | +0.050 |
Neg logit contributions | |
Lauder | -0.094 |
Loving | -0.088 |
Sioux | -0.087 |
Hots | -0.083 |
Subtle | -0.081 |
Token | Theory |
Token ID | 17003 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
obar | +1.369 |
rane | +1.343 |
minist | +1.239 |
oba | +1.236 |
ega | +1.216 |
Neg logit contributions | |
Lauder | -0.912 |
Loving | -0.775 |
Sioux | -0.743 |
Hots | -0.717 |
Subtle | -0.695 |
Token | CBS |
Token ID | 11133 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
obar | +0.025 |
rane | +0.024 |
minist | +0.022 |
oba | +0.022 |
ega | +0.022 |
Neg logit contributions | |
Lauder | -0.021 |
Loving | -0.018 |
Sioux | -0.018 |
Hots | -0.017 |
Subtle | -0.016 |
Token | Amy |
Token ID | 14235 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Lauder | +0.207 |
Loving | +0.185 |
Sioux | +0.182 |
Hots | +0.171 |
Subtle | +0.168 |
Neg logit contributions | |
obar | -0.238 |
rane | -0.231 |
minist | -0.212 |
oba | -0.208 |
ega | -0.206 |
Token | Poe |
Token ID | 34815 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Lauder | +0.219 |
Loving | +0.201 |
Sioux | +0.199 |
Hots | +0.189 |
Subtle | +0.187 |
Neg logit contributions | |
obar | -0.138 |
rane | -0.133 |
minist | -0.116 |
oba | -0.114 |
ega | -0.113 |
Token | hler |
Token ID | 49737 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
obar | +2.477 |
rane | +2.363 |
minist | +2.098 |
oba | +2.046 |
ega | +2.040 |
Neg logit contributions | |
Lauder | -3.159 |
Loving | -2.907 |
Sioux | -2.876 |
Hots | -2.713 |
Subtle | -2.684 |
Token | Parks |
Token ID | 20604 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
obar | +0.932 |
rane | +0.908 |
minist | +0.834 |
oba | +0.817 |
ega | +0.815 |
Neg logit contributions | |
Lauder | -0.760 |
Loving | -0.661 |
Sioux | -0.650 |
Hots | -0.615 |
Subtle | -0.602 |
Token | and |
Token ID | 290 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
obar | +0.711 |
rane | +0.694 |
minist | +0.637 |
oba | +0.624 |
ega | +0.617 |
Neg logit contributions | |
Lauder | -0.619 |
Loving | -0.547 |
Sioux | -0.544 |
Hots | -0.506 |
Subtle | -0.493 |
Token | Recreation |
Token ID | 34285 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
Lauder | +0.199 |
Loving | +0.173 |
Sioux | +0.171 |
Hots | +0.157 |
Sikh | +0.153 |
Neg logit contributions | |
obar | -0.306 |
rane | -0.298 |
minist | -0.277 |
oba | -0.271 |
ega | -0.268 |
Token | NBC |
Token ID | 9716 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
Lauder | +0.286 |
Loving | +0.253 |
Sioux | +0.248 |
Hots | +0.232 |
Subtle | +0.228 |
Neg logit contributions | |
obar | -0.359 |
rane | -0.349 |
minist | -0.323 |
oba | -0.316 |
ega | -0.314 |
Token | "] |
Token ID | 8973 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
obar | +0.012 |
rane | +0.012 |
minist | +0.010 |
oba | +0.010 |
ega | +0.010 |
Neg logit contributions | |
Lauder | -0.025 |
Loving | -0.023 |
Sioux | -0.023 |
Subtle | -0.022 |
Sikh | -0.022 |
Token | [ |
Token ID | 685 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
obar | +2.562 |
rane | +2.546 |
ega | +2.291 |
oba | +2.229 |
minist | +2.200 |
Neg logit contributions | |
Lauder | -3.489 |
Sioux | -3.036 |
Loving | -3.016 |
etooth | -2.928 |
Sikh | -2.804 |
Token | Round |
Token ID | 22685 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
obar | +0.263 |
rane | +0.250 |
minist | +0.222 |
oba | +0.217 |
ega | +0.215 |
Neg logit contributions | |
Lauder | -0.452 |
Loving | -0.419 |
Sioux | -0.415 |
Hots | -0.392 |
Subtle | -0.391 |
Token | " |
Token ID | 366 |
Feature activation | +3.19e-03 |
Pos logit contributions | |
Lauder | +0.407 |
Loving | +0.352 |
Sioux | +0.351 |
Subtle | +0.311 |
Sikh | +0.301 |
Neg logit contributions | |
obar | -0.826 |
rane | -0.806 |
oba | -0.749 |
minist | -0.748 |
ega | -0.741 |
Token | 11 |
Token ID | 1157 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
obar | +0.006 |
rane | +0.006 |
minist | +0.005 |
oba | +0.005 |
ega | +0.005 |
Neg logit contributions | |
Lauder | -0.005 |
Loving | -0.005 |
Sioux | -0.005 |
Hots | -0.005 |
Subtle | -0.005 |
Token | "] |
Token ID | 8973 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Lauder | +0.529 |
Loving | +0.485 |
Sioux | +0.479 |
Hots | +0.451 |
Subtle | +0.444 |
Neg logit contributions | |
obar | -0.447 |
rane | -0.430 |
minist | -0.391 |
oba | -0.383 |
ega | -0.377 |
Token | [ |
Token ID | 685 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
obar | +2.418 |
rane | +2.342 |
ega | +2.095 |
oba | +2.058 |
minist | +2.057 |
Neg logit contributions | |
Lauder | -3.103 |
Sioux | -2.728 |
Loving | -2.715 |
Hots | -2.554 |
Sikh | -2.524 |
Token | White |
Token ID | 12256 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
obar | +0.326 |
rane | +0.315 |
minist | +0.291 |
oba | +0.284 |
ega | +0.279 |
Neg logit contributions | |
Lauder | -0.301 |
Loving | -0.273 |
Sioux | -0.269 |
Hots | -0.251 |
Subtle | -0.247 |
Token | " |
Token ID | 366 |
Feature activation | +6.13e-03 |
Pos logit contributions | |
Lauder | +0.238 |
Loving | +0.205 |
Sioux | +0.198 |
Subtle | +0.185 |
Sikh | +0.180 |
Neg logit contributions | |
obar | -0.504 |
rane | -0.479 |
oba | -0.456 |
ega | -0.447 |
minist | -0.444 |
Token | Ab |
Token ID | 4826 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
obar | +0.011 |
rane | +0.010 |
minist | +0.010 |
oba | +0.009 |
ega | +0.009 |
Neg logit contributions | |
Lauder | -0.011 |
Loving | -0.010 |
Sioux | -0.010 |
Hots | -0.009 |
Subtle | -0.009 |
Token | as |
Token ID | 292 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
obar | +0.172 |
rane | +0.165 |
minist | +0.149 |
oba | +0.147 |
ega | +0.145 |
Neg logit contributions | |
Lauder | -0.201 |
Loving | -0.183 |
Sioux | -0.182 |
Hots | -0.171 |
Sikh | -0.168 |
Token |
|
Token ID | 198 |
Feature activation | -8.41e-02 |
Pos logit contributions | |
Lauder | +0.187 |
Loving | +0.165 |
Sioux | +0.165 |
Hots | +0.153 |
Subtle | +0.152 |
Neg logit contributions | |
obar | -0.194 |
rane | -0.187 |
minist | -0.172 |
oba | -0.169 |
ega | -0.166 |
Token | 24 |
Token ID | 1731 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Lauder | +0.147 |
Loving | +0.133 |
Sioux | +0.132 |
Hots | +0.123 |
Subtle | +0.121 |
Neg logit contributions | |
obar | -0.149 |
rane | -0.144 |
minist | -0.132 |
oba | -0.129 |
ega | -0.127 |
Token | 11 |
Token ID | 1157 |
Feature activation | -9.59e-02 |
Pos logit contributions | |
Lauder | +0.299 |
Loving | +0.272 |
Sioux | +0.267 |
Hots | +0.252 |
Subtle | +0.247 |
Neg logit contributions | |
obar | -0.295 |
rane | -0.284 |
minist | -0.259 |
oba | -0.253 |
ega | -0.252 |
Token | S |
Token ID | 311 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
Lauder | +0.144 |
Loving | +0.129 |
Sioux | +0.127 |
Hots | +0.118 |
Subtle | +0.116 |
Neg logit contributions | |
obar | -0.189 |
rane | -0.184 |
minist | -0.170 |
oba | -0.167 |
ega | -0.166 |
Token | . |
Token ID | 13 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Lauder | +0.564 |
Loving | +0.513 |
Sioux | +0.504 |
Hots | +0.477 |
Subtle | +0.467 |
Neg logit contributions | |
obar | -0.626 |
rane | -0.602 |
minist | -0.556 |
oba | -0.549 |
ega | -0.535 |
Token | Shepherd |
Token ID | 30890 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Lauder | +0.274 |
Loving | +0.245 |
Sioux | +0.241 |
Hots | +0.225 |
Subtle | +0.221 |
Neg logit contributions | |
obar | -0.353 |
rane | -0.342 |
minist | -0.316 |
oba | -0.311 |
ega | -0.307 |
Token | Today |
Token ID | 6288 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
obar | +2.782 |
rane | +2.652 |
minist | +2.448 |
oba | +2.444 |
ega | +2.412 |
Neg logit contributions | |
Lauder | -2.789 |
Loving | -2.440 |
Sioux | -2.426 |
Subtle | -2.286 |
Hots | -2.283 |
Token | : |
Token ID | 25 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
obar | +0.586 |
rane | +0.564 |
minist | +0.515 |
oba | +0.511 |
ega | +0.505 |
Neg logit contributions | |
Lauder | -0.556 |
Loving | -0.487 |
Sioux | -0.486 |
Hots | -0.452 |
Subtle | -0.446 |
Token | Tor |
Token ID | 4022 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
Lauder | +0.376 |
Loving | +0.335 |
Sioux | +0.329 |
Hots | +0.307 |
Subtle | +0.301 |
Neg logit contributions | |
obar | -0.470 |
rane | -0.456 |
minist | -0.419 |
oba | -0.415 |
ega | -0.409 |
Token | chy |
Token ID | 29658 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
obar | +0.546 |
rane | +0.528 |
minist | +0.478 |
oba | +0.470 |
ega | +0.459 |
Neg logit contributions | |
Lauder | -0.625 |
Loving | -0.573 |
Sioux | -0.569 |
Hots | -0.535 |
Subtle | -0.527 |
Token | 's |
Token ID | 338 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
Lauder | +0.890 |
Loving | +0.799 |
Sioux | +0.788 |
Hots | +0.731 |
Subtle | +0.719 |
Neg logit contributions | |
obar | -1.071 |
rane | -1.037 |
minist | -0.956 |
oba | -0.941 |
ega | -0.925 |
Token | , |
Token ID | 11 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
Lauder | +0.793 |
Loving | +0.712 |
Sioux | +0.706 |
Hots | +0.656 |
Subtle | +0.646 |
Neg logit contributions | |
obar | -0.909 |
rane | -0.875 |
minist | -0.810 |
oba | -0.796 |
ega | -0.780 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
Lauder | +0.094 |
Loving | +0.085 |
Sioux | +0.084 |
Hots | +0.079 |
Subtle | +0.078 |
Neg logit contributions | |
obar | -0.088 |
rane | -0.084 |
minist | -0.077 |
oba | -0.075 |
ega | -0.074 |
Token | The |
Token ID | 464 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
Lauder | +0.309 |
Loving | +0.282 |
Sioux | +0.279 |
Hots | +0.263 |
Subtle | +0.258 |
Neg logit contributions | |
obar | -0.265 |
rane | -0.254 |
minist | -0.232 |
oba | -0.226 |
ega | -0.222 |
Token | urge |
Token ID | 14960 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
Lauder | +0.433 |
Loving | +0.390 |
Sioux | +0.383 |
Hots | +0.357 |
Subtle | +0.349 |
Neg logit contributions | |
obar | -0.515 |
rane | -0.499 |
minist | -0.461 |
oba | -0.453 |
ega | -0.445 |
Token | to |
Token ID | 284 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
obar | +0.093 |
rane | +0.090 |
minist | +0.084 |
oba | +0.082 |
ega | +0.081 |
Neg logit contributions | |
Lauder | -0.074 |
Loving | -0.067 |
Sioux | -0.066 |
Hots | -0.061 |
Subtle | -0.060 |
Token | binge |
Token ID | 34735 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Lauder | +0.534 |
Loving | +0.485 |
Sioux | +0.477 |
Hots | +0.448 |
Subtle | +0.441 |
Neg logit contributions | |
obar | -0.500 |
rane | -0.483 |
minist | -0.440 |
oba | -0.432 |
ega | -0.424 |
Token | on |
Token ID | 319 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
obar | +2.756 |
rane | +2.688 |
minist | +2.460 |
ega | +2.420 |
oba | +2.417 |
Neg logit contributions | |
Lauder | -2.686 |
Loving | -2.412 |
Sioux | -2.349 |
Hots | -2.210 |
Subtle | -2.197 |
Token | streaming |
Token ID | 11305 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
Lauder | +0.185 |
Loving | +0.167 |
Sioux | +0.163 |
Hots | +0.153 |
Subtle | +0.151 |
Neg logit contributions | |
obar | -0.208 |
rane | -0.202 |
minist | -0.185 |
oba | -0.182 |
ega | -0.180 |
Token | Netflix |
Token ID | 12074 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
obar | +1.654 |
rane | +1.582 |
minist | +1.439 |
ega | +1.408 |
oba | +1.406 |
Neg logit contributions | |
Lauder | -1.767 |
Loving | -1.614 |
Sioux | -1.557 |
Subtle | -1.451 |
Hots | -1.441 |
Token | television |
Token ID | 5581 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
obar | +0.196 |
rane | +0.190 |
minist | +0.175 |
oba | +0.171 |
ega | +0.170 |
Neg logit contributions | |
Lauder | -0.173 |
Loving | -0.156 |
Sioux | -0.152 |
Sikh | -0.140 |
Subtle | -0.139 |
Token | and |
Token ID | 290 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
obar | +1.203 |
rane | +1.178 |
minist | +1.085 |
ega | +1.049 |
oba | +1.045 |
Neg logit contributions | |
Lauder | -1.108 |
Loving | -1.004 |
Sioux | -0.977 |
Subtle | -0.897 |
Sikh | -0.895 |
Token | [ |
Token ID | 685 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
obar | +0.838 |
rane | +0.813 |
minist | +0.742 |
ega | +0.732 |
oba | +0.728 |
Neg logit contributions | |
Lauder | -0.731 |
Loving | -0.650 |
Sioux | -0.642 |
Hots | -0.596 |
Subtle | -0.590 |
Token | who |
Token ID | 8727 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
Lauder | +0.613 |
Loving | +0.558 |
Sioux | +0.551 |
Hots | +0.518 |
Subtle | +0.510 |
Neg logit contributions | |
obar | -0.565 |
rane | -0.545 |
minist | -0.500 |
oba | -0.486 |
ega | -0.477 |
Token | plays |
Token ID | 5341 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
obar | +1.356 |
rane | +1.312 |
minist | +1.203 |
oba | +1.180 |
ega | +1.171 |
Neg logit contributions | |
Lauder | -1.207 |
Loving | -1.068 |
Sioux | -1.051 |
Hots | -0.980 |
Subtle | -0.973 |
Token | Mr |
Token ID | 1770 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
obar | +0.050 |
rane | +0.048 |
minist | +0.044 |
oba | +0.044 |
ega | +0.043 |
Neg logit contributions | |
Lauder | -0.042 |
Loving | -0.037 |
Sioux | -0.037 |
Hots | -0.034 |
Sikh | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
Lauder | +0.665 |
Loving | +0.601 |
Sioux | +0.593 |
Hots | +0.552 |
Subtle | +0.541 |
Neg logit contributions | |
obar | -0.778 |
rane | -0.751 |
minist | -0.695 |
oba | -0.678 |
ega | -0.671 |
Token | Poe |
Token ID | 34815 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Lauder | +0.409 |
Loving | +0.366 |
Sioux | +0.362 |
Hots | +0.336 |
Sikh | +0.330 |
Neg logit contributions | |
obar | -0.506 |
rane | -0.490 |
minist | -0.452 |
oba | -0.445 |
ega | -0.437 |
Token | ] |
Token ID | 60 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
obar | +2.812 |
rane | +2.636 |
minist | +2.442 |
oba | +2.410 |
ega | +2.389 |
Neg logit contributions | |
Lauder | -2.577 |
Loving | -2.329 |
Sioux | -2.304 |
Subtle | -2.142 |
Hots | -2.123 |
Token | sings |
Token ID | 33041 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
obar | +0.471 |
rane | +0.456 |
minist | +0.417 |
oba | +0.408 |
ega | +0.407 |
Neg logit contributions | |
Lauder | -0.410 |
Loving | -0.366 |
Sioux | -0.360 |
Hots | -0.335 |
Subtle | -0.332 |
Token | really |
Token ID | 1107 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
Lauder | +0.771 |
Loving | +0.690 |
Sioux | +0.673 |
Hots | +0.628 |
Sikh | +0.618 |
Neg logit contributions | |
obar | -0.913 |
rane | -0.882 |
minist | -0.816 |
oba | -0.799 |
ega | -0.790 |
Token | well |
Token ID | 880 |
Feature activation | -9.17e-03 |
Pos logit contributions | |
Lauder | +0.852 |
Loving | +0.763 |
Sioux | +0.740 |
Hots | +0.692 |
Subtle | +0.678 |
Neg logit contributions | |
obar | -1.002 |
rane | -0.964 |
minist | -0.897 |
oba | -0.873 |
ega | -0.868 |
Token | . |
Token ID | 13 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
Lauder | +0.015 |
Loving | +0.014 |
Sioux | +0.014 |
Hots | +0.013 |
Subtle | +0.013 |
Neg logit contributions | |
obar | -0.017 |
rane | -0.016 |
minist | -0.015 |
oba | -0.015 |
ega | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
obar | +2.204 |
rane | +2.084 |
minist | +1.956 |
ega | +1.872 |
oba | +1.871 |
Neg logit contributions | |
Lauder | -1.899 |
Sioux | -1.715 |
Loving | -1.711 |
Hots | -1.559 |
Subtle | -1.554 |
Token | driving |
Token ID | 5059 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
obar | +0.102 |
rane | +0.099 |
minist | +0.091 |
oba | +0.088 |
ega | +0.087 |
Neg logit contributions | |
Lauder | -0.104 |
Loving | -0.094 |
Sioux | -0.092 |
Hots | -0.087 |
Subtle | -0.085 |
Token | related |
Token ID | 3519 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
obar | +0.023 |
rane | +0.022 |
minist | +0.020 |
oba | +0.020 |
ega | +0.020 |
Neg logit contributions | |
Lauder | -0.022 |
Loving | -0.020 |
Sioux | -0.020 |
Hots | -0.019 |
Subtle | -0.018 |
Token | skills |
Token ID | 4678 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Lauder | +0.604 |
Loving | +0.550 |
Sioux | +0.540 |
Hots | +0.511 |
Subtle | +0.501 |
Neg logit contributions | |
obar | -0.526 |
rane | -0.511 |
minist | -0.466 |
oba | -0.451 |
ega | -0.444 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
obar | +0.202 |
rane | +0.197 |
minist | +0.180 |
oba | +0.177 |
ega | +0.173 |
Neg logit contributions | |
Lauder | -0.186 |
Loving | -0.167 |
Sioux | -0.165 |
Hots | -0.153 |
Subtle | -0.151 |
Token | Springfield |
Token ID | 27874 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Lauder | +0.175 |
Loving | +0.155 |
Sioux | +0.153 |
Hots | +0.142 |
Sikh | +0.138 |
Neg logit contributions | |
obar | -0.219 |
rane | -0.215 |
minist | -0.196 |
oba | -0.192 |
ega | -0.189 |
Token | , |
Token ID | 11 |
Feature activation | -7.45e-03 |
Pos logit contributions | |
obar | +2.841 |
rane | +2.757 |
minist | +2.519 |
oba | +2.478 |
ega | +2.455 |
Neg logit contributions | |
Lauder | -2.548 |
Loving | -2.293 |
Sioux | -2.239 |
Hots | -2.105 |
Subtle | -2.062 |
Token | VA |
Token ID | 13753 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
Lauder | +0.010 |
Loving | +0.009 |
Sioux | +0.009 |
Hots | +0.008 |
Subtle | +0.008 |
Neg logit contributions | |
obar | -0.016 |
rane | -0.015 |
minist | -0.014 |
oba | -0.014 |
ega | -0.014 |
Token | : |
Token ID | 25 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
obar | +1.197 |
rane | +1.156 |
minist | +1.060 |
oba | +1.038 |
ega | +1.025 |
Neg logit contributions | |
Lauder | -1.155 |
Loving | -1.041 |
Sioux | -1.020 |
Hots | -0.949 |
Subtle | -0.937 |
Token | US |
Token ID | 1294 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Lauder | +0.361 |
Loving | +0.317 |
Sioux | +0.312 |
Hots | +0.286 |
Subtle | +0.278 |
Neg logit contributions | |
obar | -0.575 |
rane | -0.563 |
minist | -0.522 |
oba | -0.512 |
ega | -0.506 |
Token | Department |
Token ID | 2732 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
obar | +0.202 |
rane | +0.197 |
minist | +0.181 |
oba | +0.175 |
ega | +0.172 |
Neg logit contributions | |
Lauder | -0.210 |
Loving | -0.189 |
Sioux | -0.187 |
Hots | -0.176 |
Subtle | -0.173 |
Token | ov |
Token ID | 709 |
Feature activation | -9.47e-02 |
Pos logit contributions | |
obar | +0.618 |
rane | +0.590 |
oba | +0.534 |
minist | +0.531 |
ega | +0.519 |
Neg logit contributions | |
Lauder | -0.640 |
Loving | -0.586 |
Sioux | -0.582 |
Hots | -0.550 |
Subtle | -0.540 |
Token | , |
Token ID | 11 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Lauder | +0.162 |
Loving | +0.146 |
Sioux | +0.145 |
Hots | +0.135 |
Subtle | +0.134 |
Neg logit contributions | |
obar | -0.172 |
rane | -0.166 |
minist | -0.152 |
oba | -0.151 |
ega | -0.149 |
Token | N |
Token ID | 399 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
obar | +0.460 |
rane | +0.440 |
minist | +0.404 |
oba | +0.402 |
ega | +0.399 |
Neg logit contributions | |
Lauder | -0.381 |
Loving | -0.342 |
Sioux | -0.339 |
Hots | -0.310 |
Subtle | -0.309 |
Token | ij |
Token ID | 2926 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
Lauder | +1.243 |
Loving | +1.135 |
Sioux | +1.126 |
Hots | +1.051 |
Subtle | +1.040 |
Neg logit contributions | |
obar | -1.139 |
rane | -1.101 |
minist | -0.998 |
oba | -0.986 |
ega | -0.967 |
Token | at |
Token ID | 265 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
obar | +0.128 |
rane | +0.123 |
oba | +0.111 |
minist | +0.111 |
ega | +0.109 |
Neg logit contributions | |
Lauder | -0.133 |
Loving | -0.120 |
Sioux | -0.119 |
Subtle | -0.112 |
Hots | -0.111 |
Token | "] |
Token ID | 8973 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
obar | +0.052 |
rane | +0.050 |
oba | +0.045 |
minist | +0.044 |
ega | +0.044 |
Neg logit contributions | |
Lauder | -0.071 |
Sioux | -0.065 |
Loving | -0.065 |
Hots | -0.061 |
Subtle | -0.061 |
Token | [ |
Token ID | 685 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
obar | +2.391 |
rane | +2.323 |
oba | +2.085 |
ega | +2.044 |
minist | +2.036 |
Neg logit contributions | |
Lauder | -2.878 |
Sioux | -2.564 |
Loving | -2.537 |
Hots | -2.388 |
Subtle | -2.355 |
Token | Black |
Token ID | 9915 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
obar | +0.367 |
rane | +0.355 |
minist | +0.326 |
oba | +0.325 |
ega | +0.318 |
Neg logit contributions | |
Lauder | -0.265 |
Loving | -0.240 |
Sioux | -0.236 |
Hots | -0.216 |
Subtle | -0.213 |
Token | " |
Token ID | 366 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
Lauder | +1.037 |
Loving | +0.857 |
Sioux | +0.842 |
Hots | +0.716 |
