Token | ment |
Token ID | 434 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
ahime | +0.065 |
usterity | +0.065 |
Berks | +0.058 |
groupon | +0.056 |
Origin | +0.055 |
Neg logit contributions | |
Deb | -0.089 |
ourke | -0.088 |
Vand | -0.086 |
$$ | -0.085 |
「 | -0.085 |
Token | ? |
Token ID | 30 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
Deb | +0.421 |
ourke | +0.410 |
Vand | +0.400 |
$$ | +0.396 |
「 | +0.395 |
Neg logit contributions | |
ahime | -0.543 |
usterity | -0.538 |
Berks | -0.498 |
groupon | -0.486 |
Origin | -0.476 |
Token | And |
Token ID | 843 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
ahime | +0.027 |
usterity | +0.027 |
Berks | +0.025 |
groupon | +0.024 |
Origin | +0.024 |
Neg logit contributions | |
Deb | -0.020 |
ourke | -0.020 |
Vand | -0.019 |
$$ | -0.019 |
「 | -0.019 |
Token | what |
Token ID | 644 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Deb | +0.059 |
ourke | +0.057 |
Vand | +0.056 |
$$ | +0.056 |
「 | +0.055 |
Neg logit contributions | |
ahime | -0.067 |
usterity | -0.067 |
Berks | -0.062 |
groupon | -0.060 |
adobe | -0.059 |
Token | better |
Token ID | 1365 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Deb | +0.662 |
ourke | +0.643 |
Vand | +0.630 |
$$ | +0.624 |
「 | +0.622 |
Neg logit contributions | |
ahime | -0.698 |
usterity | -0.694 |
Berks | -0.634 |
groupon | -0.617 |
Origin | -0.604 |
Token | way |
Token ID | 835 |
Feature activation | +7.71e+00 |
Pos logit contributions | |
Deb | +0.336 |
ourke | +0.309 |
Vand | +0.287 |
$$ | +0.281 |
「 | +0.276 |
Neg logit contributions | |
ahime | -1.720 |
usterity | -1.713 |
Berks | -1.621 |
groupon | -1.598 |
Origin | -1.578 |
Token | to |
Token ID | 284 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
Deb | +3.709 |
ourke | +3.450 |
Vand | +3.431 |
「 | +3.381 |
$$ | +3.337 |
Neg logit contributions | |
ahime | -6.486 |
usterity | -6.441 |
Berks | -5.976 |
adobe | -5.768 |
Origin | -5.687 |
Token | get |
Token ID | 651 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
Deb | +2.198 |
ourke | +2.099 |
Vand | +2.088 |
「 | +2.071 |
$$ | +2.067 |
Neg logit contributions | |
ahime | -2.084 |
usterity | -2.053 |
Berks | -1.861 |
groupon | -1.803 |
adobe | -1.774 |
Token | people |
Token ID | 661 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
Deb | +0.027 |
ourke | +0.027 |
Vand | +0.026 |
$$ | +0.026 |
「 | +0.026 |
Neg logit contributions | |
ahime | -0.028 |
usterity | -0.028 |
Berks | -0.026 |
groupon | -0.025 |
Origin | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
ahime | +0.233 |
usterity | +0.232 |
Berks | +0.214 |
groupon | +0.208 |
Origin | +0.203 |
Neg logit contributions | |
Deb | -0.219 |
ourke | -0.216 |
Vand | -0.209 |
$$ | -0.208 |
「 | -0.208 |
Token | pay |
Token ID | 1414 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
Deb | +0.244 |
ourke | +0.239 |
Vand | +0.232 |
$$ | +0.230 |
「 | +0.229 |
Neg logit contributions | |
ahime | -0.261 |
usterity | -0.261 |
Berks | -0.240 |
groupon | -0.233 |
adobe | -0.227 |
Token | � |
Token ID | 447 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
Deb | +0.156 |
ourke | +0.151 |
Vand | +0.148 |
$$ | +0.146 |
「 | +0.146 |
Neg logit contributions | |
ahime | -0.190 |
usterity | -0.189 |
Berks | -0.174 |
groupon | -0.169 |
Origin | -0.166 |
Token | � |
Token ID | 251 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
Deb | +0.089 |
ourke | +0.086 |
Vand | +0.084 |
「 | +0.083 |
$$ | +0.083 |
Neg logit contributions | |
ahime | -0.130 |
usterity | -0.130 |
Berks | -0.120 |
groupon | -0.118 |
Origin | -0.115 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
ahime | +0.562 |
usterity | +0.560 |
Berks | +0.518 |
groupon | +0.507 |
Origin | +0.496 |
Neg logit contributions | |
Deb | -0.444 |
ourke | -0.434 |
Vand | -0.421 |
$$ | -0.416 |
「 | -0.415 |
Token | What |
Token ID | 2061 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
usterity | +0.633 |
ahime | +0.632 |
Berks | +0.575 |
groupon | +0.570 |
Origin | +0.563 |
Neg logit contributions | |
Deb | -0.597 |
ourke | -0.575 |
Vand | -0.568 |
「 | -0.559 |
$$ | -0.550 |
Token | better |
Token ID | 1365 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
usterity | +0.359 |
ahime | +0.358 |
Berks | +0.328 |
groupon | +0.320 |
Origin | +0.315 |
Neg logit contributions | |
Deb | -0.331 |
ourke | -0.324 |
Vand | -0.316 |
$$ | -0.315 |
「 | -0.313 |
Token | way |
Token ID | 835 |
Feature activation | +7.63e+00 |
Pos logit contributions | |
Deb | +0.335 |
ourke | +0.314 |
Vand | +0.298 |
$$ | +0.293 |
「 | +0.290 |
Neg logit contributions | |
ahime | -1.198 |
usterity | -1.193 |
Berks | -1.125 |
groupon | -1.106 |
Origin | -1.092 |
Token | to |
Token ID | 284 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
Deb | +3.525 |
Vand | +3.300 |
ourke | +3.259 |
$$ | +3.229 |
「 | +3.219 |
Neg logit contributions | |
usterity | -6.502 |
ahime | -6.501 |
Berks | -6.045 |
adobe | -5.837 |
Origin | -5.773 |
Token | raise |
Token ID | 5298 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Deb | +2.196 |
ourke | +2.085 |
Vand | +2.085 |
「 | +2.068 |
$$ | +2.065 |
Neg logit contributions | |
ahime | -2.216 |
usterity | -2.180 |
Berks | -1.990 |
groupon | -1.930 |
adobe | -1.898 |
Token | awareness |
Token ID | 9359 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
Deb | +0.910 |
ourke | +0.880 |
Vand | +0.862 |
$$ | +0.854 |
「 | +0.851 |
Neg logit contributions | |
ahime | -1.092 |
usterity | -1.085 |
Berks | -0.996 |
groupon | -0.972 |
Origin | -0.952 |
Token | of |
Token ID | 286 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
Deb | +0.514 |
ourke | +0.496 |
Vand | +0.488 |
$$ | +0.484 |
「 | +0.481 |
Neg logit contributions | |
ahime | -0.556 |
usterity | -0.552 |
Berks | -0.505 |
groupon | -0.490 |
adobe | -0.482 |
Token | an |
Token ID | 281 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Deb | +0.272 |
ourke | +0.265 |
Vand | +0.259 |
$$ | +0.257 |
「 | +0.256 |
Neg logit contributions | |
ahime | -0.298 |
usterity | -0.297 |
Berks | -0.272 |
groupon | -0.265 |
Origin | -0.259 |
Token | with |
Token ID | 351 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
ahime | +0.369 |
usterity | +0.367 |
Berks | +0.337 |
groupon | +0.327 |
Origin | +0.319 |
Neg logit contributions | |
Deb | -0.371 |
ourke | -0.364 |
Vand | -0.354 |
$$ | -0.352 |
「 | -0.349 |
Token | two |
Token ID | 734 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
ahime | +0.024 |
usterity | +0.024 |
Berks | +0.022 |
groupon | +0.022 |
Origin | +0.021 |
Neg logit contributions | |
Deb | -0.022 |
ourke | -0.021 |
Vand | -0.020 |
「 | -0.020 |
$$ | -0.020 |
Token | openings |
Token ID | 28431 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
usterity | +0.655 |
ahime | +0.643 |
Berks | +0.610 |
groupon | +0.582 |
Origin | +0.576 |
Neg logit contributions | |
ourke | -0.522 |
Deb | -0.520 |
$$ | -0.494 |
Vand | -0.489 |
「 | -0.483 |
Token | on |
Token ID | 319 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
Deb | +0.510 |
ourke | +0.494 |
Vand | +0.485 |
$$ | +0.481 |
「 | +0.480 |
Neg logit contributions | |
ahime | -0.526 |
usterity | -0.522 |
Berks | -0.476 |
groupon | -0.463 |
Origin | -0.453 |
Token | the |
Token ID | 262 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Deb | +0.153 |
ourke | +0.150 |
Vand | +0.145 |
$$ | +0.144 |
「 | +0.143 |
Neg logit contributions | |
usterity | -0.176 |
ahime | -0.176 |
Berks | -0.162 |
groupon | -0.157 |
adobe | -0.154 |
Token | defensive |
Token ID | 6110 |
Feature activation | +7.31e+00 |
Pos logit contributions | |
Deb | +0.631 |
ourke | +0.615 |
Vand | +0.590 |
$$ | +0.588 |
「 | +0.586 |
Neg logit contributions | |
usterity | -0.887 |
ahime | -0.887 |
Berks | -0.827 |
groupon | -0.802 |
adobe | -0.785 |
Token | line |
Token ID | 1627 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
Deb | +3.697 |
Vand | +3.543 |
ourke | +3.471 |
「 | +3.458 |
$$ | +3.452 |
Neg logit contributions | |
ahime | -6.041 |
usterity | -5.878 |
Origin | -5.353 |
adobe | -5.332 |
Berks | -5.321 |
Token | , |
Token ID | 11 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
Deb | +0.193 |
ourke | +0.187 |
Vand | +0.183 |
$$ | +0.182 |
「 | +0.181 |
Neg logit contributions | |
ahime | -0.195 |
usterity | -0.193 |
Berks | -0.176 |
groupon | -0.172 |
adobe | -0.168 |
Token | hopes |
Token ID | 7176 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
Deb | +0.224 |
ourke | +0.219 |
Vand | +0.213 |
$$ | +0.211 |
「 | +0.211 |
Neg logit contributions | |
ahime | -0.246 |
usterity | -0.244 |
Berks | -0.225 |
groupon | -0.219 |
Origin | -0.214 |
Token | are |
Token ID | 389 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
Deb | +0.154 |
ourke | +0.150 |
Vand | +0.146 |
$$ | +0.146 |
「 | +0.145 |
Neg logit contributions | |
ahime | -0.184 |
usterity | -0.182 |
Berks | -0.169 |
groupon | -0.164 |
Origin | -0.161 |
Token | high |
Token ID | 1029 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
ahime | +1.330 |
usterity | +1.315 |
Berks | +1.231 |
groupon | +1.202 |
Origin | +1.170 |
Neg logit contributions | |
Deb | -1.023 |
ourke | -0.998 |
Vand | -0.958 |
「 | -0.958 |
$$ | -0.957 |
Token | . |
Token ID | 13 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Deb | +0.242 |
ourke | +0.235 |
Vand | +0.230 |
$$ | +0.228 |
「 | +0.228 |
Neg logit contributions | |
ahime | -0.238 |
usterity | -0.237 |
Berks | -0.215 |
groupon | -0.210 |
Origin | -0.205 |
Token |
|
Token ID | 198 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ahime | +0.199 |
usterity | +0.198 |
Berks | +0.183 |
groupon | +0.179 |
Origin | +0.175 |
Neg logit contributions | |
Deb | -0.153 |
ourke | -0.149 |
Vand | -0.145 |
$$ | -0.143 |
「 | -0.143 |
Token |
|
Token ID | 198 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
Deb | +0.630 |
ourke | +0.612 |
Vand | +0.597 |
$$ | +0.589 |
「 | +0.589 |
Neg logit contributions | |
ahime | -0.818 |
usterity | -0.814 |
Berks | -0.750 |
groupon | -0.735 |
Origin | -0.720 |
Token | On |
Token ID | 2202 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
Deb | +0.546 |
ourke | +0.529 |
Vand | +0.518 |
「 | +0.512 |
$$ | +0.512 |
Neg logit contributions | |
ahime | -0.631 |
usterity | -0.628 |
Berks | -0.575 |
groupon | -0.562 |
Origin | -0.552 |
Token | the |
Token ID | 262 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
Deb | +0.493 |
ourke | +0.480 |
Vand | +0.470 |
$$ | +0.467 |
「 | +0.465 |
Neg logit contributions | |
ahime | -0.518 |
usterity | -0.516 |
Berks | -0.470 |
groupon | -0.459 |
Origin | -0.449 |
Token | left |
Token ID | 1364 |
Feature activation | +7.15e+00 |
Pos logit contributions | |
Deb | +1.624 |
ourke | +1.570 |
Vand | +1.539 |
$$ | +1.522 |
「 | +1.520 |
Neg logit contributions | |
ahime | -1.909 |
usterity | -1.894 |
Berks | -1.737 |
groupon | -1.693 |
adobe | -1.660 |
Token | : |
Token ID | 25 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Deb | +4.132 |
ourke | +3.857 |
Vand | +3.844 |
「 | +3.825 |
$$ | +3.779 |
Neg logit contributions | |
ahime | -5.388 |
usterity | -5.304 |
Berks | -4.855 |
groupon | -4.759 |
adobe | -4.702 |
Token | Bo |
Token ID | 3248 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
Deb | +1.177 |
ourke | +1.139 |
Vand | +1.115 |
$$ | +1.104 |
「 | +1.101 |
Neg logit contributions | |
ahime | -1.430 |
usterity | -1.421 |
Berks | -1.305 |
groupon | -1.273 |
Origin | -1.248 |
Token | Scar |
Token ID | 12089 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
usterity | +0.330 |
ahime | +0.330 |
Berks | +0.304 |
groupon | +0.296 |
Origin | +0.288 |
Neg logit contributions | |
Deb | -0.270 |
ourke | -0.263 |
Vand | -0.256 |
「 | -0.255 |
$$ | -0.251 |
Token | b |
Token ID | 65 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
Deb | +1.064 |
ourke | +1.030 |
Vand | +1.010 |
$$ | +1.000 |
「 | +0.996 |
Neg logit contributions | |
ahime | -1.231 |
usterity | -1.225 |
Berks | -1.121 |
groupon | -1.094 |
Origin | -1.072 |
Token | rough |
Token ID | 740 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
usterity | +2.327 |
ahime | +2.274 |
Berks | +2.104 |
groupon | +2.066 |
urger | +2.061 |
Neg logit contributions | |
Deb | -1.795 |
ourke | -1.700 |
Vand | -1.696 |
「 | -1.669 |
Lama | -1.668 |
Token | irrational |
Token ID | 25086 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
Deb | +1.589 |
ourke | +1.522 |
Vand | +1.500 |
「 | +1.494 |
$$ | +1.479 |
Neg logit contributions | |
ahime | -1.957 |
usterity | -1.936 |
Berks | -1.780 |
groupon | -1.738 |
adobe | -1.706 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Deb | +0.327 |
ourke | +0.317 |
Vand | +0.311 |
$$ | +0.309 |
「 | +0.308 |
Neg logit contributions | |
ahime | -0.342 |
usterity | -0.339 |
Berks | -0.309 |
groupon | -0.301 |
adobe | -0.295 |
Token | shall |
Token ID | 2236 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Deb | +0.663 |
ourke | +0.643 |
Vand | +0.630 |
$$ | +0.624 |
「 | +0.623 |
Neg logit contributions | |
ahime | -0.722 |
usterity | -0.717 |
Berks | -0.656 |
groupon | -0.639 |
adobe | -0.626 |
Token | seem |
Token ID | 1283 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
usterity | +0.972 |
ahime | +0.962 |
Berks | +0.873 |
groupon | +0.865 |
fore | +0.851 |
Neg logit contributions | |
Deb | -0.799 |
ourke | -0.785 |
Vand | -0.771 |
$$ | -0.744 |
「 | -0.741 |
Token | rational |
Token ID | 9377 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Deb | +2.080 |
ourke | +1.979 |
「 | +1.969 |
Vand | +1.964 |
$$ | +1.940 |
Neg logit contributions | |
ahime | -2.482 |
usterity | -2.434 |
Berks | -2.254 |
groupon | -2.180 |
adobe | -2.157 |
Token | enough |
Token ID | 1576 |
Feature activation | +7.08e+00 |
Pos logit contributions | |
Deb | +0.680 |
ourke | +0.659 |
Vand | +0.647 |
$$ | +0.641 |
「 | +0.639 |
Neg logit contributions | |
ahime | -0.738 |
usterity | -0.733 |
Berks | -0.670 |
groupon | -0.653 |
Origin | -0.639 |
Token | . |
Token ID | 13 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
Deb | +3.915 |
「 | +3.760 |
ourke | +3.729 |
$$ | +3.688 |
Vand | +3.664 |
Neg logit contributions | |
ahime | -5.420 |
usterity | -5.404 |
Berks | -5.038 |
groupon | -4.814 |
adobe | -4.805 |
Token | � |
Token ID | 447 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
Deb | +0.314 |
ourke | +0.308 |
Vand | +0.298 |
$$ | +0.295 |
「 | +0.294 |
Neg logit contributions | |
ahime | -0.423 |
usterity | -0.422 |
Berks | -0.390 |
groupon | -0.381 |
Origin | -0.376 |
Token | � |
Token ID | 251 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
ahime | +0.341 |
usterity | +0.339 |
Berks | +0.314 |
groupon | +0.307 |
Origin | +0.301 |
Neg logit contributions | |
Deb | -0.242 |
ourke | -0.234 |
Vand | -0.228 |
$$ | -0.225 |
「 | -0.224 |
Token | [ |
Token ID | 58 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Deb | +0.055 |
ourke | +0.054 |
Vand | +0.052 |
$$ | +0.051 |
「 | +0.051 |
Neg logit contributions | |
ahime | -0.078 |
usterity | -0.077 |
Berks | -0.072 |
groupon | -0.070 |
Origin | -0.069 |
Token | 20 |
Token ID | 1238 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
Deb | +0.910 |
ourke | +0.882 |
$$ | +0.868 |
Vand | +0.859 |
「 | +0.857 |
Neg logit contributions | |
ahime | -1.000 |
usterity | -0.991 |
Berks | -0.907 |
groupon | -0.869 |
adobe | -0.859 |
Token | and |
Token ID | 290 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Deb | +0.446 |
ourke | +0.434 |
Vand | +0.424 |
$$ | +0.421 |
「 | +0.419 |
Neg logit contributions | |
ahime | -0.491 |
usterity | -0.487 |
Berks | -0.449 |
groupon | -0.435 |
Origin | -0.426 |
Token | Cody |
Token ID | 27035 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
usterity | +0.112 |
ahime | +0.111 |
Berks | +0.104 |
groupon | +0.100 |
Origin | +0.098 |
Neg logit contributions | |
Deb | -0.092 |
ourke | -0.091 |
$$ | -0.088 |
「 | -0.088 |
Vand | -0.087 |
Token | Mand |
Token ID | 13314 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Deb | +0.322 |
ourke | +0.317 |
$$ | +0.306 |
Vand | +0.306 |
「 | +0.305 |
Neg logit contributions | |
ahime | -0.385 |
usterity | -0.384 |
Berks | -0.357 |
groupon | -0.345 |
Origin | -0.337 |
Token | ell |
Token ID | 695 |
Feature activation | -5.84e-03 |
Pos logit contributions | |
Deb | +1.075 |
ourke | +1.039 |
Vand | +1.017 |
$$ | +1.006 |
「 | +1.003 |
Neg logit contributions | |
ahime | -1.394 |
usterity | -1.386 |
Berks | -1.276 |
groupon | -1.245 |
adobe | -1.222 |
Token | , |
Token ID | 11 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
ahime | +0.004 |
usterity | +0.004 |
Berks | +0.004 |
groupon | +0.004 |
adobe | +0.003 |
Neg logit contributions | |
Deb | -0.004 |
ourke | -0.004 |
Vand | -0.004 |
$$ | -0.004 |
「 | -0.004 |
Token | center |
Token ID | 3641 |
Feature activation | +7.06e+00 |
Pos logit contributions | |
Deb | +0.382 |
ourke | +0.372 |
Vand | +0.365 |
$$ | +0.363 |
「 | +0.362 |
Neg logit contributions | |
ahime | -0.328 |
usterity | -0.327 |
Berks | -0.297 |
groupon | -0.286 |
Origin | -0.279 |
Token | , |
Token ID | 11 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Deb | +4.154 |
ourke | +3.943 |
Vand | +3.870 |
「 | +3.847 |
$$ | +3.790 |
Neg logit contributions | |
ahime | -5.215 |
usterity | -5.053 |
Berks | -4.638 |
groupon | -4.616 |
adobe | -4.594 |
Token | were |
Token ID | 547 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
Deb | +0.944 |
ourke | +0.916 |
Vand | +0.897 |
$$ | +0.889 |
「 | +0.885 |
Neg logit contributions | |
ahime | -1.068 |
usterity | -1.061 |
Berks | -0.973 |
groupon | -0.947 |
Origin | -0.927 |
Token | also |
Token ID | 635 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
Deb | +0.411 |
ourke | +0.401 |
Vand | +0.389 |
$$ | +0.389 |
「 | +0.387 |
Neg logit contributions | |
ahime | -0.442 |
usterity | -0.441 |
Berks | -0.406 |
groupon | -0.394 |
adobe | -0.385 |
Token | try |
Token ID | 1949 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
usterity | +0.173 |
ahime | +0.172 |
Berks | +0.160 |
groupon | +0.154 |
adobe | +0.151 |
Neg logit contributions | |
Deb | -0.167 |
ourke | -0.164 |
$$ | -0.159 |
Vand | -0.158 |
「 | -0.158 |
Token | out |
Token ID | 448 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
Deb | +1.605 |
ourke | +1.565 |
Vand | +1.541 |
$$ | +1.529 |
「 | +1.526 |
Neg logit contributions | |
ahime | -1.104 |
usterity | -1.094 |
Berks | -0.973 |
groupon | -0.941 |
Origin | -0.915 |
Token |
|
Token ID | 198 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
ahime | +0.644 |
usterity | +0.643 |
Berks | +0.602 |
groupon | +0.583 |
Origin | +0.568 |
Neg logit contributions | |
ourke | -0.560 |
Deb | -0.556 |
Vand | -0.528 |
$$ | -0.528 |
「 | -0.526 |
Token |
|
Token ID | 198 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
ahime | +0.220 |
usterity | +0.220 |
Berks | +0.203 |
groupon | +0.202 |
Origin | +0.197 |
Neg logit contributions | |
Deb | -0.185 |
ourke | -0.182 |
Vand | -0.177 |
「 | -0.174 |
$$ | -0.173 |
Token | R |
Token ID | 49 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
ahime | +0.207 |
usterity | +0.206 |
Berks | +0.189 |
groupon | +0.185 |
Origin | +0.182 |
Neg logit contributions | |
Deb | -0.172 |
ourke | -0.167 |
Vand | -0.163 |
「 | -0.161 |
$$ | -0.161 |
Token | eds |
Token ID | 5379 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
ahime | +0.358 |
usterity | +0.354 |
Berks | +0.323 |
groupon | +0.311 |
Origin | +0.309 |
Neg logit contributions | |
Deb | -0.355 |
Vand | -0.340 |
ourke | -0.340 |
「 | -0.335 |
$$ | -0.332 |
Token | kins |
Token ID | 5331 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
usterity | +0.237 |
ahime | +0.237 |
Berks | +0.218 |
groupon | +0.212 |
Origin | +0.210 |
Neg logit contributions | |
Deb | -0.202 |
ourke | -0.197 |
Vand | -0.190 |
$$ | -0.190 |
「 | -0.188 |
Token | defensive |
Token ID | 6110 |
Feature activation | +7.06e+00 |
Pos logit contributions | |
Deb | +0.895 |
ourke | +0.863 |
Vand | +0.843 |
$$ | +0.834 |
「 | +0.831 |
Neg logit contributions | |
ahime | -1.300 |
usterity | -1.292 |
Berks | -1.195 |
groupon | -1.168 |
Origin | -1.147 |
Token | players |
Token ID | 1938 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
Deb | +3.169 |
Vand | +2.969 |
ourke | +2.958 |
「 | +2.885 |
$$ | +2.854 |
Neg logit contributions | |
ahime | -6.220 |
usterity | -6.144 |
adobe | -5.597 |
Berks | -5.596 |
groupon | -5.513 |
Token | take |
Token ID | 1011 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
Deb | +0.026 |
ourke | +0.026 |
$$ | +0.025 |
Vand | +0.025 |
「 | +0.025 |
Neg logit contributions | |
ahime | -0.029 |
usterity | -0.029 |
Berks | -0.026 |
groupon | -0.025 |
Origin | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Deb | +0.250 |
ourke | +0.247 |
Vand | +0.237 |
$$ | +0.237 |
「 | +0.234 |
Neg logit contributions | |
ahime | -0.334 |
usterity | -0.331 |
Berks | -0.308 |
groupon | -0.299 |
adobe | -0.293 |
Token | water |
Token ID | 1660 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
usterity | +1.144 |
ahime | +1.126 |
Berks | +1.044 |
groupon | +1.003 |
Origin | +0.976 |
Neg logit contributions | |
Deb | -1.054 |
ourke | -1.051 |
Vand | -1.003 |
$$ | -1.002 |
「 | -0.991 |
Token | break |
Token ID | 2270 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Deb | +0.945 |
ourke | +0.916 |
Vand | +0.895 |
$$ | +0.886 |
「 | +0.883 |
Neg logit contributions | |
ahime | -1.198 |
usterity | -1.191 |
Berks | -1.096 |
groupon | -1.070 |
adobe | -1.049 |
Token | long |
Token ID | 890 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Deb | +0.365 |
ourke | +0.358 |
Vand | +0.348 |
$$ | +0.347 |
「 | +0.345 |
Neg logit contributions | |
ahime | -0.393 |
usterity | -0.393 |
Berks | -0.361 |
groupon | -0.351 |
Origin | -0.344 |
Token | as |
Token ID | 355 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Deb | +0.834 |
ourke | +0.800 |
Vand | +0.794 |
「 | +0.784 |
$$ | +0.782 |
Neg logit contributions | |
ahime | -0.732 |
usterity | -0.720 |
Berks | -0.648 |
groupon | -0.631 |
adobe | -0.618 |
Token | outlets |
Token ID | 12527 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
Deb | +1.003 |
ourke | +0.975 |
Vand | +0.950 |
$$ | +0.943 |
「 | +0.938 |
Neg logit contributions | |
ahime | -1.270 |
usterity | -1.265 |
Berks | -1.166 |
groupon | -1.138 |
Origin | -1.116 |
Token | on |
Token ID | 319 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
Deb | +1.481 |
ourke | +1.419 |
Vand | +1.392 |
「 | +1.380 |