Sikh | +0.715 |
Neg logit contributions | |
obar | -2.422 |
rane | -2.356 |
minist | -2.202 |
oba | -2.191 |
ega | -2.164 |
Token | Ant |
Token ID | 13217 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Lauder | +0.031 |
Loving | +0.028 |
Sioux | +0.028 |
Hots | +0.026 |
Subtle | +0.026 |
Neg logit contributions | |
obar | -0.030 |
rane | -0.029 |
minist | -0.027 |
oba | -0.026 |
ega | -0.026 |
Token | ip |
Token ID | 541 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
Lauder | +0.281 |
Loving | +0.256 |
Sioux | +0.254 |
Hots | +0.237 |
Subtle | +0.235 |
Neg logit contributions | |
obar | -0.271 |
rane | -0.264 |
minist | -0.237 |
oba | -0.236 |
ega | -0.233 |
Token | create |
Token ID | 2251 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Lauder | +0.809 |
Loving | +0.736 |
Sioux | +0.726 |
Hots | +0.677 |
Subtle | +0.668 |
Neg logit contributions | |
obar | -0.784 |
rane | -0.755 |
minist | -0.692 |
oba | -0.677 |
ega | -0.664 |
Token | an |
Token ID | 281 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Lauder | +0.371 |
Loving | +0.335 |
Sioux | +0.333 |
Hots | +0.305 |
Sikh | +0.301 |
Neg logit contributions | |
obar | -0.410 |
rane | -0.394 |
minist | -0.365 |
oba | -0.354 |
ega | -0.350 |
Token | initialization |
Token ID | 37588 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
Lauder | +0.368 |
Loving | +0.331 |
Sioux | +0.330 |
Hots | +0.298 |
Sikh | +0.298 |
Neg logit contributions | |
obar | -0.431 |
rane | -0.411 |
minist | -0.377 |
oba | -0.367 |
ega | -0.365 |
Token | file |
Token ID | 2393 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
obar | +0.623 |
rane | +0.588 |
minist | +0.531 |
oba | +0.514 |
ega | +0.505 |
Neg logit contributions | |
Lauder | -0.858 |
Loving | -0.796 |
Sioux | -0.786 |
Hots | -0.738 |
Subtle | -0.730 |
Token | with |
Token ID | 351 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
Lauder | +0.285 |
Loving | +0.257 |
Sioux | +0.255 |
Hots | +0.235 |
Sikh | +0.232 |
Neg logit contributions | |
obar | -0.338 |
rane | -0.325 |
minist | -0.302 |
oba | -0.295 |
ega | -0.289 |
Token | | |
Token ID | 930 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
obar | +0.137 |
rane | +0.131 |
minist | +0.122 |
oba | +0.119 |
ega | +0.117 |
Neg logit contributions | |
Lauder | -0.120 |
Loving | -0.108 |
Sioux | -0.107 |
Hots | -0.099 |
Sikh | -0.098 |
Token | : |
Token ID | 25 |
Feature activation | -8.47e-02 |
Pos logit contributions | |
obar | +2.709 |
rane | +2.584 |
minist | +2.387 |
oba | +2.316 |
ega | +2.277 |
Neg logit contributions | |
Lauder | -2.665 |
Loving | -2.403 |
Sioux | -2.398 |
Hots | -2.209 |
Sikh | -2.192 |
Token | mk |
Token ID | 28015 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
Lauder | +0.161 |
Loving | +0.148 |
Sioux | +0.146 |
Hots | +0.137 |
Subtle | +0.135 |
Neg logit contributions | |
obar | -0.137 |
rane | -0.132 |
minist | -0.120 |
oba | -0.117 |
ega | -0.115 |
Token | vim |
Token ID | 31124 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
Lauder | +1.235 |
Loving | +1.142 |
Sioux | +1.129 |
Hots | +1.070 |
Subtle | +1.054 |
Neg logit contributions | |
obar | -0.848 |
rane | -0.813 |
minist | -0.729 |
oba | -0.708 |
ega | -0.693 |
Token | rc |
Token ID | 6015 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
Lauder | +1.018 |
Loving | +0.928 |
Sioux | +0.916 |
Hots | +0.858 |
Subtle | +0.842 |
Neg logit contributions | |
obar | -1.015 |
rane | -0.981 |
minist | -0.899 |
oba | -0.879 |
ega | -0.864 |
Token | | |
Token ID | 91 |
Feature activation | +7.93e-01 |
Pos logit contributions | |
Lauder | +0.614 |
Loving | +0.558 |
Sioux | +0.552 |
Hots | +0.516 |
Subtle | +0.506 |
Neg logit contributions | |
obar | -0.624 |
rane | -0.602 |
minist | -0.554 |
oba | -0.541 |
ega | -0.531 |
Token | able |
Token ID | 1498 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
Lauder | +0.101 |
Loving | +0.091 |
Sioux | +0.089 |
Hots | +0.083 |
Subtle | +0.082 |
Neg logit contributions | |
obar | -0.135 |
rane | -0.131 |
minist | -0.122 |
oba | -0.119 |
ega | -0.117 |
Token | to |
Token ID | 284 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
obar | +0.067 |
rane | +0.065 |
minist | +0.060 |
oba | +0.059 |
ega | +0.058 |
Neg logit contributions | |
Lauder | -0.059 |
Loving | -0.053 |
Sioux | -0.052 |
Hots | -0.048 |
Subtle | -0.048 |
Token | direct |
Token ID | 1277 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Lauder | +0.068 |
Loving | +0.062 |
Sioux | +0.061 |
Hots | +0.057 |
Subtle | +0.057 |
Neg logit contributions | |
obar | -0.058 |
rane | -0.056 |
minist | -0.051 |
oba | -0.050 |
ega | -0.049 |
Token | more |
Token ID | 517 |
Feature activation | +9.09e-02 |
Pos logit contributions | |
obar | +0.499 |
rane | +0.481 |
minist | +0.445 |
oba | +0.436 |
ega | +0.427 |
Neg logit contributions | |
Lauder | -0.493 |
Loving | -0.448 |
Sioux | -0.442 |
Hots | -0.412 |
Subtle | -0.410 |
Token | light |
Token ID | 1657 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
obar | +0.174 |
rane | +0.170 |
minist | +0.157 |
oba | +0.153 |
ega | +0.150 |
Neg logit contributions | |
Lauder | -0.146 |
Loving | -0.131 |
Sioux | -0.129 |
Hots | -0.120 |
Subtle | -0.118 |
Token | reflected |
Token ID | 12548 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Lauder | +0.339 |
Loving | +0.308 |
Sioux | +0.304 |
Hots | +0.282 |
Subtle | +0.279 |
Neg logit contributions | |
obar | -0.367 |
rane | -0.354 |
minist | -0.328 |
oba | -0.319 |
ega | -0.316 |
Token | by |
Token ID | 416 |
Feature activation | +7.07e-02 |
Pos logit contributions | |
obar | +2.714 |
rane | +2.606 |
minist | +2.464 |
oba | +2.367 |
ega | +2.338 |
Neg logit contributions | |
Lauder | -2.566 |
Loving | -2.358 |
Sioux | -2.298 |
Subtle | -2.179 |
Hots | -2.148 |
Token | the |
Token ID | 262 |
Feature activation | +7.56e-03 |
Pos logit contributions | |
obar | +0.129 |
rane | +0.125 |
minist | +0.115 |
oba | +0.113 |
ega | +0.111 |
Neg logit contributions | |
Lauder | -0.118 |
Loving | -0.108 |
Sioux | -0.106 |
Hots | -0.099 |
Subtle | -0.098 |
Token | scaff |
Token ID | 41498 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
obar | +0.013 |
rane | +0.012 |
minist | +0.011 |
oba | +0.011 |
ega | +0.011 |
Neg logit contributions | |
Lauder | -0.013 |
Loving | -0.013 |
Sioux | -0.012 |
Hots | -0.011 |
Subtle | -0.011 |
Token | old |
Token ID | 727 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
Lauder | +1.640 |
Loving | +1.507 |
Sioux | +1.492 |
Hots | +1.408 |
Subtle | +1.385 |
Neg logit contributions | |
obar | -1.308 |
rane | -1.258 |
minist | -1.138 |
oba | -1.110 |
ega | -1.088 |
Token | into |
Token ID | 656 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
obar | +0.023 |
rane | +0.022 |
minist | +0.021 |
oba | +0.020 |
ega | +0.020 |
Neg logit contributions | |
Lauder | -0.022 |
Loving | -0.020 |
Sioux | -0.020 |
Hots | -0.018 |
Subtle | -0.018 |
Token | " |
Token ID | 366 |
Feature activation | +6.19e-02 |
Pos logit contributions | |
obar | +0.085 |
rane | +0.082 |
minist | +0.077 |
oba | +0.075 |
ega | +0.074 |
Neg logit contributions | |
Lauder | -0.051 |
Loving | -0.045 |
Sioux | -0.045 |
Hots | -0.041 |
Subtle | -0.040 |
Token | which |
Token ID | 4758 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
obar | +0.096 |
rane | +0.092 |
minist | +0.084 |
oba | +0.081 |
ega | +0.079 |
Neg logit contributions | |
Lauder | -0.123 |
Loving | -0.113 |
Sioux | -0.112 |
Hots | -0.106 |
Subtle | -0.104 |
Token | can |
Token ID | 460 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
obar | +0.209 |
rane | +0.203 |
minist | +0.185 |
oba | +0.182 |
ega | +0.181 |
Neg logit contributions | |
Lauder | -0.197 |
Loving | -0.178 |
Sioux | -0.174 |
Hots | -0.163 |
Subtle | -0.162 |
Token | come |
Token ID | 1282 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
Lauder | +0.357 |
Loving | +0.325 |
Sioux | +0.318 |
Hots | +0.299 |
Subtle | +0.295 |
Neg logit contributions | |
obar | -0.319 |
rane | -0.307 |
minist | -0.276 |
oba | -0.276 |
ega | -0.272 |
Token | from |
Token ID | 422 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
obar | +1.630 |
rane | +1.554 |
minist | +1.448 |
ega | +1.424 |
oba | +1.419 |
Neg logit contributions | |
Lauder | -1.387 |
Loving | -1.233 |
Sioux | -1.218 |
Subtle | -1.137 |
Hots | -1.126 |
Token | stroke |
Token ID | 14000 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Lauder | +0.356 |
Loving | +0.318 |
Sioux | +0.315 |
Hots | +0.293 |
Subtle | +0.287 |
Neg logit contributions | |
obar | -0.424 |
rane | -0.411 |
minist | -0.380 |
oba | -0.372 |
ega | -0.367 |
Token | , |
Token ID | 11 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
obar | +2.626 |
rane | +2.531 |
minist | +2.331 |
oba | +2.306 |
ega | +2.293 |
Neg logit contributions | |
Lauder | -2.681 |
Loving | -2.413 |
Sioux | -2.384 |
Hots | -2.249 |
Subtle | -2.192 |
Token | head |
Token ID | 1182 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
obar | +0.298 |
rane | +0.286 |
minist | +0.262 |
oba | +0.256 |
ega | +0.253 |
Neg logit contributions | |
Lauder | -0.287 |
Loving | -0.258 |
Sioux | -0.255 |
Hots | -0.241 |
Subtle | -0.237 |
Token | trauma |
Token ID | 14649 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
obar | +0.520 |
rane | +0.499 |
minist | +0.460 |
oba | +0.456 |
ega | +0.447 |
Neg logit contributions | |
Lauder | -0.476 |
Loving | -0.424 |
Sioux | -0.423 |
Hots | -0.397 |
Subtle | -0.388 |
Token | or |
Token ID | 393 |
Feature activation | +9.07e-03 |
Pos logit contributions | |
obar | +1.125 |
rane | +1.080 |
minist | +0.996 |
oba | +0.981 |
ega | +0.977 |
Neg logit contributions | |
Lauder | -1.044 |
Loving | -0.942 |
Sioux | -0.931 |
Hots | -0.872 |
Subtle | -0.860 |
Token | other |
Token ID | 584 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
obar | +0.017 |
rane | +0.016 |
minist | +0.015 |
oba | +0.015 |
ega | +0.014 |
Neg logit contributions | |
Lauder | -0.015 |
Loving | -0.013 |
Sioux | -0.013 |
Hots | -0.013 |
Subtle | -0.012 |
Token | of |
Token ID | 286 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
obar | +0.055 |
rane | +0.054 |
minist | +0.050 |
oba | +0.049 |
ega | +0.048 |
Neg logit contributions | |
Lauder | -0.038 |
Loving | -0.034 |
Sioux | -0.033 |
Hots | -0.031 |
Subtle | -0.030 |
Token | her |
Token ID | 607 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
Lauder | +0.105 |
Loving | +0.095 |
Sioux | +0.094 |
Hots | +0.088 |
Subtle | +0.086 |
Neg logit contributions | |
obar | -0.117 |
rane | -0.113 |
minist | -0.104 |
oba | -0.102 |
ega | -0.100 |
Token | Dec |
Token ID | 4280 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
Lauder | +0.744 |
Loving | +0.675 |
Sioux | +0.662 |
Hots | +0.627 |
Subtle | +0.616 |
Neg logit contributions | |
obar | -0.732 |
rane | -0.710 |
minist | -0.648 |
oba | -0.636 |
ega | -0.627 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
obar | +0.443 |
rane | +0.433 |
oba | +0.389 |
minist | +0.388 |
ega | +0.377 |
Neg logit contributions | |
Lauder | -0.455 |
Loving | -0.409 |
Sioux | -0.406 |
Hots | -0.385 |
Subtle | -0.375 |
Token | 6 |
Token ID | 718 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
obar | +0.229 |
rane | +0.224 |
minist | +0.204 |
oba | +0.202 |
ega | +0.199 |
Neg logit contributions | |
Lauder | -0.207 |
Loving | -0.184 |
Sioux | -0.182 |
Hots | -0.171 |
Subtle | -0.166 |
Token | runoff |
Token ID | 37536 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Lauder | +0.229 |
Loving | +0.208 |
Sioux | +0.205 |
Hots | +0.193 |
Subtle | +0.190 |
Neg logit contributions | |
obar | -0.213 |
rane | -0.206 |
minist | -0.187 |
oba | -0.185 |
ega | -0.182 |
Token | against |
Token ID | 1028 |
Feature activation | +9.51e-03 |
Pos logit contributions | |
obar | +2.556 |
rane | +2.480 |
ega | +2.249 |
minist | +2.236 |
oba | +2.233 |
Neg logit contributions | |
Lauder | -2.750 |
Loving | -2.458 |
Sioux | -2.377 |
Hots | -2.290 |
Subtle | -2.282 |
Token | Rep |
Token ID | 1432 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
obar | +0.017 |
rane | +0.016 |
minist | +0.015 |
oba | +0.015 |
ega | +0.015 |
Neg logit contributions | |
Lauder | -0.016 |
Loving | -0.015 |
Sioux | -0.015 |
Hots | -0.014 |
Subtle | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
obar | +0.187 |
rane | +0.182 |
minist | +0.165 |
oba | +0.163 |
ega | +0.160 |
Neg logit contributions | |
Lauder | -0.189 |
Loving | -0.170 |
Sioux | -0.168 |
Hots | -0.158 |
Subtle | -0.157 |
Token | Bill |
Token ID | 3941 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
Lauder | +0.200 |
Loving | +0.181 |
Sioux | +0.178 |
Hots | +0.166 |
Subtle | +0.165 |
Neg logit contributions | |
obar | -0.229 |
rane | -0.222 |
minist | -0.202 |
oba | -0.200 |
ega | -0.199 |
Token | Cassidy |
Token ID | 41373 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
Lauder | +0.869 |
Loving | +0.769 |
Sioux | +0.758 |
Hots | +0.712 |
Subtle | +0.699 |
Neg logit contributions | |
obar | -1.098 |
rane | -1.085 |
oba | -0.974 |
minist | -0.968 |
ega | -0.966 |
Token | baking |
Token ID | 16871 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
obar | +0.290 |
rane | +0.280 |
minist | +0.255 |
oba | +0.251 |
ega | +0.245 |
Neg logit contributions | |
Lauder | -0.326 |
Loving | -0.295 |
Sioux | -0.292 |
Hots | -0.276 |
Subtle | -0.272 |
Token | that |
Token ID | 326 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
Lauder | +0.275 |
Loving | +0.248 |
Sioux | +0.244 |
Hots | +0.228 |
Subtle | +0.223 |
Neg logit contributions | |
obar | -0.296 |
rane | -0.284 |
minist | -0.264 |
oba | -0.257 |
ega | -0.252 |
Token | also |
Token ID | 635 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
obar | +0.583 |
rane | +0.561 |
minist | +0.517 |
oba | +0.510 |
ega | +0.497 |
Neg logit contributions | |
Lauder | -0.508 |
Loving | -0.460 |
Sioux | -0.447 |
Hots | -0.419 |
Subtle | -0.410 |
Token | contains |
Token ID | 4909 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
obar | +0.878 |
rane | +0.855 |
minist | +0.782 |
oba | +0.776 |
ega | +0.765 |
Neg logit contributions | |
Lauder | -0.831 |
Loving | -0.748 |
Sioux | -0.728 |
Hots | -0.679 |
Subtle | -0.672 |
Token | baking |
Token ID | 16871 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
obar | +1.489 |
rane | +1.434 |
oba | +1.336 |
minist | +1.306 |
ega | +1.288 |
Neg logit contributions | |
Lauder | -1.318 |
Loving | -1.179 |
Sioux | -1.149 |
Hots | -1.085 |
Subtle | -1.051 |
Token | soda |
Token ID | 20584 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Lauder | +0.047 |
Loving | +0.042 |
Sioux | +0.041 |
Hots | +0.039 |
Sikh | +0.038 |
Neg logit contributions | |
obar | -0.049 |
rane | -0.047 |
oba | -0.043 |
minist | -0.043 |
ega | -0.041 |
Token | ( |
Token ID | 357 |
Feature activation | +7.17e-02 |
Pos logit contributions | |
obar | +2.685 |
rane | +2.570 |
oba | +2.377 |
minist | +2.371 |
ega | +2.320 |
Neg logit contributions | |
Lauder | -2.639 |
Loving | -2.339 |
Sioux | -2.329 |
Hots | -2.160 |
Sikh | -2.128 |
Token | it |
Token ID | 270 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
obar | +0.126 |
rane | +0.121 |
minist | +0.111 |
oba | +0.110 |
ega | +0.107 |
Neg logit contributions | |
Lauder | -0.128 |
Loving | -0.116 |
Sioux | -0.115 |
Hots | -0.107 |
Subtle | -0.106 |
Token | � |
Token ID | 447 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
Lauder | +0.061 |
Loving | +0.055 |
Sioux | +0.054 |
Hots | +0.050 |
Subtle | +0.049 |
Neg logit contributions | |
obar | -0.072 |
rane | -0.069 |
minist | -0.064 |
oba | -0.063 |
ega | -0.062 |
Token | � |
Token ID | 247 |
Feature activation | +9.58e-02 |
Pos logit contributions | |
Lauder | +0.305 |
Sioux | +0.279 |
Loving | +0.272 |
Hots | +0.258 |
Sikh | +0.251 |
Neg logit contributions | |
obar | -0.273 |
rane | -0.263 |
minist | -0.238 |
oba | -0.230 |
ega | -0.229 |
Token | s |
Token ID | 82 |
Feature activation | +8.96e-04 |
Pos logit contributions | |
obar | +0.182 |
rane | +0.179 |
minist | +0.167 |
oba | +0.162 |
ega | +0.161 |
Neg logit contributions | |
Lauder | -0.156 |
Loving | -0.136 |
Sioux | -0.135 |
Hots | -0.125 |
Subtle | -0.123 |
Token | panels |
Token ID | 13043 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
obar | +0.351 |
rane | +0.342 |
minist | +0.312 |
oba | +0.305 |
ega | +0.302 |
Neg logit contributions | |
Lauder | -0.321 |
Loving | -0.292 |
Sioux | -0.289 |
Subtle | -0.268 |
Hots | -0.266 |
Token | is |
Token ID | 318 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
obar | +1.252 |
rane | +1.214 |
minist | +1.102 |
oba | +1.097 |
ega | +1.089 |
Neg logit contributions | |
Lauder | -1.208 |
Loving | -1.093 |
Sioux | -1.078 |
Hots | -0.993 |
Subtle | -0.989 |
Token | composed |
Token ID | 13160 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
obar | +0.315 |
rane | +0.303 |
oba | +0.276 |
minist | +0.276 |
ega | +0.269 |
Neg logit contributions | |
Lauder | -0.250 |
Loving | -0.226 |
Sioux | -0.218 |
Subtle | -0.205 |
Hots | -0.203 |
Token | of |
Token ID | 286 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
obar | +0.130 |
rane | +0.127 |
minist | +0.119 |
oba | +0.116 |
ega | +0.115 |
Neg logit contributions | |
Lauder | -0.077 |
Loving | -0.067 |
Sioux | -0.066 |
Hots | -0.060 |
Sikh | -0.059 |
Token | combust |
Token ID | 27500 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
obar | +0.331 |
rane | +0.320 |
minist | +0.291 |
oba | +0.289 |
ega | +0.283 |
Neg logit contributions | |
Lauder | -0.296 |
Loving | -0.268 |
Sioux | -0.263 |
Hots | -0.247 |
Subtle | -0.245 |
Token | ible |
Token ID | 856 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Lauder | +0.998 |
Loving | +0.892 |
Sioux | +0.876 |
Hots | +0.806 |
Subtle | +0.799 |
Neg logit contributions | |
obar | -1.357 |
rane | -1.314 |
minist | -1.216 |
oba | -1.202 |
ega | -1.181 |
Token | plastic |
Token ID | 7309 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
obar | +2.561 |
rane | +2.477 |
oba | +2.203 |
minist | +2.165 |
ega | +2.133 |
Neg logit contributions | |
Lauder | -2.727 |
Loving | -2.461 |
Sioux | -2.362 |
Subtle | -2.306 |
Hots | -2.273 |
Token | material |
Token ID | 2587 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
obar | +0.760 |
rane | +0.734 |
oba | +0.659 |
minist | +0.653 |
ega | +0.652 |
Neg logit contributions | |
Lauder | -0.727 |
Loving | -0.650 |
Sioux | -0.644 |
Hots | -0.601 |
Subtle | -0.601 |
Token | . |
Token ID | 13 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
obar | +0.650 |
rane | +0.630 |
minist | +0.572 |
oba | +0.566 |
ega | +0.560 |
Neg logit contributions | |
Lauder | -0.613 |
Loving | -0.547 |
Sioux | -0.543 |
Hots | -0.501 |
Subtle | -0.501 |
Token | A |
Token ID | 317 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
obar | +0.323 |
rane | +0.310 |
minist | +0.285 |
oba | +0.284 |
ega | +0.276 |
Neg logit contributions | |
Lauder | -0.276 |
Loving | -0.248 |
Sioux | -0.245 |
Hots | -0.223 |
Sikh | -0.221 |
Token | sample |
Token ID | 6291 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
obar | +0.953 |
rane | +0.924 |
minist | +0.848 |
oba | +0.842 |
ega | +0.816 |
Neg logit contributions | |
Lauder | -0.866 |
Loving | -0.791 |
Sioux | -0.780 |
Subtle | -0.722 |
Hots | -0.720 |
Token | did |
Token ID | 750 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
Lauder | +0.134 |
Loving | +0.120 |
Sioux | +0.119 |
Hots | +0.111 |
Subtle | +0.111 |
Neg logit contributions | |
obar | -0.132 |
rane | -0.127 |
minist | -0.116 |
oba | -0.114 |
ega | -0.113 |
Token | not |
Token ID | 407 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
obar | +0.818 |
rane | +0.791 |
minist | +0.724 |
oba | +0.716 |
ega | +0.704 |
Neg logit contributions | |
Lauder | -0.814 |
Loving | -0.724 |
Sioux | -0.719 |
Hots | -0.672 |
Subtle | -0.665 |
Token | issue |
Token ID | 2071 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
Lauder | +0.062 |
Sioux | +0.055 |
Loving | +0.055 |
Hots | +0.051 |
Subtle | +0.051 |
Neg logit contributions | |
obar | -0.057 |
rane | -0.055 |
minist | -0.050 |
oba | -0.049 |
ega | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | -9.21e-03 |
Pos logit contributions | |
Lauder | +1.369 |
Loving | +1.220 |
Sioux | +1.213 |
Hots | +1.129 |
Subtle | +1.107 |
Neg logit contributions | |
obar | -1.676 |
rane | -1.626 |
minist | -1.503 |
oba | -1.475 |
ega | -1.449 |
Token | total |
Token ID | 2472 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
Lauder | +0.014 |
Sioux | +0.012 |
Loving | +0.012 |
Hots | +0.012 |
Subtle | +0.011 |
Neg logit contributions | |
obar | -0.018 |
rane | -0.017 |
minist | -0.016 |
oba | -0.016 |
ega | -0.015 |
Token | Loving |
Token ID | 39202 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
Lauder | +0.700 |
Sioux | +0.615 |
Loving | +0.613 |
Hots | +0.578 |
Subtle | +0.568 |
Neg logit contributions | |
obar | -0.799 |
rane | -0.776 |
minist | -0.714 |
oba | -0.705 |
ega | -0.686 |
Token | v |
Token ID | 410 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
Lauder | +3.637 |
Loving | +3.343 |
Sioux | +3.286 |
Hots | +3.037 |
Sikh | +2.964 |
Neg logit contributions | |
obar | -4.406 |
rane | -4.271 |
minist | -3.954 |
oba | -3.853 |
ega | -3.782 |
Token | . |
Token ID | 13 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
Lauder | +1.404 |
Loving | +1.238 |
Sioux | +1.233 |
Hots | +1.160 |
Subtle | +1.149 |
Neg logit contributions | |
obar | -1.450 |
rane | -1.403 |
minist | -1.284 |
oba | -1.262 |
ega | -1.236 |
Token | Virginia |
Token ID | 6025 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
Lauder | +0.180 |
Sioux | +0.148 |
Loving | +0.148 |
Hots | +0.132 |
Sikh | +0.129 |
Neg logit contributions | |
obar | -0.380 |
rane | -0.368 |
minist | -0.344 |
oba | -0.344 |
ega | -0.337 |
Token | victory |
Token ID | 5373 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Lauder | +0.163 |
Sioux | +0.142 |
Loving | +0.140 |
Hots | +0.134 |
Subtle | +0.134 |
Neg logit contributions | |
obar | -0.155 |
rane | -0.149 |
oba | -0.135 |
minist | -0.135 |
ega | -0.132 |
Token | that |
Token ID | 326 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
obar | +0.274 |
rane | +0.265 |
minist | +0.243 |
oba | +0.240 |
ega | +0.237 |
Neg logit contributions | |
Lauder | -0.269 |
Sioux | -0.237 |
Loving | -0.234 |
Hots | -0.223 |
Subtle | -0.222 |
Token | will |
Token ID | 481 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
obar | +0.473 |
rane | +0.455 |
minist | +0.420 |
ega | +0.409 |
oba | +0.408 |
Neg logit contributions | |
Lauder | -0.464 |
Loving | -0.416 |
Sioux | -0.411 |
Hots | -0.387 |
Subtle | -0.386 |
Token | be |
Token ID | 307 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Lauder | +0.205 |
Loving | +0.187 |
Sioux | +0.183 |
Hots | +0.172 |
Subtle | +0.171 |
Neg logit contributions | |
obar | -0.194 |
rane | -0.185 |
minist | -0.170 |
oba | -0.167 |
ega | -0.165 |
Token | the |
Token ID | 262 |
Feature activation | -9.71e-02 |
Pos logit contributions | |
Lauder | +0.278 |
Loving | +0.245 |
Sioux | +0.242 |
Subtle | +0.227 |
Hots | +0.226 |
Neg logit contributions | |
obar | -0.342 |
rane | -0.325 |
minist | -0.303 |
ega | -0.296 |
oba | -0.295 |
Token | equivalent |
Token ID | 7548 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
Lauder | +0.173 |
Loving | +0.155 |
Sioux | +0.154 |
Hots | +0.145 |
Subtle | +0.143 |
Neg logit contributions | |
obar | -0.168 |
rane | -0.161 |
minist | -0.148 |
oba | -0.144 |
ega | -0.142 |
Token | of |
Token ID | 286 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
Lauder | +0.803 |
Loving | +0.709 |
Sioux | +0.695 |
Hots | +0.620 |
Ku | +0.613 |
Neg logit contributions | |
obar | -1.440 |
rane | -1.409 |
minist | -1.318 |
oba | -1.298 |
ega | -1.269 |
Token | Loving |
Token ID | 39202 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Lauder | +0.037 |
Sioux | +0.033 |
Loving | +0.032 |
Hots | +0.030 |
Subtle | +0.030 |
Neg logit contributions | |
obar | -0.047 |
rane | -0.045 |
minist | -0.042 |
oba | -0.041 |
ega | -0.040 |
Token | v |
Token ID | 410 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
Lauder | +2.576 |
Loving | +2.298 |
Sioux | +2.229 |
Hots | +2.006 |
Sikh | +1.929 |
Neg logit contributions | |
obar | -5.114 |
rane | -5.008 |
minist | -4.698 |
oba | -4.604 |
ega | -4.527 |
Token | . |
Token ID | 13 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
Lauder | +1.595 |
Loving | +1.412 |
Sioux | +1.407 |
Hots | +1.320 |
Subtle | +1.299 |
Neg logit contributions | |
obar | -1.647 |
rane | -1.595 |
minist | -1.453 |
oba | -1.433 |
ega | -1.411 |
Token | Virginia |
Token ID | 6025 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Lauder | +0.277 |
Sioux | +0.228 |
Loving | +0.225 |
Hots | +0.208 |
Sikh | +0.201 |
Neg logit contributions | |
obar | -0.563 |
rane | -0.546 |
minist | -0.509 |
oba | -0.508 |
ega | -0.502 |
Token | , |
Token ID | 11 |
Feature activation | -7.90e-02 |
Pos logit contributions | |
Lauder | +0.189 |
Sioux | +0.166 |
Loving | +0.165 |
Subtle | +0.154 |
Hots | +0.154 |
Neg logit contributions | |
obar | -0.213 |
rane | -0.203 |
minist | -0.188 |
oba | -0.185 |
ega | -0.184 |
Token | which |
Token ID | 543 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
Lauder | +0.134 |
Sioux | +0.118 |
Loving | +0.116 |
Hots | +0.110 |
Subtle | +0.109 |
Neg logit contributions | |
obar | -0.146 |
rane | -0.138 |
minist | -0.126 |
oba | -0.124 |
ega | -0.124 |
Token | outright |
Token ID | 15828 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
Lauder | +0.076 |
Loving | +0.068 |
Sioux | +0.067 |
Hots | +0.063 |
Subtle | +0.062 |
Neg logit contributions | |
obar | -0.097 |
rane | -0.095 |
minist | -0.086 |
oba | -0.085 |
ega | -0.083 |
Token | ban |
Token ID | 3958 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
Lauder | +0.948 |
Loving | +0.861 |
Sioux | +0.849 |
Hots | +0.801 |
Subtle | +0.797 |
Neg logit contributions | |
obar | -0.961 |
rane | -0.940 |
minist | -0.857 |
oba | -0.846 |
ega | -0.825 |
Token | on |
Token ID | 319 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
Lauder | +0.692 |
Loving | +0.620 |
Sioux | +0.614 |
Hots | +0.571 |
Subtle | +0.562 |
Neg logit contributions | |
obar | -0.841 |
rane | -0.811 |
minist | -0.754 |
oba | -0.735 |
ega | -0.728 |
Token | wearing |
Token ID | 5762 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
Lauder | +0.029 |
Loving | +0.026 |
Sioux | +0.025 |
Hots | +0.024 |
Subtle | +0.024 |
Neg logit contributions | |
obar | -0.035 |
rane | -0.034 |
minist | -0.032 |
oba | -0.031 |
ega | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +9.33e-03 |
Pos logit contributions | |
Lauder | +0.792 |
Loving | +0.715 |
Sioux | +0.698 |
Hots | +0.653 |
Subtle | +0.648 |
Neg logit contributions | |
obar | -1.005 |
rane | -0.968 |
minist | -0.902 |
oba | -0.879 |
ega | -0.871 |
Token | hijab |
Token ID | 48492 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
obar | +0.022 |
rane | +0.021 |
minist | +0.020 |
oba | +0.020 |
ega | +0.020 |
Neg logit contributions | |
Lauder | -0.011 |
Loving | -0.009 |
Sioux | -0.009 |
Hots | -0.008 |
Subtle | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
Lauder | +2.983 |
Loving | +2.691 |
Sioux | +2.643 |
Hots | +2.458 |
Sikh | +2.431 |
Neg logit contributions | |
obar | -3.775 |
rane | -3.665 |
minist | -3.387 |
oba | -3.316 |
ega | -3.261 |
Token |
|
Token ID | 198 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
obar | +0.595 |
rane | +0.572 |
minist | +0.529 |
oba | +0.524 |
ega | +0.516 |
Neg logit contributions | |
Lauder | -0.526 |
Sioux | -0.469 |
Loving | -0.469 |
Hots | -0.434 |
Subtle | -0.426 |
Token |
|
Token ID | 198 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
obar | +0.632 |
rane | +0.606 |
minist | +0.558 |
oba | +0.551 |
ega | +0.539 |
Neg logit contributions | |
Lauder | -0.633 |
Sioux | -0.557 |
Loving | -0.555 |
Hots | -0.517 |
Subtle | -0.513 |
Token | Sad |
Token ID | 26699 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
obar | +0.510 |
rane | +0.490 |
minist | +0.449 |
oba | +0.436 |
ega | +0.425 |
Neg logit contributions | |
Lauder | -0.627 |
Loving | -0.574 |
Sioux | -0.570 |
Hots | -0.536 |
Subtle | -0.529 |
Token | ain |
Token ID | 391 |
Feature activation | +8.32e-02 |
Pos logit contributions | |
obar | +0.060 |
rane | +0.058 |
minist | +0.053 |
oba | +0.052 |
ega | +0.052 |
Neg logit contributions | |
Lauder | -0.061 |
Loving | -0.055 |
Sioux | -0.055 |
Hots | -0.052 |
Subtle | -0.051 |
Token | - |
Token ID | 12 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
Lauder | +0.414 |
Loving | +0.370 |
Sioux | +0.363 |
Hots | +0.333 |
Sikh | +0.327 |
Neg logit contributions | |
obar | -0.601 |
rane | -0.583 |
minist | -0.542 |
oba | -0.532 |
ega | -0.525 |
Token | w |
Token ID | 86 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
obar | +0.059 |
rane | +0.058 |
minist | +0.054 |
oba | +0.052 |
ega | +0.051 |
Neg logit contributions | |
Lauder | -0.063 |
Loving | -0.057 |
Sioux | -0.057 |
Hots | -0.054 |
Subtle | -0.052 |
Token | earing |
Token ID | 6648 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
obar | +0.672 |
rane | +0.649 |
minist | +0.606 |
oba | +0.595 |
ega | +0.585 |
Neg logit contributions | |
Lauder | -0.540 |
Loving | -0.476 |
Sioux | -0.468 |
Hots | -0.440 |
Subtle | -0.434 |
Token | of |
Token ID | 286 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
obar | +0.127 |
rane | +0.123 |
minist | +0.117 |
oba | +0.113 |
ega | +0.111 |
Neg logit contributions | |
Lauder | -0.091 |
Loving | -0.081 |
Sioux | -0.079 |
Hots | -0.074 |
Subtle | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
obar | +0.314 |
rane | +0.302 |
minist | +0.283 |
oba | +0.273 |
ega | +0.273 |
Neg logit contributions | |
Lauder | -0.252 |
Loving | -0.227 |
Sioux | -0.223 |
Hots | -0.208 |
Subtle | -0.204 |
Token | hijab |
Token ID | 48492 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
obar | +0.341 |
rane | +0.331 |
minist | +0.315 |
oba | +0.308 |
ega | +0.308 |
Neg logit contributions | |
Lauder | -0.145 |
Loving | -0.124 |
Sioux | -0.119 |
Hots | -0.106 |
Subtle | -0.103 |
Token | or |
Token ID | 393 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
Lauder | +2.736 |
Loving | +2.467 |
Sioux | +2.425 |
Hots | +2.256 |
Sikh | +2.216 |
Neg logit contributions | |
obar | -3.449 |
rane | -3.343 |
minist | -3.092 |
oba | -3.030 |
ega | -2.984 |
Token | veil |
Token ID | 30615 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
Lauder | +0.033 |
Loving | +0.029 |
Sioux | +0.029 |
Hots | +0.026 |
Subtle | +0.026 |
Neg logit contributions | |
obar | -0.044 |
rane | -0.043 |
minist | -0.040 |
oba | -0.039 |
ega | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
Lauder | +0.940 |
Loving | +0.843 |
Sioux | +0.837 |
Hots | +0.776 |
Subtle | +0.759 |
Neg logit contributions | |
obar | -1.089 |
rane | -1.052 |
minist | -0.974 |
oba | -0.952 |
ega | -0.938 |
Token | � |
Token ID | 447 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
obar | +0.458 |
rane | +0.442 |
minist | +0.410 |
oba | +0.399 |
ega | +0.389 |
Neg logit contributions | |
Lauder | -0.408 |
Sioux | -0.363 |
Loving | -0.361 |
Hots | -0.338 |
Subtle | -0.329 |
Token | � |
Token ID | 251 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Lauder | +0.146 |
Loving | +0.131 |
Sioux | +0.130 |
Hots | +0.120 |
Sikh | +0.118 |
Neg logit contributions | |
obar | -0.171 |
rane | -0.164 |
minist | -0.151 |
oba | -0.149 |
ega | -0.146 |
Token | acing |
Token ID | 4092 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
obar | +0.303 |
rane | +0.289 |
minist | +0.258 |
oba | +0.250 |
ega | +0.244 |
Neg logit contributions | |
Lauder | -0.488 |
Loving | -0.453 |
Sioux | -0.448 |
Hots | -0.426 |
Subtle | -0.420 |
Token | inter |
Token ID | 987 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
Lauder | +0.055 |
Loving | +0.050 |
Sioux | +0.049 |
Hots | +0.046 |
Subtle | +0.045 |
Neg logit contributions | |
obar | -0.061 |
rane | -0.059 |
minist | -0.054 |
oba | -0.053 |
ega | -0.053 |
Token | p |
Token ID | 279 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
Lauder | +0.363 |
Loving | +0.327 |
Sioux | +0.324 |
Hots | +0.303 |
Sikh | +0.297 |
Neg logit contributions | |
obar | -0.383 |
rane | -0.375 |
minist | -0.349 |
oba | -0.333 |
ega | -0.330 |
Token | ares |
Token ID | 3565 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
obar | +0.802 |
rane | +0.770 |
minist | +0.707 |
oba | +0.699 |
ega | +0.691 |
Neg logit contributions | |
Lauder | -0.647 |
Loving | -0.576 |
Sioux | -0.573 |
Hots | -0.530 |
Sikh | -0.525 |
Token | and |
Token ID | 290 |
Feature activation | -2.05e-03 |
Pos logit contributions | |
Lauder | +0.440 |
Loving | +0.403 |
Sioux | +0.399 |
Hots | +0.374 |
Sikh | +0.368 |
Neg logit contributions | |
obar | -0.390 |
rane | -0.377 |
minist | -0.346 |
oba | -0.334 |
ega | -0.329 |
Token | supra |
Token ID | 28614 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Lauder | +0.003 |
Loving | +0.003 |
Sioux | +0.003 |
Hots | +0.003 |
Subtle | +0.003 |
Neg logit contributions | |
obar | -0.004 |
rane | -0.004 |
minist | -0.004 |
oba | -0.003 |
ega | -0.003 |
Token | - |
Token ID | 12 |
Feature activation | +3.95e-02 |
Pos logit contributions | |
Lauder | +2.723 |
Loving | +2.445 |
Sioux | +2.409 |
Hots | +2.232 |
Subtle | +2.184 |
Neg logit contributions | |
obar | -3.474 |
rane | -3.369 |
minist | -3.121 |
oba | -3.057 |
ega | -3.013 |
Token | national |
Token ID | 14648 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
obar | +0.071 |
rane | +0.069 |
minist | +0.064 |
oba | +0.062 |
ega | +0.061 |
Neg logit contributions | |
Lauder | -0.068 |
Loving | -0.061 |
Sioux | -0.061 |
Hots | -0.057 |
Subtle | -0.056 |
Token | nature |
Token ID | 3450 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
Lauder | +0.697 |
Loving | +0.631 |
Sioux | +0.621 |
Hots | +0.576 |
Subtle | +0.568 |
Neg logit contributions | |
obar | -0.833 |
rane | -0.807 |
minist | -0.748 |
oba | -0.730 |
ega | -0.722 |
Token | of |
Token ID | 286 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
obar | +0.699 |
rane | +0.679 |
minist | +0.634 |
oba | +0.623 |
ega | +0.615 |
Neg logit contributions | |
Lauder | -0.427 |
Loving | -0.377 |
Sioux | -0.370 |
Hots | -0.338 |
Subtle | -0.329 |
Token | the |
Token ID | 262 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
obar | +0.049 |
rane | +0.047 |
minist | +0.044 |
oba | +0.043 |
ega | +0.042 |
Neg logit contributions | |
Lauder | -0.041 |
Loving | -0.037 |
Sioux | -0.037 |
Hots | -0.034 |
Subtle | -0.034 |
Token | trip |
Token ID | 5296 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
Lauder | +0.544 |
Loving | +0.486 |
Sioux | +0.481 |
Hots | +0.445 |
Subtle | +0.440 |
Neg logit contributions | |
obar | -0.645 |
rane | -0.618 |
minist | -0.578 |
oba | -0.562 |
ega | -0.556 |
Token | worsh |
Token ID | 26511 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Lauder | +0.175 |
Loving | +0.156 |
Sioux | +0.154 |
Hots | +0.144 |
Subtle | +0.141 |
Neg logit contributions | |
obar | -0.205 |
rane | -0.197 |
minist | -0.185 |
oba | -0.179 |
ega | -0.177 |
Token | ipping |
Token ID | 4501 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
Lauder | +2.937 |
Loving | +2.720 |
Sioux | +2.683 |
Hots | +2.533 |
Sikh | +2.487 |
Neg logit contributions | |
obar | -2.351 |
rane | -2.268 |
minist | -2.028 |
oba | -1.998 |
ega | -1.970 |
Token | Lenin |
Token ID | 22899 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
Lauder | +0.889 |
Loving | +0.793 |
Sioux | +0.780 |
Hots | +0.726 |
Subtle | +0.712 |
Neg logit contributions | |
obar | -1.108 |
rane | -1.071 |
minist | -1.000 |
oba | -0.971 |
ega | -0.956 |
Token | and |
Token ID | 290 |
Feature activation | +9.34e-02 |
Pos logit contributions | |
Lauder | +1.028 |
Loving | +0.923 |
Sioux | +0.908 |
Hots | +0.838 |
Subtle | +0.828 |
Neg logit contributions | |
obar | -1.287 |
rane | -1.243 |
minist | -1.156 |
oba | -1.131 |
ega | -1.113 |
Token | Trotsky |
Token ID | 32706 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
obar | +0.195 |
rane | +0.189 |
minist | +0.178 |
oba | +0.173 |
ega | +0.170 |
Neg logit contributions | |
Lauder | -0.131 |
Loving | -0.114 |
Sioux | -0.113 |
Subtle | -0.104 |
Hots | -0.104 |
Token | , |
Token ID | 11 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
Lauder | +2.484 |
Loving | +2.208 |
Sioux | +2.175 |
Hots | +2.006 |
Subtle | +1.948 |
Neg logit contributions | |
obar | -3.676 |
rane | -3.575 |
minist | -3.319 |
oba | -3.259 |
ega | -3.219 |
Token | around |
Token ID | 1088 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
obar | +0.411 |
rane | +0.393 |
minist | +0.369 |
oba | +0.356 |
ega | +0.350 |
Neg logit contributions | |
Lauder | -0.339 |
Loving | -0.302 |
Sioux | -0.298 |
Hots | -0.276 |
Subtle | -0.276 |
Token | whom |
Token ID | 4150 |
Feature activation | +7.80e-02 |
Pos logit contributions | |
Lauder | +0.694 |
Loving | +0.625 |
Sioux | +0.616 |
Hots | +0.575 |
Subtle | +0.566 |
Neg logit contributions | |
obar | -0.794 |
rane | -0.767 |
minist | -0.711 |
oba | -0.691 |
ega | -0.678 |
Token | all |
Token ID | 477 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
obar | +0.152 |
rane | +0.148 |
minist | +0.138 |
oba | +0.134 |
ega | +0.131 |
Neg logit contributions | |
Lauder | -0.120 |
Loving | -0.107 |
Sioux | -0.105 |
Hots | -0.098 |
Subtle | -0.097 |
Token | history |
Token ID | 2106 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
obar | +0.516 |
rane | +0.503 |
minist | +0.467 |
oba | +0.455 |
ega | +0.442 |
Neg logit contributions | |
Lauder | -0.444 |
Loving | -0.396 |
Sioux | -0.391 |
Hots | -0.365 |
Subtle | -0.356 |
Token | intellig |
Token ID | 10878 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
Lauder | +0.528 |
Loving | +0.477 |
Sioux | +0.464 |
Hots | +0.430 |
Subtle | +0.426 |
Neg logit contributions | |
obar | -0.657 |
rane | -0.637 |
minist | -0.596 |
oba | -0.581 |
ega | -0.571 |
Token | ents |
Token ID | 658 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
Lauder | +0.832 |
Loving | +0.738 |
Sioux | +0.724 |
Hots | +0.662 |
Subtle | +0.646 |
Neg logit contributions | |
obar | -1.324 |
rane | -1.288 |
minist | -1.203 |
oba | -1.180 |
ega | -1.164 |
Token | ia |
Token ID | 544 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
obar | +0.016 |
rane | +0.016 |
minist | +0.014 |
oba | +0.013 |
ega | +0.013 |
Neg logit contributions | |
Lauder | -0.025 |
Loving | -0.023 |
Sioux | -0.022 |
Hots | -0.021 |
Subtle | -0.021 |
Token | resisted |
Token ID | 26643 |
Feature activation | -9.74e-02 |
Pos logit contributions | |
Lauder | +0.243 |
Loving | +0.220 |
Sioux | +0.214 |
Hots | +0.199 |
Subtle | +0.197 |
Neg logit contributions | |
obar | -0.307 |
rane | -0.298 |
minist | -0.277 |
oba | -0.270 |
ega | -0.267 |
Token | en |
Token ID | 551 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
Lauder | +0.158 |
Loving | +0.143 |
Sioux | +0.141 |
Hots | +0.131 |
Subtle | +0.128 |
Neg logit contributions | |
obar | -0.185 |
rane | -0.179 |
minist | -0.167 |
oba | -0.162 |
ega | -0.160 |
Token | masse |
Token ID | 41869 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
obar | +0.057 |
rane | +0.056 |
minist | +0.051 |
oba | +0.050 |
ega | +0.049 |
Neg logit contributions | |
Lauder | -0.054 |
Loving | -0.049 |
Sioux | -0.049 |
Hots | -0.046 |
Subtle | -0.045 |
Token | letting |
Token ID | 9616 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
Lauder | +2.749 |
Loving | +2.476 |
Sioux | +2.440 |
Hots | +2.268 |
Subtle | +2.218 |
Neg logit contributions | |
obar | -3.372 |
rane | -3.273 |
minist | -3.019 |
oba | -2.962 |
ega | -2.917 |
Token | itself |
Token ID | 2346 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
obar | +1.084 |
rane | +1.046 |
minist | +0.962 |
oba | +0.945 |
ega | +0.918 |
Neg logit contributions | |
Lauder | -1.062 |
Loving | -0.974 |
Sioux | -0.959 |
Hots | -0.894 |
Subtle | -0.879 |
Token | be |
Token ID | 307 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
obar | +0.361 |
rane | +0.347 |
minist | +0.317 |
oba | +0.314 |
ega | +0.309 |
Neg logit contributions | |
Lauder | -0.380 |
Loving | -0.348 |
Sioux | -0.341 |
Hots | -0.319 |
Subtle | -0.317 |
Token | travers |
Token ID | 33038 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
Lauder | +0.246 |
Loving | +0.222 |
Sioux | +0.218 |
Hots | +0.201 |
Subtle | +0.199 |
Neg logit contributions | |
obar | -0.300 |
rane | -0.286 |
minist | -0.265 |
oba | -0.263 |
ega | -0.259 |
Token | ed |
Token ID | 276 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
obar | +1.127 |
rane | +1.077 |
minist | +0.971 |
oba | +0.925 |
ega | +0.908 |
Neg logit contributions | |
Lauder | -1.790 |
Loving | -1.643 |
Sioux | -1.631 |