$$ | +1.375 |
Neg logit contributions | |
ahime | -2.106 |
usterity | -2.085 |
Berks | -1.925 |
groupon | -1.882 |
Origin | -1.848 |
Token | the |
Token ID | 262 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
Deb | +0.241 |
ourke | +0.234 |
Vand | +0.229 |
$$ | +0.227 |
「 | +0.226 |
Neg logit contributions | |
ahime | -0.263 |
usterity | -0.262 |
Berks | -0.240 |
groupon | -0.234 |
Origin | -0.229 |
Token | left |
Token ID | 1364 |
Feature activation | +6.90e+00 |
Pos logit contributions | |
Deb | +1.767 |
ourke | +1.705 |
Vand | +1.683 |
「 | +1.661 |
$$ | +1.650 |
Neg logit contributions | |
ahime | -1.709 |
usterity | -1.672 |
Berks | -1.518 |
groupon | -1.478 |
adobe | -1.456 |
Token | and |
Token ID | 290 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Deb | +4.410 |
「 | +4.248 |
ourke | +4.189 |
Vand | +4.142 |
$$ | +4.118 |
Neg logit contributions | |
ahime | -4.848 |
usterity | -4.658 |
Berks | -4.273 |
groupon | -4.121 |
Origin | -4.054 |
Token | in |
Token ID | 287 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
Deb | +1.012 |
ourke | +0.978 |
Vand | +0.972 |
「 | +0.963 |
$$ | +0.952 |
Neg logit contributions | |
ahime | -1.034 |
usterity | -1.002 |
Berks | -0.903 |
groupon | -0.887 |
adobe | -0.877 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Deb | +0.578 |
ourke | +0.561 |
Vand | +0.549 |
$$ | +0.545 |
「 | +0.543 |
Neg logit contributions | |
ahime | -0.651 |
usterity | -0.647 |
Berks | -0.593 |
groupon | -0.578 |
Origin | -0.566 |
Token | center |
Token ID | 3641 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
Deb | +0.783 |
ourke | +0.759 |
Vand | +0.747 |
$$ | +0.739 |
「 | +0.738 |
Neg logit contributions | |
ahime | -0.760 |
usterity | -0.753 |
Berks | -0.683 |
groupon | -0.666 |
adobe | -0.651 |
Token | let |
Token ID | 1309 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
Deb | +3.269 |
ourke | +3.135 |
Vand | +3.116 |
「 | +3.110 |
$$ | +3.059 |
Neg logit contributions | |
ahime | -3.315 |
usterity | -3.198 |
Berks | -2.935 |
groupon | -2.838 |
Origin | -2.794 |
Token | or |
Token ID | 393 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
ahime | +2.048 |
usterity | +2.040 |
Berks | +1.905 |
groupon | +1.833 |
Origin | +1.812 |
Neg logit contributions | |
Deb | -2.125 |
ourke | -2.107 |
$$ | -2.034 |
Vand | -2.026 |
「 | -1.995 |
Token | the |
Token ID | 262 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
ahime | +1.983 |
usterity | +1.972 |
Berks | +1.816 |
groupon | +1.761 |
Origin | +1.742 |
Neg logit contributions | |
Deb | -1.927 |
ourke | -1.873 |
Vand | -1.836 |
$$ | -1.807 |
「 | -1.792 |
Token | day |
Token ID | 1110 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
usterity | +1.024 |
ahime | +1.019 |
Berks | +0.938 |
groupon | +0.909 |
Origin | +0.894 |
Neg logit contributions | |
Deb | -0.970 |
ourke | -0.946 |
Vand | -0.925 |
$$ | -0.917 |
「 | -0.908 |
Token | after |
Token ID | 706 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
ahime | +1.001 |
usterity | +0.997 |
Berks | +0.928 |
groupon | +0.902 |
Origin | +0.890 |
Neg logit contributions | |
Deb | -0.816 |
ourke | -0.794 |
Vand | -0.773 |
$$ | -0.767 |
「 | -0.758 |
Token | G |
Token ID | 402 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ahime | +1.066 |
usterity | +1.064 |
Berks | +0.985 |
groupon | +0.951 |
Origin | +0.939 |
Neg logit contributions | |
Deb | -0.991 |
ourke | -0.977 |
$$ | -0.944 |
Vand | -0.942 |
「 | -0.927 |
Token | ant |
Token ID | 415 |
Feature activation | +6.83e+00 |
Pos logit contributions | |
Deb | +0.068 |
ourke | +0.066 |
Vand | +0.065 |
「 | +0.064 |
$$ | +0.064 |
Neg logit contributions | |
ahime | -0.075 |
usterity | -0.075 |
Berks | -0.069 |
groupon | -0.067 |
Origin | -0.066 |
Token | Heart |
Token ID | 8894 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
Deb | +4.487 |
ourke | +4.230 |
Vand | +4.213 |
「 | +4.138 |
$$ | +4.087 |
Neg logit contributions | |
usterity | -4.593 |
ahime | -4.560 |
Berks | -4.148 |
groupon | -4.067 |
adobe | -3.988 |
Token | . |
Token ID | 13 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
Deb | +1.590 |
ourke | +1.533 |
Vand | +1.505 |
「 | +1.491 |
$$ | +1.490 |
Neg logit contributions | |
ahime | -1.933 |
usterity | -1.911 |
Berks | -1.754 |
groupon | -1.715 |
adobe | -1.682 |
Token | He |
Token ID | 679 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
ahime | +0.027 |
usterity | +0.026 |
Berks | +0.024 |
groupon | +0.024 |
Origin | +0.023 |
Neg logit contributions | |
Deb | -0.022 |
ourke | -0.021 |
Vand | -0.021 |
$$ | -0.020 |
「 | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
ahime | +0.676 |
usterity | +0.672 |
Berks | +0.619 |
groupon | +0.604 |
Origin | +0.594 |
Neg logit contributions | |
Deb | -0.538 |
ourke | -0.523 |
Vand | -0.509 |
$$ | -0.502 |
「 | -0.501 |
Token | visiting |
Token ID | 10013 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
ahime | +0.430 |
usterity | +0.428 |
Berks | +0.392 |
groupon | +0.381 |
Origin | +0.373 |
Neg logit contributions | |
Deb | -0.395 |
ourke | -0.384 |
Vand | -0.375 |
$$ | -0.372 |
「 | -0.371 |
Token | : |
Token ID | 25 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
ahime | +0.674 |
usterity | +0.670 |
Berks | +0.623 |
groupon | +0.599 |
Origin | +0.592 |
Neg logit contributions | |
Deb | -0.658 |
ourke | -0.657 |
$$ | -0.636 |
Vand | -0.629 |
「 | -0.624 |
Token | it |
Token ID | 340 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ahime | +0.150 |
usterity | +0.149 |
Berks | +0.139 |
groupon | +0.135 |
Origin | +0.132 |
Neg logit contributions | |
Deb | -0.119 |
ourke | -0.117 |
Vand | -0.113 |
$$ | -0.112 |
「 | -0.112 |
Token | 's |
Token ID | 338 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
Deb | +0.993 |
ourke | +0.953 |
Vand | +0.938 |
$$ | +0.933 |
「 | +0.932 |
Neg logit contributions | |
ahime | -1.195 |
usterity | -1.186 |
Berks | -1.080 |
groupon | -1.055 |
adobe | -1.040 |
Token | just |
Token ID | 655 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
Deb | +1.229 |
ourke | +1.174 |
Vand | +1.159 |
「 | +1.143 |
$$ | +1.140 |
Neg logit contributions | |
ahime | -1.600 |
usterity | -1.586 |
Berks | -1.452 |
groupon | -1.423 |
adobe | -1.402 |
Token | a |
Token ID | 257 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
Deb | +2.110 |
ourke | +1.987 |
Vand | +1.987 |
「 | +1.959 |
$$ | +1.943 |
Neg logit contributions | |
ahime | -2.810 |
usterity | -2.769 |
Berks | -2.515 |
groupon | -2.478 |
adobe | -2.454 |
Token | rumor |
Token ID | 24989 |
Feature activation | +6.81e+00 |
Pos logit contributions | |
Deb | +1.120 |
ourke | +1.043 |
Vand | +1.039 |
$$ | +1.014 |
「 | +1.012 |
Neg logit contributions | |
ahime | -2.636 |
usterity | -2.604 |
Berks | -2.423 |
groupon | -2.392 |
adobe | -2.377 |
Token | . |
Token ID | 13 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Deb | +3.982 |
「 | +3.690 |
$$ | +3.686 |
Vand | +3.671 |
ourke | +3.574 |
Neg logit contributions | |
ahime | -5.115 |
usterity | -5.033 |
Berks | -4.540 |
adobe | -4.456 |
groupon | -4.450 |
Token | But |
Token ID | 887 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
Deb | +0.958 |
ourke | +0.922 |
Vand | +0.903 |
$$ | +0.894 |
「 | +0.891 |
Neg logit contributions | |
ahime | -1.318 |
usterity | -1.309 |
Berks | -1.207 |
groupon | -1.179 |
adobe | -1.158 |
Token | given |
Token ID | 1813 |
Feature activation | +7.93e-02 |
Pos logit contributions | |
Deb | +0.045 |
ourke | +0.045 |
$$ | +0.043 |
Vand | +0.043 |
「 | +0.043 |
Neg logit contributions | |
ahime | -0.051 |
usterity | -0.051 |
Berks | -0.047 |
groupon | -0.045 |
Origin | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
Deb | +0.049 |
ourke | +0.048 |
Vand | +0.047 |
$$ | +0.047 |
「 | +0.046 |
Neg logit contributions | |
ahime | -0.056 |
usterity | -0.056 |
Berks | -0.051 |
groupon | -0.050 |
Origin | -0.049 |
Token | growing |
Token ID | 3957 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
ahime | +0.137 |
usterity | +0.136 |
Berks | +0.127 |
groupon | +0.122 |
Origin | +0.120 |
Neg logit contributions | |
Deb | -0.124 |
ourke | -0.123 |
$$ | -0.118 |
Vand | -0.118 |
「 | -0.118 |
Token | rather |
Token ID | 2138 |
Feature activation | +9.63e-02 |
Pos logit contributions | |
Deb | +0.369 |
ourke | +0.358 |
Vand | +0.351 |
$$ | +0.348 |
「 | +0.346 |
Neg logit contributions | |
ahime | -0.427 |
usterity | -0.425 |
Berks | -0.390 |
groupon | -0.380 |
Origin | -0.372 |
Token | that |
Token ID | 326 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
Deb | +0.062 |
ourke | +0.061 |
Vand | +0.059 |
$$ | +0.059 |
「 | +0.059 |
Neg logit contributions | |
ahime | -0.065 |
usterity | -0.065 |
Berks | -0.059 |
groupon | -0.058 |
Origin | -0.057 |
Token | they |
Token ID | 484 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Deb | +1.052 |
ourke | +1.014 |
Vand | +0.994 |
$$ | +0.982 |
「 | +0.981 |
Neg logit contributions | |
ahime | -1.385 |
usterity | -1.375 |
Berks | -1.266 |
groupon | -1.237 |
Origin | -1.213 |
Token | were |
Token ID | 547 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
Deb | +0.912 |
ourke | +0.885 |
Vand | +0.868 |
$$ | +0.861 |
「 | +0.859 |
Neg logit contributions | |
ahime | -0.928 |
usterity | -0.921 |
Berks | -0.839 |
groupon | -0.817 |
Origin | -0.800 |
Token | stupid |
Token ID | 8531 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
Deb | +1.355 |
ourke | +1.306 |
Vand | +1.286 |
「 | +1.273 |
$$ | +1.272 |
Neg logit contributions | |
ahime | -1.539 |
usterity | -1.523 |
Berks | -1.392 |
groupon | -1.358 |
Origin | -1.334 |
Token | enough |
Token ID | 1576 |
Feature activation | +6.80e+00 |
Pos logit contributions | |
Deb | +1.014 |
ourke | +0.971 |
Vand | +0.947 |
$$ | +0.938 |
「 | +0.932 |
Neg logit contributions | |
ahime | -1.801 |
usterity | -1.791 |
Berks | -1.665 |
groupon | -1.629 |
Origin | -1.604 |
Token | to |
Token ID | 284 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
Deb | +3.220 |
ourke | +2.991 |
$$ | +2.982 |
「 | +2.951 |
Vand | +2.908 |
Neg logit contributions | |
ahime | -5.794 |
usterity | -5.763 |
Berks | -5.338 |
groupon | -5.202 |
Origin | -5.095 |
Token | expect |
Token ID | 1607 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
Deb | +1.346 |
ourke | +1.306 |
Vand | +1.280 |
$$ | +1.269 |
「 | +1.265 |
Neg logit contributions | |
ahime | -1.426 |
usterity | -1.416 |
Berks | -1.293 |
groupon | -1.259 |
Origin | -1.233 |
Token | a |
Token ID | 257 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
Deb | +0.460 |
ourke | +0.447 |
Vand | +0.435 |
$$ | +0.432 |
「 | +0.429 |
Neg logit contributions | |
ahime | -0.615 |
usterity | -0.613 |
Berks | -0.566 |
groupon | -0.551 |
Origin | -0.543 |
Token | piece |
Token ID | 3704 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
usterity | +0.495 |
ahime | +0.492 |
Berks | +0.453 |
groupon | +0.439 |
Origin | +0.430 |
Neg logit contributions | |
Deb | -0.432 |
ourke | -0.420 |
Vand | -0.409 |
$$ | -0.406 |
「 | -0.405 |
Token | from |
Token ID | 422 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
ahime | +0.460 |
usterity | +0.460 |
Berks | +0.416 |
groupon | +0.405 |
Origin | +0.396 |
Neg logit contributions | |
Deb | -0.503 |
ourke | -0.490 |
Vand | -0.481 |
$$ | -0.475 |
「 | -0.475 |
Token | have |
Token ID | 423 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
Deb | +0.108 |
ourke | +0.105 |
Vand | +0.103 |
$$ | +0.102 |
「 | +0.102 |
Neg logit contributions | |
ahime | -0.122 |
usterity | -0.121 |
Berks | -0.111 |
groupon | -0.108 |
Origin | -0.106 |
Token | been |
Token ID | 587 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
usterity | +0.356 |
ahime | +0.355 |
Berks | +0.333 |
groupon | +0.318 |
Origin | +0.309 |
Neg logit contributions | |
ourke | -0.312 |
Deb | -0.308 |
$$ | -0.297 |
「 | -0.295 |
Vand | -0.292 |
Token | better |
Token ID | 1365 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
usterity | +0.188 |
ahime | +0.187 |
Berks | +0.173 |
groupon | +0.167 |
adobe | +0.163 |
Neg logit contributions | |
Deb | -0.172 |
ourke | -0.170 |
$$ | -0.164 |
「 | -0.164 |
Vand | -0.163 |
Token | under |
Token ID | 739 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
ahime | +0.609 |
usterity | +0.606 |
Berks | +0.555 |
groupon | +0.540 |
adobe | +0.528 |
Neg logit contributions | |
Deb | -0.551 |
ourke | -0.537 |
Vand | -0.524 |
$$ | -0.520 |
「 | -0.519 |
Token | new |
Token ID | 649 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ourke | +0.413 |
Deb | +0.413 |
「 | +0.396 |
$$ | +0.396 |
Vand | +0.393 |
Neg logit contributions | |
usterity | -0.565 |
ahime | -0.559 |
Berks | -0.523 |
groupon | -0.504 |
adobe | -0.493 |
Token | defensive |
Token ID | 6110 |
Feature activation | +6.72e+00 |
Pos logit contributions | |
Deb | +0.843 |
ourke | +0.815 |
Vand | +0.791 |
$$ | +0.784 |
「 | +0.782 |
Neg logit contributions | |
ahime | -1.375 |
usterity | -1.368 |
Berks | -1.270 |
groupon | -1.241 |
adobe | -1.219 |
Token | coordinator |
Token ID | 16052 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
Deb | +2.032 |
ourke | +1.819 |
Vand | +1.819 |
$$ | +1.708 |
「 | +1.656 |
Neg logit contributions | |
ahime | -6.977 |
usterity | -6.903 |
Berks | -6.392 |
groupon | -6.360 |
Origin | -6.335 |
Token | Dennis |
Token ID | 16902 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Deb | +2.012 |
ourke | +1.963 |
Vand | +1.896 |
「 | +1.889 |
$$ | +1.884 |
Neg logit contributions | |
ahime | -2.712 |
usterity | -2.697 |
Berks | -2.495 |
groupon | -2.433 |
adobe | -2.387 |
Token | Allen |
Token ID | 9659 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
ourke | +0.081 |
Deb | +0.076 |
Sov | +0.073 |
mble | +0.072 |
「 | +0.072 |
Neg logit contributions | |
Berks | -0.091 |
usterity | -0.091 |
ahime | -0.088 |
groupon | -0.085 |
fore | -0.084 |
Token | the |
Token ID | 262 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Deb | +0.488 |
ourke | +0.472 |
Vand | +0.463 |
$$ | +0.459 |
「 | +0.457 |
Neg logit contributions | |
ahime | -0.554 |
usterity | -0.551 |
Berks | -0.505 |
groupon | -0.492 |
adobe | -0.482 |
Token | past |
Token ID | 1613 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
usterity | +1.309 |
ahime | +1.306 |
Berks | +1.230 |
groupon | +1.179 |
Origin | +1.146 |
Neg logit contributions | |
ourke | -1.151 |
Deb | -1.145 |
$$ | -1.101 |
「 | -1.089 |
Vand | -1.081 |
Token | for |
Token ID | 329 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
ahime | +0.830 |
usterity | +0.823 |
Berks | +0.762 |
groupon | +0.741 |
Origin | +0.727 |
Neg logit contributions | |
Deb | -0.682 |
ourke | -0.665 |
Vand | -0.650 |
$$ | -0.648 |
「 | -0.639 |
Token | References |
Token ID | 31458 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Deb | +0.221 |
ourke | +0.214 |
Vand | +0.209 |
$$ | +0.207 |
「 | +0.206 |
Neg logit contributions | |
ahime | -0.291 |
usterity | -0.289 |
Berks | -0.266 |
groupon | -0.260 |
Origin | -0.255 |
Token | : |
Token ID | 25 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
Deb | +0.868 |
ourke | +0.833 |
Vand | +0.818 |
「 | +0.808 |
$$ | +0.804 |
Neg logit contributions | |
ahime | -1.209 |
usterity | -1.202 |
Berks | -1.104 |
groupon | -1.082 |
adobe | -1.063 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
Deb | +0.482 |
ourke | +0.465 |
Vand | +0.455 |
$$ | +0.450 |
「 | +0.449 |
Neg logit contributions | |
ahime | -0.646 |
usterity | -0.642 |
Berks | -0.591 |
groupon | -0.578 |
adobe | -0.567 |
Token | It |
Token ID | 1026 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
usterity | +0.404 |
ahime | +0.403 |
Berks | +0.367 |
groupon | +0.363 |
Origin | +0.358 |
Neg logit contributions | |
Deb | -0.381 |
ourke | -0.368 |
Vand | -0.363 |
「 | -0.357 |
$$ | -0.353 |
Token | took |
Token ID | 1718 |
Feature activation | +6.70e+00 |
Pos logit contributions | |
Deb | +0.895 |
ourke | +0.861 |
Vand | +0.844 |
$$ | +0.839 |
「 | +0.836 |
Neg logit contributions | |
ahime | -1.122 |
usterity | -1.112 |
Berks | -1.023 |
groupon | -0.998 |
Origin | -0.978 |
Token | until |
Token ID | 1566 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
Deb | +4.256 |
Vand | +4.043 |
「 | +3.896 |
ourke | +3.859 |
$$ | +3.856 |
Neg logit contributions | |
ahime | -4.757 |
usterity | -4.640 |
Berks | -4.133 |
groupon | -4.108 |
adobe | -4.064 |
Token | Sunday |
Token ID | 3502 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Deb | +2.613 |
Vand | +2.491 |
ourke | +2.472 |
「 | +2.451 |
$$ | +2.430 |
Neg logit contributions | |
ahime | -2.354 |
usterity | -2.308 |
Berks | -2.059 |
groupon | -2.026 |
adobe | -1.984 |
Token | morning |
Token ID | 3329 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Deb | +1.125 |
ourke | +1.083 |
Vand | +1.066 |
$$ | +1.052 |
「 | +1.051 |
Neg logit contributions | |
ahime | -1.372 |
usterity | -1.359 |
Berks | -1.243 |
groupon | -1.215 |
Origin | -1.190 |
Token | for |
Token ID | 329 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
Deb | +1.151 |
ourke | +1.108 |
Vand | +1.090 |
「 | +1.075 |
$$ | +1.075 |
Neg logit contributions | |
ahime | -1.457 |
usterity | -1.445 |
Berks | -1.324 |
groupon | -1.295 |
Origin | -1.268 |
Token | a |
Token ID | 257 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ahime | +0.474 |
usterity | +0.474 |
Berks | +0.440 |
groupon | +0.425 |
Origin | +0.416 |
Neg logit contributions | |
Deb | -0.429 |
ourke | -0.424 |
$$ | -0.411 |
Vand | -0.409 |
「 | -0.407 |
Token | …. |
Token ID | 11580 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
ahime | +0.230 |
usterity | +0.228 |
Berks | +0.211 |
groupon | +0.205 |
Origin | +0.200 |
Neg logit contributions | |
Deb | -0.199 |
ourke | -0.195 |
Vand | -0.190 |
$$ | -0.189 |
「 | -0.187 |
Token |
|
Token ID | 198 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
Deb | +1.133 |
ourke | +1.093 |
Vand | +1.070 |
$$ | +1.059 |
「 | +1.058 |
Neg logit contributions | |
ahime | -1.494 |
usterity | -1.486 |
Berks | -1.367 |
groupon | -1.336 |
adobe | -1.311 |
Token |
|
Token ID | 198 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
Deb | +1.620 |
ourke | +1.529 |
$$ | +1.526 |
Vand | +1.510 |
「 | +1.500 |
Neg logit contributions | |
ahime | -2.463 |
usterity | -2.438 |
Berks | -2.246 |
groupon | -2.151 |
adobe | -2.137 |
Token | " |
Token ID | 1 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
Deb | +1.631 |
ourke | +1.579 |
Vand | +1.547 |
$$ | +1.543 |
「 | +1.538 |
Neg logit contributions | |
ahime | -2.077 |
usterity | -2.061 |
Berks | -1.898 |
groupon | -1.841 |
adobe | -1.812 |
Token | Ah |
Token ID | 10910 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
Deb | +0.527 |
ourke | +0.512 |
Vand | +0.498 |
$$ | +0.489 |
「 | +0.487 |
Neg logit contributions | |
ahime | -0.666 |
usterity | -0.663 |
Berks | -0.612 |
groupon | -0.600 |
Origin | -0.594 |
Token | ." |
Token ID | 526 |
Feature activation | +6.66e+00 |
Pos logit contributions | |
ahime | +0.535 |
usterity | +0.529 |
Berks | +0.482 |
groupon | +0.469 |
Origin | +0.459 |
Neg logit contributions | |
Deb | -0.505 |
ourke | -0.495 |
Vand | -0.485 |
$$ | -0.475 |
「 | -0.473 |
Token |
|
Token ID | 198 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
Deb | +3.315 |
「 | +3.175 |
Vand | +3.016 |
ourke | +2.966 |
$$ | +2.949 |
Neg logit contributions | |
ahime | -5.649 |
usterity | -5.618 |
Berks | -5.086 |
groupon | -5.078 |
Origin | -4.969 |
Token |
|
Token ID | 198 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
Deb | +1.749 |
ourke | +1.643 |
$$ | +1.642 |
Vand | +1.632 |
「 | +1.619 |
Neg logit contributions | |
ahime | -2.668 |
usterity | -2.640 |
Berks | -2.426 |
groupon | -2.327 |
adobe | -2.315 |
Token | " |
Token ID | 1 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
Deb | +1.477 |
ourke | +1.428 |
Vand | +1.396 |
$$ | +1.390 |
「 | +1.385 |
Neg logit contributions | |
ahime | -2.014 |
usterity | -1.999 |
Berks | -1.845 |
groupon | -1.793 |
adobe | -1.765 |
Token | Ste |
Token ID | 7447 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
usterity | +0.486 |
ahime | +0.485 |
Berks | +0.447 |
groupon | +0.442 |
Origin | +0.442 |
Neg logit contributions | |
Deb | -0.424 |
ourke | -0.417 |
Vand | -0.402 |
$$ | -0.389 |
「 | -0.388 |
Token | lla |
Token ID | 8466 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
Deb | +2.636 |
ourke | +2.592 |
Vand | +2.553 |
$$ | +2.547 |
「 | +2.540 |
Neg logit contributions | |
ahime | -0.877 |
usterity | -0.865 |
Berks | -0.713 |
groupon | -0.652 |
Origin | -0.627 |
Token | energy |
Token ID | 2568 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
Deb | +1.135 |
ourke | +1.095 |
Vand | +1.075 |
$$ | +1.061 |
「 | +1.059 |
Neg logit contributions | |
ahime | -1.458 |
usterity | -1.447 |
Berks | -1.332 |
groupon | -1.300 |
adobe | -1.278 |
Token | goals |
Token ID | 4661 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
Deb | +0.330 |
ourke | +0.320 |
Vand | +0.313 |
$$ | +0.310 |
「 | +0.310 |
Neg logit contributions | |
ahime | -0.390 |
usterity | -0.388 |
Berks | -0.355 |
groupon | -0.346 |
Origin | -0.340 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Deb | +1.349 |
ourke | +1.287 |
Vand | +1.273 |
$$ | +1.257 |
「 | +1.257 |
Neg logit contributions | |
usterity | -1.557 |
ahime | -1.554 |
Berks | -1.428 |
groupon | -1.380 |
Origin | -1.363 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
Deb | +0.685 |
ourke | +0.655 |
Vand | +0.646 |
$$ | +0.638 |
「 | +0.636 |
Neg logit contributions | |
ahime | -0.940 |
usterity | -0.934 |
Berks | -0.860 |
groupon | -0.840 |
Origin | -0.825 |
Token | Media |
Token ID | 13152 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
ahime | +0.236 |
usterity | +0.236 |
Berks | +0.214 |
groupon | +0.211 |
Origin | +0.208 |
Neg logit contributions | |
Deb | -0.223 |
ourke | -0.215 |
Vand | -0.212 |
「 | -0.209 |
$$ | -0.207 |
Token | playback |
Token ID | 16388 |
Feature activation | +6.60e+00 |
Pos logit contributions | |
Deb | +1.163 |
ourke | +1.091 |
Vand | +1.060 |
「 | +1.039 |
$$ | +1.039 |
Neg logit contributions | |
ahime | -2.906 |
usterity | -2.888 |
Berks | -2.708 |
groupon | -2.659 |
adobe | -2.625 |
Token | is |
Token ID | 318 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
Deb | +3.611 |
ourke | +3.448 |
Vand | +3.259 |
$$ | +3.258 |
Lama | +3.255 |
Neg logit contributions | |
ahime | -5.377 |
usterity | -5.334 |
Berks | -4.772 |
adobe | -4.668 |
groupon | -4.470 |
Token | unsupported |