Hots | -1.558 |
Subtle | -1.534 |
Token | its |
Token ID | 663 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Lauder | +0.450 |
Loving | +0.409 |
Sioux | +0.403 |
Hots | +0.376 |
Subtle | +0.370 |
Neg logit contributions | |
obar | -0.457 |
rane | -0.442 |
minist | -0.407 |
oba | -0.397 |
ega | -0.389 |
Token | national |
Token ID | 2260 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
Lauder | +0.288 |
Loving | +0.261 |
Sioux | +0.257 |
Hots | +0.239 |
Subtle | +0.235 |
Neg logit contributions | |
obar | -0.302 |
rane | -0.293 |
minist | -0.269 |
oba | -0.264 |
ega | -0.257 |
Token | debt |
Token ID | 5057 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Lauder | +0.136 |
Loving | +0.123 |
Sioux | +0.121 |
Hots | +0.113 |
Subtle | +0.111 |
Neg logit contributions | |
obar | -0.150 |
rane | -0.146 |
minist | -0.134 |
oba | -0.131 |
ega | -0.129 |
Token | to |
Token ID | 284 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
Lauder | +0.359 |
Loving | +0.326 |
Sioux | +0.319 |
Hots | +0.295 |
Subtle | +0.291 |
Neg logit contributions | |
obar | -0.422 |
rane | -0.406 |
minist | -0.379 |
oba | -0.370 |
ega | -0.363 |
Token | a |
Token ID | 257 |
Feature activation | -7.57e-02 |
Pos logit contributions | |
Lauder | +0.051 |
Loving | +0.046 |
Sioux | +0.045 |
Hots | +0.042 |
Subtle | +0.041 |
Neg logit contributions | |
obar | -0.053 |
rane | -0.052 |
minist | -0.047 |
oba | -0.047 |
ega | -0.046 |
Token | level |
Token ID | 1241 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Lauder | +0.131 |
Loving | +0.119 |
Sioux | +0.117 |
Hots | +0.109 |
Subtle | +0.107 |
Neg logit contributions | |
obar | -0.135 |
rane | -0.131 |
minist | -0.119 |
oba | -0.119 |
ega | -0.115 |
Token | that |
Token ID | 326 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
Lauder | +2.813 |
Loving | +2.539 |
Sioux | +2.503 |
Hots | +2.327 |
Subtle | +2.281 |
Neg logit contributions | |
obar | -3.315 |
rane | -3.210 |
minist | -2.965 |
oba | -2.904 |
ega | -2.858 |
Token | the |
Token ID | 262 |
Feature activation | -8.23e-02 |
Pos logit contributions | |
obar | +0.378 |
rane | +0.364 |
minist | +0.335 |
oba | +0.326 |
ega | +0.322 |
Neg logit contributions | |
Lauder | -0.352 |
Loving | -0.321 |
Sioux | -0.309 |
Subtle | -0.291 |
Hots | -0.286 |
Token | market |
Token ID | 1910 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
Lauder | +0.139 |
Loving | +0.126 |
Sioux | +0.124 |
Hots | +0.116 |
Subtle | +0.114 |
Neg logit contributions | |
obar | -0.150 |
rane | -0.146 |
minist | -0.134 |
oba | -0.131 |
ega | -0.128 |
Token | thinks |
Token ID | 6834 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
obar | +0.706 |
rane | +0.682 |
minist | +0.627 |
ega | +0.613 |
oba | +0.606 |
Neg logit contributions | |
Lauder | -0.618 |
Loving | -0.560 |
Sioux | -0.542 |
Subtle | -0.515 |
Hots | -0.506 |
Token | is |
Token ID | 318 |
Feature activation | -3.95e-03 |
Pos logit contributions | |
Lauder | +0.384 |
Loving | +0.348 |
Sioux | +0.340 |
Hots | +0.315 |
Subtle | +0.313 |
Neg logit contributions | |
obar | -0.429 |
rane | -0.417 |
minist | -0.384 |
oba | -0.375 |
ega | -0.370 |
Token | making |
Token ID | 8601 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
obar | +0.112 |
rane | +0.109 |
minist | +0.103 |
oba | +0.101 |
ega | +0.100 |
Neg logit contributions | |
Lauder | -0.064 |
Loving | -0.055 |
Sioux | -0.054 |
Hots | -0.050 |
Subtle | -0.049 |
Token | at |
Token ID | 379 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Lauder | +0.675 |
Loving | +0.607 |
Sioux | +0.598 |
Hots | +0.558 |
Subtle | +0.547 |
Neg logit contributions | |
obar | -0.767 |
rane | -0.743 |
minist | -0.691 |
oba | -0.671 |
ega | -0.662 |
Token | the |
Token ID | 262 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
obar | +0.347 |
rane | +0.335 |
minist | +0.312 |
oba | +0.302 |
ega | +0.297 |
Neg logit contributions | |
Lauder | -0.312 |
Loving | -0.276 |
Sioux | -0.274 |
Hots | -0.256 |
Sikh | -0.250 |
Token | state |
Token ID | 1181 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
Lauder | +0.055 |
Loving | +0.049 |
Sioux | +0.048 |
Hots | +0.045 |
Subtle | +0.045 |
Neg logit contributions | |
obar | -0.057 |
rane | -0.056 |
minist | -0.052 |
oba | -0.050 |
ega | -0.049 |
Token | court |
Token ID | 2184 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
Lauder | +0.351 |
Loving | +0.317 |
Sioux | +0.313 |
Hots | +0.294 |
Subtle | +0.291 |
Neg logit contributions | |
obar | -0.359 |
rane | -0.346 |
minist | -0.319 |
oba | -0.310 |
ega | -0.306 |
Token | level |
Token ID | 1241 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
obar | +0.507 |
rane | +0.485 |
minist | +0.443 |
oba | +0.425 |
ega | +0.419 |
Neg logit contributions | |
Lauder | -0.642 |
Loving | -0.594 |
Sioux | -0.580 |
Hots | -0.551 |
Subtle | -0.545 |
Token | , |
Token ID | 11 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
Lauder | +2.682 |
Loving | +2.427 |
Sioux | +2.393 |
Hots | +2.225 |
Sikh | +2.178 |
Neg logit contributions | |
obar | -3.249 |
rane | -3.150 |
minist | -2.899 |
oba | -2.854 |
ega | -2.806 |
Token | where |
Token ID | 810 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
obar | +0.053 |
rane | +0.051 |
minist | +0.047 |
oba | +0.046 |
ega | +0.046 |
Neg logit contributions | |
Lauder | -0.049 |
Loving | -0.044 |
Sioux | -0.043 |
Hots | -0.040 |
Subtle | -0.040 |
Token | 95 |
Token ID | 6957 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
obar | +0.480 |
rane | +0.465 |
minist | +0.428 |
oba | +0.415 |
ega | +0.409 |
Neg logit contributions | |
Lauder | -0.486 |
Loving | -0.440 |
Sioux | -0.433 |
Hots | -0.412 |
Subtle | -0.402 |
Token | percent |
Token ID | 1411 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
obar | +0.618 |
rane | +0.598 |
minist | +0.553 |
oba | +0.540 |
ega | +0.531 |
Neg logit contributions | |
Lauder | -0.510 |
Loving | -0.451 |
Sioux | -0.443 |
Hots | -0.419 |
Subtle | -0.410 |
Token | of |
Token ID | 286 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
obar | +0.475 |
rane | +0.461 |
minist | +0.431 |
oba | +0.424 |
ega | +0.418 |
Neg logit contributions | |
Lauder | -0.282 |
Loving | -0.248 |
Sioux | -0.245 |
Hots | -0.222 |
Sikh | -0.216 |
Token | M |
Token ID | 337 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
Lauder | +0.196 |
Loving | +0.172 |
Sioux | +0.169 |
Hots | +0.157 |
Subtle | +0.155 |
Neg logit contributions | |
obar | -0.272 |
rane | -0.266 |
minist | -0.247 |
oba | -0.244 |
ega | -0.235 |
Token | akh |
Token ID | 11322 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
Lauder | +0.839 |
Loving | +0.761 |
Sioux | +0.751 |
Hots | +0.716 |
Subtle | +0.713 |
Neg logit contributions | |
obar | -0.707 |
rane | -0.678 |
minist | -0.614 |
oba | -0.611 |
ega | -0.587 |
Token | nov |
Token ID | 37302 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Lauder | +0.053 |
Loving | +0.048 |
Sioux | +0.048 |
Hots | +0.045 |
Subtle | +0.044 |
Neg logit contributions | |
obar | -0.055 |
rane | -0.053 |
minist | -0.049 |
oba | -0.048 |
ega | -0.047 |
Token | ists |
Token ID | 1023 |
Feature activation | -5.67e-02 |
Pos logit contributions | |
Lauder | +1.491 |
Loving | +1.301 |
Sioux | +1.278 |
Hots | +1.154 |
Subtle | +1.121 |
Neg logit contributions | |
obar | -2.782 |
rane | -2.709 |
minist | -2.536 |
oba | -2.495 |
ega | -2.465 |
Token | , |
Token ID | 11 |
Feature activation | -4.93e-03 |
Pos logit contributions | |
Lauder | +0.091 |
Loving | +0.082 |
Sioux | +0.081 |
Hots | +0.075 |
Subtle | +0.074 |
Neg logit contributions | |
obar | -0.108 |
rane | -0.105 |
minist | -0.097 |
oba | -0.095 |
ega | -0.094 |
Token | Trotsky |
Token ID | 32706 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Lauder | +0.008 |
Loving | +0.007 |
Sioux | +0.007 |
Hots | +0.006 |
Subtle | +0.006 |
Neg logit contributions | |
obar | -0.010 |
rane | -0.009 |
minist | -0.009 |
oba | -0.008 |
ega | -0.008 |
Token | ists |
Token ID | 1023 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
Lauder | +2.574 |
Loving | +2.307 |
Sioux | +2.274 |
Hots | +2.106 |
Subtle | +2.057 |
Neg logit contributions | |
obar | -3.374 |
rane | -3.274 |
minist | -3.032 |
oba | -2.976 |
ega | -2.932 |
Token | par |
Token ID | 1582 |
Feature activation | -7.71e-02 |
Pos logit contributions | |
Lauder | +0.081 |
Loving | +0.073 |
Sioux | +0.072 |
Hots | +0.067 |
Subtle | +0.066 |
Neg logit contributions | |
obar | -0.087 |
rane | -0.084 |
minist | -0.078 |
oba | -0.076 |
ega | -0.075 |
Token | rot |
Token ID | 10599 |
Feature activation | +9.98e-02 |
Pos logit contributions | |
Lauder | +0.170 |
Loving | +0.158 |
Sioux | +0.157 |
Hots | +0.149 |
Subtle | +0.147 |
Neg logit contributions | |
obar | -0.101 |
rane | -0.096 |
minist | -0.085 |
oba | -0.083 |
ega | -0.081 |
Token | the |
Token ID | 262 |
Feature activation | +6.41e-03 |
Pos logit contributions | |
obar | +0.192 |
rane | +0.186 |
minist | +0.175 |
oba | +0.169 |
ega | +0.166 |
Neg logit contributions | |
Lauder | -0.158 |
Loving | -0.142 |
Sioux | -0.139 |
Hots | -0.129 |
Subtle | -0.127 |
Token | line |
Token ID | 1627 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
obar | +0.012 |
rane | +0.012 |
minist | +0.011 |
oba | +0.011 |
ega | +0.011 |
Neg logit contributions | |
Lauder | -0.010 |
Loving | -0.009 |
Sioux | -0.009 |
Hots | -0.008 |
Subtle | -0.008 |
Token | Nigel |
Token ID | 28772 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
obar | +1.229 |
rane | +1.190 |
minist | +1.086 |
oba | +1.084 |
ega | +1.071 |
Neg logit contributions | |
Lauder | -1.015 |
Loving | -0.900 |
Sioux | -0.889 |
Hots | -0.823 |
Subtle | -0.812 |
Token | Farage |
Token ID | 33904 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
obar | +0.523 |
rane | +0.505 |
minist | +0.444 |
oba | +0.437 |
ega | +0.428 |
Neg logit contributions | |
Lauder | -0.708 |
Loving | -0.648 |
Sioux | -0.645 |
Hots | -0.611 |
Subtle | -0.607 |
Token | : |
Token ID | 25 |
Feature activation | -8.62e-02 |
Pos logit contributions | |
Lauder | +0.345 |
Loving | +0.311 |
Sioux | +0.308 |
Subtle | +0.284 |
Hots | +0.284 |
Neg logit contributions | |
obar | -0.395 |
rane | -0.384 |
minist | -0.352 |
oba | -0.345 |
ega | -0.344 |
Token | " |
Token ID | 366 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
Lauder | +0.097 |
Loving | +0.083 |
Sioux | +0.082 |
Hots | +0.073 |
Subtle | +0.070 |
Neg logit contributions | |
obar | -0.205 |
rane | -0.200 |
minist | -0.187 |
oba | -0.185 |
ega | -0.183 |
Token | Lord |
Token ID | 22438 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
Lauder | +0.577 |
Loving | +0.527 |
Sioux | +0.523 |
Hots | +0.491 |
Subtle | +0.484 |
Neg logit contributions | |
obar | -0.477 |
rane | -0.460 |
minist | -0.420 |
oba | -0.408 |
ega | -0.399 |
Token | Hes |
Token ID | 44773 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Lauder | +0.911 |
Loving | +0.824 |
Sioux | +0.815 |
Hots | +0.755 |
Subtle | +0.746 |
Neg logit contributions | |
obar | -1.072 |
rane | -1.046 |
minist | -0.956 |
oba | -0.943 |
ega | -0.936 |
Token | elt |
Token ID | 2120 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
Lauder | +2.292 |
Loving | +2.054 |
Sioux | +1.981 |
Hots | +1.852 |
Sikh | +1.790 |
Neg logit contributions | |
obar | -3.561 |
rane | -3.471 |
minist | -3.248 |
oba | -3.164 |
ega | -3.111 |
Token | ine |
Token ID | 500 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Lauder | +1.103 |
Loving | +0.999 |
Sioux | +0.992 |
Hots | +0.926 |
Subtle | +0.909 |
Neg logit contributions | |
obar | -1.382 |
rane | -1.359 |
minist | -1.240 |
oba | -1.215 |
ega | -1.206 |
Token | fears |
Token ID | 10251 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Lauder | +0.255 |
Loving | +0.230 |
Sioux | +0.228 |
Hots | +0.210 |
Subtle | +0.209 |
Neg logit contributions | |
obar | -0.296 |
rane | -0.287 |
minist | -0.265 |
oba | -0.259 |
ega | -0.258 |
Token | what |
Token ID | 644 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
Lauder | +0.375 |
Loving | +0.339 |
Sioux | +0.334 |
Hots | +0.308 |
Subtle | +0.305 |
Neg logit contributions | |
obar | -0.461 |
rane | -0.448 |
minist | -0.413 |
oba | -0.403 |
ega | -0.400 |
Token | the |
Token ID | 262 |
Feature activation | -7.78e-02 |
Pos logit contributions | |
Lauder | +0.936 |
Loving | +0.847 |
Sioux | +0.834 |
Hots | +0.776 |
Subtle | +0.767 |
Neg logit contributions | |
obar | -1.072 |
rane | -1.039 |
minist | -0.955 |
oba | -0.935 |
ega | -0.923 |
Token | 47 |
Token ID | 2857 |
Feature activation | +6.62e-02 |
Pos logit contributions | |
Lauder | +0.301 |
Loving | +0.267 |
Sioux | +0.262 |
Hots | +0.240 |
Subtle | +0.234 |
Neg logit contributions | |
obar | -0.473 |
rane | -0.459 |
minist | -0.429 |
oba | -0.421 |
ega | -0.415 |
Token | ] |
Token ID | 60 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
obar | +0.112 |
rane | +0.108 |
minist | +0.098 |
oba | +0.096 |
ega | +0.095 |
Neg logit contributions | |
Lauder | -0.122 |
Sioux | -0.109 |
Loving | -0.109 |
Hots | -0.101 |
Subtle | -0.101 |
Token | < |
Token ID | 1279 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
obar | +0.701 |
rane | +0.683 |
minist | +0.634 |
oba | +0.623 |
ega | +0.614 |
Neg logit contributions | |
Lauder | -0.488 |
Loving | -0.435 |
Sioux | -0.428 |
Hots | -0.394 |
Subtle | -0.385 |
Token | k |
Token ID | 74 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
obar | +1.372 |
rane | +1.323 |
minist | +1.224 |
oba | +1.187 |
ega | +1.159 |
Neg logit contributions | |
Lauder | -1.406 |
Loving | -1.280 |
Sioux | -1.267 |
Hots | -1.183 |
Subtle | -1.164 |
Token | link |
Token ID | 8726 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
obar | +0.101 |
rane | +0.097 |
minist | +0.089 |
oba | +0.087 |
ega | +0.085 |
Neg logit contributions | |
Lauder | -0.110 |
Loving | -0.101 |
Sioux | -0.100 |
Hots | -0.093 |
Subtle | -0.092 |
Token | ttp |
Token ID | 29281 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
obar | +0.696 |
rane | +0.672 |
minist | +0.618 |
oba | +0.607 |
ega | +0.596 |
Neg logit contributions | |
Lauder | -0.675 |
Loving | -0.609 |
Sioux | -0.606 |
Hots | -0.563 |
Sikh | -0.555 |
Token | > |
Token ID | 29 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Lauder | +2.709 |
Loving | +2.469 |
Sioux | +2.418 |
Hots | +2.266 |
Subtle | +2.222 |
Neg logit contributions | |
obar | -3.128 |
rane | -3.036 |
minist | -2.792 |
oba | -2.729 |
ega | -2.683 |
Token | lol |
Token ID | 19462 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
Lauder | +0.223 |
Loving | +0.200 |
Sioux | +0.199 |
Hots | +0.184 |
Subtle | +0.181 |
Neg logit contributions | |
obar | -0.243 |
rane | -0.234 |
minist | -0.216 |
oba | -0.212 |
ega | -0.208 |
Token | m |
Token ID | 285 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Lauder | +0.519 |
Loving | +0.470 |
Sioux | +0.464 |
Hots | +0.433 |
Subtle | +0.425 |
Neg logit contributions | |
obar | -0.562 |
rane | -0.544 |
minist | -0.501 |
oba | -0.490 |
ega | -0.482 |
Token | 2 |
Token ID | 17 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
obar | +0.237 |
rane | +0.229 |
minist | +0.210 |
oba | +0.208 |
ega | +0.203 |
Neg logit contributions | |
Lauder | -0.212 |
Sioux | -0.191 |
Loving | -0.191 |
Hots | -0.175 |
Subtle | -0.174 |
Token | k |
Token ID | 74 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
obar | +0.069 |
rane | +0.068 |
minist | +0.063 |
oba | +0.063 |
ega | +0.061 |
Neg logit contributions | |
Lauder | -0.041 |
Sioux | -0.035 |
Loving | -0.035 |
Hots | -0.031 |
Subtle | -0.031 |
Token | talk |
Token ID | 1561 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
Lauder | +0.320 |
Loving | +0.293 |
Sioux | +0.290 |
Hots | +0.274 |
Subtle | +0.270 |
Neg logit contributions | |
obar | -0.268 |
rane | -0.261 |
minist | -0.237 |
oba | -0.229 |
ega | -0.226 |
Token | about |
Token ID | 546 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
obar | +0.038 |
rane | +0.037 |
minist | +0.034 |
oba | +0.033 |
ega | +0.033 |
Neg logit contributions | |
Lauder | -0.027 |
Loving | -0.024 |
Sioux | -0.024 |
Hots | -0.022 |
Subtle | -0.022 |
Token | � |
Token ID | 564 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
Lauder | +0.460 |
Loving | +0.415 |
Sioux | +0.412 |
Hots | +0.380 |
Subtle | +0.376 |
Neg logit contributions | |
obar | -0.524 |
rane | -0.509 |
minist | -0.470 |
oba | -0.457 |
ega | -0.452 |
Token | � |
Token ID | 246 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Lauder | +0.086 |
Sioux | +0.079 |
Loving | +0.078 |
Hots | +0.072 |
Subtle | +0.072 |
Neg logit contributions | |
obar | -0.084 |
rane | -0.081 |
minist | -0.074 |
oba | -0.072 |
ega | -0.070 |
Token | pass |
Token ID | 6603 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
obar | +0.217 |
rane | +0.210 |
minist | +0.195 |
oba | +0.189 |
ega | +0.185 |
Neg logit contributions | |
Lauder | -0.217 |
Loving | -0.197 |
Sioux | -0.196 |
Hots | -0.182 |
Subtle | -0.180 |
Token | porting |
Token ID | 26527 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
obar | +0.378 |
rane | +0.363 |
minist | +0.335 |
oba | +0.329 |
ega | +0.324 |
Neg logit contributions | |
Lauder | -0.376 |
Loving | -0.339 |
Sioux | -0.338 |
Hots | -0.316 |
Subtle | -0.311 |
Token | � |
Token ID | 447 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
Lauder | +2.570 |
Loving | +2.310 |
Sioux | +2.268 |
Hots | +2.111 |
Sikh | +2.074 |
Neg logit contributions | |
obar | -3.276 |
rane | -3.185 |
minist | -2.930 |
oba | -2.886 |
ega | -2.840 |
Token | � |
Token ID | 247 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
Lauder | +0.126 |
Loving | +0.114 |
Sioux | +0.113 |
Hots | +0.104 |
Subtle | +0.103 |
Neg logit contributions | |
obar | -0.127 |
rane | -0.122 |
minist | -0.112 |
oba | -0.110 |
ega | -0.108 |
Token | of |
Token ID | 286 |
Feature activation | -7.44e-02 |
Pos logit contributions | |
Lauder | +0.179 |
Loving | +0.161 |
Sioux | +0.159 |
Hots | +0.148 |
Subtle | +0.146 |
Neg logit contributions | |
obar | -0.198 |
rane | -0.192 |
minist | -0.178 |
oba | -0.173 |
ega | -0.170 |
Token | the |
Token ID | 262 |
Feature activation | -5.13e-02 |
Pos logit contributions | |
Lauder | +0.126 |
Loving | +0.114 |
Sioux | +0.113 |
Hots | +0.105 |
Subtle | +0.104 |
Neg logit contributions | |
obar | -0.136 |
rane | -0.132 |
minist | -0.122 |
oba | -0.118 |
ega | -0.117 |
Token | financial |
Token ID | 3176 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
Lauder | +0.085 |
Loving | +0.077 |
Sioux | +0.076 |
Hots | +0.071 |
Subtle | +0.070 |
Neg logit contributions | |
obar | -0.095 |
rane | -0.092 |
minist | -0.085 |
oba | -0.083 |
ega | -0.082 |
Token | childhood |
Token ID | 9963 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
obar | +0.022 |
rane | +0.021 |
minist | +0.019 |
oba | +0.019 |
ega | +0.019 |
Neg logit contributions | |
Lauder | -0.019 |
Loving | -0.017 |
Sioux | -0.017 |
Hots | -0.016 |
Subtle | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +7.45e-02 |
Pos logit contributions | |
obar | +0.584 |
rane | +0.564 |
minist | +0.524 |
oba | +0.508 |
ega | +0.502 |
Neg logit contributions | |
Lauder | -0.518 |
Loving | -0.462 |
Sioux | -0.460 |
Hots | -0.428 |
Subtle | -0.424 |
Token | and |
Token ID | 290 |
Feature activation | +9.02e-02 |
Pos logit contributions | |
obar | +0.143 |
rane | +0.137 |
minist | +0.126 |
oba | +0.124 |
ega | +0.121 |
Neg logit contributions | |
Lauder | -0.121 |
Loving | -0.107 |
Sioux | -0.107 |
Hots | -0.099 |
Subtle | -0.097 |
Token | a |
Token ID | 257 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
obar | +0.184 |
rane | +0.178 |
minist | +0.165 |
oba | +0.162 |
ega | +0.159 |
Neg logit contributions | |
Lauder | -0.134 |
Loving | -0.119 |
Sioux | -0.117 |
Hots | -0.109 |
Sikh | -0.106 |
Token | " |
Token ID | 366 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
obar | +0.226 |
rane | +0.220 |
minist | +0.207 |
oba | +0.204 |
ega | +0.201 |
Neg logit contributions | |
Lauder | -0.106 |
Loving | -0.089 |
Sioux | -0.088 |
Hots | -0.080 |
Subtle | -0.077 |
Token | Girl |
Token ID | 24151 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
obar | +0.100 |
rane | +0.097 |
minist | +0.090 |
oba | +0.088 |
ega | +0.086 |
Neg logit contributions | |
Lauder | -0.095 |
Loving | -0.085 |
Sioux | -0.085 |
Hots | -0.079 |
Subtle | -0.078 |
Token | " |
Token ID | 1 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