Token ID | 24222 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Deb | +0.345 |
ourke | +0.336 |
Vand | +0.326 |
$$ | +0.324 |
「 | +0.321 |
Neg logit contributions | |
usterity | -0.541 |
ahime | -0.538 |
Berks | -0.501 |
groupon | -0.490 |
Origin | -0.480 |
Token | on |
Token ID | 319 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
Deb | +0.875 |
ourke | +0.849 |
Vand | +0.834 |
$$ | +0.828 |
「 | +0.825 |
Neg logit contributions | |
ahime | -0.832 |
usterity | -0.824 |
Berks | -0.747 |
groupon | -0.722 |
adobe | -0.710 |
Token | your |
Token ID | 534 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ahime | +0.043 |
usterity | +0.042 |
Berks | +0.039 |
groupon | +0.037 |
adobe | +0.037 |
Neg logit contributions | |
Deb | -0.041 |
ourke | -0.039 |
Vand | -0.039 |
$$ | -0.038 |
「 | -0.038 |
Token | device |
Token ID | 3335 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ahime | +0.798 |
usterity | +0.789 |
Berks | +0.724 |
groupon | +0.721 |
Origin | +0.705 |
Neg logit contributions | |
Deb | -0.661 |
ourke | -0.638 |
Vand | -0.633 |
$$ | -0.624 |
「 | -0.620 |
Token | iquette |
Token ID | 40387 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
Deb | +1.592 |
ourke | +1.551 |
Vand | +1.524 |
$$ | +1.513 |
「 | +1.509 |
Neg logit contributions | |
ahime | -1.235 |
usterity | -1.225 |
Berks | -1.099 |
groupon | -1.064 |
Origin | -1.038 |
Token | and |
Token ID | 290 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Deb | +2.104 |
Vand | +1.985 |
ourke | +1.980 |
「 | +1.970 |
$$ | +1.955 |
Neg logit contributions | |
ahime | -2.482 |
usterity | -2.461 |
Berks | -2.218 |
groupon | -2.171 |
adobe | -2.151 |
Token | Manual |
Token ID | 17969 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
Deb | +0.760 |
ourke | +0.731 |
Vand | +0.718 |
$$ | +0.709 |
「 | +0.708 |
Neg logit contributions | |
ahime | -0.973 |
usterity | -0.967 |
Berks | -0.888 |
groupon | -0.867 |
adobe | -0.852 |
Token | of |
Token ID | 286 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
Deb | +0.230 |
ourke | +0.222 |
Vand | +0.218 |
$$ | +0.216 |
「 | +0.215 |
Neg logit contributions | |
ahime | -0.260 |
usterity | -0.258 |
Berks | -0.236 |
groupon | -0.230 |
adobe | -0.225 |
Token | Polit |
Token ID | 7793 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Deb | +0.133 |
ourke | +0.130 |
Vand | +0.126 |
$$ | +0.126 |
「 | +0.125 |
Neg logit contributions | |
ahime | -0.172 |
usterity | -0.171 |
Berks | -0.158 |
groupon | -0.154 |
Origin | -0.151 |
Token | eness |
Token ID | 9449 |
Feature activation | +6.59e+00 |
Pos logit contributions | |
Deb | +0.540 |
ourke | +0.519 |
Vand | +0.505 |
$$ | +0.499 |
「 | +0.497 |
Neg logit contributions | |
ahime | -0.935 |
usterity | -0.930 |
Berks | -0.864 |
groupon | -0.846 |
Origin | -0.832 |
Token | , |
Token ID | 11 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Deb | +3.963 |
Vand | +3.734 |
「 | +3.733 |
ourke | +3.661 |
$$ | +3.640 |
Neg logit contributions | |
ahime | -4.839 |
usterity | -4.771 |
Berks | -4.254 |
adobe | -4.195 |
groupon | -4.178 |
Token | 18 |
Token ID | 1248 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
Deb | +1.272 |
ourke | +1.224 |
Vand | +1.216 |
「 | +1.201 |
$$ | +1.196 |
Neg logit contributions | |
ahime | -1.109 |
usterity | -1.104 |
Berks | -0.980 |
groupon | -0.961 |
adobe | -0.943 |
Token | 76 |
Token ID | 4304 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ahime | +0.396 |
usterity | +0.392 |
Berks | +0.367 |
groupon | +0.361 |
Origin | +0.354 |
Neg logit contributions | |
Deb | -0.312 |
ourke | -0.306 |
Vand | -0.294 |
$$ | -0.291 |
「 | -0.290 |
Token | . |
Token ID | 13 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
Deb | +0.667 |
ourke | +0.638 |
Vand | +0.632 |
「 | +0.625 |
$$ | +0.624 |
Neg logit contributions | |
ahime | -0.762 |
usterity | -0.756 |
Berks | -0.687 |
groupon | -0.670 |
adobe | -0.661 |
Token |
|
Token ID | 198 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
Deb | +0.106 |
ourke | +0.102 |
Vand | +0.100 |
「 | +0.099 |
$$ | +0.099 |
Neg logit contributions | |
ahime | -0.151 |
usterity | -0.149 |
Berks | -0.137 |
groupon | -0.134 |
adobe | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
ahime | +0.466 |
usterity | +0.462 |
Berks | +0.422 |
groupon | +0.412 |
Origin | +0.405 |
Neg logit contributions | |
Deb | -0.446 |
ourke | -0.436 |
Vand | -0.425 |
$$ | -0.421 |
「 | -0.418 |
Token |
|
Token ID | 198 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
Deb | +0.181 |
ourke | +0.179 |
Vand | +0.172 |
$$ | +0.171 |
「 | +0.169 |
Neg logit contributions | |
ahime | -0.227 |
usterity | -0.225 |
Berks | -0.209 |
groupon | -0.203 |
Origin | -0.200 |
Token |
|
Token ID | 198 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
Deb | +0.448 |
ourke | +0.435 |
Vand | +0.424 |
$$ | +0.419 |
「 | +0.418 |
Neg logit contributions | |
ahime | -0.581 |
usterity | -0.578 |
Berks | -0.533 |
groupon | -0.522 |
Origin | -0.512 |
Token | Part |
Token ID | 7841 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
Deb | +0.549 |
ourke | +0.533 |
Vand | +0.522 |
$$ | +0.513 |
「 | +0.513 |
Neg logit contributions | |
ahime | -0.577 |
usterity | -0.575 |
Berks | -0.524 |
groupon | -0.513 |
Origin | -0.505 |
Token | 6 |
Token ID | 718 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
Deb | +0.507 |
ourke | +0.492 |
Vand | +0.481 |
$$ | +0.478 |
「 | +0.474 |
Neg logit contributions | |
ahime | -0.582 |
usterity | -0.577 |
Berks | -0.530 |
groupon | -0.517 |
Origin | -0.507 |
Token | [ |
Token ID | 685 |
Feature activation | +6.51e+00 |
Pos logit contributions | |
Deb | +1.789 |
ourke | +1.710 |
「 | +1.687 |
Vand | +1.683 |
$$ | +1.661 |
Neg logit contributions | |
ahime | -2.358 |
usterity | -2.353 |
Berks | -2.162 |
groupon | -2.109 |
adobe | -2.083 |
Token | edit |
Token ID | 4370 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
Deb | +3.664 |
「 | +3.502 |
$$ | +3.464 |
ourke | +3.455 |
Vand | +3.418 |
Neg logit contributions | |
ahime | -4.947 |
usterity | -4.923 |
Berks | -4.523 |
adobe | -4.392 |
groupon | -4.381 |
Token | ] |
Token ID | 2361 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Deb | +1.259 |
ourke | +1.214 |
Vand | +1.187 |
$$ | +1.174 |
「 | +1.172 |
Neg logit contributions | |
ahime | -1.762 |
usterity | -1.752 |
Berks | -1.617 |
groupon | -1.580 |
adobe | -1.551 |
Token |
|
Token ID | 198 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Deb | +1.240 |
ourke | +1.194 |
Vand | +1.171 |
$$ | +1.159 |
「 | +1.156 |
Neg logit contributions | |
ahime | -1.668 |
usterity | -1.656 |
Berks | -1.527 |
groupon | -1.488 |
adobe | -1.463 |
Token |
|
Token ID | 198 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
Deb | +1.082 |
ourke | +1.037 |
Vand | +1.018 |
$$ | +1.013 |
「 | +1.007 |
Neg logit contributions | |
ahime | -1.505 |
usterity | -1.492 |
Berks | -1.376 |
groupon | -1.334 |
adobe | -1.315 |
Token | It |
Token ID | 1026 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
Deb | +1.356 |
ourke | +1.313 |
Vand | +1.287 |
$$ | +1.283 |
「 | +1.278 |
Neg logit contributions | |
ahime | -1.573 |
usterity | -1.560 |
Berks | -1.432 |
groupon | -1.389 |
adobe | -1.364 |
Token | que |
Token ID | 4188 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
Deb | +0.747 |
ourke | +0.725 |
Vand | +0.717 |
「 | +0.710 |
$$ | +0.709 |
Neg logit contributions | |
ahime | -0.560 |
usterity | -0.555 |
Berks | -0.496 |
groupon | -0.485 |
Origin | -0.470 |
Token | , |
Token ID | 11 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
Deb | +0.303 |
ourke | +0.298 |
Vand | +0.288 |
$$ | +0.286 |
「 | +0.284 |
Neg logit contributions | |
ahime | -0.348 |
usterity | -0.346 |
Berks | -0.321 |
groupon | -0.312 |
Origin | -0.305 |
Token | excellent |
Token ID | 6275 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
Deb | +0.111 |
ourke | +0.110 |
$$ | +0.107 |
Vand | +0.106 |
「 | +0.106 |
Neg logit contributions | |
ahime | -0.122 |
usterity | -0.122 |
Berks | -0.113 |
groupon | -0.109 |
Origin | -0.106 |
Token | on |
Token ID | 319 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ahime | +0.576 |
usterity | +0.573 |
Berks | +0.523 |
groupon | +0.509 |
Origin | +0.498 |
Neg logit contributions | |
Deb | -0.550 |
ourke | -0.538 |
Vand | -0.525 |
$$ | -0.523 |
「 | -0.521 |
Token | the |
Token ID | 262 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Deb | +0.698 |
ourke | +0.679 |
Vand | +0.664 |
$$ | +0.659 |
「 | +0.657 |
Neg logit contributions | |
ahime | -0.790 |
usterity | -0.784 |
Berks | -0.718 |
groupon | -0.701 |
adobe | -0.686 |
Token | left |
Token ID | 1364 |
Feature activation | +6.51e+00 |
Pos logit contributions | |
Deb | +0.966 |
ourke | +0.922 |
Vand | +0.908 |
「 | +0.893 |
$$ | +0.891 |
Neg logit contributions | |
ahime | -1.280 |
usterity | -1.269 |
Berks | -1.164 |
groupon | -1.139 |
Origin | -1.122 |
Token | , |
Token ID | 11 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Deb | +3.751 |
Vand | +3.488 |
ourke | +3.442 |
「 | +3.409 |
$$ | +3.369 |
Neg logit contributions | |
ahime | -4.964 |
usterity | -4.898 |
Berks | -4.432 |
groupon | -4.314 |
Origin | -4.273 |
Token | helped |
Token ID | 4193 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
Deb | +0.948 |
ourke | +0.923 |
Vand | +0.900 |
$$ | +0.893 |
「 | +0.889 |
Neg logit contributions | |
ahime | -1.127 |
usterity | -1.120 |
Berks | -1.032 |
groupon | -1.005 |
Origin | -0.984 |
Token | create |
Token ID | 2251 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ahime | +0.360 |
usterity | +0.356 |
Berks | +0.332 |
groupon | +0.321 |
adobe | +0.316 |
Neg logit contributions | |
Deb | -0.300 |
ourke | -0.294 |
$$ | -0.286 |
Vand | -0.284 |
「 | -0.283 |
Token | the |
Token ID | 262 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
Deb | +0.594 |
ourke | +0.581 |
Vand | +0.563 |
$$ | +0.563 |
「 | +0.559 |
Neg logit contributions | |
ahime | -0.756 |
usterity | -0.752 |
Berks | -0.697 |
groupon | -0.677 |
Origin | -0.665 |
Token | second |
Token ID | 1218 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
usterity | +0.721 |
ahime | +0.721 |
Berks | +0.672 |
groupon | +0.650 |
Origin | +0.639 |
Neg logit contributions | |
Deb | -0.550 |
ourke | -0.539 |
$$ | -0.522 |
Vand | -0.522 |
「 | -0.517 |
Token | not |
Token ID | 407 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
Deb | +0.866 |
ourke | +0.836 |
Vand | +0.820 |
$$ | +0.811 |
「 | +0.810 |
Neg logit contributions | |
ahime | -1.029 |
usterity | -1.021 |
Berks | -0.934 |
groupon | -0.913 |
adobe | -0.896 |
Token | going |
Token ID | 1016 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ahime | +0.122 |
usterity | +0.122 |
Berks | +0.111 |
groupon | +0.108 |
Origin | +0.106 |
Neg logit contributions | |
Deb | -0.114 |
ourke | -0.112 |
Vand | -0.109 |
$$ | -0.108 |
「 | -0.108 |
Token | to |
Token ID | 284 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
ahime | +0.887 |
usterity | +0.878 |
Berks | +0.815 |
groupon | +0.792 |
Origin | +0.769 |
Neg logit contributions | |
Deb | -0.740 |
ourke | -0.720 |
Vand | -0.704 |
$$ | -0.695 |
「 | -0.693 |
Token | cave |
Token ID | 11527 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
ahime | +0.098 |
usterity | +0.098 |
Berks | +0.091 |
groupon | +0.088 |
Origin | +0.085 |
Neg logit contributions | |
Deb | -0.085 |
ourke | -0.083 |
Vand | -0.081 |
$$ | -0.080 |
「 | -0.080 |
Token | just |
Token ID | 655 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
Deb | +0.460 |
ourke | +0.446 |
Vand | +0.437 |
$$ | +0.433 |
「 | +0.432 |
Neg logit contributions | |
ahime | -0.519 |
usterity | -0.515 |
Berks | -0.472 |
groupon | -0.460 |
Origin | -0.450 |
Token | c |
Token ID | 269 |
Feature activation | +6.50e+00 |
Pos logit contributions | |
Deb | +0.536 |
ourke | +0.520 |
Vand | +0.511 |
$$ | +0.506 |
「 | +0.505 |
Neg logit contributions | |
ahime | -0.538 |
usterity | -0.533 |
Berks | -0.485 |
groupon | -0.472 |
adobe | -0.462 |
Token | uz |
Token ID | 10277 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
Deb | +4.072 |
ourke | +3.957 |
$$ | +3.869 |
「 | +3.843 |
Vand | +3.834 |
Neg logit contributions | |
ahime | -4.597 |
usterity | -4.548 |
Berks | -4.119 |
groupon | -4.006 |
adobe | -4.001 |
Token | he |
Token ID | 339 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
Deb | +1.472 |
ourke | +1.417 |
Vand | +1.392 |
$$ | +1.377 |
「 | +1.376 |
Neg logit contributions | |
ahime | -1.756 |
usterity | -1.739 |
Berks | -1.588 |
groupon | -1.554 |
adobe | -1.528 |
Token | sends |
Token ID | 12800 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Deb | +1.564 |
ourke | +1.510 |
Vand | +1.480 |
$$ | +1.474 |
「 | +1.470 |
Neg logit contributions | |
ahime | -1.834 |
usterity | -1.820 |
Berks | -1.660 |
groupon | -1.622 |
adobe | -1.599 |
Token | me |
Token ID | 502 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
Deb | +1.230 |
ourke | +1.191 |
Vand | +1.164 |
$$ | +1.151 |
「 | +1.149 |
Neg logit contributions | |
ahime | -1.595 |
usterity | -1.586 |
Berks | -1.463 |
groupon | -1.427 |
Origin | -1.398 |
Token | a |
Token ID | 257 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Deb | +1.455 |
ourke | +1.405 |
Vand | +1.374 |
$$ | +1.359 |
「 | +1.356 |
Neg logit contributions | |
ahime | -1.972 |
usterity | -1.960 |
Berks | -1.808 |
groupon | -1.766 |
Origin | -1.733 |
Token | winner |
Token ID | 8464 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
usterity | +0.391 |
ahime | +0.391 |
Berks | +0.361 |
groupon | +0.350 |
Origin | +0.343 |
Neg logit contributions | |
Deb | -0.327 |
ourke | -0.320 |
Vand | -0.309 |
$$ | -0.309 |
「 | -0.307 |
Token | of |
Token ID | 286 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
ahime | +0.624 |
usterity | +0.621 |
Berks | +0.566 |
groupon | +0.550 |
Origin | +0.537 |
Neg logit contributions | |
Deb | -0.709 |
ourke | -0.696 |
Vand | -0.679 |
$$ | -0.676 |
「 | -0.672 |
Token | the |
Token ID | 262 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
Deb | +0.036 |
ourke | +0.035 |
Vand | +0.034 |
$$ | +0.034 |
「 | +0.034 |
Neg logit contributions | |
ahime | -0.043 |
usterity | -0.043 |
Berks | -0.040 |
groupon | -0.039 |
Origin | -0.038 |
Token | UFC |
Token ID | 11448 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
Deb | +0.097 |
ourke | +0.094 |
Vand | +0.092 |
$$ | +0.091 |
「 | +0.091 |
Neg logit contributions | |
ahime | -0.106 |
usterity | -0.105 |
Berks | -0.096 |
groupon | -0.093 |
adobe | -0.091 |
Token | 216 |
Token ID | 26881 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Deb | +0.520 |
ourke | +0.504 |
Vand | +0.494 |
$$ | +0.490 |
「 | +0.489 |
Neg logit contributions | |
ahime | -0.554 |
usterity | -0.551 |
Berks | -0.503 |
groupon | -0.490 |
Origin | -0.479 |
Token | interim |
Token ID | 19303 |
Feature activation | +6.49e+00 |
Pos logit contributions | |
Deb | +1.110 |
ourke | +1.057 |
Vand | +1.049 |
$$ | +1.035 |
「 | +1.035 |
Neg logit contributions | |
ahime | -1.211 |
usterity | -1.192 |
Berks | -1.080 |
groupon | -1.049 |
adobe | -1.045 |
Token | title |
Token ID | 3670 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
Deb | +3.351 |
Vand | +3.187 |
「 | +3.118 |
ourke | +3.046 |
$$ | +3.018 |
Neg logit contributions | |
ahime | -5.340 |
usterity | -5.258 |
Berks | -4.859 |
adobe | -4.731 |
groupon | -4.695 |
Token | showdown |
Token ID | 33338 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
Deb | +1.456 |
ourke | +1.384 |
Vand | +1.371 |
「 | +1.355 |
$$ | +1.343 |
Neg logit contributions | |
ahime | -1.511 |
usterity | -1.505 |
Berks | -1.361 |
groupon | -1.321 |
adobe | -1.311 |
Token | between |
Token ID | 1022 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
Deb | +0.355 |
ourke | +0.342 |
Vand | +0.338 |
「 | +0.334 |
$$ | +0.334 |
Neg logit contributions | |
ahime | -0.362 |
usterity | -0.360 |
Berks | -0.326 |
groupon | -0.317 |
adobe | -0.311 |
Token | Tony |
Token ID | 8832 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
usterity | +0.639 |
ahime | +0.637 |
Berks | +0.594 |
groupon | +0.578 |
Origin | +0.568 |
Neg logit contributions | |
Deb | -0.482 |
ourke | -0.474 |
$$ | -0.460 |
Vand | -0.457 |
「 | -0.454 |
Token | Ferguson |
Token ID | 15031 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
usterity | +0.027 |
ahime | +0.027 |
Berks | +0.025 |
groupon | +0.024 |
Origin | +0.024 |
Neg logit contributions | |
Deb | -0.022 |
ourke | -0.022 |
$$ | -0.021 |
Vand | -0.021 |
「 | -0.021 |
Token | ? |
Token ID | 30 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Deb | +0.141 |
ourke | +0.136 |
Vand | +0.133 |
$$ | +0.131 |
「 | +0.131 |
Neg logit contributions | |
ahime | -0.214 |
usterity | -0.213 |
Berks | -0.198 |
groupon | -0.193 |
Origin | -0.190 |
Token | ( |
Token ID | 357 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ahime | +0.791 |
usterity | +0.790 |
Berks | +0.741 |
groupon | +0.722 |
Origin | +0.706 |
Neg logit contributions | |
Deb | -0.590 |
ourke | -0.584 |
Vand | -0.558 |
$$ | -0.558 |
「 | -0.553 |
Token | Think |
Token ID | 22073 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
Deb | +0.679 |
ourke | +0.658 |
Vand | +0.645 |
$$ | +0.637 |
「 | +0.637 |
Neg logit contributions | |
ahime | -0.753 |
usterity | -0.749 |
Berks | -0.686 |
groupon | -0.670 |
Origin | -0.657 |
Token | of |
Token ID | 286 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
ahime | +0.274 |
usterity | +0.274 |
Berks | +0.249 |
groupon | +0.241 |
Origin | +0.236 |
Neg logit contributions | |
Deb | -0.295 |
ourke | -0.287 |
Vand | -0.281 |
$$ | -0.280 |
「 | -0.278 |
Token | The |
Token ID | 383 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Deb | +1.456 |
ourke | +1.401 |
Vand | +1.383 |
「 | +1.366 |
$$ | +1.362 |
Neg logit contributions | |
ahime | -1.706 |
usterity | -1.695 |
Berks | -1.538 |
groupon | -1.506 |
Origin | -1.480 |
Token | Simpsons |
Token ID | 34376 |
Feature activation | -7.90e+00 |
Pos logit contributions | |
ahime | +1.410 |
usterity | +1.396 |
Berks | +1.309 |
groupon | +1.258 |
Origin | +1.233 |
Neg logit contributions | |
Deb | -1.260 |
ourke | -1.245 |
$$ | -1.206 |
「 | -1.199 |
Vand | -1.197 |
Token | and |
Token ID | 290 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ahime | +5.091 |
usterity | +4.974 |
Berks | +4.734 |
groupon | +4.610 |
Origin | +4.513 |
Neg logit contributions | |
Deb | -4.861 |
ourke | -4.771 |
Sov | -4.675 |
Vand | -4.632 |
$$ | -4.625 |
Token | the |
Token ID | 262 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
ahime | +0.767 |
usterity | +0.763 |
Berks | +0.710 |
groupon | +0.687 |
Origin | +0.671 |
Neg logit contributions | |
Deb | -0.665 |
ourke | -0.654 |
$$ | -0.634 |
Vand | -0.633 |
「 | -0.627 |
Token | mon |
Token ID | 937 |
Feature activation | -8.30e-01 |
Pos logit contributions | |
ahime | +0.015 |
usterity | +0.015 |
Berks | +0.014 |
groupon | +0.013 |
Origin | +0.013 |
Neg logit contributions | |
Deb | -0.014 |
ourke | -0.013 |
$$ | -0.013 |
Vand | -0.013 |
「 | -0.013 |
Token | or |
Token ID | 273 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
ahime | +0.658 |
usterity | +0.654 |
Berks | +0.608 |
groupon | +0.592 |
adobe | +0.583 |
Neg logit contributions | |
Deb | -0.444 |
ourke | -0.426 |
Vand | -0.416 |
$$ | -0.412 |
「 | -0.405 |
Token | ail |
Token ID | 603 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
Deb | +1.178 |
ourke | +1.143 |
Vand | +1.113 |
$$ | +1.105 |
「 | +1.100 |
Neg logit contributions | |
ahime | -1.517 |
usterity | -1.506 |
Berks | -1.388 |
groupon | -1.356 |
Origin | -1.332 |
Token | Magic |
Token ID | 6139 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
Deb | +0.117 |
ourke | +0.113 |
Vand | +0.111 |
$$ | +0.110 |
「 | +0.110 |
Neg logit contributions | |
ahime | -0.136 |
usterity | -0.135 |
Berks | -0.124 |
groupon | -0.121 |
Origin | -0.119 |
Token | iterations |
Token ID | 34820 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ahime | +0.485 |
usterity | +0.478 |
Berks | +0.439 |
groupon | +0.427 |
Origin | +0.418 |
Neg logit contributions | |
Deb | -0.481 |
ourke | -0.471 |
Vand | -0.461 |
$$ | -0.457 |
「 | -0.454 |
Token | of |
Token ID | 286 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
Deb | +0.767 |
ourke | +0.742 |
Vand | +0.728 |
$$ | +0.723 |
「 | +0.722 |
Neg logit contributions | |
ahime | -0.813 |
usterity | -0.810 |
Berks | -0.738 |
groupon | -0.718 |
adobe | -0.703 |
Token | My |
Token ID | 2011 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
Deb | +0.255 |
ourke | +0.247 |
Vand | +0.242 |
$$ | +0.239 |
「 | +0.239 |
Neg logit contributions | |
ahime | -0.305 |
usterity | -0.303 |
Berks | -0.278 |
groupon | -0.271 |
Origin | -0.266 |
Token | Little |
Token ID | 7703 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
ahime | +0.628 |
usterity | +0.624 |
Berks | +0.585 |
groupon | +0.573 |
Origin | +0.565 |
Neg logit contributions | |
Deb | -0.289 |
ourke | -0.278 |
Vand | -0.268 |
$$ | -0.265 |
「 | -0.262 |
Token | Pony |
Token ID | 30377 |
Feature activation | -7.74e+00 |
Pos logit contributions | |
ahime | +1.259 |
usterity | +1.248 |
Berks | +1.113 |
groupon | +1.064 |
Origin | +1.035 |
Neg logit contributions | |
Deb | -2.210 |
ourke | -2.199 |
$$ | -2.140 |
Vand | -2.140 |
「 | -2.133 |
Token | . |
Token ID | 13 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
ahime | +4.863 |
usterity | +4.595 |
Berks | +4.407 |
Origin | +4.294 |
groupon | +4.252 |
Neg logit contributions | |
ourke | -5.031 |
Deb | -4.911 |
$$ | -4.830 |
Vand | -4.792 |
Lama | -4.758 |
Token | It |
Token ID | 632 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
ahime | +0.461 |
usterity | +0.458 |
Berks | +0.425 |
groupon | +0.415 |
Origin | +0.411 |
Neg logit contributions | |
Deb | -0.379 |
ourke | -0.373 |
Vand | -0.361 |
$$ | -0.356 |
「 | -0.355 |
Token | gave |
Token ID | 2921 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ahime | +0.481 |
usterity | +0.478 |
Berks | +0.440 |
groupon | +0.428 |
Origin | +0.420 |
Neg logit contributions | |
Deb | -0.420 |
ourke | -0.410 |
Vand | -0.400 |
$$ | -0.394 |
「 | -0.392 |
Token | me |
Token ID | 502 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Deb | +0.558 |
ourke | +0.538 |
Vand | +0.526 |
$$ | +0.520 |
「 | +0.518 |
Neg logit contributions | |
ahime | -0.827 |
usterity | -0.822 |
Berks | -0.761 |
groupon | -0.744 |
Origin | -0.730 |
Token | an |
Token ID | 281 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Deb | +1.053 |
ourke | +1.015 |
Vand | +0.997 |
$$ | +0.988 |
「 | +0.986 |
Neg logit contributions | |
ahime | -1.325 |
usterity | -1.321 |
Berks | -1.211 |
groupon | -1.183 |
adobe | -1.161 |
Token | f |
Token ID | 69 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
ahime | +1.213 |
usterity | +1.212 |
Berks | +1.116 |
groupon | +1.115 |
adobe | +1.083 |
Neg logit contributions | |
Deb | -0.941 |
ourke | -0.927 |
Vand | -0.897 |
「 | -0.876 |
$$ | -0.866 |
Token | 4 |
Token ID | 19 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
ahime | +2.634 |
usterity | +2.614 |
Berks | +2.411 |
groupon | +2.387 |
adobe | +2.363 |
Neg logit contributions | |
Deb | -1.639 |
ourke | -1.586 |
Vand | -1.545 |
$$ | -1.494 |
「 | -1.489 |
Token | b |
Token ID | 65 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
ahime | +1.694 |
usterity | +1.671 |
Berks | +1.532 |
groupon | +1.518 |
adobe | +1.470 |
Neg logit contributions | |
Deb | -1.580 |
ourke | -1.552 |
Vand | -1.522 |
「 | -1.488 |
$$ | -1.484 |
Token | be |
Token ID | 1350 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
ahime | +3.102 |
usterity | +3.098 |
groupon | +2.896 |
fore | +2.858 |
adobe | +2.792 |
Neg logit contributions | |
Deb | -2.438 |
ourke | -2.377 |
Vand | -2.346 |
Sov | -2.336 |
Lama | -2.288 |
Token | 66 |
Token ID | 2791 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
ahime | +2.221 |
usterity | +2.192 |
Berks | +2.031 |
groupon | +1.999 |
Origin | +1.956 |
Neg logit contributions | |
Deb | -1.510 |
ourke | -1.478 |
Vand | -1.415 |
「 | -1.383 |
$$ | -1.380 |
Token | IEEE |
Token ID | 40552 |
Feature activation | -7.73e+00 |
Pos logit contributions | |
ahime | +2.252 |
usterity | +2.232 |
Berks | +2.055 |
groupon | +1.985 |
adobe | +1.947 |
Neg logit contributions | |
ourke | -2.361 |
Deb | -2.361 |
Vand | -2.263 |
$$ | -2.254 |
Sov | -2.227 |
Token | 802 |
Token ID | 33121 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
ahime | +3.992 |
usterity | +3.803 |
groupon | +3.656 |
Berks | +3.536 |
Origin | +3.505 |
Neg logit contributions | |
ourke | -5.800 |
Deb | -5.716 |
Sov | -5.597 |
Lama | -5.504 |
mble | -5.497 |
Token | . |
Token ID | 13 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
ahime | +1.705 |
usterity | +1.705 |
groupon | +1.607 |
Origin | +1.547 |
Berks | +1.543 |
Neg logit contributions | |
Deb | -1.994 |
ourke | -1.975 |
Vand | -1.909 |
「 | -1.889 |
Seah | -1.854 |
Token | 11 |
Token ID | 1157 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ahime | +0.593 |
usterity | +0.593 |
groupon | +0.561 |
Origin | +0.546 |
Berks | +0.545 |
Neg logit contributions | |
Deb | -0.403 |
ourke | -0.388 |
Vand | -0.374 |
「 | -0.369 |
Lama | -0.359 |
Token | b |
Token ID | 65 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
ahime | +1.018 |
usterity | +1.011 |
Berks | +0.927 |
groupon | +0.904 |
Origin | +0.886 |
Neg logit contributions | |
Deb | -0.878 |
ourke | -0.851 |
Vand | -0.834 |
$$ | -0.825 |
「 | -0.823 |
Token | gn |
Token ID | 4593 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
usterity | +1.160 |
ahime | +1.155 |
groupon | +0.963 |
Berks | +0.947 |
adobe | +0.900 |
Neg logit contributions | |
Deb | -3.160 |
ourke | -3.055 |
Vand | -3.038 |
「 | -2.984 |
$$ | -2.974 |
Token | year |
Token ID | 614 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
ahime | +0.533 |
usterity | +0.532 |
Berks | +0.493 |
groupon | +0.479 |
Origin | +0.474 |
Neg logit contributions | |
Deb | -0.366 |
ourke | -0.359 |
$$ | -0.346 |
Vand | -0.344 |
「 | -0.340 |
Token | both |
Token ID | 1111 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ahime | +1.143 |
usterity | +1.133 |
Berks | +1.033 |
groupon | +1.005 |
Origin | +0.984 |
Neg logit contributions | |
Deb | -1.177 |
ourke | -1.151 |
Vand | -1.123 |
$$ | -1.117 |
「 | -1.110 |
Token | The |
Token ID | 383 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ahime | +0.912 |
usterity | +0.912 |
Berks | +0.839 |
groupon | +0.816 |
Origin | +0.801 |
Neg logit contributions | |
Deb | -0.830 |
ourke | -0.820 |
$$ | -0.792 |
Vand | -0.788 |
「 | -0.779 |
Token | Terminator |
Token ID | 41830 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
ahime | +1.094 |
usterity | +1.084 |
Berks | +1.005 |
groupon | +0.966 |
Origin | +0.955 |
Neg logit contributions | |
Deb | -0.987 |
ourke | -0.971 |
$$ | -0.946 |
「 | -0.935 |
Vand | -0.934 |
Token | and |
Token ID | 290 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
ahime | +2.361 |
usterity | +2.336 |
Berks | +2.117 |
groupon | +2.079 |
Origin | +2.043 |
Neg logit contributions | |
Deb | -2.359 |
ourke | -2.335 |
Vand | -2.272 |
$$ | -2.260 |
Sov | -2.200 |
Token | Transformers |
Token ID | 39185 |
Feature activation | -7.67e+00 |
Pos logit contributions | |
ahime | +0.317 |
usterity | +0.315 |
Berks | +0.291 |
groupon | +0.283 |
Origin | +0.278 |
Neg logit contributions | |
Deb | -0.254 |
ourke | -0.247 |
Vand | -0.241 |
$$ | -0.239 |
「 | -0.238 |
Token | debut |
Token ID | 8886 |
Feature activation | +9.30e-02 |
Pos logit contributions | |
usterity | +4.704 |
ahime | +4.671 |
Origin | +4.285 |
Berks | +4.262 |
groupon | +4.191 |
Neg logit contributions | |
ourke | -4.929 |
Deb | -4.714 |
$$ | -4.665 |
Vand | -4.568 |
Lama | -4.499 |
Token | . |
Token ID | 13 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
Deb | +0.060 |
ourke | +0.058 |
Vand | +0.057 |
$$ | +0.056 |
「 | +0.056 |
Neg logit contributions | |
ahime | -0.064 |
usterity | -0.064 |
Berks | -0.058 |
groupon | -0.057 |
adobe | -0.056 |
Token |
|
Token ID | 198 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Deb | +0.149 |
ourke | +0.143 |
Vand | +0.141 |
「 | +0.139 |
$$ | +0.139 |
Neg logit contributions | |
ahime | -0.204 |
usterity | -0.203 |
Berks | -0.187 |
groupon | -0.183 |
adobe | -0.179 |
Token |
|
Token ID | 198 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
ahime | +0.095 |
usterity | +0.095 |
Berks | +0.088 |
groupon | +0.087 |
Origin | +0.085 |
Neg logit contributions | |
Deb | -0.079 |
ourke | -0.077 |
Vand | -0.075 |
「 | -0.074 |
$$ | -0.074 |
Token | W |
Token ID | 54 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ahime | +0.154 |
usterity | +0.153 |
Berks | +0.139 |
groupon | +0.137 |
Origin | +0.135 |
Neg logit contributions | |
Deb | -0.146 |
ourke | -0.142 |
Vand | -0.139 |
「 | -0.137 |
$$ | -0.136 |
Token | Has |
Token ID | 7875 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
Deb | +0.133 |
ourke | +0.130 |
Vand | +0.126 |
$$ | +0.125 |
「 | +0.125 |
Neg logit contributions | |
ahime | -0.164 |
usterity | -0.163 |
Berks | -0.150 |
groupon | -0.146 |
Origin | -0.144 |
Token | bro |
Token ID | 7957 |
Feature activation | -7.06e+00 |
Pos logit contributions | |
ahime | +0.550 |
usterity | +0.533 |
Berks | +0.481 |
groupon | +0.470 |
Origin | +0.460 |
Neg logit contributions | |
Deb | -0.751 |
ourke | -0.741 |
$$ | -0.722 |
Vand | -0.721 |
「 | -0.719 |
Token | , |
Token ID | 11 |
Feature activation | +7.23e-03 |
Pos logit contributions | |
ahime | +4.166 |
usterity | +4.025 |
Berks | +3.844 |
Origin | +3.705 |
groupon | +3.641 |
Neg logit contributions | |
ourke | -4.789 |
Deb | -4.779 |
Vand | -4.595 |
$$ | -4.588 |
Sov | -4.549 |
Token | Barbie |
Token ID | 46829 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
Deb | +0.004 |
ourke | +0.004 |
Vand | +0.004 |
$$ | +0.004 |
「 | +0.004 |
Neg logit contributions | |
ahime | -0.005 |
usterity | -0.005 |
Berks | -0.005 |
groupon | -0.005 |
Origin | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
ahime | +2.217 |
usterity | +2.213 |
Berks | +2.073 |
groupon | +1.974 |
Origin | +1.948 |
Neg logit contributions | |
Deb | -2.550 |
ourke | -2.532 |
Vand | -2.466 |
$$ | -2.438 |
Sov | -2.426 |
Token | Lego |
Token ID | 33198 |
Feature activation | -7.67e+00 |
Pos logit contributions | |
ahime | +0.576 |
usterity | +0.570 |
Berks | +0.536 |
groupon | +0.516 |
Origin | +0.510 |
Neg logit contributions | |
ourke | -0.488 |
Deb | -0.487 |
$$ | -0.468 |
Vand | -0.465 |
「 | -0.463 |
Token | , |
Token ID | 11 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
ahime | +4.290 |
usterity | +4.262 |
Berks | +3.975 |
Origin | +3.815 |
groupon | +3.769 |
Neg logit contributions | |
ourke | -5.382 |
Deb | -5.312 |
Vand | -5.136 |
$$ | -5.126 |
「 | -5.084 |
Token | Toys |
Token ID | 35397 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
ahime | +0.573 |
usterity | +0.568 |
Berks | +0.534 |
groupon | +0.514 |
Origin | +0.508 |
Neg logit contributions | |
ourke | -0.486 |
Deb | -0.486 |
$$ | -0.466 |
Vand | -0.463 |
「 | -0.462 |
Token | R |
Token ID | 371 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ahime | +1.241 |
usterity | +1.208 |
Berks | +1.131 |
groupon | +1.109 |
Origin | +1.090 |
Neg logit contributions | |
ourke | -1.137 |
Deb | -1.137 |
Vand | -1.101 |
$$ | -1.088 |
「 | -1.085 |
Token | Us |
Token ID | 4021 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Deb | +0.583 |
ourke | +0.561 |
Vand | +0.541 |
$$ | +0.540 |
「 | +0.531 |
Neg logit contributions | |
ahime | -0.918 |
usterity | -0.906 |
Berks | -0.836 |
groupon | -0.820 |
adobe | -0.808 |
Token | , |
Token ID | 11 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
ahime | +0.894 |
usterity | +0.888 |
Berks | +0.811 |
groupon | +0.787 |
Origin | +0.775 |
Neg logit contributions | |
Deb | -0.938 |
ourke | -0.916 |
Vand | -0.897 |
$$ | -0.887 |
「 | -0.884 |
Token | . |
Token ID | 13 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
ahime | +1.466 |
usterity | +1.453 |
Berks | +1.328 |
groupon | +1.282 |
adobe | +1.250 |
Neg logit contributions | |
Deb | -1.555 |
ourke | -1.521 |
$$ | -1.485 |
Vand | -1.480 |
「 | -1.469 |
Token | Though |
Token ID | 7486 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
ahime | +0.616 |
usterity | +0.610 |
Berks | +0.570 |
groupon | +0.555 |
Origin | +0.544 |
Neg logit contributions | |
Deb | -0.486 |
ourke | -0.485 |
Vand | -0.463 |
$$ | -0.460 |
「 | -0.459 |
Token | shows |
Token ID | 2523 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
ahime | +1.869 |
usterity | +1.841 |
Berks | +1.696 |
groupon | +1.652 |
Origin | +1.621 |
Neg logit contributions | |
Deb | -1.721 |
ourke | -1.708 |
$$ | -1.659 |
Vand | -1.655 |
「 | -1.632 |
Token | like |
Token ID | 588 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
ahime | +2.594 |
usterity | +2.587 |
Berks | +2.412 |
groupon | +2.353 |
Origin | +2.327 |
Neg logit contributions | |
Deb | -1.660 |
ourke | -1.637 |
Vand | -1.582 |
$$ | -1.567 |
「 | -1.546 |
Token | Or |
Token ID | 1471 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
Deb | +0.475 |
ourke | +0.459 |
Vand | +0.452 |
$$ | +0.447 |
「 | +0.447 |
Neg logit contributions | |
ahime | -0.474 |
usterity | -0.470 |
Berks | -0.427 |
groupon | -0.416 |
adobe | -0.407 |
Token | phan |
Token ID | 19080 |
Feature activation | -7.57e+00 |
Pos logit contributions | |
ahime | +1.200 |
usterity | +1.185 |
Berks | +1.044 |
groupon | +1.006 |
Origin | +0.977 |
Neg logit contributions | |
Deb | -1.994 |
ourke | -1.943 |
Vand | -1.922 |
$$ | -1.914 |
「 | -1.907 |
Token | Black |
Token ID | 2619 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
usterity | +4.288 |
ahime | +4.251 |
Berks | +4.059 |
groupon | +3.770 |
Origin | +3.770 |
Neg logit contributions | |
ourke | -5.374 |
Vand | -5.206 |
Sov | -5.160 |
「 | -5.145 |
Deb | -5.140 |
Token | and |
Token ID | 290 |
Feature activation | -7.90e-02 |
Pos logit contributions | |
ahime | +1.165 |
usterity | +1.158 |
Berks | +1.057 |
groupon | +1.029 |
Origin | +1.013 |
Neg logit contributions | |
Deb | -1.120 |
ourke | -1.093 |
Vand | -1.069 |
$$ | -1.057 |
「 | -1.050 |
Token | The |
Token ID | 383 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
ahime | +0.055 |
usterity | +0.055 |
Berks | +0.050 |
groupon | +0.049 |
Origin | +0.048 |
Neg logit contributions | |
Deb | -0.050 |
ourke | -0.049 |
Vand | -0.048 |
$$ | -0.047 |
「 | -0.047 |
Token | Vampire |
Token ID | 21463 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
usterity | +1.701 |
ahime | +1.692 |
Berks | +1.576 |
groupon | +1.504 |
Origin | +1.478 |
Neg logit contributions | |
ourke | -1.744 |
Deb | -1.732 |
$$ | -1.684 |
「 | -1.673 |
Vand | -1.671 |
Token | Di |
Token ID | 6031 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
usterity | +2.047 |
ahime | +2.013 |
Berks | +1.860 |
groupon | +1.770 |
Origin | +1.736 |
Neg logit contributions | |
Deb | -2.843 |
ourke | -2.836 |
$$ | -2.738 |
Sov | -2.735 |
Vand | -2.735 |
Token | As |
Token ID | 1081 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
Deb | +0.212 |
ourke | +0.211 |
Vand | +0.201 |
$$ | +0.201 |
「 | +0.200 |
Neg logit contributions | |
usterity | -0.277 |
ahime | -0.277 |
Berks | -0.258 |
groupon | -0.251 |
Origin | -0.245 |
Token | far |
Token ID | 1290 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
Deb | +0.329 |
ourke | +0.322 |
Vand | +0.312 |
$$ | +0.311 |
「 | +0.310 |
Neg logit contributions | |
ahime | -0.390 |
usterity | -0.389 |
Berks | -0.357 |
groupon | -0.348 |
Origin | -0.340 |
Token | as |
Token ID | 355 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
ahime | +2.125 |
usterity | +2.113 |
Berks | +1.909 |
groupon | +1.841 |
Origin | +1.786 |
Neg logit contributions | |
Deb | -2.841 |
ourke | -2.791 |
Vand | -2.747 |
$$ | -2.721 |
「 | -2.715 |
Token | I |
Token ID | 314 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
Deb | +0.873 |
ourke | +0.838 |
Vand | +0.826 |
$$ | +0.814 |
「 | +0.813 |
Neg logit contributions | |
ahime | -1.079 |
usterity | -1.070 |
Berks | -0.980 |
groupon | -0.958 |
adobe | -0.943 |
Token | can |
Token ID | 460 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
ahime | +0.320 |
usterity | +0.318 |
Berks | +0.288 |
groupon | +0.279 |
Origin | +0.273 |
Neg logit contributions | |
Deb | -0.360 |
ourke | -0.350 |
Vand | -0.344 |
$$ | -0.341 |
「 | -0.340 |
Token | tell |
Token ID | 1560 |
Feature activation | -7.54e+00 |
Pos logit contributions | |
usterity | +1.142 |
ahime | +1.125 |
Berks | +1.028 |
groupon | +0.999 |
trust | +0.977 |
Neg logit contributions | |
Deb | -1.292 |
ourke | -1.282 |
Vand | -1.246 |
$$ | -1.226 |
「 | -1.220 |
Token | , |
Token ID | 11 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
usterity | +4.125 |
ahime | +4.011 |
Berks | +3.849 |
groupon | +3.619 |
fore | +3.536 |
Neg logit contributions | |
ourke | -5.481 |
Deb | -5.303 |
$$ | -5.246 |
Sov | -5.165 |
Vand | -5.162 |
Token | there |
Token ID | 612 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
usterity | +0.661 |
ahime | +0.659 |
Berks | +0.613 |
groupon | +0.594 |
Origin | +0.577 |
Neg logit contributions | |
Deb | -0.586 |
ourke | -0.583 |
$$ | -0.559 |
Vand | -0.556 |
「 | -0.554 |
Token | are |
Token ID | 389 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Deb | +1.216 |
ourke | +1.172 |
Vand | +1.147 |
$$ | +1.138 |
「 | +1.138 |
Neg logit contributions | |
ahime | -1.532 |
usterity | -1.520 |
Berks | -1.395 |
groupon | -1.361 |
adobe | -1.339 |
Token | three |
Token ID | 1115 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
usterity | +0.864 |
ahime | +0.863 |
Berks | +0.800 |
groupon | +0.771 |
Origin | +0.752 |
Neg logit contributions | |
Deb | -0.787 |
ourke | -0.785 |
$$ | -0.753 |
Vand | -0.749 |
「 | -0.745 |
Token | big |
Token ID | 1263 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
usterity | +0.649 |
ahime | +0.647 |
Berks | +0.595 |
groupon | +0.578 |
Origin | +0.560 |
Neg logit contributions | |
Deb | -0.633 |
ourke | -0.628 |
$$ | -0.605 |
Vand | -0.602 |
「 | -0.598 |
Token | prev |
Token ID | 8654 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
ahime | +1.726 |
usterity | +1.691 |
Berks | +1.571 |
Origin | +1.533 |
groupon | +1.512 |
Neg logit contributions | |
Deb | -1.404 |
ourke | -1.402 |
Vand | -1.347 |
「 | -1.335 |
$$ | -1.318 |
Token | _ |
Token ID | 62 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ahime | +0.678 |
usterity | +0.674 |
Berks | +0.615 |
groupon | +0.601 |
Origin | +0.593 |
Neg logit contributions | |
Deb | -0.642 |
ourke | -0.629 |
Vand | -0.614 |
「 | -0.606 |
$$ | -0.605 |
Token | state |
Token ID | 5219 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
ahime | +0.905 |
usterity | +0.896 |
Berks | +0.826 |
groupon | +0.814 |
Origin | +0.801 |
Neg logit contributions | |
Deb | -0.665 |
ourke | -0.646 |
Vand | -0.630 |
「 | -0.620 |
$$ | -0.614 |
Token | : |
Token ID | 1058 |
Feature activation | -5.66e+00 |
Pos logit contributions | |
Deb | +0.643 |
ourke | +0.621 |
Vand | +0.611 |
$$ | +0.606 |
「 | +0.605 |
Neg logit contributions | |
ahime | -0.655 |
usterity | -0.651 |
Berks | -0.592 |
groupon | -0.577 |
adobe | -0.565 |
Token | Option |
Token ID | 16018 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
ahime | +3.857 |
usterity | +3.760 |
Berks | +3.607 |
groupon | +3.431 |
Origin | +3.391 |
Neg logit contributions | |
ourke | -3.472 |
Deb | -3.331 |
Sov | -3.287 |
Vand | -3.266 |
$$ | -3.211 |
Token | < |
Token ID | 1279 |
Feature activation | -7.47e+00 |
Pos logit contributions | |
ahime | +0.453 |
usterity | +0.450 |
Berks | +0.405 |
groupon | +0.393 |
adobe | +0.383 |
Neg logit contributions | |
Deb | -0.545 |
ourke | -0.530 |
Vand | -0.521 |
$$ | -0.517 |
「 | -0.516 |
Token | Arc |
Token ID | 10173 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ahime | +4.137 |
usterity | +4.136 |
Berks | +3.893 |
Origin | +3.806 |
groupon | +3.715 |
Neg logit contributions | |
ourke | -5.280 |
Deb | -5.137 |
Vand | -5.034 |
Sov | -4.995 |
「 | -4.985 |
Token | < |
Token ID | 1279 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
Deb | +0.841 |
ourke | +0.807 |
Vand | +0.793 |
$$ | +0.785 |
「 | +0.783 |
Neg logit contributions | |
ahime | -1.013 |
usterity | -1.007 |
Berks | -0.924 |
groupon | -0.902 |
adobe | -0.882 |
Token | Board |
Token ID | 5926 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ahime | +2.413 |
usterity | +2.399 |
Berks | +2.270 |
groupon | +2.181 |
Origin | +2.170 |
Neg logit contributions | |
ourke | -2.104 |
Deb | -2.061 |
「 | -1.997 |
Vand | -1.995 |
$$ | -1.981 |
Token | >> |
Token ID | 9609 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
ahime | +0.786 |
usterity | +0.783 |
Berks | +0.724 |
groupon | +0.706 |
Origin | +0.704 |
Neg logit contributions | |
Deb | -0.608 |
ourke | -0.598 |
Vand | -0.580 |
「 | -0.574 |
$$ | -0.571 |
Token | , |
Token ID | 837 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
ahime | +2.290 |
usterity | +2.278 |
Berks | +2.088 |
groupon | +2.005 |
Origin | +2.002 |
Neg logit contributions | |
Deb | -2.481 |
ourke | -2.439 |
Vand | -2.389 |
$$ | -2.349 |
「 | -2.348 |
Token | " |
Token ID | 366 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
ahime | +1.974 |
usterity | +1.965 |
Berks | +1.808 |
groupon | +1.807 |
Origin | +1.775 |
Neg logit contributions | |
ourke | -1.925 |
Deb | -1.909 |
Vand | -1.824 |
Sov | -1.805 |
$$ | -1.792 |
Token | -- |
Token ID | 438 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
usterity | +1.734 |
ahime | +1.733 |
groupon | +1.605 |
Berks | +1.583 |
Origin | +1.568 |
Neg logit contributions | |
Deb | -1.436 |
ourke | -1.389 |
Vand | -1.338 |
「 | -1.330 |
Lama | -1.296 |
Token | images |
Token ID | 17566 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
ahime | +0.045 |
usterity | +0.045 |
Berks | +0.040 |
groupon | +0.039 |
Origin | +0.038 |
Neg logit contributions | |
Deb | -0.059 |
ourke | -0.057 |
Vand | -0.056 |
「 | -0.056 |
$$ | -0.055 |
Token | ", |
Token ID | 1600 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
Deb | +0.305 |
ourke | +0.296 |
Vand | +0.290 |
「 | +0.287 |
$$ | +0.286 |
Neg logit contributions | |
ahime | -0.337 |
usterity | -0.336 |
Berks | -0.306 |
groupon | -0.300 |
Origin | -0.294 |
Token | required |
Token ID | 2672 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
ahime | +1.442 |
usterity | +1.437 |
Berks | +1.322 |
groupon | +1.281 |
Origin | +1.257 |
Neg logit contributions | |
Deb | -1.340 |
ourke | -1.321 |
Vand | -1.269 |
$$ | -1.254 |
「 | -1.247 |
Token | = |
Token ID | 28 |
Feature activation | -7.42e+00 |
Pos logit contributions | |
usterity | +1.092 |
ahime | +1.091 |
groupon | +0.993 |
Origin | +0.968 |
Berks | +0.967 |
Neg logit contributions | |
Deb | -1.597 |
ourke | -1.579 |
Vand | -1.541 |
「 | -1.525 |
Lama | -1.498 |
Token | True |
Token ID | 17821 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
Origin | +2.749 |
groupon | +2.623 |
usterity | +2.533 |
ahime | +2.410 |
fore | +2.326 |
Neg logit contributions | |
ourke | -6.720 |
ende | -6.622 |
Deb | -6.609 |
mble | -6.591 |
unden | -6.539 |
Token | , |
Token ID | 11 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
usterity | +2.262 |
ahime | +2.230 |
groupon | +2.137 |
Origin | +2.046 |
fore | +2.015 |
Neg logit contributions | |
ourke | -3.346 |
Deb | -3.317 |
Vand | -3.259 |
unden | -3.199 |
Seah | -3.197 |
Token | help |
Token ID | 1037 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
usterity | +3.166 |
ahime | +2.991 |
groupon | +2.812 |
Berks | +2.805 |
Origin | +2.718 |
Neg logit contributions | |
ourke | -3.916 |
Deb | -3.878 |
Vand | -3.806 |
Sov | -3.759 |
「 | -3.690 |
Token | =" |
Token ID | 2625 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
ahime | +1.364 |
usterity | +1.361 |
groupon | +1.256 |
Berks | +1.238 |
Origin | +1.238 |
Neg logit contributions | |
Deb | -1.264 |
ourke | -1.243 |
Vand | -1.215 |
「 | -1.173 |
Lama | -1.163 |
Token | path |
Token ID | 6978 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
ahime | +1.417 |
usterity | +1.387 |
groupon | +1.264 |
Origin | +1.185 |
fore | +1.180 |
Neg logit contributions | |
Deb | -3.397 |
Vand | -3.273 |
ourke | -3.253 |
「 | -3.213 |
Seah | -3.199 |
Token | bind |
Token ID | 21653 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
ahime | +0.012 |
usterity | +0.012 |
Berks | +0.011 |
groupon | +0.011 |
Origin | +0.011 |
Neg logit contributions | |
Deb | -0.012 |
ourke | -0.012 |
Vand | -0.011 |
「 | -0.011 |
$$ | -0.011 |
Token | directive |
Token ID | 22644 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
Deb | +0.603 |
ourke | +0.585 |
Vand | +0.575 |
$$ | +0.570 |
「 | +0.569 |
Neg logit contributions | |
ahime | -0.573 |
usterity | -0.568 |
Berks | -0.516 |
groupon | -0.502 |
adobe | -0.491 |