Lauder | +2.793 |
Loving | +2.607 |
Sioux | +2.537 |
Hots | +2.362 |
Sikh | +2.302 |
Neg logit contributions | |
obar | -2.990 |
rane | -2.891 |
minist | -2.684 |
oba | -2.610 |
ega | -2.536 |
Token | side |
Token ID | 1735 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
Lauder | +1.156 |
Loving | +1.050 |
Sioux | +1.036 |
Hots | +0.964 |
Sikh | +0.945 |
Neg logit contributions | |
obar | -1.285 |
rane | -1.245 |
minist | -1.146 |
oba | -1.122 |
ega | -1.103 |
Token | , |
Token ID | 11 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
Lauder | +0.606 |
Loving | +0.545 |
Sioux | +0.538 |
Hots | +0.501 |
Subtle | +0.492 |
Neg logit contributions | |
obar | -0.709 |
rane | -0.686 |
minist | -0.633 |
oba | -0.620 |
ega | -0.612 |
Token | for |
Token ID | 329 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
obar | +0.148 |
rane | +0.142 |
minist | +0.131 |
oba | +0.127 |
ega | +0.127 |
Neg logit contributions | |
Lauder | -0.139 |
Loving | -0.124 |
Sioux | -0.123 |
Hots | -0.115 |
Subtle | -0.115 |
Token | the |
Token ID | 262 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
obar | +0.185 |
rane | +0.179 |
minist | +0.165 |
oba | +0.161 |
ega | +0.158 |
Neg logit contributions | |
Lauder | -0.172 |
Loving | -0.155 |
Sioux | -0.154 |
Hots | -0.145 |
Sikh | -0.142 |
Token | devoid |
Token ID | 34065 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Lauder | +0.610 |
Loving | +0.547 |
Sioux | +0.539 |
Hots | +0.501 |
Subtle | +0.497 |
Neg logit contributions | |
obar | -0.706 |
rane | -0.680 |
minist | -0.637 |
oba | -0.616 |
ega | -0.608 |
Token | of |
Token ID | 286 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
obar | +0.300 |
rane | +0.292 |
minist | +0.272 |
oba | +0.268 |
ega | +0.264 |
Neg logit contributions | |
Lauder | -0.184 |
Loving | -0.163 |
Sioux | -0.160 |
Hots | -0.146 |
Subtle | -0.142 |
Token | social |
Token ID | 1919 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
obar | +0.425 |
rane | +0.413 |
minist | +0.384 |
oba | +0.375 |
ega | +0.368 |
Neg logit contributions | |
Lauder | -0.381 |
Loving | -0.338 |
Sioux | -0.336 |
Hots | -0.317 |
Subtle | -0.308 |
Token | content |
Token ID | 2695 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
obar | +0.110 |
rane | +0.106 |
minist | +0.098 |
oba | +0.096 |
ega | +0.094 |
Neg logit contributions | |
Lauder | -0.110 |
Loving | -0.099 |
Sioux | -0.098 |
Hots | -0.092 |
Subtle | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
Lauder | +0.412 |
Loving | +0.370 |
Sioux | +0.368 |
Hots | +0.343 |
Subtle | +0.335 |
Neg logit contributions | |
obar | -0.474 |
rane | -0.458 |
minist | -0.425 |
oba | -0.415 |
ega | -0.407 |
Token | Trotsky |
Token ID | 32706 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
obar | +0.141 |
rane | +0.136 |
minist | +0.126 |
oba | +0.124 |
ega | +0.121 |
Neg logit contributions | |
Lauder | -0.124 |
Sioux | -0.109 |
Loving | -0.109 |
Hots | -0.101 |
Sikh | -0.099 |
Token | ism |
Token ID | 1042 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
Lauder | +2.435 |
Loving | +2.174 |
Sioux | +2.138 |
Hots | +1.969 |
Subtle | +1.928 |
Neg logit contributions | |
obar | -3.414 |
rane | -3.313 |
minist | -3.082 |
oba | -3.021 |
ega | -2.978 |
Token | is |
Token ID | 318 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
obar | +0.388 |
rane | +0.374 |
minist | +0.349 |
oba | +0.340 |
ega | +0.337 |
Neg logit contributions | |
Lauder | -0.342 |
Loving | -0.309 |
Sioux | -0.303 |
Hots | -0.279 |
Subtle | -0.278 |
Token | a |
Token ID | 257 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
obar | +0.323 |
rane | +0.310 |
minist | +0.292 |
oba | +0.283 |
ega | +0.277 |
Neg logit contributions | |
Lauder | -0.262 |
Loving | -0.236 |
Sioux | -0.230 |
Hots | -0.214 |
Subtle | -0.210 |
Token | religion |
Token ID | 5737 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
obar | +0.131 |
rane | +0.127 |
minist | +0.119 |
oba | +0.116 |
ega | +0.114 |
Neg logit contributions | |
Lauder | -0.110 |
Loving | -0.098 |
Sioux | -0.096 |
Hots | -0.090 |
Subtle | -0.089 |
Token | trip |
Token ID | 5296 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
Lauder | +0.544 |
Loving | +0.486 |
Sioux | +0.481 |
Hots | +0.445 |
Subtle | +0.440 |
Neg logit contributions | |
obar | -0.645 |
rane | -0.618 |
minist | -0.578 |
oba | -0.562 |
ega | -0.556 |
Token | � |
Token ID | 447 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
Lauder | +0.229 |
Loving | +0.204 |
Sioux | +0.200 |
Hots | +0.184 |
Subtle | +0.180 |
Neg logit contributions | |
obar | -0.344 |
rane | -0.334 |
minist | -0.311 |
oba | -0.305 |
ega | -0.301 |
Token | � |
Token ID | 250 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
obar | +0.112 |
rane | +0.106 |
minist | +0.096 |
oba | +0.096 |
ega | +0.093 |
Neg logit contributions | |
Lauder | -0.122 |
Sioux | -0.112 |
Loving | -0.109 |
Hots | -0.102 |
Sikh | -0.101 |
Token | When |
Token ID | 2215 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
Lauder | +0.229 |
Loving | +0.209 |
Sioux | +0.209 |
Hots | +0.196 |
Sikh | +0.193 |
Neg logit contributions | |
obar | -0.175 |
rane | -0.169 |
minist | -0.154 |
oba | -0.150 |
ega | -0.146 |
Token | a |
Token ID | 257 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
Lauder | +1.017 |
Loving | +0.909 |
Sioux | +0.907 |
Hots | +0.837 |
Subtle | +0.823 |
Neg logit contributions | |
obar | -1.235 |
rane | -1.197 |
minist | -1.106 |
oba | -1.084 |
ega | -1.070 |
Token | lady |
Token ID | 10846 |
Feature activation | -8.32e-01 |
Pos logit contributions | |
Lauder | +0.249 |
Loving | +0.218 |
Sioux | +0.217 |
Hots | +0.198 |
Subtle | +0.193 |
Neg logit contributions | |
obar | -0.380 |
rane | -0.369 |
minist | -0.347 |
oba | -0.342 |
ega | -0.336 |
Token | politely |
Token ID | 34313 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Lauder | +1.348 |
Loving | +1.212 |
Sioux | +1.204 |
Hots | +1.108 |
Subtle | +1.099 |
Neg logit contributions | |
obar | -1.583 |
rane | -1.535 |
minist | -1.419 |
oba | -1.387 |
ega | -1.375 |
Token | declines |
Token ID | 24459 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
Lauder | +2.620 |
Loving | +2.351 |
Sioux | +2.325 |
Hots | +2.150 |
Subtle | +2.116 |
Neg logit contributions | |
obar | -3.228 |
rane | -3.127 |
minist | -2.895 |
oba | -2.839 |
ega | -2.803 |
Token | to |
Token ID | 284 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Lauder | +0.476 |
Loving | +0.423 |
Sioux | +0.421 |
Hots | +0.390 |
Subtle | +0.382 |
Neg logit contributions | |
obar | -0.577 |
rane | -0.556 |
minist | -0.516 |
ega | -0.505 |
oba | -0.505 |
Token | dance |
Token ID | 9280 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
Lauder | +0.213 |
Loving | +0.194 |
Sioux | +0.192 |
Hots | +0.179 |
Subtle | +0.178 |
Neg logit contributions | |
obar | -0.194 |
rane | -0.187 |
minist | -0.170 |
oba | -0.168 |
ega | -0.165 |
Token | with |
Token ID | 351 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Lauder | +1.590 |
Loving | +1.432 |
Sioux | +1.411 |
Hots | +1.309 |
Subtle | +1.289 |
Neg logit contributions | |
obar | -1.886 |
rane | -1.822 |
minist | -1.687 |
oba | -1.650 |
ega | -1.630 |
Token | you |
Token ID | 345 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
Lauder | +0.218 |
Loving | +0.196 |
Sioux | +0.194 |
Hots | +0.179 |
Subtle | +0.177 |
Neg logit contributions | |
obar | -0.253 |
rane | -0.244 |
minist | -0.224 |
oba | -0.221 |
ega | -0.218 |
Token | prime |
Token ID | 6994 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Lauder | +0.238 |
Loving | +0.217 |
Sioux | +0.213 |
Hots | +0.199 |
Subtle | +0.198 |
Neg logit contributions | |
obar | -0.238 |
rane | -0.233 |
minist | -0.213 |
oba | -0.208 |
ega | -0.205 |
Token | minister |
Token ID | 5342 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
obar | +0.222 |
rane | +0.211 |
minist | +0.197 |
oba | +0.186 |
ega | +0.182 |
Neg logit contributions | |
Lauder | -0.337 |
Loving | -0.311 |
Sioux | -0.310 |
Subtle | -0.293 |
Hots | -0.293 |
Token | should |
Token ID | 815 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
obar | +0.175 |
rane | +0.169 |
minist | +0.154 |
oba | +0.152 |
ega | +0.152 |
Neg logit contributions | |
Lauder | -0.155 |
Loving | -0.140 |
Sioux | -0.139 |
Subtle | -0.130 |
Hots | -0.126 |
Token | take |
Token ID | 1011 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
obar | +1.594 |
rane | +1.552 |
oba | +1.408 |
minist | +1.407 |
ega | +1.394 |
Neg logit contributions | |
Lauder | -1.621 |
Loving | -1.458 |
Sioux | -1.435 |
Subtle | -1.336 |
Hots | -1.319 |
Token | Mr |
Token ID | 1770 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
obar | +0.218 |
rane | +0.212 |
minist | +0.195 |
ega | +0.191 |
oba | +0.191 |
Neg logit contributions | |
Lauder | -0.199 |
Loving | -0.178 |
Sioux | -0.176 |
Hots | -0.164 |
Subtle | -0.162 |
Token | Hes |
Token ID | 44773 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Lauder | +0.830 |
Loving | +0.737 |
Sioux | +0.727 |
Hots | +0.667 |
Subtle | +0.652 |
Neg logit contributions | |
obar | -1.223 |
rane | -1.190 |
minist | -1.105 |
oba | -1.086 |
ega | -1.072 |
Token | elt |
Token ID | 2120 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
Lauder | +2.104 |
Loving | +1.844 |
Sioux | +1.808 |
Hots | +1.643 |
Subtle | +1.598 |
Neg logit contributions | |
obar | -3.731 |
rane | -3.631 |
minist | -3.396 |
oba | -3.339 |
ega | -3.296 |
Token | ine |
Token ID | 500 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
Lauder | +0.879 |
Loving | +0.791 |
Sioux | +0.785 |
Hots | +0.732 |
Subtle | +0.715 |
Neg logit contributions | |
obar | -1.084 |
rane | -1.063 |
minist | -0.975 |
oba | -0.958 |
ega | -0.953 |
Token | 's |
Token ID | 338 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
Lauder | +0.297 |
Loving | +0.269 |
Sioux | +0.263 |
Hots | +0.244 |
Subtle | +0.243 |
Neg logit contributions | |
obar | -0.340 |
rane | -0.328 |
minist | -0.303 |
oba | -0.297 |
ega | -0.295 |
Token | comments |
Token ID | 3651 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
Lauder | +0.084 |
Loving | +0.076 |
Sioux | +0.075 |
Hots | +0.071 |
Subtle | +0.070 |
Neg logit contributions | |
obar | -0.067 |
rane | -0.065 |
minist | -0.059 |
oba | -0.058 |
ega | -0.056 |
Token | " |
Token ID | 366 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Lauder | +0.787 |
Loving | +0.702 |
Sioux | +0.694 |
Hots | +0.640 |
Subtle | +0.634 |
Neg logit contributions | |
obar | -0.988 |
rane | -0.954 |
minist | -0.884 |
oba | -0.867 |
ega | -0.858 |
Token | ap |
Token ID | 2471 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Lauder | +0.570 |
Loving | +0.516 |
Sioux | +0.509 |
Hots | +0.476 |
Subtle | +0.464 |
Neg logit contributions | |
obar | -0.617 |
rane | -0.594 |
minist | -0.546 |
oba | -0.534 |
ega | -0.527 |
Token | = |
Token ID | 796 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
Lauder | +0.425 |
Loving | +0.381 |
Sioux | +0.377 |
Hots | +0.350 |
Subtle | +0.343 |
Neg logit contributions | |
obar | -0.498 |
rane | -0.480 |
minist | -0.442 |
oba | -0.435 |
ega | -0.430 |
Token | arg |
Token ID | 1822 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
Lauder | +0.822 |
Loving | +0.746 |
Sioux | +0.740 |
Hots | +0.688 |
Subtle | +0.676 |
Neg logit contributions | |
obar | -0.787 |
rane | -0.759 |
minist | -0.692 |
oba | -0.679 |
ega | -0.669 |
Token | parse |
Token ID | 29572 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
Lauder | +2.017 |
Loving | +1.870 |
Sioux | +1.856 |
Hots | +1.761 |
Subtle | +1.734 |
Neg logit contributions | |
obar | -1.226 |
rane | -1.172 |
minist | -1.042 |
oba | -1.010 |
ega | -0.986 |
Token | . |
Token ID | 13 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
Lauder | +0.607 |
Loving | +0.549 |
Sioux | +0.540 |
Hots | +0.501 |
Subtle | +0.494 |
Neg logit contributions | |
obar | -0.688 |
rane | -0.665 |
minist | -0.611 |
oba | -0.599 |
ega | -0.597 |
Token | Arg |
Token ID | 28100 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Lauder | +0.381 |
Loving | +0.338 |
Sioux | +0.333 |
Hots | +0.306 |
Subtle | +0.299 |
Neg logit contributions | |
obar | -0.560 |
rane | -0.544 |
minist | -0.506 |
oba | -0.497 |
ega | -0.490 |
Token | ument |
Token ID | 1713 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
Lauder | +2.510 |
Loving | +2.240 |
Sioux | +2.197 |
Hots | +2.028 |
Sikh | +1.992 |
Neg logit contributions | |
obar | -3.277 |
rane | -3.195 |
minist | -2.957 |
oba | -2.911 |
ega | -2.863 |
Token | Parser |
Token ID | 46677 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
Lauder | +0.985 |
Loving | +0.911 |
Sioux | +0.901 |
Hots | +0.854 |
Subtle | +0.841 |
Neg logit contributions | |
obar | -0.677 |
rane | -0.649 |
minist | -0.582 |
oba | -0.566 |
ega | -0.554 |
Token | () |
Token ID | 3419 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
Lauder | +1.449 |
Loving | +1.331 |
Sioux | +1.316 |
Hots | +1.239 |
Subtle | +1.220 |
Neg logit contributions | |
obar | -1.196 |
rane | -1.151 |
minist | -1.045 |
oba | -1.017 |
ega | -1.001 |
Token | ap |
Token ID | 2471 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
Lauder | +1.364 |
Loving | +1.219 |
Sioux | +1.200 |
Hots | +1.108 |
Subtle | +1.084 |
Neg logit contributions | |
obar | -1.864 |
rane | -1.808 |
minist | -1.678 |
oba | -1.647 |
ega | -1.623 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
Lauder | +0.519 |
Loving | +0.469 |
Sioux | +0.463 |
Hots | +0.432 |
Subtle | +0.425 |
Neg logit contributions | |
obar | -0.550 |
rane | -0.530 |
minist | -0.488 |
oba | -0.477 |
ega | -0.471 |
Token | akh |
Token ID | 11322 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
Lauder | +0.403 |
Loving | +0.372 |
Sioux | +0.369 |
Hots | +0.351 |
Subtle | +0.349 |
Neg logit contributions | |
obar | -0.229 |
rane | -0.215 |
minist | -0.189 |
oba | -0.187 |
ega | -0.178 |
Token | no |
Token ID | 3919 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
obar | +0.111 |
rane | +0.107 |
minist | +0.098 |
oba | +0.097 |
ega | +0.094 |
Neg logit contributions | |
Lauder | -0.107 |
Loving | -0.096 |
Sioux | -0.096 |
Hots | -0.090 |
Sikh | -0.088 |
Token | against |
Token ID | 1028 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Lauder | +0.471 |
Loving | +0.424 |
Sioux | +0.415 |
Hots | +0.385 |
Subtle | +0.383 |
Neg logit contributions | |
obar | -0.568 |
rane | -0.547 |
minist | -0.509 |
oba | -0.497 |
ega | -0.489 |
Token | Lenin |
Token ID | 22899 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
obar | +0.254 |
rane | +0.245 |
minist | +0.229 |
oba | +0.225 |
ega | +0.221 |
Neg logit contributions | |
Lauder | -0.198 |
Loving | -0.178 |
Sioux | -0.173 |
Hots | -0.160 |
Subtle | -0.160 |
Token | and |
Token ID | 290 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
Lauder | +0.801 |
Loving | +0.717 |
Sioux | +0.703 |
Hots | +0.648 |
Subtle | +0.640 |
Neg logit contributions | |
obar | -1.075 |
rane | -1.039 |
minist | -0.969 |
oba | -0.948 |
ega | -0.934 |
Token | Trotsky |
Token ID | 32706 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Lauder | +0.090 |
Loving | +0.079 |
Sioux | +0.077 |
Subtle | +0.070 |
Hots | +0.069 |
Neg logit contributions | |
obar | -0.154 |
rane | -0.150 |
minist | -0.141 |
oba | -0.138 |
ega | -0.136 |
Token | , |
Token ID | 11 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
Lauder | +2.589 |
Loving | +2.331 |
Sioux | +2.298 |
Hots | +2.134 |
Subtle | +2.087 |
Neg logit contributions | |
obar | -3.199 |
rane | -3.101 |
minist | -2.869 |
oba | -2.810 |
ega | -2.768 |
Token |
|
Token ID | 198 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
Lauder | +0.027 |
Loving | +0.024 |
Sioux | +0.023 |
Hots | +0.022 |
Subtle | +0.022 |
Neg logit contributions | |
obar | -0.033 |
rane | -0.032 |
minist | -0.030 |
oba | -0.029 |
ega | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
Lauder | +0.477 |
Loving | +0.421 |
Sioux | +0.420 |
Hots | +0.392 |
Subtle | +0.387 |
Neg logit contributions | |
obar | -0.495 |
rane | -0.479 |
minist | -0.441 |
oba | -0.432 |
ega | -0.424 |
Token | for |
Token ID | 1640 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
Lauder | +0.437 |
Loving | +0.397 |
Sioux | +0.392 |
Hots | +0.367 |
Subtle | +0.362 |
Neg logit contributions | |
obar | -0.435 |
rane | -0.420 |
minist | -0.388 |
oba | -0.376 |
ega | -0.369 |
Token | worldwide |
Token ID | 8688 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
obar | +0.493 |
rane | +0.474 |
minist | +0.443 |
oba | +0.432 |
ega | +0.423 |
Neg logit contributions | |
Lauder | -0.401 |
Loving | -0.356 |
Sioux | -0.355 |
Hots | -0.328 |
Subtle | -0.324 |
Token | . |
Token ID | 13 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
obar | +0.934 |
rane | +0.902 |
minist | +0.833 |
oba | +0.813 |
ega | +0.800 |
Neg logit contributions | |
Lauder | -0.876 |
Loving | -0.797 |
Sioux | -0.784 |
Hots | -0.733 |
Subtle | -0.722 |
Token | government |
Token ID | 1230 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
obar | +0.273 |
rane | +0.262 |
minist | +0.246 |
oba | +0.238 |
ega | +0.234 |
Neg logit contributions | |
Lauder | -0.219 |
Loving | -0.198 |
Sioux | -0.193 |
Subtle | -0.178 |
Hots | -0.178 |
Token | worked |
Token ID | 3111 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
obar | +0.524 |
rane | +0.503 |
minist | +0.470 |
oba | +0.459 |
ega | +0.451 |
Neg logit contributions | |
Lauder | -0.415 |
Loving | -0.381 |
Sioux | -0.369 |
Subtle | -0.342 |
Hots | -0.337 |
Token | with |
Token ID | 351 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
Lauder | +0.299 |
Loving | +0.270 |
Sioux | +0.265 |
Hots | +0.246 |
Subtle | +0.245 |
Neg logit contributions | |
obar | -0.349 |
rane | -0.335 |
minist | -0.314 |
oba | -0.303 |
ega | -0.300 |
Token | Exxon |
Token ID | 27879 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
obar | +0.063 |
rane | +0.060 |
minist | +0.057 |
oba | +0.056 |
ega | +0.055 |
Neg logit contributions | |
Lauder | -0.044 |
Loving | -0.039 |
Sioux | -0.038 |
Hots | -0.035 |
Subtle | -0.035 |
Token | Mobil |
Token ID | 47100 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Lauder | +0.916 |
Loving | +0.817 |
Sioux | +0.800 |
Hots | +0.735 |
Subtle | +0.721 |
Neg logit contributions | |
obar | -1.372 |
rane | -1.327 |
minist | -1.239 |
oba | -1.216 |
ega | -1.197 |
Token | and |
Token ID | 290 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
Lauder | +2.492 |
Loving | +2.230 |
Sioux | +2.204 |
Hots | +2.039 |
Subtle | +1.988 |
Neg logit contributions | |
obar | -3.287 |
rane | -3.194 |
minist | -2.955 |
oba | -2.902 |
ega | -2.859 |
Token | Chevron |
Token ID | 50083 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
obar | +0.025 |
rane | +0.024 |
minist | +0.023 |
oba | +0.022 |
ega | +0.022 |
Neg logit contributions | |
Lauder | -0.020 |
Loving | -0.018 |
Sioux | -0.018 |
Hots | -0.017 |
Subtle | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Lauder | +0.614 |
Loving | +0.555 |
Sioux | +0.540 |
Hots | +0.499 |
Sikh | +0.497 |
Neg logit contributions | |
obar | -0.769 |
rane | -0.742 |
minist | -0.690 |
oba | -0.674 |
ega | -0.664 |
Token | the |
Token ID | 262 |
Feature activation | +9.93e-02 |
Pos logit contributions | |
obar | +0.228 |
rane | +0.218 |
minist | +0.204 |
oba | +0.197 |
ega | +0.195 |
Neg logit contributions | |
Lauder | -0.194 |
Loving | -0.177 |
Sioux | -0.173 |
Subtle | -0.160 |
Hots | -0.160 |
Token | two |
Token ID | 734 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
obar | +0.186 |
rane | +0.179 |
minist | +0.166 |
oba | +0.163 |
ega | +0.160 |
Neg logit contributions | |
Lauder | -0.160 |
Loving | -0.147 |
Sioux | -0.142 |
Hots | -0.133 |
Subtle | -0.133 |
Token | Temple |
Token ID | 10857 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
obar | +0.726 |
rane | +0.704 |
minist | +0.657 |
oba | +0.645 |
ega | +0.635 |
Neg logit contributions | |
Lauder | -0.537 |
Loving | -0.476 |
Sioux | -0.469 |
Hots | -0.434 |
Subtle | -0.423 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Lauder | +0.551 |
Loving | +0.496 |
Sioux | +0.488 |
Hots | +0.452 |
Sikh | +0.445 |
Neg logit contributions | |
obar | -0.729 |
rane | -0.707 |
minist | -0.655 |
oba | -0.643 |
ega | -0.632 |
Token |
|
Token ID | 198 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Lauder | +0.223 |
Loving | +0.197 |