Token | : |
Token ID | 25 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ahime | +1.200 |
usterity | +1.186 |
Berks | +1.100 |
groupon | +1.062 |
Origin | +1.050 |
Neg logit contributions | |
Deb | -1.146 |
ourke | -1.126 |
Vand | -1.092 |
$$ | -1.074 |
Sov | -1.068 |
Token |
|
Token ID | 198 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
ahime | +1.009 |
usterity | +1.008 |
Berks | +0.929 |
groupon | +0.904 |
Origin | +0.892 |
Neg logit contributions | |
Deb | -0.823 |
ourke | -0.801 |
Vand | -0.780 |
$$ | -0.766 |
「 | -0.761 |
Token |
|
Token ID | 198 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
Deb | +0.164 |
ourke | +0.159 |
Vand | +0.155 |
「 | +0.153 |
$$ | +0.153 |
Neg logit contributions | |
ahime | -0.207 |
usterity | -0.207 |
Berks | -0.190 |
groupon | -0.187 |
Origin | -0.184 |
Token | < |
Token ID | 27 |
Feature activation | -7.29e+00 |
Pos logit contributions | |
Deb | +0.406 |
ourke | +0.393 |
Vand | +0.386 |
「 | +0.381 |
$$ | +0.380 |
Neg logit contributions | |
ahime | -0.415 |
usterity | -0.412 |
Berks | -0.375 |
groupon | -0.367 |
Origin | -0.359 |
Token | body |
Token ID | 2618 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
ahime | +4.063 |
usterity | +4.026 |
fore | +3.711 |
groupon | +3.642 |
Origin | +3.584 |
Neg logit contributions | |
Deb | -5.371 |
ourke | -5.278 |
Vand | -5.241 |
「 | -5.054 |
Rover | -4.972 |
Token | ng |
Token ID | 23370 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
ahime | +0.166 |
usterity | +0.165 |
Berks | +0.152 |
groupon | +0.148 |
adobe | +0.145 |
Neg logit contributions | |
Deb | -0.126 |
ourke | -0.122 |
Vand | -0.119 |
$$ | -0.118 |
「 | -0.118 |
Token | - |
Token ID | 12 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
Deb | +0.274 |
ourke | +0.267 |
Vand | +0.263 |
「 | +0.260 |
$$ | +0.260 |
Neg logit contributions | |
ahime | -0.191 |
usterity | -0.190 |
Berks | -0.169 |
groupon | -0.165 |
Origin | -0.160 |
Token | controller |
Token ID | 36500 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
Deb | +0.044 |
ourke | +0.043 |
Vand | +0.042 |
「 | +0.042 |
$$ | +0.041 |
Neg logit contributions | |
ahime | -0.028 |
usterity | -0.027 |
Berks | -0.024 |
groupon | -0.024 |
Origin | -0.023 |
Token | =" |
Token ID | 2625 |
Feature activation | -4.78e+00 |
Pos logit contributions | |
Deb | +0.505 |
ourke | +0.485 |
$$ | +0.477 |
Vand | +0.473 |
「 | +0.473 |
Neg logit contributions | |
ahime | -0.732 |
usterity | -0.730 |
Berks | -0.672 |
groupon | -0.656 |
adobe | -0.648 |
Token | Angular |
Token ID | 28147 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
ahime | +0.469 |
usterity | +0.467 |
Berks | +0.431 |
groupon | +0.420 |
Origin | +0.413 |
Neg logit contributions | |
Deb | -0.389 |
ourke | -0.380 |
Vand | -0.368 |
$$ | -0.365 |
「 | -0.363 |
Token | tutorial |
Token ID | 11808 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ahime | +1.953 |
usterity | +1.939 |
Berks | +1.799 |
Origin | +1.741 |
groupon | +1.736 |
Neg logit contributions | |
Deb | -1.611 |
ourke | -1.588 |
Vand | -1.554 |
「 | -1.520 |
$$ | -1.516 |
Token | : |
Token ID | 25 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
Deb | +0.815 |
ourke | +0.792 |
Vand | +0.775 |
$$ | +0.767 |
「 | +0.765 |
Neg logit contributions | |
ahime | -0.907 |
usterity | -0.900 |
Berks | -0.824 |
groupon | -0.803 |
Origin | -0.787 |
Token |
|
Token ID | 198 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Deb | +0.094 |
ourke | +0.091 |
Vand | +0.089 |
$$ | +0.088 |
「 | +0.087 |
Neg logit contributions | |
ahime | -0.120 |
usterity | -0.119 |
Berks | -0.110 |
groupon | -0.107 |
Origin | -0.105 |
Token |
|
Token ID | 198 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Deb | +0.878 |
ourke | +0.845 |
Vand | +0.828 |
$$ | +0.823 |
「 | +0.818 |
Neg logit contributions | |
ahime | -1.197 |
usterity | -1.188 |
Berks | -1.095 |
groupon | -1.064 |
adobe | -1.047 |
Token | < |
Token ID | 27 |
Feature activation | -7.28e+00 |
Pos logit contributions | |
Deb | +1.024 |
ourke | +0.992 |
Vand | +0.972 |
$$ | +0.964 |
「 | +0.961 |
Neg logit contributions | |
ahime | -1.164 |
usterity | -1.155 |
Berks | -1.059 |
groupon | -1.031 |
adobe | -1.010 |
Token | body |
Token ID | 2618 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
ahime | +4.602 |
usterity | +4.549 |
groupon | +4.110 |
fore | +4.096 |
Berks | +4.089 |
Neg logit contributions | |
Deb | -4.826 |
ourke | -4.808 |
Vand | -4.696 |
「 | -4.591 |
Lama | -4.489 |
Token | ng |
Token ID | 23370 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
Deb | +0.511 |
ourke | +0.492 |
Vand | +0.485 |
$$ | +0.483 |
「 | +0.482 |
Neg logit contributions | |
ahime | -0.573 |
usterity | -0.570 |
Berks | -0.523 |
groupon | -0.505 |
adobe | -0.498 |
Token | - |
Token ID | 12 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
Deb | +0.217 |
ourke | +0.210 |
Vand | +0.208 |
$$ | +0.207 |
「 | +0.206 |
Neg logit contributions | |
ahime | -0.167 |
usterity | -0.165 |
Berks | -0.147 |
groupon | -0.142 |
adobe | -0.140 |
Token | controller |
Token ID | 36500 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Deb | +0.182 |
ourke | +0.176 |
Vand | +0.173 |
$$ | +0.171 |
「 | +0.171 |
Neg logit contributions | |
ahime | -0.199 |
usterity | -0.197 |
Berks | -0.180 |
groupon | -0.176 |
Origin | -0.172 |
Token | =" |
Token ID | 2625 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
Deb | +0.741 |
ourke | +0.711 |
Vand | +0.699 |
$$ | +0.693 |
「 | +0.689 |
Neg logit contributions | |
ahime | -1.024 |
usterity | -1.019 |
Berks | -0.938 |
groupon | -0.917 |
adobe | -0.902 |
Token | episode |
Token ID | 4471 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ahime | +0.012 |
usterity | +0.012 |
Berks | +0.011 |
groupon | +0.010 |
Origin | +0.010 |
Neg logit contributions | |
Deb | -0.010 |
ourke | -0.009 |
Vand | -0.009 |
$$ | -0.009 |
「 | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ahime | +0.976 |
usterity | +0.965 |
Berks | +0.893 |
groupon | +0.864 |
Origin | +0.851 |
Neg logit contributions | |
Deb | -0.885 |
ourke | -0.874 |
Vand | -0.843 |
$$ | -0.840 |
「 | -0.829 |
Token | a |
Token ID | 257 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Deb | +0.718 |
ourke | +0.690 |
Vand | +0.680 |
「 | +0.673 |
$$ | +0.671 |
Neg logit contributions | |
ahime | -0.828 |
usterity | -0.823 |
Berks | -0.752 |
groupon | -0.735 |
adobe | -0.721 |
Token | little |
Token ID | 1310 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
Deb | +0.685 |
ourke | +0.662 |
Vand | +0.649 |
$$ | +0.642 |
「 | +0.641 |
Neg logit contributions | |
ahime | -0.834 |
usterity | -0.827 |
Berks | -0.760 |
groupon | -0.742 |
adobe | -0.728 |
Token | TO |
Token ID | 5390 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
usterity | +0.666 |
ahime | +0.664 |
Berks | +0.611 |
groupon | +0.588 |
Origin | +0.579 |
Neg logit contributions | |
Deb | -0.620 |
ourke | -0.608 |
Vand | -0.589 |
$$ | -0.588 |
「 | -0.582 |
Token | O |
Token ID | 46 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
ahime | +0.726 |
usterity | +0.721 |
Berks | +0.671 |
groupon | +0.654 |
Origin | +0.648 |
Neg logit contributions | |
Deb | -0.433 |
ourke | -0.415 |
Vand | -0.409 |
「 | -0.400 |
$$ | -0.398 |
Token | simple |
Token ID | 2829 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ahime | +4.590 |
usterity | +4.583 |
Berks | +4.232 |
fore | +4.020 |
Origin | +3.988 |
Neg logit contributions | |
Deb | -4.624 |
ourke | -4.621 |
$$ | -4.438 |
Vand | -4.415 |
Sov | -4.382 |
Token | [ |
Token ID | 685 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Deb | +0.957 |
ourke | +0.923 |
Vand | +0.908 |
$$ | +0.901 |
「 | +0.900 |
Neg logit contributions | |
ahime | -1.065 |
usterity | -1.060 |
Berks | -0.968 |
groupon | -0.942 |
adobe | -0.927 |
Token | laughs |
Token ID | 28124 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Deb | +1.084 |
ourke | +1.055 |
Vand | +1.036 |
$$ | +1.032 |
「 | +1.027 |
Neg logit contributions | |
ahime | -0.930 |
usterity | -0.924 |
Berks | -0.833 |
groupon | -0.805 |
adobe | -0.788 |
Token | ]. |
Token ID | 4083 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
usterity | +1.787 |
ahime | +1.773 |
Berks | +1.665 |
groupon | +1.617 |
Origin | +1.600 |
Neg logit contributions | |
Deb | -1.103 |
ourke | -1.084 |
Vand | -1.042 |
「 | -1.028 |
$$ | -1.026 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ahime | +0.515 |
usterity | +0.513 |
Berks | +0.480 |
groupon | +0.466 |
Origin | +0.457 |
Neg logit contributions | |
ourke | -0.427 |
Deb | -0.423 |
Vand | -0.402 |
$$ | -0.401 |
「 | -0.398 |
Token |
|
Token ID | 198 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
Deb | +0.447 |
ourke | +0.434 |
Vand | +0.424 |
「 | +0.418 |
$$ | +0.418 |
Neg logit contributions | |
ahime | -0.575 |
usterity | -0.573 |
Berks | -0.528 |
groupon | -0.518 |
Origin | -0.508 |
Token | pub |
Token ID | 12984 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
Deb | +0.514 |
ourke | +0.497 |
Vand | +0.489 |
「 | +0.483 |
$$ | +0.481 |
Neg logit contributions | |
ahime | -0.541 |
usterity | -0.537 |
Berks | -0.489 |
groupon | -0.479 |
Origin | -0.469 |
Token | struct |
Token ID | 2878 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
ahime | +2.758 |
usterity | +2.753 |
Berks | +2.553 |
groupon | +2.493 |
Origin | +2.471 |
Neg logit contributions | |
Deb | -1.999 |
ourke | -1.967 |
Vand | -1.888 |
$$ | -1.877 |
「 | -1.873 |
Token | Own |
Token ID | 11744 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
ahime | +2.265 |
usterity | +2.235 |
Berks | +2.113 |
groupon | +2.040 |
Origin | +2.017 |
Neg logit contributions | |
ourke | -1.723 |
Deb | -1.700 |
$$ | -1.635 |
Vand | -1.621 |
Sov | -1.619 |
Token | ed |
Token ID | 276 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
ahime | +0.331 |
usterity | +0.327 |
Berks | +0.290 |
groupon | +0.279 |
Origin | +0.272 |
Neg logit contributions | |
Deb | -0.532 |
ourke | -0.520 |
Vand | -0.512 |
$$ | -0.508 |
「 | -0.507 |
Token | < |
Token ID | 1279 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
ahime | +1.472 |
usterity | +1.455 |
Berks | +1.315 |
groupon | +1.290 |
Origin | +1.289 |
Neg logit contributions | |
Deb | -1.636 |
ourke | -1.594 |
Vand | -1.561 |
$$ | -1.542 |
「 | -1.536 |
Token | T |
Token ID | 309 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
usterity | +4.742 |
ahime | +4.723 |
Berks | +4.456 |
Origin | +4.419 |
groupon | +4.331 |
Neg logit contributions | |
ourke | -4.329 |
Deb | -4.267 |
「 | -4.159 |
Vand | -4.136 |
Sov | -4.071 |
Token | > |
Token ID | 1875 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
Deb | +0.825 |
ourke | +0.795 |
Vand | +0.777 |
$$ | +0.770 |
「 | +0.766 |
Neg logit contributions | |
ahime | -0.987 |
usterity | -0.983 |
Berks | -0.901 |
groupon | -0.880 |
adobe | -0.859 |
Token | { |
Token ID | 1391 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
ahime | +2.790 |
usterity | +2.726 |
Berks | +2.530 |
Origin | +2.435 |
groupon | +2.417 |
Neg logit contributions | |
Deb | -3.254 |
ourke | -3.243 |
Vand | -3.146 |
Sov | -3.139 |
$$ | -3.136 |
Token | ... |
Token ID | 2644 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
usterity | +2.729 |
ahime | +2.728 |
Berks | +2.506 |
Origin | +2.446 |
groupon | +2.438 |
Neg logit contributions | |
ourke | -2.714 |
Deb | -2.697 |
「 | -2.604 |
Vand | -2.603 |
Sov | -2.595 |
Token | } |
Token ID | 1782 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ahime | +1.513 |
usterity | +1.491 |
Berks | +1.366 |
groupon | +1.314 |
Origin | +1.302 |
Neg logit contributions | |
Deb | -1.738 |
ourke | -1.719 |
Vand | -1.672 |
「 | -1.660 |
$$ | -1.659 |
Token | I |
Token ID | 314 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
ahime | +1.136 |
usterity | +1.134 |
Berks | +1.047 |
groupon | +1.013 |
Origin | +0.993 |
Neg logit contributions | |
Deb | -1.091 |
ourke | -1.068 |
$$ | -1.039 |
Vand | -1.038 |
「 | -1.031 |
Token | am |
Token ID | 716 |
Feature activation | -7.66e-01 |
Pos logit contributions | |
ahime | +0.665 |
usterity | +0.663 |
Berks | +0.608 |
groupon | +0.593 |
Origin | +0.581 |
Neg logit contributions | |
Deb | -0.605 |
ourke | -0.589 |
Vand | -0.574 |
$$ | -0.570 |
「 | -0.565 |
Token | against |
Token ID | 1028 |
Feature activation | +5.63e-03 |
Pos logit contributions | |
ahime | +0.553 |
usterity | +0.553 |
Berks | +0.510 |
groupon | +0.494 |
Origin | +0.486 |
Neg logit contributions | |
Deb | -0.458 |
ourke | -0.446 |
Vand | -0.434 |
$$ | -0.434 |
「 | -0.432 |
Token | the |
Token ID | 262 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
Deb | +0.004 |
ourke | +0.003 |
Vand | +0.003 |
$$ | +0.003 |
「 | +0.003 |
Neg logit contributions | |
ahime | -0.004 |
usterity | -0.004 |
Berks | -0.004 |
groupon | -0.003 |
Origin | -0.003 |
Token | First |
Token ID | 3274 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ahime | +0.650 |
usterity | +0.650 |
Berks | +0.595 |
groupon | +0.575 |
Origin | +0.566 |
Neg logit contributions | |
Deb | -0.624 |
ourke | -0.608 |
$$ | -0.593 |
Vand | -0.590 |
「 | -0.588 |
Token | Amendment |
Token ID | 8441 |
Feature activation | -7.17e+00 |
Pos logit contributions | |
ahime | +1.193 |
usterity | +1.187 |
Berks | +1.087 |
groupon | +1.061 |
adobe | +1.040 |
Neg logit contributions | |
Deb | -1.011 |
ourke | -0.975 |
Vand | -0.958 |
$$ | -0.948 |
「 | -0.944 |
Token | . |
Token ID | 13 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
usterity | +4.115 |
ahime | +4.098 |
Origin | +3.620 |
Berks | +3.618 |
groupon | +3.613 |
Neg logit contributions | |
Deb | -4.970 |
ourke | -4.938 |
Vand | -4.801 |
Sov | -4.724 |
$$ | -4.722 |
Token | My |
Token ID | 2011 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
ahime | +1.051 |
usterity | +1.050 |
Berks | +0.978 |
groupon | +0.951 |
Origin | +0.934 |
Neg logit contributions | |
Deb | -0.819 |
ourke | -0.809 |
Vand | -0.778 |
$$ | -0.775 |
「 | -0.772 |
Token | tweets |
Token ID | 12665 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ahime | +1.190 |
usterity | +1.189 |
Berks | +1.096 |
groupon | +1.061 |
Origin | +1.048 |
Neg logit contributions | |
Deb | -1.001 |
ourke | -0.980 |
$$ | -0.959 |
Vand | -0.953 |
「 | -0.942 |
Token | reflected |
Token ID | 12548 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
ahime | +0.721 |
usterity | +0.719 |
Berks | +0.658 |
groupon | +0.642 |
Origin | +0.630 |
Neg logit contributions | |
Deb | -0.672 |
ourke | -0.659 |
Vand | -0.643 |
$$ | -0.636 |
「 | -0.632 |
Token | my |
Token ID | 616 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
Deb | +0.218 |
ourke | +0.212 |
Vand | +0.207 |
$$ | +0.206 |
「 | +0.205 |
Neg logit contributions | |
ahime | -0.256 |
usterity | -0.255 |
Berks | -0.234 |
groupon | -0.228 |
Origin | -0.224 |
Token | : |
Token ID | 25 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
ahime | +0.100 |
usterity | +0.100 |
Berks | +0.091 |
groupon | +0.089 |
Origin | +0.087 |
Neg logit contributions | |
Deb | -0.091 |
ourke | -0.088 |
Vand | -0.086 |
$$ | -0.085 |
「 | -0.085 |
Token |
|
Token ID | 198 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
Deb | +1.226 |
ourke | +1.172 |
Vand | +1.160 |
「 | +1.146 |
$$ | +1.146 |
Neg logit contributions | |
ahime | -1.588 |
usterity | -1.572 |
Berks | -1.443 |
groupon | -1.414 |
adobe | -1.385 |
Token |
|
Token ID | 198 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
Deb | +1.283 |
ourke | +1.223 |
$$ | +1.205 |
Vand | +1.205 |
「 | +1.191 |
Neg logit contributions | |
ahime | -1.830 |
usterity | -1.812 |
Berks | -1.670 |
groupon | -1.613 |
adobe | -1.591 |
Token | Own |
Token ID | 23858 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
Deb | +1.634 |
ourke | +1.592 |
$$ | +1.571 |
Vand | +1.555 |
「 | +1.543 |
Neg logit contributions | |
ahime | -1.662 |
usterity | -1.642 |
Berks | -1.506 |
groupon | -1.445 |
adobe | -1.413 |
Token | ed |
Token ID | 276 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Deb | +0.198 |
ourke | +0.193 |
Vand | +0.189 |
$$ | +0.188 |
「 | +0.187 |
Neg logit contributions | |
ahime | -0.165 |
usterity | -0.164 |
Berks | -0.148 |
groupon | -0.143 |
Origin | -0.140 |
Token | < |
Token ID | 27 |
Feature activation | -7.14e+00 |
Pos logit contributions | |
ahime | +1.195 |
usterity | +1.188 |
Berks | +1.093 |
groupon | +1.060 |
Origin | +1.053 |
Neg logit contributions | |
Deb | -1.047 |
ourke | -1.031 |
Vand | -0.999 |
「 | -0.983 |
$$ | -0.982 |
Token | T |
Token ID | 51 |
Feature activation | -9.21e-02 |
Pos logit contributions | |
usterity | +4.822 |
ahime | +4.793 |
Berks | +4.500 |
Origin | +4.468 |
groupon | +4.419 |
Neg logit contributions | |
ourke | -4.315 |
Deb | -4.196 |
「 | -4.082 |
Vand | -4.072 |
airst | -4.006 |
Token | > |
Token ID | 29 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
ahime | +0.062 |
usterity | +0.062 |
Berks | +0.056 |
groupon | +0.055 |
Origin | +0.054 |
Neg logit contributions | |
Deb | -0.061 |
ourke | -0.059 |
Vand | -0.058 |
$$ | -0.057 |
「 | -0.057 |
Token | , |
Token ID | 837 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
ahime | +2.452 |
usterity | +2.428 |
Berks | +2.267 |
groupon | +2.180 |
Origin | +2.172 |
Neg logit contributions | |
Deb | -2.440 |
ourke | -2.422 |
Vand | -2.346 |
「 | -2.324 |
$$ | -2.316 |
Token | akin |
Token ID | 22107 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ahime | +2.563 |
usterity | +2.531 |
Berks | +2.384 |
groupon | +2.280 |
trust | +2.268 |
Neg logit contributions | |
ourke | -2.248 |
Deb | -2.237 |
Vand | -2.140 |
Sov | -2.137 |
$$ | -2.130 |
Token | to |
Token ID | 284 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Deb | +0.555 |
ourke | +0.535 |
Vand | +0.521 |
「 | +0.518 |
$$ | +0.517 |
Neg logit contributions | |
ahime | -0.814 |
usterity | -0.806 |
Berks | -0.745 |
groupon | -0.730 |
adobe | -0.717 |
Token | Property |
Token ID | 21746 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
Deb | +0.376 |
$$ | +0.355 |
ourke | +0.354 |
Vand | +0.353 |
「 | +0.352 |
Neg logit contributions | |
ahime | -0.488 |
usterity | -0.478 |
Berks | -0.441 |
groupon | -0.429 |
adobe | -0.420 |
Token | ' |
Token ID | 705 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
ahime | +0.166 |
usterity | +0.164 |
Berks | +0.151 |
groupon | +0.147 |
adobe | +0.144 |
Neg logit contributions | |
Deb | -0.137 |
ourke | -0.132 |
Vand | -0.129 |
$$ | -0.128 |
「 | -0.128 |
Token | H |
Token ID | 39 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ahime | +1.528 |
usterity | +1.522 |
Berks | +1.374 |
groupon | +1.360 |
Origin | +1.342 |
Neg logit contributions | |
Deb | -1.508 |
ourke | -1.465 |
Vand | -1.440 |
「 | -1.421 |
$$ | -1.399 |
Token | KC |
Token ID | 36222 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ahime | +1.026 |
usterity | +1.017 |
Berks | +0.922 |
groupon | +0.908 |
Origin | +0.894 |
Neg logit contributions | |
Deb | -1.058 |
ourke | -1.020 |
Vand | -1.005 |
「 | -0.997 |
$$ | -0.983 |
Token | U |
Token ID | 52 |
Feature activation | +8.22e-02 |
Pos logit contributions | |
ahime | +0.968 |
usterity | +0.963 |
Berks | +0.887 |
groupon | +0.869 |
Origin | +0.854 |
Neg logit contributions | |
Deb | -0.734 |
ourke | -0.710 |
Vand | -0.694 |
「 | -0.684 |
$$ | -0.681 |
Token | :\ |
Token ID | 7479 |
Feature activation | -7.11e+00 |
Pos logit contributions | |
Deb | +0.058 |
ourke | +0.056 |
Vand | +0.055 |
$$ | +0.054 |
「 | +0.054 |
Neg logit contributions | |
ahime | -0.052 |
usterity | -0.052 |
Berks | -0.047 |
groupon | -0.045 |
Origin | -0.044 |
Token | Control |
Token ID | 15988 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
usterity | +4.935 |
ahime | +4.899 |
Origin | +4.654 |
groupon | +4.554 |
Berks | +4.539 |
Neg logit contributions | |
Deb | -4.242 |
ourke | -4.226 |
Vand | -4.027 |
「 | -3.983 |
Lama | -3.968 |
Token | Panel |
Token ID | 18810 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
usterity | +0.324 |
ahime | +0.324 |
Berks | +0.292 |
groupon | +0.285 |
Origin | +0.282 |
Neg logit contributions | |
Deb | -0.419 |
ourke | -0.416 |
Vand | -0.410 |
「 | -0.403 |
$$ | -0.398 |
Token | \ |
Token ID | 59 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
ahime | +0.199 |
usterity | +0.198 |
Berks | +0.180 |
groupon | +0.175 |
Origin | +0.172 |
Neg logit contributions | |
Deb | -0.207 |
ourke | -0.202 |
Vand | -0.198 |
$$ | -0.195 |
「 | -0.195 |
Token | Desktop |
Token ID | 36881 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ahime | +3.953 |
usterity | +3.893 |
Origin | +3.708 |
groupon | +3.595 |
Berks | +3.570 |
Neg logit contributions | |
Deb | -3.831 |
ourke | -3.738 |
Vand | -3.637 |
「 | -3.623 |
Lama | -3.609 |
Token | ' |
Token ID | 6 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
Deb | +0.667 |
ourke | +0.644 |
Vand | +0.632 |
$$ | +0.629 |
「 | +0.625 |
Neg logit contributions | |
ahime | -0.777 |
usterity | -0.770 |
Berks | -0.707 |
groupon | -0.688 |
adobe | -0.675 |
Token | relay |
Token ID | 24248 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Deb | +0.337 |
ourke | +0.328 |
$$ | +0.319 |
Vand | +0.318 |
「 | +0.316 |
Neg logit contributions | |
ahime | -0.392 |
usterity | -0.388 |
Berks | -0.358 |
groupon | -0.347 |
Origin | -0.341 |
Token | network |
Token ID | 3127 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
Deb | +0.822 |
ourke | +0.796 |
Vand | +0.780 |
$$ | +0.773 |
「 | +0.771 |
Neg logit contributions | |
ahime | -0.948 |
usterity | -0.941 |
Berks | -0.863 |
groupon | -0.841 |
Origin | -0.824 |
Token | protocol |
Token ID | 8435 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
ahime | +1.553 |
usterity | +1.517 |
Berks | +1.400 |
groupon | +1.357 |
Origin | +1.329 |
Neg logit contributions | |
Deb | -1.511 |
ourke | -1.471 |
Vand | -1.434 |
$$ | -1.428 |
「 | -1.424 |
Token | or |
Token ID | 393 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
ahime | +1.657 |
usterity | +1.610 |
Berks | +1.493 |
groupon | +1.447 |
adobe | +1.417 |
Neg logit contributions | |
Deb | -1.663 |
ourke | -1.618 |
Vand | -1.589 |
「 | -1.572 |
$$ | -1.567 |
Token | I |
Token ID | 314 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
Deb | +0.295 |
ourke | +0.286 |
Vand | +0.280 |
$$ | +0.278 |
「 | +0.277 |
Neg logit contributions | |
ahime | -0.327 |
usterity | -0.325 |
Berks | -0.298 |
groupon | -0.290 |
Origin | -0.284 |
Token | BL |
Token ID | 9148 |
Feature activation | -7.07e+00 |