Sioux | +0.197 |
Hots | +0.182 |
Subtle | +0.181 |
Neg logit contributions | |
obar | -0.235 |
rane | -0.228 |
minist | -0.209 |
oba | -0.206 |
ega | -0.202 |
Token | Address |
Token ID | 20231 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Lauder | +0.221 |
Loving | +0.201 |
Sioux | +0.200 |
Hots | +0.186 |
Subtle | +0.185 |
Neg logit contributions | |
obar | -0.173 |
rane | -0.168 |
minist | -0.151 |
oba | -0.148 |
ega | -0.145 |
Token | : |
Token ID | 25 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
Lauder | +0.482 |
Loving | +0.428 |
Sioux | +0.426 |
Hots | +0.394 |
Subtle | +0.388 |
Neg logit contributions | |
obar | -0.533 |
rane | -0.514 |
minist | -0.473 |
oba | -0.466 |
ega | -0.459 |
Token | Sector |
Token ID | 25892 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Lauder | +0.327 |
Loving | +0.293 |
Sioux | +0.287 |
Hots | +0.268 |
Subtle | +0.263 |
Neg logit contributions | |
obar | -0.421 |
rane | -0.407 |
minist | -0.374 |
oba | -0.371 |
ega | -0.367 |
Token | 20 |
Token ID | 1160 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
obar | +2.046 |
rane | +1.980 |
oba | +1.794 |
minist | +1.778 |
ega | +1.776 |
Neg logit contributions | |
Lauder | -1.729 |
Loving | -1.557 |
Sioux | -1.526 |
Hots | -1.429 |
Subtle | -1.392 |
Token | , |
Token ID | 11 |
Feature activation | +7.06e-03 |
Pos logit contributions | |
obar | +0.040 |
rane | +0.039 |
minist | +0.036 |
oba | +0.035 |
ega | +0.035 |
Neg logit contributions | |
Lauder | -0.035 |
Loving | -0.032 |
Sioux | -0.031 |
Hots | -0.029 |
Subtle | -0.029 |
Token | J |
Token ID | 41 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
obar | +0.014 |
rane | +0.014 |
minist | +0.012 |
oba | +0.012 |
ega | +0.012 |
Neg logit contributions | |
Lauder | -0.011 |
Loving | -0.010 |
Sioux | -0.009 |
Hots | -0.009 |
Subtle | -0.009 |
Token | Road |
Token ID | 5567 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Lauder | +0.662 |
Loving | +0.602 |
Sioux | +0.595 |
Hots | +0.564 |
Subtle | +0.552 |
Neg logit contributions | |
obar | -0.603 |
rane | -0.579 |
minist | -0.523 |
oba | -0.517 |
ega | -0.510 |
Token | , |
Token ID | 11 |
Feature activation | +1.73e-03 |
Pos logit contributions | |
obar | +0.254 |
rane | +0.246 |
minist | +0.227 |
oba | +0.223 |
ega | +0.220 |
Neg logit contributions | |
Lauder | -0.217 |
Loving | -0.195 |
Sioux | -0.192 |
Hots | -0.179 |
Subtle | -0.175 |
Token | boards |
Token ID | 12821 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Lauder | +0.597 |
Loving | +0.539 |
Sioux | +0.535 |
Hots | +0.499 |
Subtle | +0.490 |
Neg logit contributions | |
obar | -0.667 |
rane | -0.644 |
minist | -0.593 |
oba | -0.582 |
ega | -0.572 |
Token | offer |
Token ID | 2897 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
obar | +0.248 |
rane | +0.239 |
minist | +0.220 |
ega | +0.215 |
oba | +0.215 |
Neg logit contributions | |
Lauder | -0.238 |
Loving | -0.216 |
Sioux | -0.214 |
Hots | -0.198 |
Subtle | -0.197 |
Token | help |
Token ID | 1037 |
Feature activation | +7.72e-02 |
Pos logit contributions | |
obar | +0.061 |
rane | +0.059 |
minist | +0.055 |
oba | +0.053 |
ega | +0.053 |
Neg logit contributions | |
Lauder | -0.052 |
Loving | -0.047 |
Sioux | -0.046 |
Hots | -0.043 |
Subtle | -0.043 |
Token | with |
Token ID | 351 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
obar | +0.144 |
rane | +0.140 |
minist | +0.131 |
oba | +0.126 |
ega | +0.125 |
Neg logit contributions | |
Lauder | -0.127 |
Loving | -0.115 |
Sioux | -0.114 |
Hots | -0.105 |
Subtle | -0.105 |
Token | beating |
Token ID | 11226 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
Lauder | +0.275 |
Loving | +0.249 |
Sioux | +0.246 |
Subtle | +0.229 |
Hots | +0.229 |
Neg logit contributions | |
obar | -0.293 |
rane | -0.284 |
minist | -0.263 |
oba | -0.255 |
ega | -0.251 |
Token | alcohol |
Token ID | 5548 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Lauder | +0.832 |
Loving | +0.748 |
Sioux | +0.738 |
Hots | +0.687 |
Subtle | +0.681 |
Neg logit contributions | |
obar | -0.969 |
rane | -0.934 |
minist | -0.864 |
oba | -0.844 |
ega | -0.832 |
Token | or |
Token ID | 393 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
obar | +2.028 |
rane | +1.925 |
minist | +1.805 |
oba | +1.771 |
ega | +1.747 |
Neg logit contributions | |
Lauder | -1.829 |
Loving | -1.656 |
Sioux | -1.652 |
Subtle | -1.513 |
Hots | -1.508 |
Token | avoiding |
Token ID | 14928 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
Lauder | +0.322 |
Loving | +0.290 |
Sioux | +0.288 |
Hots | +0.267 |
Subtle | +0.264 |
Neg logit contributions | |
obar | -0.387 |
rane | -0.374 |
minist | -0.346 |
oba | -0.338 |
ega | -0.333 |
Token | d |
Token ID | 288 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
obar | +1.610 |
rane | +1.542 |
minist | +1.448 |
oba | +1.386 |
ega | +1.375 |
Neg logit contributions | |
Lauder | -1.433 |
Loving | -1.282 |
Sioux | -1.267 |
Subtle | -1.195 |
Hots | -1.194 |
Token | eng |
Token ID | 1516 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Lauder | +0.254 |
Loving | +0.231 |
Sioux | +0.229 |
Hots | +0.215 |
Subtle | +0.212 |
Neg logit contributions | |
obar | -0.240 |
rane | -0.231 |
minist | -0.212 |
oba | -0.207 |
ega | -0.203 |
Token | ue |
Token ID | 518 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
Lauder | +0.333 |
Loving | +0.296 |
Sioux | +0.291 |
Hots | +0.267 |
Subtle | +0.261 |
Neg logit contributions | |
obar | -0.510 |
rane | -0.496 |
minist | -0.461 |
oba | -0.453 |
ega | -0.447 |
Token | Say |
Token ID | 13816 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
Lauder | +0.004 |
Loving | +0.004 |
Sioux | +0.004 |
Hots | +0.003 |
Subtle | +0.003 |
Neg logit contributions | |
obar | -0.005 |
rane | -0.005 |
minist | -0.004 |
oba | -0.004 |
ega | -0.004 |
Token | y |
Token ID | 88 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Lauder | +0.057 |
Loving | +0.052 |
Sioux | +0.051 |
Hots | +0.047 |
Subtle | +0.047 |
Neg logit contributions | |
obar | -0.065 |
rane | -0.063 |
minist | -0.058 |
oba | -0.057 |
ega | -0.056 |
Token | af |
Token ID | 1878 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
obar | +0.258 |
rane | +0.249 |
minist | +0.226 |
oba | +0.225 |
ega | +0.222 |
Neg logit contributions | |
Lauder | -0.237 |
Loving | -0.211 |
Sioux | -0.210 |
Hots | -0.195 |
Subtle | -0.193 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Lauder | +0.668 |
Loving | +0.602 |
Sioux | +0.593 |
Hots | +0.550 |
Subtle | +0.540 |
Neg logit contributions | |
obar | -0.814 |
rane | -0.790 |
minist | -0.728 |
oba | -0.716 |
ega | -0.705 |
Token | Dr |
Token ID | 1583 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
obar | +0.180 |
rane | +0.175 |
minist | +0.159 |
oba | +0.158 |
ega | +0.155 |
Neg logit contributions | |
Lauder | -0.170 |
Loving | -0.154 |
Sioux | -0.152 |
Hots | -0.142 |
Subtle | -0.139 |
Token | Abdullah |
Token ID | 26804 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
obar | +0.650 |
rane | +0.629 |
minist | +0.576 |
oba | +0.567 |
ega | +0.556 |
Neg logit contributions | |
Lauder | -0.606 |
Loving | -0.549 |
Sioux | -0.543 |
Hots | -0.506 |
Subtle | -0.498 |
Token | has |
Token ID | 468 |
Feature activation | +9.47e-02 |
Pos logit contributions | |
obar | +1.882 |
rane | +1.822 |
minist | +1.647 |
ega | +1.633 |
oba | +1.631 |
Neg logit contributions | |
Lauder | -1.738 |
Loving | -1.575 |
Sioux | -1.549 |
Subtle | -1.444 |
Hots | -1.417 |
Token | been |
Token ID | 587 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
obar | +0.178 |
rane | +0.173 |
minist | +0.158 |
oba | +0.156 |
ega | +0.155 |
Neg logit contributions | |
Lauder | -0.154 |
Loving | -0.139 |
Sioux | -0.136 |
Subtle | -0.126 |
Hots | -0.125 |
Token | publicly |
Token ID | 7271 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Lauder | +0.393 |
Loving | +0.353 |
Sioux | +0.348 |
Subtle | +0.324 |
Hots | +0.321 |
Neg logit contributions | |
obar | -0.471 |
rane | -0.454 |
minist | -0.416 |
oba | -0.409 |
ega | -0.406 |
Token | generous |
Token ID | 14431 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
Lauder | +0.411 |
Loving | +0.367 |
Sioux | +0.367 |
Subtle | +0.339 |
Hots | +0.337 |
Neg logit contributions | |
obar | -0.521 |
rane | -0.505 |
minist | -0.465 |
oba | -0.459 |
ega | -0.457 |
Token | about |
Token ID | 546 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
obar | +1.305 |
rane | +1.255 |
minist | +1.166 |
ega | +1.135 |
oba | +1.128 |
Neg logit contributions | |
Lauder | -1.150 |
Loving | -1.029 |
Sioux | -1.023 |
Subtle | -0.954 |
Hots | -0.946 |
Token | a |
Token ID | 257 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
obar | +0.291 |
rane | +0.279 |
minist | +0.258 |
oba | +0.256 |
ega | +0.250 |
Neg logit contributions | |
Lauder | -0.238 |
Loving | -0.211 |
Sioux | -0.208 |
Hots | -0.194 |
Subtle | -0.191 |
Token | total |
Token ID | 2472 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
Lauder | +0.195 |
Loving | +0.175 |
Sioux | +0.173 |
Hots | +0.162 |
Subtle | +0.160 |
Neg logit contributions | |
obar | -0.186 |
rane | -0.180 |
minist | -0.164 |
oba | -0.164 |
ega | -0.158 |
Token | to |
Token ID | 284 |
Feature activation | -1.96e-03 |
Pos logit contributions | |
Lauder | +0.759 |
Loving | +0.684 |
Sioux | +0.678 |
Hots | +0.629 |
Subtle | +0.619 |
Neg logit contributions | |
obar | -0.843 |
rane | -0.816 |
minist | -0.750 |
oba | -0.740 |
ega | -0.721 |
Token | thumb |
Token ID | 15683 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
Lauder | +0.003 |
Loving | +0.003 |
Sioux | +0.003 |
Hots | +0.003 |
Subtle | +0.003 |
Neg logit contributions | |
obar | -0.003 |
rane | -0.003 |
minist | -0.003 |
oba | -0.003 |
ega | -0.003 |
Token | your |
Token ID | 534 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
Lauder | +0.798 |
Loving | +0.719 |
Sioux | +0.709 |
Hots | +0.658 |
Subtle | +0.644 |
Neg logit contributions | |
obar | -0.983 |
rane | -0.954 |
minist | -0.882 |
oba | -0.864 |
ega | -0.852 |
Token | nose |
Token ID | 9686 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
obar | +0.243 |
rane | +0.230 |
minist | +0.210 |
oba | +0.205 |
ega | +0.199 |
Neg logit contributions | |
Lauder | -0.314 |
Loving | -0.286 |
Sioux | -0.279 |
Hots | -0.265 |
Subtle | -0.263 |
Token | at |
Token ID | 379 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
obar | +2.009 |
rane | +1.901 |
minist | +1.788 |
oba | +1.756 |
ega | +1.721 |
Neg logit contributions | |
Lauder | -1.731 |
Loving | -1.567 |
Sioux | -1.537 |
Hots | -1.429 |
Subtle | -1.412 |
Token | , |
Token ID | 11 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
obar | +0.552 |
rane | +0.533 |
minist | +0.495 |
oba | +0.480 |
ega | +0.474 |
Neg logit contributions | |
Lauder | -0.517 |
Loving | -0.466 |
Sioux | -0.457 |
Hots | -0.428 |
Subtle | -0.422 |
Token | and |
Token ID | 290 |
Feature activation | -8.85e-02 |
Pos logit contributions | |
obar | +0.054 |
rane | +0.051 |
minist | +0.047 |
oba | +0.045 |
ega | +0.044 |
Neg logit contributions | |
Lauder | -0.068 |
Loving | -0.062 |
Sioux | -0.061 |
Hots | -0.057 |
Subtle | -0.057 |
Token | his |
Token ID | 465 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Lauder | +0.152 |
Loving | +0.137 |
Sioux | +0.134 |
Hots | +0.126 |
Sikh | +0.124 |
Neg logit contributions | |
obar | -0.159 |
rane | -0.154 |
minist | -0.141 |
oba | -0.138 |
ega | -0.136 |
Token | advanced |
Token ID | 6190 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
Lauder | +0.224 |
Loving | +0.202 |
Sioux | +0.196 |
Hots | +0.185 |
Subtle | +0.182 |
Neg logit contributions | |
obar | -0.237 |
rane | -0.229 |
minist | -0.210 |
oba | -0.206 |
ega | -0.200 |
Token | rest |
Token ID | 1334 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Lauder | +0.021 |
Loving | +0.018 |
Sioux | +0.018 |
Hots | +0.017 |
Subtle | +0.017 |
Neg logit contributions | |
obar | -0.026 |
rane | -0.026 |
minist | -0.024 |
oba | -0.023 |
ega | -0.023 |
Token | is |
Token ID | 318 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Lauder | +0.334 |
Loving | +0.290 |
Sioux | +0.285 |
Hots | +0.257 |
Subtle | +0.251 |
Neg logit contributions | |
obar | -0.586 |
rane | -0.567 |
minist | -0.534 |
oba | -0.522 |
ega | -0.515 |
Token | history |
Token ID | 2106 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
obar | +0.248 |
rane | +0.239 |
minist | +0.214 |
oba | +0.209 |
ega | +0.206 |
Neg logit contributions | |
Lauder | -0.320 |
Loving | -0.293 |
Sioux | -0.288 |
Hots | -0.275 |
Subtle | -0.272 |
Token | . |
Token ID | 13 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
obar | +1.014 |
rane | +0.974 |
minist | +0.903 |
oba | +0.884 |
ega | +0.874 |
Neg logit contributions | |
Lauder | -0.950 |
Loving | -0.858 |
Sioux | -0.842 |
Hots | -0.795 |
Subtle | -0.786 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
obar | +0.300 |
rane | +0.287 |
minist | +0.262 |
oba | +0.262 |
ega | +0.258 |
Neg logit contributions | |
Lauder | -0.264 |
Loving | -0.235 |
Sioux | -0.234 |
Hots | -0.218 |
Subtle | -0.216 |
Token | About |
Token ID | 8585 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
obar | +0.453 |
rane | +0.434 |
minist | +0.397 |
oba | +0.387 |
ega | +0.379 |
Neg logit contributions | |
Lauder | -0.529 |
Loving | -0.482 |
Sioux | -0.478 |
Hots | -0.449 |
Subtle | -0.441 |
Token | This |
Token ID | 770 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
obar | +1.903 |
rane | +1.835 |
oba | +1.671 |
minist | +1.661 |
ega | +1.643 |
Neg logit contributions | |
Lauder | -1.614 |
Loving | -1.440 |
Sioux | -1.430 |
Hots | -1.318 |
Sikh | -1.287 |
Token | Game |
Token ID | 3776 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
obar | +0.698 |
rane | +0.674 |
minist | +0.607 |
oba | +0.599 |
ega | +0.590 |
Neg logit contributions | |
Lauder | -0.795 |
Sioux | -0.722 |
Loving | -0.719 |
Hots | -0.665 |
Sikh | -0.657 |
Token |
|
Token ID | 198 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
obar | +0.555 |
rane | +0.537 |
minist | +0.495 |
oba | +0.489 |
ega | +0.482 |
Neg logit contributions | |
Lauder | -0.462 |
Loving | -0.411 |
Sioux | -0.406 |
Hots | -0.377 |
Sikh | -0.370 |
Token |
|
Token ID | 198 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
Lauder | +0.117 |
Sioux | +0.104 |
Loving | +0.103 |
Hots | +0.096 |
Subtle | +0.094 |
Neg logit contributions | |
obar | -0.120 |
rane | -0.116 |
minist | -0.107 |
oba | -0.105 |
ega | -0.103 |
Token | Choose |
Token ID | 31851 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
Lauder | +0.094 |
Loving | +0.086 |
Sioux | +0.085 |
Hots | +0.080 |
Subtle | +0.079 |
Neg logit contributions | |
obar | -0.078 |
rane | -0.075 |
minist | -0.069 |
oba | -0.067 |
ega | -0.066 |
Token | ine |
Token ID | 500 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
Lauder | +0.003 |
Sioux | +0.003 |
Loving | +0.003 |
Hots | +0.003 |
Subtle | +0.003 |
Neg logit contributions | |
obar | -0.004 |
rane | -0.004 |
minist | -0.004 |
oba | -0.004 |
ega | -0.004 |
Token | Page |
Token ID | 7873 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
Lauder | +1.082 |
Loving | +0.971 |
Sioux | +0.961 |
Hots | +0.894 |
Sikh | +0.878 |
Neg logit contributions | |
obar | -1.379 |
rane | -1.336 |
minist | -1.227 |
oba | -1.219 |
ega | -1.207 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
obar | +0.311 |
rane | +0.300 |
minist | +0.277 |
oba | +0.272 |
ega | +0.272 |
Neg logit contributions | |
Lauder | -0.243 |
Loving | -0.216 |
Sioux | -0.213 |
Hots | -0.198 |
Subtle | -0.194 |
Token | Ma |
Token ID | 6669 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
Lauder | +0.189 |
Loving | +0.170 |
Sioux | +0.168 |
Hots | +0.157 |
Subtle | +0.155 |
Neg logit contributions | |
obar | -0.224 |
rane | -0.217 |
minist | -0.199 |
oba | -0.196 |
ega | -0.194 |
Token | ureen |
Token ID | 49851 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
obar | +0.724 |
rane | +0.689 |
minist | +0.614 |
oba | +0.601 |
ega | +0.593 |
Neg logit contributions | |
Lauder | -1.152 |
Loving | -1.061 |
Sioux | -1.051 |
Hots | -1.012 |
Sikh | -0.996 |
Token | St |
Token ID | 520 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
Lauder | +0.424 |
Loving | +0.385 |
Sioux | +0.382 |
Hots | +0.357 |
Subtle | +0.350 |
Neg logit contributions | |
obar | -0.496 |
rane | -0.486 |
oba | -0.440 |
minist | -0.439 |
ega | -0.431 |
Token | ap |
Token ID | 499 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
obar | +0.779 |
rane | +0.755 |
minist | +0.676 |
oba | +0.668 |
ega | +0.662 |
Neg logit contributions | |
Lauder | -0.826 |
Loving | -0.760 |
Sioux | -0.751 |
Hots | -0.708 |
Subtle | -0.699 |
Token | leton |
Token ID | 10565 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
obar | +0.235 |
rane | +0.229 |
minist | +0.210 |
oba | +0.207 |
ega | +0.203 |
Neg logit contributions | |
Lauder | -0.212 |
Loving | -0.192 |
Sioux | -0.188 |
Hots | -0.177 |
Subtle | -0.175 |
Token | , |
Token ID | 11 |
Feature activation | +6.88e-03 |
Pos logit contributions | |
obar | +1.152 |
rane | +1.110 |
minist | +1.016 |
oba | +1.003 |
ega | +1.000 |
Neg logit contributions | |
Lauder | -1.039 |
Loving | -0.937 |
Sioux | -0.923 |
Hots | -0.850 |
Sikh | -0.849 |
Token | particularly |
Token ID | 3573 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
obar | +0.013 |
rane | +0.012 |
minist | +0.011 |
oba | +0.011 |
ega | +0.011 |
Neg logit contributions | |
Lauder | -0.011 |
Loving | -0.010 |
Sioux | -0.010 |
Hots | -0.009 |
Subtle | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Lauder | +0.133 |
Loving | +0.119 |
Sioux | +0.118 |
Hots | +0.109 |
Subtle | +0.108 |
Neg logit contributions | |
obar | -0.152 |
rane | -0.147 |
minist | -0.136 |
oba | -0.133 |
ega | -0.131 |
Token | version |
Token ID | 2196 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
obar | +0.044 |
rane | +0.043 |
minist | +0.039 |
oba | +0.038 |
ega | +0.038 |
Neg logit contributions | |
Lauder | -0.044 |
Loving | -0.040 |
Sioux | -0.039 |
Hots | -0.036 |
Subtle | -0.036 |
Token | unlocks |
Token ID | 23872 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
Lauder | +0.991 |
Loving | +0.896 |
Sioux | +0.888 |
Hots | +0.826 |
Subtle | +0.813 |
Neg logit contributions | |
obar | -0.998 |
rane | -0.965 |
minist | -0.881 |
oba | -0.866 |
ega | -0.851 |
Token | more |
Token ID | 517 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
obar | +0.058 |
rane | +0.057 |
minist | +0.052 |
oba | +0.051 |
ega | +0.050 |
Neg logit contributions | |
Lauder | -0.052 |
Loving | -0.047 |
Sioux | -0.046 |
Hots | -0.043 |
Sikh | -0.042 |
Token | effects |
Token ID | 3048 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
obar | +0.118 |
rane | +0.115 |
minist | +0.104 |
oba | +0.102 |
ega | +0.100 |
Neg logit contributions | |
Lauder | -0.121 |
Loving | -0.109 |
Sioux | -0.108 |
Hots | -0.101 |
Sikh | -0.099 |
Token | and |
Token ID | 290 |
Feature activation | +8.94e-02 |
Pos logit contributions | |
Lauder | +0.685 |
Loving | +0.621 |
Sioux | +0.614 |
Hots | +0.574 |
Subtle | +0.564 |
Neg logit contributions | |
obar | -0.698 |
rane | -0.675 |
minist | -0.619 |
oba | -0.605 |
ega | -0.595 |
Token | frames |
Token ID | 13431 |
Feature activation | -7.22e-03 |
Pos logit contributions | |
obar | +0.162 |
rane | +0.157 |
minist | +0.143 |
oba | +0.140 |
ega | +0.139 |
Neg logit contributions | |
Lauder | -0.152 |
Loving | -0.137 |
Sioux | -0.136 |
Hots | -0.127 |
Sikh | -0.124 |
Token | ) |
Token ID | 8 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Lauder | +0.013 |
Loving | +0.012 |
Sioux | +0.011 |
Hots | +0.011 |
Sikh | +0.010 |
Neg logit contributions | |
obar | -0.013 |
rane | -0.012 |
minist | -0.011 |
oba | -0.011 |
ega | -0.011 |
Token | [ |
Token ID | 685 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
obar | +0.308 |
rane | +0.299 |
minist | +0.273 |
oba | +0.270 |
ega | +0.266 |
Neg logit contributions | |
Lauder | -0.260 |
Loving | -0.232 |
Sioux | -0.231 |
Hots | -0.214 |
Sikh | -0.210 |
Token | Home |
Token ID | 16060 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
obar | +0.241 |
rane | +0.233 |
minist | +0.212 |
oba | +0.207 |
ega | +0.204 |
Neg logit contributions | |
Lauder | -0.262 |
Loving | -0.238 |
Sioux | -0.235 |
Hots | -0.221 |
Sikh | -0.216 |
Token | page |
Token ID | 7700 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
obar | +0.328 |
rane | +0.314 |
minist | +0.290 |
oba | +0.287 |
ega | +0.278 |
Neg logit contributions | |
Lauder | -0.326 |
Loving | -0.292 |
Sioux | -0.290 |
Hots | -0.268 |
Subtle | -0.267 |
Token | ] |
Token ID | 60 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
obar | +0.452 |
rane | +0.436 |
minist | +0.396 |
oba | +0.394 |
ega | +0.387 |
Neg logit contributions | |
Lauder | -0.447 |
Loving | -0.399 |
Sioux | -0.396 |
Hots | -0.368 |
Subtle | -0.363 |
Token | said |
Token ID | 531 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
obar | +1.010 |
rane | +0.976 |
minist | +0.899 |
oba | +0.879 |
ega | +0.867 |
Neg logit contributions | |
Lauder | -0.923 |
Loving | -0.836 |
Sioux | -0.824 |
Hots | -0.770 |
Subtle | -0.757 |
Token | . |
Token ID | 13 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
obar | +1.145 |
rane | +1.102 |
minist | +1.010 |
oba | +0.993 |
ega | +0.979 |
Neg logit contributions | |
Lauder | -1.118 |
Loving | -1.013 |
Sioux | -0.997 |
Hots | -0.936 |
Subtle | -0.931 |
Token | " |
Token ID | 366 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
obar | +0.992 |
rane | +0.969 |
minist | +0.915 |
oba | +0.902 |
ega | +0.892 |
Neg logit contributions | |
Lauder | -0.360 |
Loving | -0.300 |
Sioux | -0.292 |
Hots | -0.253 |
Subtle | -0.243 |
Token | I |
Token ID | 40 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
obar | +0.431 |
rane | +0.415 |
minist | +0.369 |
oba | +0.363 |
ega | +0.355 |
Neg logit contributions | |
Lauder | -0.611 |
Loving | -0.553 |
Sioux | -0.550 |
Hots | -0.522 |
Sikh | -0.514 |
Token | don |
Token ID | 836 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
obar | +0.419 |
rane | +0.406 |
minist | +0.370 |
oba | +0.370 |
ega | +0.360 |
Neg logit contributions | |
Lauder | -0.422 |
Loving | -0.379 |
Sioux | -0.379 |
Hots | -0.350 |
Subtle | -0.348 |
Token | 't |
Token ID | 470 |
Feature activation | +8.42e-02 |
Pos logit contributions | |
Lauder | +1.006 |
Loving | +0.905 |
Sioux | +0.901 |
Hots | +0.842 |
Subtle | +0.830 |
Neg logit contributions | |
obar | -0.925 |
rane | -0.892 |
minist | -0.814 |
oba | -0.799 |
ega | -0.784 |
Token | know |
Token ID | 760 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
obar | +0.146 |
rane | +0.140 |
minist | +0.128 |
oba | +0.127 |
ega | +0.124 |
Neg logit contributions | |
Lauder | -0.153 |
Loving | -0.138 |
Sioux | -0.137 |
Hots | -0.127 |
Subtle | -0.126 |
Token | how |
Token ID | 703 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
Lauder | +0.626 |
Loving | +0.566 |
Sioux | +0.557 |
Hots | +0.523 |
Subtle | +0.519 |
Neg logit contributions | |
obar | -0.635 |
rane | -0.614 |
minist | -0.560 |
oba | -0.552 |
ega | -0.543 |
Token | guys |
Token ID | 3730 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
obar | +0.368 |
rane | +0.358 |
minist | +0.325 |
oba | +0.321 |
ega | +0.319 |
Neg logit contributions | |
Lauder | -0.321 |
Loving | -0.288 |
Sioux | -0.282 |
Hots | -0.266 |
Subtle | -0.261 |
Token | on |
Token ID | 319 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
Lauder | +0.027 |
Loving | +0.025 |
Sioux | +0.024 |
Hots | +0.023 |
Subtle | +0.022 |
Neg logit contributions | |
obar | -0.028 |
rane | -0.027 |
minist | -0.024 |
oba | -0.024 |
ega | -0.024 |
Token | either |
Token ID | 2035 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
Lauder | +0.081 |
Loving | +0.073 |
Sioux | +0.072 |
Hots | +0.067 |
Subtle | +0.066 |
Neg logit contributions | |
obar | -0.092 |
rane | -0.088 |
minist | -0.081 |
oba | -0.080 |
ega | -0.079 |
Token |
|
Token ID | 198 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
Lauder | +0.153 |
Loving | +0.137 |
Sioux | +0.135 |
Hots | +0.124 |
Sikh | +0.123 |
Neg logit contributions | |
obar | -0.177 |
rane | -0.171 |
minist | -0.158 |
oba | -0.156 |
ega | -0.152 |
Token |
|
Token ID | 198 |
Feature activation | -8.53e-02 |
Pos logit contributions | |
Lauder | +0.161 |
Loving | +0.143 |
Sioux | +0.142 |
Hots | +0.132 |
Subtle | +0.130 |
Neg logit contributions | |
obar | -0.170 |
rane | -0.164 |
minist | -0.151 |
oba | -0.148 |
ega | -0.145 |
Token | C |
Token ID | 34 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
Lauder | +0.158 |
Loving | +0.144 |
Sioux | +0.142 |
Hots | +0.133 |
Subtle | +0.132 |
Neg logit contributions | |
obar | -0.143 |
rane | -0.138 |
minist | -0.126 |
oba | -0.123 |
ega | -0.120 |
Token | ultural |
Token ID | 8596 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
obar | +0.678 |
rane | +0.647 |
minist | +0.587 |
oba | +0.583 |
ega | +0.570 |
Neg logit contributions | |
Lauder | -0.738 |
Loving | -0.674 |
Sioux | -0.666 |
Hots | -0.627 |
Subtle | -0.616 |
Token |
|
Token ID | 198 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
Lauder | +0.308 |
Loving | +0.277 |
Sioux | +0.274 |
Hots | +0.253 |
Subtle | +0.251 |
Neg logit contributions | |
obar | -0.358 |
rane | -0.345 |
minist | -0.319 |
oba | -0.313 |
ega | -0.306 |
Token |
|
Token ID | 198 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
Lauder | +0.157 |
Loving | +0.139 |
Sioux | +0.139 |
Hots | +0.129 |
Subtle | +0.128 |
Neg logit contributions | |
obar | -0.164 |
rane | -0.159 |
minist | -0.146 |
oba | -0.143 |
ega | -0.140 |
Token | If |
Token ID | 1532 |
Feature activation | -5.58e-02 |
Pos logit contributions | |
Lauder | +0.141 |
Loving | +0.129 |
Sioux | +0.128 |
Hots | +0.120 |
Subtle | +0.118 |
Neg logit contributions | |
obar | -0.121 |
rane | -0.116 |
minist | -0.106 |
oba | -0.103 |
ega | -0.101 |
Token | you |
Token ID | 345 |
Feature activation | -7.91e-02 |
Pos logit contributions | |
Lauder | +0.089 |
Loving | +0.080 |
Sioux | +0.079 |
Hots | +0.073 |
Subtle | +0.072 |
Neg logit contributions | |
obar | -0.107 |
rane | -0.104 |
minist | -0.095 |
oba | -0.094 |
ega | -0.092 |
Token | 're |
Token ID | 821 |
Feature activation | -5.92e-02 |
Pos logit contributions | |
Lauder | +0.140 |
Loving | +0.126 |
Sioux | +0.126 |
Hots | +0.117 |
Subtle | +0.116 |
Neg logit contributions | |
obar | -0.139 |
rane | -0.135 |
minist | -0.122 |
oba | -0.121 |
ega | -0.118 |
Token | not |
Token ID | 407 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Lauder | +0.087 |
Loving | +0.077 |
Sioux | +0.076 |
Subtle | +0.070 |
Hots | +0.070 |
Neg logit contributions | |
obar | -0.121 |
rane | -0.118 |
minist | -0.108 |
oba | -0.106 |
ega | -0.105 |
Token | tempted |
Token ID | 26194 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
Lauder | +0.214 |
Loving | +0.192 |
Sioux | +0.188 |
Subtle | +0.176 |
Hots | +0.176 |
Neg logit contributions | |
obar | -0.265 |
rane | -0.257 |
minist | -0.235 |
oba | -0.231 |
ega | -0.228 |
Token | page |
Token ID | 2443 |
Feature activation | +3.18e-03 |
Pos logit contributions | |
obar | +0.188 |
rane | +0.182 |
minist | +0.166 |
oba | +0.163 |
ega | +0.160 |
Neg logit contributions | |
Lauder | -0.179 |
Loving | -0.160 |
Sioux | -0.159 |
Hots | -0.147 |
Sikh | -0.146 |
Token | layout |
Token ID | 12461 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
obar | +0.005 |
rane | +0.005 |
minist | +0.005 |
oba | +0.005 |
ega | +0.005 |
Neg logit contributions | |
Lauder | -0.006 |
Loving | -0.005 |
Sioux | -0.005 |
Hots | -0.005 |
Subtle | -0.005 |
Token | templates |
Token ID | 24019 |
Feature activation | +1.06e-03 |
Pos logit contributions | |
obar | +0.554 |
rane | +0.535 |
minist | +0.490 |
oba | +0.476 |
ega | +0.468 |
Neg logit contributions | |
Lauder | -0.584 |
Loving | -0.522 |
Sioux | -0.518 |
Hots | -0.486 |
Subtle | -0.479 |
Token | are |
Token ID | 389 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
obar | +0.002 |
rane | +0.002 |
minist | +0.002 |
oba | +0.002 |
ega | +0.002 |
Neg logit contributions | |
Lauder | -0.002 |
Loving | -0.002 |
Sioux | -0.002 |
Hots | -0.001 |
Subtle | -0.001 |
Token | gone |
Token ID | 3750 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
obar | +0.306 |
rane | +0.296 |
minist | +0.268 |
oba | +0.264 |
ega | +0.260 |
Neg logit contributions | |
Lauder | -0.292 |
Loving | -0.263 |
Sioux | -0.259 |
Hots | -0.242 |
Subtle | -0.239 |
Token | . |
Token ID | 13 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
obar | +1.063 |
rane | +1.022 |
minist | +0.942 |
oba | +0.928 |
ega | +0.913 |
Neg logit contributions | |
Lauder | -0.996 |
Loving | -0.899 |
Sioux | -0.886 |
Hots | -0.822 |
Subtle | -0.814 |
Token | If |
Token ID | 1002 |
Feature activation | +8.79e-02 |
Pos logit contributions | |
obar | +0.280 |
rane | +0.270 |
minist | +0.247 |
oba | +0.243 |
ega | +0.240 |
Neg logit contributions | |
Lauder | -0.250 |
Loving | -0.220 |
Sioux | -0.220 |
Hots | -0.201 |
Sikh | -0.200 |
Token | you |
Token ID | 345 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
obar | +0.170 |
rane | +0.165 |
minist | +0.152 |
oba | +0.149 |
ega | +0.146 |
Neg logit contributions | |
Lauder | -0.140 |
Loving | -0.125 |
Sioux | -0.123 |
Hots | -0.114 |
Sikh | -0.112 |
Token | open |
Token ID | 1280 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
obar | +0.214 |
rane | +0.210 |
minist | +0.190 |
oba | +0.188 |
ega | +0.182 |
Neg logit contributions | |
Lauder | -0.211 |
Loving | -0.188 |
Sioux | -0.187 |
Hots | -0.172 |
Subtle | -0.171 |
Token | a |
Token ID | 257 |
Feature activation | +7.87e-02 |
Pos logit contributions | |
Lauder | +0.044 |
Loving | +0.039 |
Sioux | +0.038 |
Hots | +0.035 |
Sikh | +0.035 |
Neg logit contributions | |
obar | -0.057 |
rane | -0.055 |
minist | -0.051 |
oba | -0.050 |
ega | -0.049 |
Token | document |
Token ID | 3188 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
obar | +0.137 |
rane | +0.132 |
minist | +0.120 |
oba | +0.118 |
ega | +0.116 |
Neg logit contributions | |
Lauder | -0.141 |
Loving | -0.127 |
Sioux | -0.126 |
Hots | -0.117 |
Sikh | -0.115 |
Token | Batman |
Token ID | 9827 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
obar | +0.171 |
rane | +0.164 |
minist | +0.151 |
oba | +0.148 |
ega | +0.147 |
Neg logit contributions | |
Lauder | -0.148 |
Loving | -0.134 |
Sioux | -0.132 |
Hots | -0.123 |
Subtle | -0.121 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Lauder | +1.012 |
Loving | +0.906 |
Sioux | +0.897 |
Hots | +0.824 |
Sikh | +0.816 |
Neg logit contributions | |
obar | -1.192 |
rane | -1.151 |
minist | -1.068 |
oba | -1.044 |
ega | -1.033 |
Token | On |
Token ID | 1550 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
Lauder | +0.199 |
Sioux | +0.178 |
Loving | +0.177 |
Hots | +0.165 |
Sikh | +0.160 |
Neg logit contributions | |
obar | -0.209 |
rane | -0.201 |
minist | -0.184 |
oba | -0.180 |
ega | -0.180 |
Token | the |
Token ID | 262 |
Feature activation | -7.91e-02 |
Pos logit contributions | |
Lauder | +0.204 |
Sioux | +0.182 |
Loving | +0.182 |
Hots | +0.169 |
Subtle | +0.166 |
Neg logit contributions | |
obar | -0.225 |
rane | -0.214 |
minist | -0.198 |
oba | -0.194 |
ega | -0.189 |
Token | other |
Token ID | 584 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
Lauder | +0.142 |
Sioux | +0.128 |
Loving | +0.128 |
Hots | +0.119 |
Subtle | +0.117 |
Neg logit contributions | |
obar | -0.136 |
rane | -0.130 |
minist | -0.120 |
oba | -0.116 |
ega | -0.115 |
Token | hand |
Token ID | 1021 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
Lauder | +1.405 |
Loving | +1.289 |
Sioux | +1.279 |
Hots | +1.211 |
Subtle | +1.187 |
Neg logit contributions | |
obar | -1.120 |
rane | -1.077 |
minist | -0.971 |
oba | -0.951 |
ega | -0.922 |
Token | , |
Token ID | 11 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
Lauder | +0.331 |
Loving | +0.298 |
Sioux | +0.293 |
Hots | +0.273 |
Subtle | +0.267 |
Neg logit contributions | |
obar | -0.399 |
rane | -0.386 |
minist | -0.357 |
oba | -0.350 |
ega | -0.344 |
Token | it |
Token ID | 340 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
Lauder | +0.254 |
Loving | +0.229 |
Sioux | +0.227 |
Hots | +0.211 |
Subtle | +0.205 |
Neg logit contributions | |
obar | -0.314 |
rane | -0.303 |
minist | -0.278 |
ega | -0.271 |
oba | -0.270 |
Token | still |
Token ID | 991 |
Feature activation | -8.31e-02 |
Pos logit contributions | |
obar | +0.038 |
rane | +0.037 |
minist | +0.034 |
oba | +0.034 |
ega | +0.033 |
Neg logit contributions | |
Lauder | -0.029 |
Loving | -0.026 |
Sioux | -0.026 |
Hots | -0.023 |
Subtle | -0.023 |
Token | might |
Token ID | 1244 |
Feature activation | +7.61e-02 |
Pos logit contributions | |
Lauder | +0.131 |
Loving | +0.117 |
Sioux | +0.115 |
Subtle | +0.106 |
Hots | +0.105 |
Neg logit contributions | |
obar | -0.162 |
rane | -0.156 |
minist | -0.144 |
ega | -0.142 |
oba | -0.141 |
Token | have |
Token ID | 423 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
obar | +0.132 |
rane | +0.126 |
minist | +0.115 |
oba | +0.114 |
ega | +0.113 |
Neg logit contributions | |
Lauder | -0.138 |
Loving | -0.125 |
Sioux | -0.123 |
Hots | -0.114 |
Subtle | -0.114 |
Token | ach |
Token ID | 620 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
Lauder | +0.128 |
Loving | +0.118 |
Sioux | +0.116 |
Subtle | +0.110 |
Hots | +0.110 |
Neg logit contributions | |
obar | -0.072 |
rane | -0.068 |
minist | -0.061 |
oba | -0.060 |
ega | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | -9.64e-03 |
Pos logit contributions | |
obar | +0.519 |
rane | +0.498 |
minist | +0.464 |
oba | +0.453 |
ega | +0.442 |
Neg logit contributions | |
Lauder | -0.458 |
Loving | -0.419 |
Sioux | -0.406 |
Subtle | -0.380 |
Hots | -0.379 |
Token | a |
Token ID | 257 |
Feature activation | -9.73e-02 |
Pos logit contributions | |
Lauder | +0.015 |
Loving | +0.014 |
Sioux | +0.013 |
Subtle | +0.012 |
Hots | +0.012 |
Neg logit contributions | |
obar | -0.019 |
rane | -0.018 |
minist | -0.017 |
oba | -0.016 |
ega | -0.016 |
Token | fuel |
Token ID | 5252 |
Feature activation | +2.64e-03 |
Pos logit contributions | |
Lauder | +0.163 |
Loving | +0.150 |
Sioux | +0.146 |
Subtle | +0.139 |
Hots | +0.137 |
Neg logit contributions | |
obar | -0.177 |
rane | -0.170 |
minist | -0.158 |
oba | -0.155 |
ega | -0.151 |
Token | supplier |
Token ID | 22693 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
obar | +0.005 |
rane | +0.004 |
minist | +0.004 |
oba | +0.004 |
ega | +0.004 |
Neg logit contributions | |
Lauder | -0.005 |
Loving | -0.004 |
Sioux | -0.004 |
Hots | -0.004 |
Subtle | -0.004 |
Token | which |
Token ID | 543 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
Lauder | +0.154 |
Loving | +0.138 |
Sioux | +0.134 |
Subtle | +0.125 |
Hots | +0.124 |
Neg logit contributions | |
obar | -0.227 |
rane | -0.219 |
minist | -0.205 |
oba | -0.200 |
ega | -0.198 |
Token | is |
Token ID | 318 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
Lauder | +0.353 |
Loving | +0.321 |
Sioux | +0.312 |
Subtle | +0.289 |
Hots | +0.288 |
Neg logit contributions | |
obar | -0.463 |
rane | -0.448 |
minist | -0.415 |
oba | -0.410 |
ega | -0.401 |
Token | connected |
Token ID | 5884 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
obar | +0.268 |
rane | +0.256 |
minist | +0.241 |
oba | +0.237 |
ega | +0.234 |
Neg logit contributions | |
Lauder | -0.168 |
Loving | -0.152 |
Sioux | -0.147 |
Subtle | -0.138 |
Hots | -0.135 |
Token | to |
Token ID | 284 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
Lauder | +0.599 |
Loving | +0.530 |
Sioux | +0.527 |
Hots | +0.481 |
Ku | +0.472 |
Neg logit contributions | |
obar | -0.840 |
rane | -0.816 |
minist | -0.755 |
oba | -0.745 |
ega | -0.731 |
Token | Priv |
Token ID | 9243 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
obar | +0.163 |
rane | +0.158 |
minist | +0.148 |
oba | +0.146 |
ega | +0.143 |
Neg logit contributions | |
Lauder | -0.101 |
Loving | -0.090 |
Sioux | -0.088 |
Hots | -0.080 |
Subtle | -0.080 |
Token | at |
Token ID | 265 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
obar | +0.845 |
rane | +0.813 |
oba | +0.751 |
minist | +0.747 |
ega | +0.729 |
Neg logit contributions | |
Lauder | -0.647 |
Loving | -0.578 |
Sioux | -0.570 |
Sikh | -0.517 |
Subtle | -0.516 |
Token | � |
Token ID | 447 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
obar | +1.414 |
rane | +1.354 |
minist | +1.243 |
oba | +1.224 |
ega | +1.202 |
Neg logit contributions | |
Lauder | -1.404 |
Loving | -1.272 |
Sioux | -1.257 |
Hots | -1.173 |
Subtle | -1.152 |
Token | � |
Token ID | 247 |
Feature activation | -8.23e-02 |
Pos logit contributions | |
obar | +0.073 |
rane | +0.071 |
minist | +0.064 |
oba | +0.062 |
ega | +0.062 |
Neg logit contributions | |
Lauder | -0.079 |
Sioux | -0.073 |
Loving | -0.071 |
Hots | -0.067 |
Subtle | -0.065 |
Token | s |
Token ID | 82 |
Feature activation | -8.22e-02 |
Pos logit contributions | |
Lauder | +0.119 |
Loving | +0.106 |
Sioux | +0.105 |
Hots | +0.096 |
Subtle | +0.094 |
Neg logit contributions | |
obar | -0.170 |
rane | -0.165 |
minist | -0.154 |
oba | -0.151 |
ega | -0.149 |
Token | take |
Token ID | 1011 |
Feature activation | -5.88e-02 |
Pos logit contributions | |
Lauder | +0.153 |
Loving | +0.139 |
Sioux | +0.138 |
Hots | +0.128 |
Subtle | +0.127 |
Neg logit contributions | |
obar | -0.137 |
rane | -0.132 |
minist | -0.120 |
oba | -0.118 |
ega | -0.116 |
Token | a |
Token ID | 257 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
Lauder | +0.090 |
Loving | +0.080 |
Sioux | +0.080 |
Hots | +0.073 |
Sikh | +0.072 |
Neg logit contributions | |
obar | -0.116 |
rane | -0.113 |
minist | -0.104 |
oba | -0.103 |
ega | -0.102 |
Token | moment |
Token ID | 2589 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
Lauder | +0.070 |
Loving | +0.062 |
Sioux | +0.062 |
Hots | +0.057 |
Sikh | +0.056 |
Neg logit contributions | |
obar | -0.075 |
rane | -0.074 |
minist | -0.068 |
oba | -0.067 |
ega | -0.066 |
Token | to |
Token ID | 284 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
Lauder | +0.325 |
Loving | +0.291 |
Sioux | +0.287 |
Hots | +0.265 |
Subtle | +0.258 |
Neg logit contributions | |
obar | -0.444 |
rane | -0.431 |
minist | -0.400 |
oba | -0.392 |
ega | -0.386 |
Token | discuss |
Token ID | 2112 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Lauder | +0.161 |
Loving | +0.145 |
Sioux | +0.144 |
Hots | +0.134 |
Subtle | +0.133 |
Neg logit contributions | |
obar | -0.139 |
rane | -0.134 |
minist | -0.122 |
oba | -0.120 |
ega | -0.118 |
Token | some |
Token ID | 617 |
Feature activation | -5.41e-02 |
Pos logit contributions | |
obar | +0.236 |
rane | +0.230 |
minist | +0.214 |
oba | +0.206 |
ega | +0.205 |
Neg logit contributions | |
Lauder | -0.205 |
Loving | -0.183 |
Sioux | -0.181 |
Hots | -0.169 |
Sikh | -0.165 |
Token | of |
Token ID | 286 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Lauder | +0.079 |
Loving | +0.069 |
Sioux | +0.068 |
Hots | +0.063 |
Subtle | +0.061 |
Neg logit contributions | |
obar | -0.111 |
rane | -0.108 |
minist | -0.100 |
oba | -0.098 |
ega | -0.097 |
Token | the |
Token ID | 262 |
Feature activation | -4.51e-02 |
Pos logit contributions | |
Lauder | +0.233 |
Loving | +0.210 |
Sioux | +0.207 |
Hots | +0.193 |
Sikh | +0.189 |
Neg logit contributions | |
obar | -0.266 |
rane | -0.258 |
minist | -0.238 |
oba | -0.232 |
ega | -0.229 |
Token | her |
Token ID | 607 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
Lauder | +0.482 |
Loving | +0.424 |
Sioux | +0.421 |
Hots | +0.393 |
Subtle | +0.387 |
Neg logit contributions | |
obar | -0.603 |
rane | -0.584 |
minist | -0.539 |
oba | -0.530 |
ega | -0.522 |
Token | " |
Token ID | 366 |
Feature activation | -7.05e-02 |
Pos logit contributions | |
Lauder | +0.736 |
Loving | +0.652 |
Sioux | +0.646 |
Hots | +0.608 |
Subtle | +0.599 |
Neg logit contributions | |
obar | -0.784 |
rane | -0.759 |
minist | -0.699 |
oba | -0.684 |
ega | -0.672 |
Token | Last |
Token ID | 5956 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
Lauder | +0.129 |
Loving | +0.117 |
Sioux | +0.116 |
Hots | +0.109 |
Subtle | +0.107 |
Neg logit contributions | |
obar | -0.119 |
rane | -0.115 |
minist | -0.106 |
oba | -0.103 |
ega | -0.101 |
Token | Will |
Token ID | 2561 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
obar | +0.108 |
rane | +0.105 |
minist | +0.097 |
oba | +0.096 |
ega | +0.095 |
Neg logit contributions | |
Lauder | -0.089 |
Loving | -0.078 |
Sioux | -0.077 |
Hots | -0.072 |
Sikh | -0.070 |
Token | and |
Token ID | 290 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
Lauder | +0.386 |
Loving | +0.342 |
Sioux | +0.340 |
Hots | +0.318 |
Subtle | +0.314 |
Neg logit contributions | |