Pos logit contributions | |
ahime | +0.360 |
usterity | +0.354 |
Berks | +0.317 |
groupon | +0.300 |
Origin | +0.298 |
Neg logit contributions | |
Deb | -0.573 |
ourke | -0.554 |
Vand | -0.552 |
「 | -0.546 |
$$ | -0.545 |
Token | T |
Token ID | 51 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
ahime | +4.846 |
usterity | +4.563 |
Berks | +4.233 |
groupon | +4.230 |
trust | +4.148 |
Neg logit contributions | |
Deb | -4.426 |
「 | -4.265 |
Fey | -4.155 |
Vand | -4.127 |
$$ | -4.113 |
Token | ) |
Token ID | 8 |
Feature activation | +7.37e-02 |
Pos logit contributions | |
ahime | +0.234 |
usterity | +0.231 |
Berks | +0.212 |
groupon | +0.206 |
Origin | +0.202 |
Neg logit contributions | |
Deb | -0.228 |
ourke | -0.221 |
Vand | -0.217 |
$$ | -0.215 |
「 | -0.215 |
Token | and |
Token ID | 290 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
Deb | +0.046 |
ourke | +0.045 |
Vand | +0.044 |
$$ | +0.044 |
「 | +0.044 |
Neg logit contributions | |
ahime | -0.052 |
usterity | -0.051 |
Berks | -0.047 |
groupon | -0.046 |
adobe | -0.045 |
Token | move |
Token ID | 1445 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Deb | +0.420 |
ourke | +0.408 |
Vand | +0.399 |
$$ | +0.396 |
「 | +0.395 |
Neg logit contributions | |
ahime | -0.437 |
usterity | -0.434 |
Berks | -0.397 |
groupon | -0.386 |
Origin | -0.378 |
Token | virtually |
Token ID | 9826 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
ahime | +0.807 |
usterity | +0.796 |
Berks | +0.740 |
groupon | +0.715 |
Origin | +0.704 |
Neg logit contributions | |
Deb | -0.737 |
ourke | -0.727 |
$$ | -0.702 |
Vand | -0.701 |
「 | -0.693 |
Token | set |
Token ID | 2617 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Deb | +0.935 |
ourke | +0.914 |
Vand | +0.902 |
$$ | +0.899 |
「 | +0.894 |
Neg logit contributions | |
ahime | -0.488 |
usterity | -0.485 |
Berks | -0.420 |
groupon | -0.403 |
Origin | -0.389 |
Token | dir |
Token ID | 26672 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Deb | +1.017 |
ourke | +0.985 |
Vand | +0.969 |
$$ | +0.961 |
「 | +0.958 |
Neg logit contributions | |
ahime | -1.039 |
usterity | -1.034 |
Berks | -0.940 |
groupon | -0.916 |
Origin | -0.896 |
Token | = |
Token ID | 28 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Deb | +0.925 |
ourke | +0.898 |
Vand | +0.883 |
$$ | +0.879 |
「 | +0.874 |
Neg logit contributions | |
ahime | -0.866 |
usterity | -0.863 |
Berks | -0.784 |
groupon | -0.761 |
adobe | -0.742 |
Token | c |
Token ID | 66 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
ahime | +0.936 |
usterity | +0.919 |
Berks | +0.847 |
groupon | +0.834 |
adobe | +0.825 |
Neg logit contributions | |
Deb | -0.734 |
ourke | -0.712 |
Vand | -0.695 |
「 | -0.685 |
$$ | -0.671 |
Token | \ |
Token ID | 59 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
ahime | +0.144 |
usterity | +0.141 |
Berks | +0.128 |
groupon | +0.126 |
Origin | +0.123 |
Neg logit contributions | |
Deb | -0.148 |
ourke | -0.144 |
Vand | -0.141 |
「 | -0.139 |
$$ | -0.138 |
Token | :\ |
Token ID | 7479 |
Feature activation | -7.06e+00 |
Pos logit contributions | |
ahime | +3.051 |
usterity | +2.967 |
Berks | +2.723 |
groupon | +2.705 |
fore | +2.703 |
Neg logit contributions | |
Deb | -2.695 |
ourke | -2.633 |
Vand | -2.549 |
「 | -2.502 |
Lama | -2.495 |
Token | tmp |
Token ID | 22065 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ahime | +4.931 |
usterity | +4.747 |
groupon | +4.390 |
fore | +4.386 |
Berks | +4.373 |
Neg logit contributions | |
Deb | -4.290 |
ourke | -4.178 |
Vand | -4.058 |
Lama | -3.985 |
「 | -3.953 |
Token | : |
Token ID | 25 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
ahime | +1.040 |
usterity | +1.026 |
Berks | +0.932 |
groupon | +0.918 |
adobe | +0.901 |
Neg logit contributions | |
Deb | -0.989 |
ourke | -0.968 |
Vand | -0.940 |
「 | -0.924 |
Lama | -0.912 |
Token | */ |
Token ID | 9466 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ahime | +1.850 |
usterity | +1.822 |
Berks | +1.708 |
groupon | +1.687 |
adobe | +1.666 |
Neg logit contributions | |
Deb | -0.811 |
ourke | -0.780 |
Vand | -0.752 |
「 | -0.728 |
Lama | -0.710 |
Token | This |
Token ID | 770 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
Deb | +0.613 |
ourke | +0.596 |
Vand | +0.579 |
$$ | +0.571 |
「 | +0.570 |
Neg logit contributions | |
ahime | -0.899 |
usterity | -0.893 |
Berks | -0.829 |
groupon | -0.810 |
Origin | -0.795 |
Token | sets |
Token ID | 5621 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
ahime | +0.167 |
usterity | +0.166 |
Berks | +0.152 |
groupon | +0.148 |
Origin | +0.145 |
Neg logit contributions | |
Deb | -0.164 |
ourke | -0.161 |
Vand | -0.157 |
$$ | -0.155 |
「 | -0.154 |
Token | top |
Token ID | 1353 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
usterity | +0.592 |
ahime | +0.588 |
Berks | +0.543 |
groupon | +0.525 |
Origin | +0.518 |
Neg logit contributions | |
Deb | -0.626 |
ourke | -0.618 |
$$ | -0.598 |
Vand | -0.597 |
「 | -0.588 |
Token | toy |
Token ID | 13373 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ahime | +1.368 |
usterity | +1.366 |
Berks | +1.244 |
groupon | +1.193 |
Origin | +1.173 |
Neg logit contributions | |
ourke | -2.032 |
Deb | -2.022 |
$$ | -1.953 |
Vand | -1.943 |
「 | -1.917 |
Token | brands |
Token ID | 11394 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
ahime | +0.745 |
usterity | +0.740 |
Berks | +0.674 |
groupon | +0.655 |
Origin | +0.641 |
Neg logit contributions | |
Deb | -0.840 |
ourke | -0.823 |
Vand | -0.804 |
$$ | -0.801 |
「 | -0.793 |
Token | include |
Token ID | 2291 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
ahime | +1.406 |
usterity | +1.398 |
Berks | +1.284 |
groupon | +1.240 |
Origin | +1.228 |
Neg logit contributions | |
Deb | -1.519 |
ourke | -1.511 |
Vand | -1.453 |
$$ | -1.437 |
Sov | -1.417 |
Token | Has |
Token ID | 7875 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
Deb | +0.133 |
ourke | +0.130 |
Vand | +0.126 |
$$ | +0.125 |
「 | +0.125 |
Neg logit contributions | |
ahime | -0.164 |
usterity | -0.163 |
Berks | -0.150 |
groupon | -0.146 |
Origin | -0.144 |
Token | bro |
Token ID | 7957 |
Feature activation | -7.06e+00 |
Pos logit contributions | |
ahime | +0.550 |
usterity | +0.533 |
Berks | +0.481 |
groupon | +0.470 |
Origin | +0.460 |
Neg logit contributions | |
Deb | -0.751 |
ourke | -0.741 |
$$ | -0.722 |
Vand | -0.721 |
「 | -0.719 |
Token | , |
Token ID | 11 |
Feature activation | +7.23e-03 |
Pos logit contributions | |
ahime | +4.166 |
usterity | +4.025 |
Berks | +3.844 |
Origin | +3.705 |
groupon | +3.641 |
Neg logit contributions | |
ourke | -4.789 |
Deb | -4.779 |
Vand | -4.595 |
$$ | -4.588 |
Sov | -4.549 |
Token | Barbie |
Token ID | 46829 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
Deb | +0.004 |
ourke | +0.004 |
Vand | +0.004 |
$$ | +0.004 |
「 | +0.004 |
Neg logit contributions | |
ahime | -0.005 |
usterity | -0.005 |
Berks | -0.005 |
groupon | -0.005 |
Origin | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
ahime | +2.217 |
usterity | +2.213 |
Berks | +2.073 |
groupon | +1.974 |
Origin | +1.948 |
Neg logit contributions | |
Deb | -2.550 |
ourke | -2.532 |
Vand | -2.466 |
$$ | -2.438 |
Sov | -2.426 |
Token | Lego |
Token ID | 33198 |
Feature activation | -7.67e+00 |
Pos logit contributions | |
ahime | +0.576 |
usterity | +0.570 |
Berks | +0.536 |
groupon | +0.516 |
Origin | +0.510 |
Neg logit contributions | |
ourke | -0.488 |
Deb | -0.487 |
$$ | -0.468 |
Vand | -0.465 |
「 | -0.463 |
Token | , |
Token ID | 11 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
ahime | +4.290 |
usterity | +4.262 |
Berks | +3.975 |
Origin | +3.815 |
groupon | +3.769 |
Neg logit contributions | |
ourke | -5.382 |
Deb | -5.312 |
Vand | -5.136 |
$$ | -5.126 |
「 | -5.084 |
Token | voters |
Token ID | 4446 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
ahime | +1.356 |
usterity | +1.353 |
Berks | +1.282 |
groupon | +1.232 |
Origin | +1.207 |
Neg logit contributions | |
Deb | -1.068 |
ourke | -1.054 |
$$ | -1.029 |
Vand | -1.019 |
「 | -1.013 |
Token | , |
Token ID | 11 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
ahime | +1.262 |
usterity | +1.247 |
Berks | +1.142 |
groupon | +1.111 |
Origin | +1.079 |
Neg logit contributions | |
Deb | -1.394 |
ourke | -1.367 |
Vand | -1.340 |
$$ | -1.334 |
「 | -1.322 |
Token | according |
Token ID | 1864 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
Deb | +0.158 |
ourke | +0.155 |
Vand | +0.150 |
$$ | +0.149 |
「 | +0.148 |
Neg logit contributions | |
ahime | -0.176 |
usterity | -0.175 |
Berks | -0.162 |
groupon | -0.158 |
Origin | -0.154 |
Token | to |
Token ID | 284 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Deb | +0.452 |
ourke | +0.441 |
Vand | +0.428 |
$$ | +0.424 |
「 | +0.423 |
Neg logit contributions | |
ahime | -0.593 |
usterity | -0.589 |
Berks | -0.547 |
groupon | -0.538 |
Origin | -0.526 |
Token | Real |
Token ID | 6416 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
ahime | +0.869 |
usterity | +0.868 |
Berks | +0.804 |
groupon | +0.775 |
Origin | +0.758 |
Neg logit contributions | |
Deb | -0.805 |
ourke | -0.797 |
$$ | -0.771 |
Vand | -0.769 |
「 | -0.766 |
Token | Clear |
Token ID | 19856 |
Feature activation | -6.99e+00 |
Pos logit contributions | |
usterity | +2.066 |
ahime | +2.047 |
Berks | +1.906 |
groupon | +1.843 |
Origin | +1.792 |
Neg logit contributions | |
ourke | -2.607 |
Deb | -2.598 |
「 | -2.519 |
$$ | -2.508 |
Vand | -2.506 |
Token | Politics |
Token ID | 43921 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
usterity | +4.457 |
groupon | +4.119 |
ahime | +4.108 |
Berks | +4.032 |
Origin | +4.031 |
Neg logit contributions | |
ourke | -4.539 |
Rover | -4.404 |
Vand | -4.303 |
Fey | -4.255 |
「 | -4.227 |
Token | , |
Token ID | 11 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ahime | +1.030 |
usterity | +1.021 |
Berks | +0.930 |
groupon | +0.905 |
adobe | +0.890 |
Neg logit contributions | |
Deb | -0.978 |
ourke | -0.944 |
Vand | -0.925 |
$$ | -0.920 |
「 | -0.918 |
Token | said |
Token ID | 531 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Deb | +0.071 |
ourke | +0.070 |
Vand | +0.068 |
$$ | +0.067 |
「 | +0.067 |
Neg logit contributions | |
ahime | -0.078 |
usterity | -0.077 |
Berks | -0.071 |
groupon | -0.069 |
Origin | -0.068 |
Token | a |
Token ID | 257 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
usterity | +1.139 |
ahime | +1.133 |
Berks | +1.053 |
groupon | +1.013 |
Origin | +0.995 |
Neg logit contributions | |
Deb | -1.034 |
ourke | -1.014 |
$$ | -0.994 |
Vand | -0.986 |
「 | -0.970 |
Token | � |
Token ID | 564 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
usterity | +0.770 |
ahime | +0.763 |
Berks | +0.703 |
groupon | +0.678 |
Origin | +0.662 |
Neg logit contributions | |
Deb | -0.685 |
ourke | -0.666 |
Vand | -0.651 |
$$ | -0.647 |
「 | -0.643 |
Token | Conclusion |
Token ID | 21481 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
Deb | +0.500 |
ourke | +0.484 |
Vand | +0.475 |
「 | +0.470 |
$$ | +0.468 |
Neg logit contributions | |
ahime | -0.556 |
usterity | -0.555 |
Berks | -0.506 |
groupon | -0.496 |
Origin | -0.487 |
Token |
|
Token ID | 198 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
ahime | +0.536 |
usterity | +0.534 |
Berks | +0.490 |
groupon | +0.479 |
Origin | +0.471 |
Neg logit contributions | |
Deb | -0.419 |
ourke | -0.408 |
Vand | -0.397 |
$$ | -0.394 |
「 | -0.392 |
Token |
|
Token ID | 198 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
Deb | +0.151 |
ourke | +0.147 |
Vand | +0.143 |
「 | +0.141 |
$$ | +0.141 |
Neg logit contributions | |
ahime | -0.190 |
usterity | -0.189 |
Berks | -0.175 |
groupon | -0.172 |
Origin | -0.168 |
Token | This |
Token ID | 1212 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
Deb | +0.231 |
ourke | +0.224 |
Vand | +0.219 |
「 | +0.217 |
$$ | +0.214 |
Neg logit contributions | |
ahime | -0.254 |
usterity | -0.254 |
Berks | -0.232 |
groupon | -0.228 |
Origin | -0.224 |
Token | post |
Token ID | 1281 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
ahime | +0.412 |
usterity | +0.410 |
Berks | +0.373 |
groupon | +0.362 |
Origin | +0.355 |
Neg logit contributions | |
Deb | -0.434 |
ourke | -0.426 |
Vand | -0.416 |
$$ | -0.414 |
「 | -0.412 |
Token | only |
Token ID | 691 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
ahime | +0.535 |
usterity | +0.531 |
Berks | +0.484 |
groupon | +0.471 |
adobe | +0.461 |
Neg logit contributions | |
Deb | -0.529 |
ourke | -0.515 |
Vand | -0.505 |
$$ | -0.500 |
「 | -0.499 |
Token | repeats |
Token ID | 29819 |
Feature activation | -8.96e-03 |
Pos logit contributions | |
Deb | +2.350 |
ourke | +2.233 |
Vand | +2.210 |
「 | +2.191 |
$$ | +2.189 |
Neg logit contributions | |
ahime | -2.795 |
usterity | -2.750 |
Berks | -2.489 |
groupon | -2.435 |
Origin | -2.419 |
Token | some |
Token ID | 617 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
ahime | +0.006 |
usterity | +0.006 |
Berks | +0.006 |
groupon | +0.006 |
Origin | +0.005 |
Neg logit contributions | |
Deb | -0.006 |
ourke | -0.005 |
$$ | -0.005 |
「 | -0.005 |
Vand | -0.005 |
Token | basic |
Token ID | 4096 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
ahime | +0.335 |
usterity | +0.335 |
Berks | +0.306 |
groupon | +0.297 |
Origin | +0.289 |
Neg logit contributions | |
Deb | -0.362 |
ourke | -0.357 |
$$ | -0.348 |
Vand | -0.347 |
「 | -0.345 |
Token | information |
Token ID | 1321 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
ahime | +0.150 |
usterity | +0.150 |
Berks | +0.138 |
groupon | +0.135 |
Origin | +0.132 |
Neg logit contributions | |
Deb | -0.119 |
ourke | -0.117 |
Vand | -0.113 |
$$ | -0.113 |
「 | -0.112 |
Token | about |
Token ID | 546 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
ahime | +2.391 |
usterity | +2.374 |
Berks | +2.206 |
groupon | +2.118 |
Origin | +2.089 |
Neg logit contributions | |
ourke | -2.791 |
Deb | -2.727 |
$$ | -2.669 |
Vand | -2.637 |
「 | -2.629 |
Token | this |
Token ID | 428 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
ahime | +0.028 |
usterity | +0.028 |
Berks | +0.026 |
groupon | +0.025 |
Origin | +0.024 |
Neg logit contributions | |
Deb | -0.024 |
ourke | -0.023 |
Vand | -0.022 |
$$ | -0.022 |
「 | -0.022 |
Token | page |
Token ID | 2443 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
Deb | +0.138 |
ourke | +0.135 |
Vand | +0.132 |
$$ | +0.131 |
「 | +0.130 |
Neg logit contributions | |
ahime | -0.155 |
usterity | -0.155 |
Berks | -0.142 |
groupon | -0.139 |
Origin | -0.136 |
Token | and |
Token ID | 290 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
ahime | +0.664 |
usterity | +0.663 |
Berks | +0.612 |
groupon | +0.596 |
Origin | +0.583 |
Neg logit contributions | |
Deb | -0.642 |
ourke | -0.631 |
Vand | -0.610 |
$$ | -0.606 |
「 | -0.602 |
Token | make |
Token ID | 787 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
Deb | +0.624 |
ourke | +0.606 |
Vand | +0.593 |
$$ | +0.588 |
「 | +0.586 |
Neg logit contributions | |
ahime | -0.678 |
usterity | -0.673 |
Berks | -0.617 |
groupon | -0.600 |
Origin | -0.588 |
Token | fun |
Token ID | 1257 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Deb | +0.189 |
ourke | +0.187 |
Vand | +0.180 |
$$ | +0.179 |
「 | +0.178 |
Neg logit contributions | |
ahime | -0.246 |
usterity | -0.243 |
Berks | -0.227 |
groupon | -0.220 |
Origin | -0.217 |
Token | of |
Token ID | 286 |
Feature activation | +5.56e+00 |
Pos logit contributions | |
Deb | +1.011 |
ourke | +0.971 |
Vand | +0.960 |
$$ | +0.947 |
「 | +0.947 |
Neg logit contributions | |
ahime | -1.027 |
usterity | -1.017 |
Berks | -0.924 |
groupon | -0.903 |
adobe | -0.880 |
Token | and |
Token ID | 290 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
Deb | +3.316 |
Vand | +3.110 |
ourke | +3.075 |
$$ | +3.044 |
「 | +3.033 |
Neg logit contributions | |
ahime | -4.176 |
usterity | -4.130 |
Berks | -3.715 |
groupon | -3.665 |
adobe | -3.655 |
Token | mock |
Token ID | 15290 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
Deb | +0.264 |
ourke | +0.258 |
Vand | +0.250 |
$$ | +0.248 |
「 | +0.247 |
Neg logit contributions | |
ahime | -0.347 |
usterity | -0.346 |
Berks | -0.320 |
groupon | -0.313 |
Origin | -0.307 |
Token | Child |
Token ID | 5932 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ahime | +0.195 |
usterity | +0.194 |
Berks | +0.179 |
groupon | +0.174 |
Origin | +0.171 |
Neg logit contributions | |
Deb | -0.167 |
ourke | -0.164 |
Vand | -0.159 |
$$ | -0.158 |
「 | -0.158 |
Token | Mol |
Token ID | 17958 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
ahime | +0.915 |
usterity | +0.913 |
Berks | +0.845 |
groupon | +0.823 |
Origin | +0.810 |
Neg logit contributions | |
Deb | -0.767 |
ourke | -0.754 |
Vand | -0.732 |
「 | -0.730 |
$$ | -0.728 |
Token | estation |
Token ID | 27364 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Deb | +0.200 |
ourke | +0.194 |
Vand | +0.190 |
$$ | +0.189 |
「 | +0.188 |
Neg logit contributions | |
ahime | -0.192 |
usterity | -0.191 |
Berks | -0.174 |
groupon | -0.169 |
Origin | -0.165 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Deb | +1.846 |
ourke | +1.752 |
Vand | +1.730 |
「 | +1.717 |
$$ | +1.712 |
Neg logit contributions | |
ahime | -2.451 |
usterity | -2.450 |
Berks | -2.232 |
groupon | -2.176 |
adobe | -2.156 |
Token | And |
Token ID | 843 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
ahime | +0.925 |
usterity | +0.921 |
Berks | +0.874 |
groupon | +0.844 |
Origin | +0.817 |
Neg logit contributions | |
ourke | -0.854 |
Deb | -0.839 |
$$ | -0.808 |
Vand | -0.808 |
「 | -0.806 |
Token | there |
Token ID | 612 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ahime | +1.288 |
usterity | +1.288 |
Berks | +1.204 |
groupon | +1.161 |
Origin | +1.126 |
Neg logit contributions | |
Deb | -1.272 |
ourke | -1.265 |
$$ | -1.233 |
Vand | -1.227 |
「 | -1.220 |
Token | were |
Token ID | 547 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Deb | +0.711 |
ourke | +0.687 |
Vand | +0.673 |
$$ | +0.666 |
「 | +0.665 |
Neg logit contributions | |
ahime | -0.890 |
usterity | -0.884 |
Berks | -0.813 |
groupon | -0.793 |
adobe | -0.778 |
Token | many |
Token ID | 867 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
usterity | +0.971 |
ahime | +0.969 |
Berks | +0.905 |
groupon | +0.873 |
Origin | +0.850 |
Neg logit contributions | |
Deb | -0.888 |
ourke | -0.881 |
$$ | -0.851 |
Vand | -0.848 |
「 | -0.841 |
Token | others |
Token ID | 1854 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
Deb | +0.312 |
ourke | +0.303 |
Vand | +0.296 |
$$ | +0.294 |
「 | +0.293 |
Neg logit contributions | |
ahime | -0.339 |
usterity | -0.338 |
Berks | -0.310 |
groupon | -0.301 |
Origin | -0.295 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Deb | +2.706 |
ourke | +2.571 |
Vand | +2.559 |
「 | +2.521 |
$$ | +2.516 |
Neg logit contributions | |
ahime | -3.299 |
usterity | -3.266 |
Berks | -2.943 |
groupon | -2.876 |
adobe | -2.849 |
Token |
|
Token ID | 198 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
Deb | +0.747 |
ourke | +0.732 |
Vand | +0.709 |
$$ | +0.705 |
「 | +0.703 |
Neg logit contributions | |
ahime | -0.905 |
usterity | -0.899 |
Berks | -0.832 |
groupon | -0.810 |
Origin | -0.793 |
Token |
|
Token ID | 198 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
Deb | +0.286 |
ourke | +0.279 |
Vand | +0.272 |
「 | +0.268 |
$$ | +0.267 |
Neg logit contributions | |
ahime | -0.356 |
usterity | -0.355 |
Berks | -0.327 |
groupon | -0.323 |
Origin | -0.316 |
Token | Yet |
Token ID | 11486 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
Deb | +0.344 |
ourke | +0.334 |
Vand | +0.329 |
「 | +0.324 |
$$ | +0.322 |
Neg logit contributions | |
ahime | -0.345 |
usterity | -0.345 |
Berks | -0.314 |
groupon | -0.309 |
Origin | -0.304 |
Token | being |
Token ID | 852 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
Deb | +0.393 |
ourke | +0.382 |
Vand | +0.374 |
$$ | +0.371 |
「 | +0.370 |
Neg logit contributions | |
ahime | -0.403 |
usterity | -0.400 |
Berks | -0.366 |
groupon | -0.355 |
Origin | -0.348 |
Token | re |
Token ID | 260 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
Deb | +1.227 |
ourke | +1.189 |
Vand | +1.165 |
$$ | +1.150 |
「 | +1.148 |
Neg logit contributions | |
ahime | -1.422 |
usterity | -1.417 |
Berks | -1.294 |
groupon | -1.262 |
adobe | -1.242 |
Token | ment |
Token ID | 434 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Deb | +1.094 |
ourke | +1.057 |
Vand | +1.035 |
$$ | +1.025 |
「 | +1.022 |
Neg logit contributions | |
ahime | -1.381 |
usterity | -1.373 |
Berks | -1.263 |
groupon | -1.233 |
adobe | -1.209 |
Token | , |
Token ID | 11 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
Deb | +1.120 |
ourke | +1.081 |
Vand | +1.057 |
$$ | +1.046 |
「 | +1.043 |
Neg logit contributions | |
ahime | -1.532 |
usterity | -1.522 |
Berks | -1.404 |
groupon | -1.372 |
Origin | -1.347 |
Token | les |
Token ID | 10287 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
ahime | +0.460 |
usterity | +0.454 |
Berks | +0.425 |
groupon | +0.412 |
Origin | +0.407 |
Neg logit contributions | |
Deb | -0.310 |
ourke | -0.307 |
Vand | -0.293 |
$$ | -0.291 |
「 | -0.290 |
Token | Cors |
Token ID | 26978 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
Deb | +1.465 |
ourke | +1.404 |
Vand | +1.388 |
$$ | +1.364 |
「 | +1.363 |
Neg logit contributions | |
ahime | -1.780 |
usterity | -1.769 |
Berks | -1.621 |
groupon | -1.584 |
adobe | -1.555 |
Token | aires |
Token ID | 17693 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
Deb | +1.600 |
ourke | +1.529 |
Vand | +1.475 |
$$ | +1.452 |
「 | +1.448 |
Neg logit contributions | |
ahime | -3.563 |
usterity | -3.553 |
Berks | -3.320 |
groupon | -3.260 |
Origin | -3.208 |
Token | l |
Token ID | 300 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
Deb | +2.420 |
ourke | +2.289 |
Vand | +2.280 |
「 | +2.245 |
$$ | +2.242 |
Neg logit contributions | |
ahime | -3.173 |
usterity | -3.163 |
Berks | -2.899 |
groupon | -2.851 |
adobe | -2.801 |
Token | oy |
Token ID | 726 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Deb | +1.256 |
ourke | +1.211 |
Vand | +1.183 |
$$ | +1.170 |
「 | +1.167 |
Neg logit contributions | |
ahime | -1.833 |
usterity | -1.823 |
Berks | -1.686 |
groupon | -1.648 |
Origin | -1.618 |
Token | aux |
Token ID | 14644 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
Deb | +0.962 |