obar | -0.434 |
rane | -0.420 |
minist | -0.384 |
oba | -0.381 |
ega | -0.376 |
Token | Testament |
Token ID | 18318 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
Lauder | +0.176 |
Loving | +0.146 |
Sioux | +0.144 |
Hots | +0.129 |
Subtle | +0.124 |
Neg logit contributions | |
obar | -0.391 |
rane | -0.381 |
minist | -0.358 |
oba | -0.354 |
ega | -0.350 |
Token | ": |
Token ID | 1298 |
Feature activation | +8.67e-02 |
Pos logit contributions | |
Lauder | +0.432 |
Loving | +0.387 |
Sioux | +0.385 |
Hots | +0.362 |
Subtle | +0.357 |
Neg logit contributions | |
obar | -0.402 |
rane | -0.387 |
minist | -0.355 |
oba | -0.348 |
ega | -0.343 |
Token |
|
Token ID | 198 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
obar | +0.197 |
rane | +0.192 |
minist | +0.180 |
oba | +0.177 |
ega | +0.175 |
Neg logit contributions | |
Lauder | -0.108 |
Loving | -0.091 |
Sioux | -0.091 |
Hots | -0.083 |
Subtle | -0.080 |
Token |
|
Token ID | 198 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
Lauder | +0.231 |
Sioux | +0.202 |
Loving | +0.202 |
Hots | +0.189 |
Subtle | +0.186 |
Neg logit contributions | |
obar | -0.236 |
rane | -0.228 |
minist | -0.209 |
oba | -0.205 |
ega | -0.201 |
Token | I |
Token ID | 40 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Lauder | +0.165 |
Loving | +0.150 |
Sioux | +0.149 |
Hots | +0.141 |
Subtle | +0.138 |
Neg logit contributions | |
obar | -0.135 |
rane | -0.131 |
minist | -0.119 |
oba | -0.116 |
ega | -0.113 |
Token | leave |
Token ID | 2666 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
obar | +0.456 |
rane | +0.443 |
minist | +0.408 |
oba | +0.400 |
ega | +0.393 |
Neg logit contributions | |
Lauder | -0.441 |
Sioux | -0.393 |
Loving | -0.393 |
Hots | -0.369 |
Subtle | -0.362 |
Token | for |
Token ID | 329 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
Lauder | +0.090 |
Loving | +0.081 |
Sioux | +0.080 |
Hots | +0.074 |
Subtle | +0.073 |
Neg logit contributions | |
obar | -0.104 |
rane | -0.101 |
minist | -0.093 |
oba | -0.091 |
ega | -0.090 |
Token | it |
Token ID | 340 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
Lauder | +0.028 |
Loving | +0.025 |
Sioux | +0.025 |
Hots | +0.023 |
Subtle | +0.023 |
Neg logit contributions | |
obar | -0.033 |
rane | -0.032 |
minist | -0.029 |
oba | -0.029 |
ega | -0.028 |
Token | first |
Token ID | 717 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
obar | +0.032 |
rane | +0.031 |
minist | +0.029 |
oba | +0.028 |
ega | +0.028 |
Neg logit contributions | |
Lauder | -0.026 |
Loving | -0.024 |
Sioux | -0.023 |
Hots | -0.021 |
Subtle | -0.021 |
Token | came |
Token ID | 1625 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
obar | +0.277 |
rane | +0.267 |
minist | +0.246 |
oba | +0.243 |
ega | +0.240 |
Neg logit contributions | |
Lauder | -0.246 |
Loving | -0.222 |
Sioux | -0.219 |
Subtle | -0.203 |
Hots | -0.201 |
Token | about |
Token ID | 546 |
Feature activation | +8.85e-02 |
Pos logit contributions | |
obar | +0.806 |
rane | +0.776 |
minist | +0.727 |
oba | +0.710 |
ega | +0.707 |
Neg logit contributions | |
Lauder | -0.621 |
Loving | -0.556 |
Sioux | -0.543 |
Subtle | -0.509 |
Hots | -0.505 |
Token | when |
Token ID | 618 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
obar | +0.156 |
rane | +0.152 |
minist | +0.139 |
oba | +0.135 |
ega | +0.134 |
Neg logit contributions | |
Lauder | -0.154 |
Loving | -0.139 |
Sioux | -0.137 |
Hots | -0.129 |
Subtle | -0.128 |
Token | L |
Token ID | 406 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Lauder | +0.695 |
Loving | +0.627 |
Sioux | +0.619 |
Hots | +0.579 |
Subtle | +0.571 |
Neg logit contributions | |
obar | -0.760 |
rane | -0.734 |
minist | -0.677 |
oba | -0.661 |
ega | -0.650 |
Token | . |
Token ID | 13 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
obar | +0.288 |
rane | +0.276 |
minist | +0.255 |
oba | +0.251 |
ega | +0.245 |
Neg logit contributions | |
Lauder | -0.274 |
Loving | -0.249 |
Sioux | -0.247 |
Hots | -0.231 |
Subtle | -0.230 |
Token | A |
Token ID | 32 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
Lauder | +0.160 |
Loving | +0.147 |
Sioux | +0.146 |
Hots | +0.139 |
Subtle | +0.138 |
Neg logit contributions | |
obar | -0.113 |
rane | -0.107 |
minist | -0.095 |
oba | -0.094 |
ega | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
obar | +0.861 |
rane | +0.828 |
minist | +0.759 |
oba | +0.742 |
ega | +0.725 |
Neg logit contributions | |
Lauder | -0.931 |
Loving | -0.851 |
Sioux | -0.837 |
Hots | -0.789 |
Subtle | -0.779 |
Token | attorney |
Token ID | 6136 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
Lauder | +0.047 |
Loving | +0.042 |
Sioux | +0.042 |
Hots | +0.039 |
Subtle | +0.039 |
Neg logit contributions | |
obar | -0.049 |
rane | -0.047 |
minist | -0.044 |
oba | -0.043 |
ega | -0.041 |
Token | refunds |
Token ID | 36903 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
Lauder | +0.513 |
Loving | +0.460 |
Sioux | +0.458 |
Hots | +0.422 |
Subtle | +0.417 |
Neg logit contributions | |
obar | -0.570 |
rane | -0.555 |
minist | -0.518 |
oba | -0.499 |
ega | -0.492 |
Token | work |
Token ID | 670 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
Lauder | +0.651 |
Loving | +0.589 |
Sioux | +0.583 |
Hots | +0.542 |
Subtle | +0.534 |
Neg logit contributions | |
obar | -0.694 |
rane | -0.671 |
minist | -0.618 |
oba | -0.604 |
ega | -0.595 |
Token | ); |
Token ID | 1776 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
Lauder | +0.379 |
Loving | +0.341 |
Sioux | +0.336 |
Hots | +0.312 |
Subtle | +0.308 |
Neg logit contributions | |
obar | -0.420 |
rane | -0.406 |
minist | -0.376 |
oba | -0.366 |
ega | -0.361 |
Token | CSV |
Token ID | 44189 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
obar | +0.597 |
rane | +0.577 |
minist | +0.536 |
oba | +0.519 |
ega | +0.505 |
Neg logit contributions | |
Lauder | -0.551 |
Sioux | -0.493 |
Loving | -0.490 |
Sikh | -0.451 |
Hots | -0.450 |
Token | ( |
Token ID | 357 |
Feature activation | -9.86e-02 |
Pos logit contributions | |
Lauder | +0.230 |
Loving | +0.206 |
Sioux | +0.204 |
Hots | +0.188 |
Subtle | +0.186 |
Neg logit contributions | |
obar | -0.267 |
rane | -0.259 |
minist | -0.240 |
oba | -0.234 |
ega | -0.231 |
Token | BIP |
Token ID | 47772 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Lauder | +0.170 |
Loving | +0.152 |
Sioux | +0.151 |
Hots | +0.141 |
Subtle | +0.138 |
Neg logit contributions | |
obar | -0.179 |
rane | -0.174 |
minist | -0.162 |
oba | -0.157 |
ega | -0.154 |
Token | 68 |
Token ID | 3104 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Lauder | +2.235 |
Loving | +2.041 |
Sioux | +2.013 |
Hots | +1.889 |
Subtle | +1.853 |
Neg logit contributions | |
obar | -2.188 |
rane | -2.113 |
minist | -1.934 |
oba | -1.889 |
ega | -1.855 |
Token | / |
Token ID | 1220 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Lauder | +0.201 |
Loving | +0.179 |
Sioux | +0.176 |
Hots | +0.163 |
Subtle | +0.161 |
Neg logit contributions | |
obar | -0.241 |
rane | -0.235 |
minist | -0.217 |
oba | -0.212 |
ega | -0.209 |
Token | B |
Token ID | 347 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
obar | +2.276 |
rane | +2.210 |
minist | +2.060 |
oba | +2.024 |
ega | +1.974 |
Neg logit contributions | |
Lauder | -1.797 |
Sioux | -1.585 |
Loving | -1.558 |
Hots | -1.443 |
Sikh | -1.427 |
Token | IP |
Token ID | 4061 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
Lauder | +0.628 |
Loving | +0.535 |
Sioux | +0.528 |
Hots | +0.468 |
Subtle | +0.456 |
Neg logit contributions | |
obar | -1.363 |
rane | -1.331 |
minist | -1.254 |
oba | -1.234 |
ega | -1.216 |
Token | 112 |
Token ID | 14686 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Lauder | +1.002 |
Loving | +0.909 |
Sioux | +0.901 |
Hots | +0.842 |
Subtle | +0.832 |
Neg logit contributions | |
obar | -0.945 |
rane | -0.910 |
minist | -0.833 |
oba | -0.819 |
ega | -0.804 |
Token | app |
Token ID | 598 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
obar | +0.039 |
rane | +0.037 |
oba | +0.034 |
ega | +0.034 |
minist | +0.034 |
Neg logit contributions | |
Lauder | -0.025 |
Loving | -0.022 |
Sioux | -0.022 |
Hots | -0.020 |
Subtle | -0.020 |
Token | data |
Token ID | 7890 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
Lauder | +1.025 |
Loving | +0.957 |
Sioux | +0.953 |
Hots | +0.906 |
Subtle | +0.895 |
Neg logit contributions | |
obar | -0.538 |
rane | -0.503 |
minist | -0.439 |
oba | -0.429 |
ega | -0.415 |
Token | _ |
Token ID | 4808 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
obar | +0.080 |
rane | +0.077 |
oba | +0.071 |
minist | +0.070 |
ega | +0.070 |
Neg logit contributions | |
Lauder | -0.058 |
Sioux | -0.051 |
Loving | -0.051 |
Hots | -0.046 |
Subtle | -0.046 |
Token | full |
Token ID | 1336 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Lauder | +0.197 |
Sioux | +0.178 |
Loving | +0.177 |
Hots | +0.166 |
Subtle | +0.163 |
Neg logit contributions | |
obar | -0.170 |
rane | -0.162 |
minist | -0.146 |
ega | -0.144 |
oba | -0.144 |
Token | v |
Token ID | 410 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
Lauder | +1.384 |
Loving | +1.213 |
Sioux | +1.192 |
Hots | +1.093 |
Subtle | +1.052 |
Neg logit contributions | |
obar | -2.441 |
rane | -2.353 |
minist | -2.189 |
oba | -2.171 |
ega | -2.146 |
Token | ) |
Token ID | 1267 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Lauder | +0.648 |
Loving | +0.590 |
Sioux | +0.585 |
Hots | +0.547 |
Subtle | +0.542 |
Neg logit contributions | |
obar | -0.581 |
rane | -0.557 |
minist | -0.509 |
oba | -0.500 |
ega | -0.490 |
Token | { |
Token ID | 1391 |
Feature activation | +9.39e-02 |
Pos logit contributions | |
Lauder | +2.360 |
Loving | +2.158 |
Sioux | +2.137 |
Hots | +2.008 |
Subtle | +1.976 |
Neg logit contributions | |
obar | -2.065 |
rane | -1.988 |
minist | -1.803 |
oba | -1.766 |
ega | -1.732 |
Token | // |
Token ID | 3373 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
obar | +0.167 |
rane | +0.161 |
minist | +0.148 |
oba | +0.144 |
ega | +0.142 |
Neg logit contributions | |
Lauder | -0.164 |
Loving | -0.149 |
Sioux | -0.148 |
Hots | -0.138 |
Sikh | -0.135 |
Token | Time |
Token ID | 3862 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
Lauder | +0.536 |
Loving | +0.478 |
Sioux | +0.466 |
Hots | +0.433 |
Subtle | +0.425 |
Neg logit contributions | |
obar | -0.768 |
rane | -0.749 |
minist | -0.700 |
oba | -0.679 |
ega | -0.671 |
Token | component |
Token ID | 7515 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
Lauder | +0.816 |
Loving | +0.752 |
Sioux | +0.745 |
Hots | +0.711 |
Subtle | +0.695 |
Neg logit contributions | |
obar | -0.632 |
rane | -0.601 |
minist | -0.552 |
oba | -0.530 |
ega | -0.522 |
Token | const |
Token ID | 1500 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
obar | +0.094 |
rane | +0.091 |
minist | +0.086 |
oba | +0.085 |
ega | +0.084 |
Neg logit contributions | |
Lauder | -0.042 |
Loving | -0.035 |
Sioux | -0.034 |
Hots | -0.029 |
Subtle | -0.029 |
Token | OF |
Token ID | 3963 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
Lauder | +0.907 |
Loving | +0.809 |
Sioux | +0.797 |
Hots | +0.739 |
Subtle | +0.720 |
Neg logit contributions | |
obar | -1.189 |
rane | -1.159 |
minist | -1.072 |
oba | -1.051 |
ega | -1.038 |
Token | TRAN |
Token ID | 48213 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
obar | +0.315 |
rane | +0.309 |
minist | +0.285 |
oba | +0.278 |
ega | +0.276 |
Neg logit contributions | |
Lauder | -0.267 |
Loving | -0.238 |
Sioux | -0.234 |
Hots | -0.219 |
Sikh | -0.212 |
Token | SM |
Token ID | 12310 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
obar | +1.792 |
rane | +1.766 |
minist | +1.641 |
oba | +1.610 |
ega | +1.608 |
Neg logit contributions | |
Lauder | -0.870 |
Loving | -0.741 |
Sioux | -0.729 |
Hots | -0.656 |
Sikh | -0.631 |
Token | ISSION |
Token ID | 40373 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
Lauder | +0.525 |
Loving | +0.470 |
Sioux | +0.463 |
Hots | +0.431 |
Subtle | +0.421 |
Neg logit contributions | |
obar | -0.641 |
rane | -0.628 |
minist | -0.576 |
oba | -0.565 |
ega | -0.563 |
Token | /// |
Token ID | 34013 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
obar | +0.292 |
rane | +0.283 |
minist | +0.261 |
oba | +0.256 |
ega | +0.252 |
Neg logit contributions | |
Lauder | -0.263 |
Loving | -0.237 |
Sioux | -0.234 |
Hots | -0.219 |
Subtle | -0.213 |
Token | ---------------------------------------------------------------- |
Token ID | 10097 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
obar | +0.041 |
rane | +0.040 |
minist | +0.037 |
oba | +0.036 |
ega | +0.036 |
Neg logit contributions | |
Lauder | -0.036 |
Loving | -0.033 |
Sioux | -0.032 |
Hots | -0.030 |
Subtle | -0.029 |
Token | ---------------------------------------------------------------- |
Token ID | 10097 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Lauder | +2.102 |
Loving | +1.916 |
Sioux | +1.891 |
Hots | +1.768 |
Subtle | +1.735 |
Neg logit contributions | |
obar | -2.173 |
rane | -2.109 |
minist | -1.937 |
oba | -1.888 |
ega | -1.853 |
Token | ------------------------ |
Token ID | 22369 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
Lauder | +1.929 |
Loving | +1.756 |
Sioux | +1.733 |
Hots | +1.618 |
Subtle | +1.590 |
Neg logit contributions | |
obar | -2.037 |
rane | -1.975 |
minist | -1.814 |
oba | -1.771 |
ega | -1.740 |
Token | -- |
Token ID | 438 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
Lauder | +0.498 |
Loving | +0.449 |
Sioux | +0.442 |
Hots | +0.412 |
Subtle | +0.403 |
Neg logit contributions | |
obar | -0.572 |
rane | -0.553 |
minist | -0.510 |
oba | -0.500 |
ega | -0.493 |
Token | /// |
Token ID | 20379 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
Lauder | +0.677 |
Loving | +0.612 |
Sioux | +0.605 |
Hots | +0.565 |
Subtle | +0.554 |
Neg logit contributions | |
obar | -0.711 |
rane | -0.688 |
minist | -0.632 |
oba | -0.619 |
ega | -0.609 |
Token | L |
Token ID | 406 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Lauder | +0.654 |
Loving | +0.589 |
Sioux | +0.581 |
Hots | +0.542 |
Subtle | +0.530 |
Neg logit contributions | |
obar | -0.740 |
rane | -0.718 |
minist | -0.662 |
oba | -0.648 |
ega | -0.638 |
Token | including |
Token ID | 1390 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
obar | +0.244 |
rane | +0.234 |
minist | +0.220 |
oba | +0.210 |
ega | +0.208 |
Neg logit contributions | |
Lauder | -0.228 |
Loving | -0.204 |
Sioux | -0.201 |
Hots | -0.190 |
Subtle | -0.189 |
Token | items |
Token ID | 3709 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
obar | +0.589 |
rane | +0.568 |
minist | +0.528 |
oba | +0.516 |
ega | +0.504 |
Neg logit contributions | |
Lauder | -0.491 |
Loving | -0.440 |
Sioux | -0.434 |
Hots | -0.406 |
Subtle | -0.402 |
Token | from |
Token ID | 422 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
obar | +0.602 |
rane | +0.585 |
minist | +0.541 |
oba | +0.526 |
ega | +0.525 |
Neg logit contributions | |
Lauder | -0.479 |
Loving | -0.423 |
Sioux | -0.420 |
Hots | -0.391 |
Subtle | -0.388 |
Token | the |
Token ID | 262 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Lauder | +0.224 |
Loving | +0.201 |
Sioux | +0.198 |
Hots | +0.185 |
Subtle | +0.183 |
Neg logit contributions | |
obar | -0.259 |
rane | -0.251 |
minist | -0.233 |
oba | -0.228 |
ega | -0.224 |
Token | Imperial |
Token ID | 11773 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
obar | +0.253 |
rane | +0.246 |
minist | +0.228 |
oba | +0.224 |
ega | +0.219 |
Neg logit contributions | |
Lauder | -0.195 |
Loving | -0.173 |
Sioux | -0.171 |
Hots | -0.160 |
Subtle | -0.157 |
Token | Hotel |
Token ID | 12696 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
obar | +1.554 |
rane | +1.483 |
oba | +1.375 |
minist | +1.372 |
ega | +1.330 |
Neg logit contributions | |
Lauder | -1.223 |
Loving | -1.090 |
Sioux | -1.069 |
Subtle | -0.984 |
Hots | -0.981 |
Token | in |
Token ID | 287 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
Lauder | +2.130 |
Loving | +1.916 |
Sioux | +1.885 |
Hots | +1.753 |
Subtle | +1.724 |
Neg logit contributions | |
obar | -2.595 |
rane | -2.516 |
minist | -2.324 |
oba | -2.280 |
ega | -2.243 |
Token | Tokyo |
Token ID | 11790 |
Feature activation | -9.51e-02 |
Pos logit contributions | |
obar | +0.113 |
rane | +0.110 |
minist | +0.101 |
oba | +0.101 |
ega | +0.098 |
Neg logit contributions | |
Lauder | -0.086 |
Loving | -0.077 |
Sioux | -0.075 |
Subtle | -0.070 |
Hots | -0.070 |
Token | and |
Token ID | 290 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
Lauder | +0.157 |
Loving | +0.140 |
Sioux | +0.140 |
Subtle | +0.128 |
Hots | +0.128 |
Neg logit contributions | |
obar | -0.178 |
rane | -0.170 |
minist | -0.157 |
oba | -0.155 |
ega | -0.153 |
Token | Wright |
Token ID | 12206 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
obar | +0.078 |
rane | +0.076 |
minist | +0.070 |
oba | +0.069 |
ega | +0.067 |
Neg logit contributions | |
Lauder | -0.063 |
Loving | -0.057 |
Sioux | -0.056 |
Hots | -0.052 |
Subtle | -0.052 |
Token | � |
Token ID | 447 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
obar | +0.359 |
rane | +0.345 |
minist | +0.324 |
oba | +0.316 |
ega | +0.311 |
Neg logit contributions | |
Lauder | -0.293 |
Loving | -0.263 |
Sioux | -0.258 |
Hots | -0.239 |
Subtle | -0.238 |
Token | d |
Token ID | 288 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
obar | +0.481 |
rane | +0.470 |
minist | +0.439 |
oba | +0.426 |
ega | +0.423 |
Neg logit contributions | |
Lauder | -0.362 |
Loving | -0.327 |
Sioux | -0.321 |
Hots | -0.297 |
Sikh | -0.290 |
Token | ans |
Token ID | 504 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
Lauder | +0.446 |
Loving | +0.414 |
Sioux | +0.408 |
Hots | +0.388 |
Subtle | +0.384 |
Neg logit contributions | |
obar | -0.274 |
rane | -0.263 |
minist | -0.234 |
oba | -0.228 |
ega | -0.221 |
Token | la |
Token ID | 8591 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
obar | +0.853 |
rane | +0.833 |
minist | +0.788 |
oba | +0.763 |
ega | +0.754 |
Neg logit contributions | |
Lauder | -0.637 |
Loving | -0.575 |
Sioux | -0.562 |
Hots | -0.520 |
Sikh | -0.511 |
Token | corporation |
Token ID | 12017 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
Lauder | +0.725 |
Loving | +0.656 |
Sioux | +0.645 |
Hots | +0.602 |
Subtle | +0.590 |
Neg logit contributions | |
obar | -0.838 |
rane | -0.810 |
minist | -0.751 |
oba | -0.734 |
ega | -0.722 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
obar | +0.748 |
rane | +0.733 |
minist | +0.685 |
oba | +0.669 |
ega | +0.665 |
Neg logit contributions | |
Lauder | -0.472 |
Loving | -0.424 |
Sioux | -0.413 |
Hots | -0.379 |
Subtle | -0.369 |
Token | Apr |
Token ID | 13680 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Lauder | +0.294 |
Loving | +0.265 |
Sioux | +0.262 |
Hots | +0.244 |
Sikh | +0.239 |
Neg logit contributions | |
obar | -0.327 |
rane | -0.319 |
minist | -0.295 |
oba | -0.286 |
ega | -0.283 |
Token | è |
Token ID | 14064 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
Lauder | +2.368 |
Loving | +2.174 |
Sioux | +2.149 |
Hots | +2.025 |
Subtle | +1.990 |
Neg logit contributions | |
obar | -1.985 |
rane | -1.910 |
minist | -1.734 |
oba | -1.691 |
ega | -1.664 |
Token | s |
Token ID | 82 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
obar | +0.684 |
rane | +0.666 |
minist | +0.623 |
oba | +0.601 |
ega | +0.594 |
Neg logit contributions | |
Lauder | -0.509 |
Loving | -0.462 |
Sioux | -0.456 |
Hots | -0.421 |
Sikh | -0.413 |
Token | une |
Token ID | 17809 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
obar | +0.043 |
rane | +0.042 |
minist | +0.039 |
oba | +0.038 |
ega | +0.038 |
Neg logit contributions | |
Lauder | -0.033 |
Loving | -0.029 |
Sioux | -0.029 |
Hots | -0.027 |
Subtle | -0.026 |
Token | tentative |
Token ID | 38358 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
obar | +0.355 |
rane | +0.345 |
minist | +0.323 |
oba | +0.313 |
ega | +0.308 |
Neg logit contributions | |
Lauder | -0.303 |
Loving | -0.276 |
Sioux | -0.270 |
Hots | -0.253 |
Subtle | -0.248 |
Token | inf |
Token ID | 1167 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
obar | +0.028 |
rane | +0.027 |
minist | +0.026 |
oba | +0.025 |
ega | +0.025 |
Neg logit contributions | |
Lauder | -0.021 |
Loving | -0.019 |
Sioux | -0.019 |
Hots | -0.017 |
Subtle | -0.017 |