ourke | +0.932 |
Vand | +0.911 |
$$ | +0.904 |
「 | +0.901 |
Neg logit contributions | |
ahime | -1.176 |
usterity | -1.166 |
Berks | -1.073 |
groupon | -1.046 |
Origin | -1.027 |
Token | rest |
Token ID | 1334 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Deb | +1.565 |
ourke | +1.497 |
Vand | +1.476 |
$$ | +1.454 |
「 | +1.453 |
Neg logit contributions | |
ahime | -2.112 |
usterity | -2.099 |
Berks | -1.932 |
groupon | -1.891 |
adobe | -1.858 |
Token | ants |
Token ID | 1187 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Deb | +0.940 |
ourke | +0.908 |
Vand | +0.889 |
$$ | +0.881 |
「 | +0.879 |
Neg logit contributions | |
ahime | -1.144 |
usterity | -1.138 |
Berks | -1.045 |
groupon | -1.022 |
Origin | -1.001 |
Token | , |
Token ID | 11 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
Deb | +1.133 |
ourke | +1.073 |
Vand | +1.070 |
「 | +1.068 |
$$ | +1.058 |
Neg logit contributions | |
ahime | -1.315 |
usterity | -1.282 |
Berks | -1.171 |
groupon | -1.136 |
adobe | -1.120 |
Token | when |
Token ID | 618 |
Feature activation | -7.59e-02 |
Pos logit contributions | |
usterity | +1.491 |
ahime | +1.485 |
Berks | +1.380 |
groupon | +1.342 |
Origin | +1.308 |
Neg logit contributions | |
Deb | -1.301 |
ourke | -1.277 |
Vand | -1.240 |
$$ | -1.227 |
「 | -1.211 |
Token | I |
Token ID | 314 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
ahime | +0.057 |
usterity | +0.057 |
Berks | +0.052 |
groupon | +0.051 |
Origin | +0.050 |
Neg logit contributions | |
Deb | -0.044 |
ourke | -0.043 |
Vand | -0.042 |
$$ | -0.041 |
「 | -0.041 |
Token | want |
Token ID | 765 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Deb | +0.356 |
ourke | +0.345 |
Vand | +0.338 |
$$ | +0.335 |
「 | +0.335 |
Neg logit contributions | |
ahime | -0.374 |
usterity | -0.371 |
Berks | -0.339 |
groupon | -0.330 |
Origin | -0.323 |
Token | to |
Token ID | 284 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
Deb | +0.930 |
ourke | +0.885 |
Vand | +0.872 |
「 | +0.865 |
$$ | +0.862 |
Neg logit contributions | |
ahime | -1.337 |
usterity | -1.319 |
Berks | -1.214 |
groupon | -1.189 |
adobe | -1.171 |
Token | feel |
Token ID | 1254 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
Deb | +0.491 |
ourke | +0.474 |
Vand | +0.466 |
$$ | +0.462 |
「 | +0.462 |
Neg logit contributions | |
ahime | -0.561 |
usterity | -0.555 |
Berks | -0.508 |
groupon | -0.495 |
Origin | -0.485 |
Token | it |
Token ID | 340 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Deb | +2.249 |
Vand | +2.125 |
「 | +2.118 |
ourke | +2.101 |
$$ | +2.087 |
Neg logit contributions | |
ahime | -3.067 |
usterity | -2.963 |
Berks | -2.705 |
groupon | -2.655 |
Origin | -2.608 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ahime | +0.105 |
usterity | +0.104 |
Berks | +0.095 |
groupon | +0.093 |
adobe | +0.091 |
Neg logit contributions | |
Deb | -0.097 |
ourke | -0.094 |
Vand | -0.093 |
$$ | -0.092 |
「 | -0.092 |
Token | And |
Token ID | 843 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
usterity | +0.972 |
ahime | +0.970 |
Berks | +0.910 |
groupon | +0.881 |
Origin | +0.863 |
Neg logit contributions | |
ourke | -0.798 |
Deb | -0.792 |
Vand | -0.757 |
$$ | -0.754 |
「 | -0.745 |
Token | I |
Token ID | 314 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
usterity | +1.317 |
ahime | +1.311 |
Berks | +1.219 |
groupon | +1.180 |
Origin | +1.156 |
Neg logit contributions | |
Deb | -1.153 |
ourke | -1.146 |
$$ | -1.107 |
Vand | -1.101 |
「 | -1.090 |
Token | think |
Token ID | 892 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Deb | +0.070 |
ourke | +0.068 |
Vand | +0.067 |
$$ | +0.066 |
「 | +0.066 |
Neg logit contributions | |
ahime | -0.071 |
usterity | -0.070 |
Berks | -0.064 |
groupon | -0.062 |
Origin | -0.061 |
Token | is |
Token ID | 318 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
ahime | +0.367 |
usterity | +0.364 |
Berks | +0.333 |
groupon | +0.325 |
Origin | +0.318 |
Neg logit contributions | |
Deb | -0.334 |
ourke | -0.323 |
Vand | -0.317 |
$$ | -0.314 |
「 | -0.313 |
Token | in |
Token ID | 287 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
ahime | +0.395 |
usterity | +0.395 |
Berks | +0.361 |
groupon | +0.353 |
Origin | +0.344 |
Neg logit contributions | |
Deb | -0.369 |
ourke | -0.361 |
Vand | -0.352 |
「 | -0.347 |
$$ | -0.347 |
Token | many |
Token ID | 867 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
Deb | +0.371 |
ourke | +0.361 |
Vand | +0.353 |
$$ | +0.349 |
「 | +0.348 |
Neg logit contributions | |
ahime | -0.415 |
usterity | -0.411 |
Berks | -0.377 |
groupon | -0.367 |
Origin | -0.359 |
Token | cases |
Token ID | 2663 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Deb | +0.342 |
ourke | +0.327 |
Vand | +0.316 |
$$ | +0.312 |
「 | +0.311 |
Neg logit contributions | |
ahime | -0.724 |
usterity | -0.721 |
Berks | -0.674 |
groupon | -0.661 |
Origin | -0.650 |
Token | a |
Token ID | 257 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Deb | +0.689 |
ourke | +0.667 |
Vand | +0.655 |
$$ | +0.649 |
「 | +0.647 |
Neg logit contributions | |
ahime | -0.746 |
usterity | -0.741 |
Berks | -0.677 |
groupon | -0.659 |
adobe | -0.646 |
Token | balancing |
Token ID | 22486 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
Deb | +0.825 |
ourke | +0.799 |
Vand | +0.783 |
$$ | +0.776 |
「 | +0.774 |
Neg logit contributions | |
ahime | -0.937 |
usterity | -0.929 |
Berks | -0.851 |
groupon | -0.830 |
adobe | -0.814 |
Token | act |
Token ID | 719 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Deb | +0.200 |
ourke | +0.195 |
Vand | +0.192 |
$$ | +0.191 |
「 | +0.191 |
Neg logit contributions | |
ahime | -0.128 |
usterity | -0.127 |
Berks | -0.112 |
groupon | -0.108 |
adobe | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
Deb | +0.128 |
ourke | +0.124 |
Vand | +0.122 |
$$ | +0.121 |
「 | +0.121 |
Neg logit contributions | |
ahime | -0.134 |
usterity | -0.133 |
Berks | -0.121 |
groupon | -0.118 |
adobe | -0.115 |
Token | Do |
Token ID | 2141 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
Deb | +0.096 |
ourke | +0.095 |
Vand | +0.091 |
$$ | +0.090 |
「 | +0.090 |
Neg logit contributions | |
ahime | -0.125 |
usterity | -0.124 |
Berks | -0.115 |
groupon | -0.113 |
Origin | -0.110 |
Token | you |
Token ID | 345 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
ahime | +0.356 |
usterity | +0.355 |
Berks | +0.328 |
groupon | +0.320 |
Origin | +0.314 |
Neg logit contributions | |
Deb | -0.247 |
ourke | -0.239 |
Vand | -0.233 |
$$ | -0.230 |
「 | -0.230 |
Token | hire |
Token ID | 11078 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Deb | +0.654 |
ourke | +0.636 |
Vand | +0.624 |
$$ | +0.618 |
「 | +0.616 |
Neg logit contributions | |
ahime | -0.658 |
usterity | -0.653 |
Berks | -0.595 |
groupon | -0.579 |
Origin | -0.566 |
Token | One |
Token ID | 1881 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
ahime | +0.103 |
usterity | +0.103 |
Berks | +0.095 |
groupon | +0.092 |
Origin | +0.090 |
Neg logit contributions | |
Deb | -0.086 |
ourke | -0.085 |
$$ | -0.082 |
Vand | -0.082 |
「 | -0.081 |
Token | is |
Token ID | 318 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
Deb | +0.331 |
ourke | +0.322 |
Vand | +0.315 |
$$ | +0.312 |
「 | +0.311 |
Neg logit contributions | |
ahime | -0.353 |
usterity | -0.351 |
Berks | -0.320 |
groupon | -0.312 |
Origin | -0.306 |
Token | its |
Token ID | 663 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Deb | +0.206 |
ourke | +0.200 |
Vand | +0.195 |
$$ | +0.193 |
「 | +0.192 |
Neg logit contributions | |
ahime | -0.279 |
usterity | -0.279 |
Berks | -0.256 |
groupon | -0.250 |
Origin | -0.246 |
Token | op |
Token ID | 1034 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Deb | +0.514 |
ourke | +0.497 |
Vand | +0.485 |
$$ | +0.480 |
「 | +0.476 |
Neg logit contributions | |
ahime | -0.834 |
usterity | -0.833 |
Berks | -0.771 |
groupon | -0.754 |
Origin | -0.743 |
Token | r |
Token ID | 81 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Deb | +0.900 |
ourke | +0.875 |
Vand | +0.859 |
$$ | +0.852 |
「 | +0.851 |
Neg logit contributions | |
ahime | -0.832 |
usterity | -0.826 |
Berks | -0.749 |
groupon | -0.729 |
adobe | -0.711 |
Token | p |
Token ID | 79 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
ahime | +0.999 |
usterity | +0.993 |
Berks | +0.907 |
groupon | +0.887 |
Origin | +0.872 |
Neg logit contributions | |
Deb | -0.819 |
ourke | -0.790 |
Vand | -0.778 |
$$ | -0.768 |
「 | -0.764 |
Token | ressive |
Token ID | 3314 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Deb | +0.011 |
ourke | +0.010 |
Vand | +0.010 |
$$ | +0.010 |
「 | +0.010 |
Neg logit contributions | |
ahime | -0.012 |
usterity | -0.012 |
Berks | -0.011 |
groupon | -0.010 |
adobe | -0.010 |
Token | spect |
Token ID | 5444 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Deb | +0.857 |
ourke | +0.831 |
Vand | +0.813 |
$$ | +0.806 |
「 | +0.802 |
Neg logit contributions | |
ahime | -1.067 |
usterity | -1.063 |
Berks | -0.975 |
groupon | -0.951 |
Origin | -0.935 |
Token | re |
Token ID | 260 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
Deb | +1.127 |
ourke | +1.091 |
Vand | +1.070 |
$$ | +1.060 |
「 | +1.057 |
Neg logit contributions | |
ahime | -1.273 |
usterity | -1.266 |
Berks | -1.159 |
groupon | -1.130 |
Origin | -1.107 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ahime | +0.229 |
usterity | +0.229 |
Berks | +0.208 |
groupon | +0.203 |
Origin | +0.201 |
Neg logit contributions | |
Deb | -0.221 |
ourke | -0.216 |
Vand | -0.211 |
$$ | -0.208 |
「 | -0.208 |
Token | p |
Token ID | 79 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Deb | +0.795 |
ourke | +0.771 |
Vand | +0.755 |
$$ | +0.747 |
「 | +0.747 |
Neg logit contributions | |
ahime | -0.899 |
usterity | -0.894 |
Berks | -0.817 |
groupon | -0.798 |
Origin | -0.784 |
Token | ickson |
Token ID | 46381 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
Deb | +0.501 |
ourke | +0.483 |
Vand | +0.474 |
「 | +0.470 |
$$ | +0.468 |
Neg logit contributions | |
ahime | -0.640 |
usterity | -0.634 |
Berks | -0.586 |
groupon | -0.571 |
Origin | -0.559 |
Token | will |
Token ID | 481 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
Deb | +0.114 |
ourke | +0.111 |
Vand | +0.109 |
$$ | +0.108 |
「 | +0.107 |
Neg logit contributions | |
ahime | -0.118 |
usterity | -0.118 |
Berks | -0.107 |
groupon | -0.105 |
Origin | -0.102 |
Token | return |
Token ID | 1441 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
usterity | +0.408 |
ahime | +0.407 |
Berks | +0.373 |
groupon | +0.366 |
Origin | +0.357 |
Neg logit contributions | |
Deb | -0.352 |
ourke | -0.348 |
Vand | -0.335 |
$$ | -0.331 |
「 | -0.329 |
Token | to |
Token ID | 284 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
ahime | +1.318 |
usterity | +1.305 |
Berks | +1.207 |
groupon | +1.189 |
Origin | +1.165 |
Neg logit contributions | |
Deb | -1.205 |
ourke | -1.202 |
Vand | -1.151 |
$$ | -1.147 |
「 | -1.140 |
Token | full |
Token ID | 1336 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ahime | +1.353 |
usterity | +1.348 |
Berks | +1.230 |
groupon | +1.194 |
Origin | +1.169 |
Neg logit contributions | |
Deb | -1.447 |
ourke | -1.425 |
Vand | -1.383 |
$$ | -1.379 |
「 | -1.376 |
Token | training |
Token ID | 3047 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
ahime | +0.719 |
usterity | +0.716 |
Berks | +0.652 |
groupon | +0.638 |
Origin | +0.624 |
Neg logit contributions | |
Deb | -0.688 |
ourke | -0.674 |
Vand | -0.655 |
$$ | -0.651 |
「 | -0.650 |
Token | this |
Token ID | 428 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
Deb | +1.105 |
ourke | +1.054 |
Vand | +1.051 |
$$ | +1.034 |
「 | +1.032 |
Neg logit contributions | |
ahime | -1.228 |
usterity | -1.219 |
Berks | -1.114 |
groupon | -1.079 |
adobe | -1.068 |
Token | week |
Token ID | 1285 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
ahime | +0.556 |
usterity | +0.553 |
Berks | +0.508 |
groupon | +0.493 |
Origin | +0.483 |
Neg logit contributions | |
Deb | -0.540 |
ourke | -0.531 |
Vand | -0.516 |
$$ | -0.513 |
「 | -0.511 |
Token | after |
Token ID | 706 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Deb | +0.059 |
ourke | +0.058 |
Vand | +0.056 |
$$ | +0.056 |
「 | +0.056 |
Neg logit contributions | |
ahime | -0.057 |
usterity | -0.057 |
Berks | -0.052 |
groupon | -0.051 |
Origin | -0.049 |
Token | an |
Token ID | 281 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Deb | +0.086 |
ourke | +0.085 |
$$ | +0.082 |
Vand | +0.082 |
「 | +0.081 |
Neg logit contributions | |
usterity | -0.110 |
ahime | -0.110 |
Berks | -0.102 |
groupon | -0.099 |
Origin | -0.097 |
Token | abdominal |
Token ID | 32692 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
ahime | +0.239 |
usterity | +0.238 |
Berks | +0.219 |
groupon | +0.213 |
Origin | +0.210 |
Neg logit contributions | |
Deb | -0.201 |
ourke | -0.197 |
$$ | -0.191 |
Vand | -0.191 |
「 | -0.188 |
Token | 10 |
Token ID | 838 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Deb | +0.474 |
ourke | +0.462 |
Vand | +0.451 |
$$ | +0.447 |
「 | +0.446 |
Neg logit contributions | |
ahime | -0.501 |
usterity | -0.498 |
Berks | -0.454 |
groupon | -0.442 |
Origin | -0.432 |
Token | years |
Token ID | 812 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
ahime | +1.008 |
usterity | +1.007 |
Berks | +0.921 |
groupon | +0.903 |
adobe | +0.879 |
Neg logit contributions | |
Deb | -0.768 |
ourke | -0.748 |
Vand | -0.733 |
$$ | -0.723 |
「 | -0.719 |
Token | with |
Token ID | 351 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
usterity | +0.204 |
ahime | +0.204 |
Berks | +0.186 |
groupon | +0.181 |
adobe | +0.176 |
Neg logit contributions | |
Deb | -0.207 |
ourke | -0.203 |
Vand | -0.198 |
$$ | -0.196 |
「 | -0.196 |
Token | the |
Token ID | 262 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
usterity | +0.298 |
ahime | +0.297 |
Berks | +0.273 |
groupon | +0.265 |
Origin | +0.259 |
Neg logit contributions | |
Deb | -0.257 |
ourke | -0.252 |
Vand | -0.246 |
$$ | -0.243 |
「 | -0.242 |
Token | Harper |
Token ID | 12686 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
Deb | +0.308 |
ourke | +0.301 |
Vand | +0.296 |
$$ | +0.294 |
「 | +0.293 |
Neg logit contributions | |
ahime | -0.240 |
usterity | -0.240 |
Berks | -0.215 |
groupon | -0.208 |
Origin | -0.203 |
Token | Conservatives |
Token ID | 17897 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
Deb | +0.338 |
ourke | +0.330 |
Vand | +0.323 |
「 | +0.320 |
$$ | +0.319 |
Neg logit contributions | |
usterity | -0.298 |
ahime | -0.297 |
Berks | -0.268 |
groupon | -0.260 |
Origin | -0.253 |
Token | . |
Token ID | 13 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
Deb | +1.727 |
ourke | +1.664 |
Vand | +1.633 |
$$ | +1.621 |
「 | +1.616 |
Neg logit contributions | |
ahime | -1.977 |
usterity | -1.957 |
Berks | -1.795 |
groupon | -1.749 |
adobe | -1.722 |
Token | There |
Token ID | 1318 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
ahime | +0.072 |
usterity | +0.072 |
Berks | +0.067 |
groupon | +0.065 |
Origin | +0.064 |
Neg logit contributions | |
Deb | -0.054 |
ourke | -0.053 |
Vand | -0.051 |
$$ | -0.051 |
「 | -0.050 |
Token | were |
Token ID | 547 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Deb | +0.323 |
ourke | +0.313 |
Vand | +0.307 |
$$ | +0.304 |
「 | +0.303 |
Neg logit contributions | |
ahime | -0.379 |
usterity | -0.376 |
Berks | -0.345 |
groupon | -0.337 |
Origin | -0.330 |
Token | high |
Token ID | 1029 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
usterity | +0.840 |
ahime | +0.834 |
Berks | +0.774 |
groupon | +0.751 |
Origin | +0.727 |
Neg logit contributions | |
Deb | -0.784 |
ourke | -0.776 |
$$ | -0.750 |
Vand | -0.749 |
「 | -0.738 |
Token | hopes |
Token ID | 7176 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
ahime | +0.639 |
usterity | +0.638 |
Berks | +0.578 |
groupon | +0.563 |
adobe | +0.544 |
Neg logit contributions | |
Deb | -0.724 |
ourke | -0.711 |
Vand | -0.696 |
$$ | -0.693 |
「 | -0.688 |
Token | � |
Token ID | 250 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
ahime | +0.889 |
usterity | +0.888 |
Berks | +0.819 |
groupon | +0.805 |
Origin | +0.785 |
Neg logit contributions | |
Deb | -0.667 |
ourke | -0.649 |
Vand | -0.633 |
$$ | -0.624 |
「 | -0.622 |
Token | It |
Token ID | 1026 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Deb | +0.122 |
ourke | +0.118 |
Vand | +0.115 |
$$ | +0.114 |
「 | +0.114 |
Neg logit contributions | |
ahime | -0.155 |
usterity | -0.155 |
Berks | -0.142 |
groupon | -0.139 |
Origin | -0.136 |
Token | will |
Token ID | 481 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
Deb | +1.268 |
ourke | +1.218 |
「 | +1.194 |
$$ | +1.194 |
Vand | +1.192 |
Neg logit contributions | |
ahime | -1.576 |
usterity | -1.556 |
Berks | -1.434 |
groupon | -1.389 |
Origin | -1.370 |
Token | reduce |
Token ID | 4646 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
ahime | +0.012 |
usterity | +0.012 |
Berks | +0.011 |
groupon | +0.011 |
adobe | +0.011 |
Neg logit contributions | |
Deb | -0.012 |
ourke | -0.012 |
Vand | -0.011 |
$$ | -0.011 |
「 | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
ahime | +1.522 |
usterity | +1.516 |
Berks | +1.405 |
groupon | +1.351 |
adobe | +1.301 |
Neg logit contributions | |
Deb | -1.421 |
ourke | -1.419 |
「 | -1.352 |
Vand | -1.351 |
$$ | -1.346 |
Token | problem |
Token ID | 1917 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
ahime | +0.281 |
usterity | +0.279 |
Berks | +0.257 |
groupon | +0.249 |
Origin | +0.242 |
Neg logit contributions | |
Deb | -0.247 |
ourke | -0.242 |
Vand | -0.235 |
$$ | -0.234 |
「 | -0.233 |
Token | of |
Token ID | 286 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Deb | +0.474 |
ourke | +0.459 |
Vand | +0.452 |
$$ | +0.448 |
「 | +0.447 |
Neg logit contributions | |
ahime | -0.466 |
usterity | -0.462 |
Berks | -0.421 |
groupon | -0.409 |
Origin | -0.401 |
Token | student |
Token ID | 3710 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
usterity | +0.787 |
ahime | +0.785 |
Berks | +0.731 |
groupon | +0.705 |
adobe | +0.686 |
Neg logit contributions | |
Deb | -0.673 |
ourke | -0.661 |
Vand | -0.637 |
$$ | -0.634 |
「 | -0.633 |
Token | debt |
Token ID | 5057 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
ahime | +0.364 |
usterity | +0.363 |
Berks | +0.334 |
groupon | +0.325 |
Origin | +0.317 |
Neg logit contributions | |
Deb | -0.302 |
ourke | -0.295 |
Vand | -0.287 |
$$ | -0.284 |
「 | -0.284 |
Token | , |
Token ID | 11 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
ahime | +1.071 |
usterity | +1.065 |
Berks | +0.966 |
groupon | +0.940 |
Origin | +0.920 |
Neg logit contributions | |
Deb | -1.047 |
ourke | -1.027 |
Vand | -0.998 |
「 | -0.985 |
$$ | -0.983 |
Token | which |
Token ID | 543 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Deb | +0.531 |
ourke | +0.513 |
Vand | +0.503 |
$$ | +0.499 |
「 | +0.497 |
Neg logit contributions | |
ahime | -0.631 |
usterity | -0.627 |
Berks | -0.575 |
groupon | -0.561 |
Origin | -0.551 |
Token | 4 |
Token ID | 19 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
Deb | +0.353 |
ourke | +0.340 |
Vand | +0.333 |
「 | +0.328 |
$$ | +0.325 |
Neg logit contributions | |
ahime | -0.558 |
usterity | -0.553 |
Berks | -0.512 |
groupon | -0.505 |
Origin | -0.497 |
Token | - |
Token ID | 12 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
ahime | +0.389 |
usterity | +0.386 |
Berks | +0.345 |
groupon | +0.333 |
Origin | +0.325 |
Neg logit contributions | |
Deb | -0.544 |
ourke | -0.533 |
Vand | -0.522 |
$$ | -0.520 |
「 | -0.519 |
Token | 1 |
Token ID | 16 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
Deb | +0.454 |
ourke | +0.437 |
Vand | +0.427 |
$$ | +0.422 |
「 | +0.421 |
Neg logit contributions | |
ahime | -0.674 |
usterity | -0.670 |
Berks | -0.620 |
groupon | -0.605 |
adobe | -0.595 |
Token | - |
Token ID | 12 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
Deb | +0.188 |
ourke | +0.182 |
Vand | +0.178 |
$$ | +0.176 |
「 | +0.175 |
Neg logit contributions | |
ahime | -0.239 |
usterity | -0.238 |
Berks | -0.219 |
groupon | -0.214 |
Origin | -0.209 |
Token | 2 |
Token ID | 17 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
Deb | +0.276 |
ourke | +0.264 |
Vand | +0.256 |
$$ | +0.253 |
「 | +0.252 |
Neg logit contributions | |
ahime | -0.547 |
usterity | -0.544 |
Berks | -0.508 |
groupon | -0.498 |
Origin | -0.490 |
Token | to |
Token ID | 284 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
Deb | +0.017 |
ourke | +0.016 |
Vand | +0.016 |
$$ | +0.016 |
「 | +0.016 |
Neg logit contributions | |
ahime | -0.019 |
usterity | -0.019 |
Berks | -0.018 |
groupon | -0.017 |
Origin | -0.017 |
Token | more |
Token ID | 517 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
ahime | +1.744 |
usterity | +1.732 |
Berks | +1.614 |
groupon | +1.548 |
adobe | +1.525 |
Neg logit contributions | |
Deb | -1.607 |
ourke | -1.587 |
$$ | -1.551 |
Vand | -1.519 |
「 | -1.509 |
Token | of |
Token ID | 286 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
ahime | +1.838 |
usterity | +1.827 |
Berks | +1.672 |
groupon | +1.623 |
Origin | +1.585 |
Neg logit contributions | |
Deb | -1.864 |
ourke | -1.857 |
$$ | -1.816 |
Vand | -1.790 |
「 | -1.774 |
Token | a |
Token ID | 257 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Deb | +0.419 |
ourke | +0.404 |
Vand | +0.395 |
$$ | +0.392 |
「 | +0.389 |
Neg logit contributions | |
ahime | -0.599 |
usterity | -0.595 |
Berks | -0.551 |
groupon | -0.538 |
adobe | -0.528 |
Token | 4 |
Token ID | 604 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
Deb | +0.935 |
ourke | +0.899 |
Vand | +0.885 |
「 | +0.872 |
$$ | +0.870 |
Neg logit contributions | |
ahime | -1.125 |
usterity | -1.115 |
Berks | -1.021 |
groupon | -1.000 |
Origin | -0.982 |
Token | - |
Token ID | 12 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
Deb | +0.536 |
ourke | +0.522 |
Vand | +0.514 |
$$ | +0.510 |
「 | +0.508 |
Neg logit contributions | |
ahime | -0.403 |
usterity | -0.401 |
Berks | -0.358 |
groupon | -0.347 |
adobe | -0.338 |
Token | really |
Token ID | 1107 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
usterity | +0.009 |
ahime | +0.009 |
Berks | +0.008 |
groupon | +0.008 |
adobe | +0.008 |
Neg logit contributions | |
Deb | -0.009 |
ourke | -0.009 |
Vand | -0.008 |
$$ | -0.008 |
「 | -0.008 |
Token | likely |
Token ID | 1884 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
Deb | +1.240 |
ourke | +1.191 |
Vand | +1.178 |
「 | +1.168 |
$$ | +1.162 |
Neg logit contributions | |
ahime | -1.326 |
usterity | -1.314 |
Berks | -1.198 |
groupon | -1.164 |
Origin | -1.145 |
Token | that |
Token ID | 326 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Deb | +0.222 |
ourke | +0.216 |
Vand | +0.212 |
$$ | +0.210 |
「 | +0.209 |
Neg logit contributions | |
ahime | -0.233 |
usterity | -0.232 |
Berks | -0.212 |
groupon | -0.206 |
adobe | -0.202 |
Token | Amazon |
Token ID | 6186 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Deb | +0.128 |
ourke | +0.126 |
Vand | +0.123 |
$$ | +0.122 |
「 | +0.121 |
Neg logit contributions | |
ahime | -0.123 |
usterity | -0.123 |
Berks | -0.113 |
groupon | -0.109 |
adobe | -0.107 |
Token | is |
Token ID | 318 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ahime | +0.679 |
usterity | +0.676 |
Berks | +0.616 |
groupon | +0.598 |
Origin | +0.586 |
Neg logit contributions | |
Deb | -0.691 |
ourke | -0.672 |
Vand | -0.658 |
$$ | -0.653 |
「 | -0.650 |
Token | going |
Token ID | 1016 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
usterity | +0.751 |
ahime | +0.748 |
Berks | +0.685 |
groupon | +0.665 |
adobe | +0.652 |
Neg logit contributions | |
Deb | -0.754 |
ourke | -0.738 |
Vand | -0.720 |
$$ | -0.711 |
「 | -0.704 |
Token | to |
Token ID | 284 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
ahime | +1.353 |
usterity | +1.345 |
Berks | +1.242 |
groupon | +1.212 |
adobe | +1.189 |
Neg logit contributions | |
Deb | -1.009 |
ourke | -0.976 |
Vand | -0.953 |
$$ | -0.943 |
「 | -0.937 |
Token | go |
Token ID | 467 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
usterity | +0.430 |
ahime | +0.428 |
Berks | +0.393 |
groupon | +0.382 |
adobe | +0.376 |
Neg logit contributions | |
Deb | -0.399 |
ourke | -0.392 |
Vand | -0.379 |
$$ | -0.376 |
「 | -0.371 |
Token | all |
Token ID | 477 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
ahime | +0.854 |
usterity | +0.852 |
Berks | +0.777 |
groupon | +0.754 |
adobe | +0.741 |
Neg logit contributions | |
Deb | -0.837 |
ourke | -0.817 |
Vand | -0.797 |
$$ | -0.793 |
「 | -0.783 |
Token | 1984 |
Token ID | 12844 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
Deb | +0.242 |
ourke | +0.233 |
Vand | +0.231 |
「 | +0.229 |
$$ | +0.228 |
Neg logit contributions | |
ahime | -0.227 |
usterity | -0.223 |
Berks | -0.202 |
groupon | -0.198 |
Origin | -0.193 |
Token | on |
Token ID | 319 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
usterity | +1.415 |
ahime | +1.414 |
Berks | +1.294 |
groupon | +1.264 |
adobe | +1.237 |
Neg logit contributions | |
Deb | -1.318 |
ourke | -1.286 |
Vand | -1.252 |
$$ | -1.246 |
「 | -1.235 |
Token | was |
Token ID | 373 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
ahime | +0.569 |
usterity | +0.567 |
Berks | +0.519 |
groupon | +0.507 |
Origin | +0.497 |
Neg logit contributions | |
Deb | -0.489 |
ourke | -0.484 |
Vand | -0.465 |
$$ | -0.462 |
「 | -0.457 |
Token | a |
Token ID | 257 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Deb | +0.643 |
ourke | +0.627 |
Vand | +0.611 |
$$ | +0.607 |
「 | +0.603 |
Neg logit contributions | |
ahime | -0.678 |
usterity | -0.677 |
Berks | -0.617 |
groupon | -0.600 |
Origin | -0.589 |
Token | result |
Token ID | 1255 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
Deb | +0.812 |
ourke | +0.790 |
Vand | +0.773 |
$$ | +0.763 |
「 | +0.761 |
Neg logit contributions | |
ahime | -0.852 |
usterity | -0.851 |
Berks | -0.774 |
groupon | -0.754 |
Origin | -0.737 |
Token | of |
Token ID | 286 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
ahime | +0.355 |
usterity | +0.352 |
Berks | +0.320 |
groupon | +0.311 |
adobe | +0.305 |
Neg logit contributions | |
Deb | -0.367 |
ourke | -0.356 |
Vand | -0.350 |
$$ | -0.347 |
「 | -0.346 |
Token | that |
Token ID | 326 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
Deb | +1.384 |
ourke | +1.334 |
Vand | +1.311 |
$$ | +1.296 |
「 | +1.295 |
Neg logit contributions | |
ahime | -1.693 |
usterity | -1.683 |
Berks | -1.546 |
groupon | -1.508 |
adobe | -1.480 |
Token | overwhelming |
Token ID | 9721 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
ahime | +0.186 |
usterity | +0.185 |
Berks | +0.169 |
groupon | +0.165 |
Origin | +0.161 |
Neg logit contributions | |
Deb | -0.173 |
ourke | -0.169 |
Vand | -0.165 |
$$ | -0.163 |
「 | -0.162 |
Token | stress |
Token ID | 5503 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
ahime | +0.191 |
usterity | +0.190 |
Berks | +0.173 |
groupon | +0.169 |
Origin | +0.165 |
Neg logit contributions | |
Deb | -0.184 |
ourke | -0.180 |
Vand | -0.175 |
$$ | -0.174 |
「 | -0.173 |
Token | . |
Token ID | 13 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
ahime | +2.409 |
usterity | +2.367 |
Berks | +2.156 |
groupon | +2.085 |
Origin | +2.077 |
Neg logit contributions | |
ourke | -2.433 |
Deb | -2.426 |
Vand | -2.322 |
$$ | -2.312 |
Sov | -2.280 |
Token | Being |
Token ID | 11204 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
usterity | +0.362 |
ahime | +0.361 |
Berks | +0.336 |
groupon | +0.327 |
Origin | +0.321 |
Neg logit contributions | |
ourke | -0.294 |
Deb | -0.290 |
Vand | -0.275 |
$$ | -0.275 |
「 | -0.271 |
Token | on |
Token ID | 319 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
ahime | +2.261 |
usterity | +2.257 |
Berks | +2.060 |
groupon | +1.998 |
Origin | +1.933 |
Neg logit contributions | |
ourke | -2.406 |
Deb | -2.381 |
$$ | -2.272 |
Vand | -2.250 |
「 | -2.218 |
Token | the |
Token ID | 262 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Deb | +0.294 |
ourke | +0.289 |
$$ | +0.279 |
Vand | +0.278 |
「 | +0.275 |
Neg logit contributions | |
ahime | -0.355 |
usterity | -0.354 |
Berks | -0.325 |
groupon | -0.316 |
Origin | -0.311 |
Token | nn |
Token ID | 20471 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
Deb | +0.208 |
ourke | +0.201 |
Vand | +0.198 |
$$ | +0.196 |
「 | +0.196 |
Neg logit contributions | |
ahime | -0.190 |
usterity | -0.188 |
Berks | -0.170 |
groupon | -0.167 |
Origin | -0.162 |
Token | - |
Token ID | 12 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
Deb | +0.620 |
ourke | +0.603 |
Vand | +0.592 |
$$ | +0.587 |
「 | +0.585 |
Neg logit contributions | |
ahime | -0.551 |
usterity | -0.544 |
Berks | -0.493 |
groupon | -0.477 |
Origin | -0.468 |
Token | drops |
Token ID | 49253 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
Deb | +1.189 |
ourke | +1.156 |
Vand | +1.129 |
$$ | +1.122 |
「 | +1.116 |
Neg logit contributions | |
ahime | -1.244 |
usterity | -1.235 |
Berks | -1.125 |
groupon | -1.089 |
Origin | -1.070 |
Token | - |
Token ID | 12 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
Deb | +2.041 |
ourke | +1.969 |
Vand | +1.937 |
$$ | +1.924 |
「 | +1.918 |
Neg logit contributions | |
ahime | -1.635 |
usterity | -1.612 |
Berks | -1.449 |
groupon | -1.396 |
Origin | -1.371 |
Token | re |
Token ID | 260 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Deb | +0.270 |
ourke | +0.263 |
Vand | +0.259 |
$$ | +0.256 |
「 | +0.256 |
Neg logit contributions | |
ahime | -0.241 |
usterity | -0.239 |
Berks | -0.216 |
groupon | -0.211 |
adobe | -0.206 |
Token | za |
Token ID | 4496 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ahime | +0.942 |
usterity | +0.936 |
Berks | +0.871 |
groupon | +0.859 |
adobe | +0.845 |
Neg logit contributions | |
Deb | -0.447 |
ourke | -0.426 |
Vand | -0.417 |
「 | -0.408 |
$$ | -0.405 |
Token | - |
Token ID | 12 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ahime | +0.711 |
usterity | +0.706 |
Berks | +0.630 |
groupon | +0.610 |
adobe | +0.593 |
Neg logit contributions | |
Deb | -0.987 |
ourke | -0.961 |
Vand | -0.946 |
$$ | -0.939 |
「 | -0.937 |
Token | as |
Token ID | 292 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Deb | +0.872 |
ourke | +0.857 |
Vand | +0.828 |
$$ | +0.828 |
「 | +0.819 |
Neg logit contributions | |
usterity | -1.098 |
ahime | -1.097 |
Berks | -1.012 |
groupon | -0.974 |
Origin | -0.964 |
Token | lan |
Token ID | 9620 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
Deb | +0.939 |
ourke | +0.935 |
$$ | +0.908 |
Vand | +0.905 |
「 | +0.897 |
Neg logit contributions | |
usterity | -0.694 |
ahime | -0.693 |
Berks | -0.635 |
groupon | -0.584 |
Origin | -0.581 |
Token | - |
Token ID | 12 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
ahime | +0.202 |
usterity | +0.201 |
Berks | +0.180 |
groupon | +0.174 |
Origin | +0.170 |
Neg logit contributions | |
Deb | -0.262 |
ourke | -0.255 |
Vand | -0.251 |
$$ | -0.249 |
「 | -0.249 |
Token | after |
Token ID | 8499 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
ahime | +0.348 |
usterity | +0.345 |
Berks | +0.313 |
groupon | +0.306 |
adobe | +0.298 |
Neg logit contributions | |
Deb | -0.407 |
ourke | -0.394 |
Vand | -0.389 |
「 | -0.385 |
$$ | -0.384 |
Token | 5 |
Token ID | 642 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ahime | +1.865 |
usterity | +1.856 |
Berks | +1.716 |
groupon | +1.685 |
adobe | +1.644 |
Neg logit contributions | |
Deb | -1.853 |
ourke | -1.814 |
Vand | -1.756 |
「 | -1.711 |
$$ | -1.706 |
Token | )) |
Token ID | 4008 |
Feature activation | -6.03e+00 |
Pos logit contributions | |
Deb | +0.884 |
ourke | +0.855 |
Vand | +0.839 |
$$ | +0.834 |
「 | +0.828 |
Neg logit contributions | |
ahime | -1.087 |
usterity | -1.079 |
Berks | -0.991 |
groupon | -0.962 |
adobe | -0.945 |
Token | sq |
Token ID | 19862 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
usterity | +3.836 |
ahime | +3.800 |
Berks | +3.453 |
groupon | +3.440 |
Origin | +3.438 |
Neg logit contributions | |
ourke | -3.916 |
Deb | -3.891 |
Vand | -3.686 |
Sov | -3.628 |
「 | -3.617 |
Token | K |
Token ID | 42 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
Deb | +0.884 |
ourke | +0.855 |
Vand | +0.837 |
$$ | +0.830 |
「 | +0.826 |
Neg logit contributions | |
ahime | -1.100 |
usterity | -1.093 |
Berks | -1.006 |
groupon | -0.980 |
adobe | -0.962 |
Token | ernel |
Token ID | 7948 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
ahime | +0.205 |
usterity | +0.203 |
groupon | +0.181 |
Berks | +0.180 |
Origin | +0.179 |
Neg logit contributions | |
Deb | -0.229 |
ourke | -0.219 |
Vand | -0.218 |
「 | -0.215 |
$$ | -0.212 |
Token | = |
Token ID | 796 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
Deb | +0.253 |
ourke | +0.245 |
Vand | +0.239 |
「 | +0.236 |
$$ | +0.236 |
Neg logit contributions | |
ahime | -0.336 |
usterity | -0.334 |
Berks | -0.308 |
groupon | -0.301 |
Origin | -0.297 |
Token | c |
Token ID | 269 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ahime | +2.317 |
usterity | +2.301 |
Berks | +2.108 |
groupon | +2.089 |
Origin | +2.055 |
Neg logit contributions | |
ourke | -2.382 |
Deb | -2.375 |
Vand | -2.279 |
$$ | -2.259 |
「 | -2.227 |
Token | v |
Token ID | 85 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Deb | +0.780 |
ourke | +0.757 |
Vand | +0.742 |
$$ | +0.736 |
「 | +0.733 |
Neg logit contributions | |
ahime | -0.819 |
usterity | -0.813 |
Berks | -0.742 |
groupon | -0.722 |
Origin | -0.707 |
Token | 2 |
Token ID | 17 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
ahime | +0.954 |
usterity | +0.953 |
groupon | +0.900 |
Origin | +0.874 |
Berks | +0.867 |
Neg logit contributions | |
Deb | -0.722 |
ourke | -0.700 |
Vand | -0.686 |
「 | -0.672 |
Seah | -0.663 |
Token | . |
Token ID | 13 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
Deb | +0.239 |
ourke | +0.233 |
Vand | +0.228 |
「 | +0.225 |
$$ | +0.223 |
Neg logit contributions | |
ahime | -0.247 |
usterity | -0.246 |
Berks | -0.224 |
groupon | -0.222 |
Origin | -0.217 |
Token | get |
Token ID | 1136 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ahime | +0.576 |
usterity | +0.570 |
Berks | +0.515 |
groupon | +0.503 |
Origin | +0.490 |
Neg logit contributions | |
Deb | -0.700 |
ourke | -0.682 |
Vand | -0.670 |
「 | -0.664 |
$$ | -0.661 |
Token | . |
Token ID | 13 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
Deb | +0.004 |
ourke | +0.004 |
$$ | +0.004 |
Vand | +0.004 |
「 | +0.004 |
Neg logit contributions | |
ahime | -0.004 |
usterity | -0.004 |
Berks | -0.004 |
groupon | -0.004 |
Origin | -0.004 |
Token | Los |
Token ID | 5401 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
ahime | +0.107 |
usterity | +0.107 |
Berks | +0.098 |
groupon | +0.094 |
Origin | +0.091 |
Neg logit contributions | |
Deb | -0.142 |
ourke | -0.141 |
$$ | -0.136 |
Vand | -0.136 |
「 | -0.136 |
Token | Angeles |
Token ID | 5652 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
Deb | +0.583 |
ourke | +0.569 |
Vand | +0.561 |
$$ | +0.554 |
「 | +0.553 |
Neg logit contributions | |
ahime | -0.335 |
usterity | -0.332 |
Berks | -0.288 |
groupon | -0.280 |
Origin | -0.270 |
Token | , |
Token ID | 11 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
Deb | +0.464 |
ourke | +0.448 |
Vand | +0.443 |
「 | +0.434 |
$$ | +0.433 |
Neg logit contributions | |
ahime | -0.473 |
usterity | -0.472 |
Berks | -0.425 |
groupon | -0.417 |
adobe | -0.407 |
Token | CA |
Token ID | 7257 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ahime | +0.632 |
usterity | +0.626 |
Berks | +0.574 |
groupon | +0.556 |
Origin | +0.546 |
Neg logit contributions | |
Deb | -0.657 |
ourke | -0.640 |
Vand | -0.626 |
$$ | -0.626 |
「 | -0.621 |
Token | : |
Token ID | 1058 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
Deb | +0.823 |
ourke | +0.794 |
Vand | +0.791 |
「 | +0.775 |
$$ | +0.764 |
Neg logit contributions | |
ahime | -0.772 |
usterity | -0.767 |
Berks | -0.685 |
groupon | -0.672 |
adobe | -0.652 |
Token | Western |
Token ID | 4885 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
ahime | +2.841 |
usterity | +2.840 |
Berks | +2.777 |
groupon | +2.594 |
Origin | +2.584 |
Neg logit contributions | |
ourke | -2.541 |
Deb | -2.443 |
$$ | -2.412 |
「 | -2.363 |
Sov | -2.332 |
Token | Psychological |
Token ID | 30583 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Deb | +0.343 |
ourke | +0.330 |
Vand | +0.326 |
「 | +0.321 |
$$ | +0.320 |
Neg logit contributions | |
ahime | -0.390 |
usterity | -0.388 |
Berks | -0.353 |
groupon | -0.346 |
adobe | -0.339 |
Token | Services |
Token ID | 6168 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
Deb | +0.100 |
ourke | +0.098 |
$$ | +0.095 |
Vand | +0.095 |
「 | +0.094 |
Neg logit contributions | |
ahime | -0.126 |
usterity | -0.125 |
Berks | -0.116 |
groupon | -0.112 |
Origin | -0.111 |
Token | . |
Token ID | 764 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
ahime | +0.263 |
usterity | +0.261 |
Berks | +0.243 |
groupon | +0.235 |
adobe | +0.231 |
Neg logit contributions | |
Deb | -0.205 |
ourke | -0.200 |
$$ | -0.194 |
Vand | -0.194 |
「 | -0.192 |
Token |
|
Token ID | 198 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
usterity | +2.283 |
ahime | +2.253 |
Berks | +2.190 |
groupon | +2.156 |
Origin | +2.118 |
Neg logit contributions | |
ourke | -2.312 |
Deb | -2.249 |
airst | -2.183 |
mble | -2.171 |
「 | -2.167 |
Token | , |
Token ID | 11 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
ahime | +1.088 |
usterity | +1.083 |
Berks | +0.987 |
groupon | +0.960 |
Origin | +0.938 |
Neg logit contributions | |
Deb | -1.096 |
ourke | -1.065 |
Vand | -1.045 |
$$ | -1.034 |
「 | -1.031 |
Token | your |
Token ID | 534 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
ahime | +0.548 |
usterity | +0.545 |
Berks | +0.500 |
groupon | +0.487 |
Origin | +0.475 |
Neg logit contributions | |
Deb | -0.506 |
ourke | -0.492 |
Vand | -0.482 |
$$ | -0.476 |
「 | -0.474 |
Token | body |
Token ID | 1767 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
ahime | +1.188 |
usterity | +1.183 |
Berks | +1.073 |
groupon | +1.033 |
Origin | +1.003 |
Neg logit contributions | |
Deb | -1.534 |
ourke | -1.503 |
Vand | -1.473 |
$$ | -1.459 |
「 | -1.442 |
Token | goes |
Token ID | 2925 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
usterity | +0.944 |
ahime | +0.943 |
Berks | +0.863 |
groupon | +0.838 |
Origin | +0.822 |
Neg logit contributions | |
Deb | -0.898 |
ourke | -0.871 |
Vand | -0.853 |
$$ | -0.841 |
「 | -0.834 |
Token | into |
Token ID | 656 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
ahime | +0.289 |
usterity | +0.287 |
Berks | +0.264 |
groupon | +0.257 |
adobe | +0.251 |
Neg logit contributions | |
Deb | -0.259 |
ourke | -0.252 |
Vand | -0.246 |
$$ | -0.243 |
「 | -0.242 |
Token | what |
Token ID | 644 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
ahime | +1.827 |
usterity | +1.823 |
Berks | +1.678 |
groupon | +1.624 |
adobe | +1.591 |
Neg logit contributions | |
Deb | -1.534 |
ourke | -1.497 |
Vand | -1.457 |
$$ | -1.444 |
「 | -1.427 |
Token | is |
Token ID | 318 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
usterity | +2.853 |
ahime | +2.786 |
Berks | +2.690 |
groupon | +2.575 |
fore | +2.546 |
Neg logit contributions | |
ourke | -2.861 |
Deb | -2.818 |
Vand | -2.723 |
$$ | -2.722 |
Sov | -2.673 |
Token | known |
Token ID | 1900 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
usterity | +1.266 |
ahime | +1.266 |
Berks | +1.153 |
groupon | +1.117 |
Origin | +1.089 |
Neg logit contributions | |
Deb | -1.321 |
ourke | -1.291 |
Vand | -1.264 |
$$ | -1.253 |
「 | -1.243 |
Token | as |
Token ID | 355 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ahime | +1.870 |
usterity | +1.867 |
Berks | +1.685 |
groupon | +1.627 |
Origin | +1.581 |
Neg logit contributions | |
Deb | -2.447 |
ourke | -2.391 |
Vand | -2.354 |
$$ | -2.329 |
「 | -2.314 |
Token | the |
Token ID | 262 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
ahime | +0.847 |
usterity | +0.847 |
Berks | +0.779 |
groupon | +0.755 |
Origin | +0.739 |
Neg logit contributions | |
Deb | -0.725 |
ourke | -0.706 |
Vand | -0.690 |
$$ | -0.684 |
「 | -0.675 |
Token | post |
Token ID | 1281 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
ahime | +0.151 |
usterity | +0.150 |
Berks | +0.137 |
groupon | +0.134 |
Origin | +0.131 |
Neg logit contributions | |
Deb | -0.133 |
ourke | -0.129 |
Vand | -0.127 |
$$ | -0.125 |
「 | -0.125 |
Token | Current |
Token ID | 9236 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Deb | +0.280 |
ourke | +0.271 |
Vand | +0.266 |
「 | +0.263 |
$$ | +0.263 |
Neg logit contributions | |
ahime | -0.266 |
usterity | -0.263 |
Berks | -0.239 |
groupon | -0.233 |
Origin | -0.228 |
Token | Population |
Token ID | 20133 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Deb | +0.610 |
ourke | +0.574 |
Vand | +0.564 |
$$ | +0.556 |
「 | +0.555 |
Neg logit contributions | |
ahime | -1.080 |
usterity | -1.075 |
Berks | -0.996 |
groupon | -0.975 |
adobe | -0.961 |
Token | Survey |
Token ID | 13084 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
ahime | +1.033 |
usterity | +1.024 |
Berks | +0.952 |
groupon | +0.931 |
Origin | +0.918 |
Neg logit contributions | |
ourke | -0.830 |
Deb | -0.828 |
$$ | -0.803 |
Vand | -0.795 |
「 | -0.791 |
Token | data |
Token ID | 1366 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Deb | +0.305 |
ourke | +0.297 |
Vand | +0.291 |
$$ | +0.289 |
「 | +0.288 |
Neg logit contributions | |
ahime | -0.299 |
usterity | -0.297 |
Berks | -0.270 |
groupon | -0.263 |
Origin | -0.257 |
Token | ( |
Token ID | 357 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
ahime | +0.917 |
usterity | +0.904 |
Berks | +0.822 |
groupon | +0.801 |
Origin | +0.784 |
Neg logit contributions | |
Deb | -0.986 |
ourke | -0.965 |
Vand | -0.945 |
$$ | -0.940 |
「 | -0.931 |
Token | IP |
Token ID | 4061 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
Deb | +0.415 |
ourke | +0.402 |
Vand | +0.394 |
$$ | +0.390 |
「 | +0.389 |
Neg logit contributions | |
ahime | -0.459 |
usterity | -0.456 |
Berks | -0.417 |
groupon | -0.406 |
Origin | -0.398 |
Token | U |
Token ID | 52 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
ahime | +2.882 |
usterity | +2.817 |
Berks | +2.561 |
Origin | +2.529 |
groupon | +2.522 |
Neg logit contributions | |
Deb | -2.728 |
ourke | -2.695 |
Vand | -2.578 |
「 | -2.561 |
$$ | -2.554 |
Token | MS |
Token ID | 5653 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
ahime | +1.446 |
usterity | +1.428 |
Berks | +1.300 |
groupon | +1.268 |
Origin | +1.246 |
Neg logit contributions | |
Deb | -1.475 |
ourke | -1.450 |
Vand | -1.418 |
$$ | -1.408 |
「 | -1.401 |
Token | - |
Token ID | 12 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Deb | +0.205 |
ourke | +0.200 |
Vand | +0.195 |
$$ | +0.194 |
「 | +0.193 |
Neg logit contributions | |
ahime | -0.218 |
usterity | -0.216 |
Berks | -0.198 |
groupon | -0.193 |
Origin | -0.189 |
Token | C |
Token ID | 34 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Deb | +0.710 |
ourke | +0.687 |
Vand | +0.673 |
$$ | +0.667 |
「 | +0.665 |
Neg logit contributions | |
ahime | -0.834 |
usterity | -0.828 |
Berks | -0.760 |
groupon | -0.741 |
Origin | -0.727 |
Token | PS |
Token ID | 3705 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Deb | +0.698 |
ourke | +0.674 |
Vand | +0.663 |
$$ | +0.657 |
「 | +0.657 |
Neg logit contributions | |
ahime | -0.705 |
usterity | -0.704 |
Berks | -0.640 |
groupon | -0.622 |
adobe | -0.610 |
Token | and |
Token ID | 290 |
Feature activation | +3.73e-02 |
Pos logit contributions | |
ahime | +0.897 |
usterity | +0.897 |
Berks | +0.831 |
groupon | +0.811 |
Origin | +0.792 |
Neg logit contributions | |
Deb | -0.813 |
ourke | -0.798 |
$$ | -0.783 |
Vand | -0.774 |
「 | -0.757 |
Token | upsetting |
Token ID | 38423 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
Deb | +0.023 |
ourke | +0.022 |
Vand | +0.022 |
$$ | +0.021 |
「 | +0.021 |
Neg logit contributions | |
ahime | -0.027 |
usterity | -0.027 |
Berks | -0.024 |
groupon | -0.024 |
Origin | -0.023 |
Token | places |
Token ID | 4113 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
ahime | +1.548 |
usterity | +1.537 |
Berks | +1.435 |
groupon | +1.392 |
Origin | +1.373 |
Neg logit contributions | |
Deb | -1.426 |
ourke | -1.398 |
$$ | -1.372 |
Vand | -1.359 |
Sov | -1.320 |
Token | . |
Token ID | 13 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
ahime | +0.182 |
usterity | +0.181 |
Berks | +0.166 |
groupon | +0.162 |
Origin | +0.159 |
Neg logit contributions | |
Deb | -0.173 |
ourke | -0.168 |
Vand | -0.165 |
$$ | -0.163 |
「 | -0.162 |
Token | Ne |
Token ID | 3169 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
Deb | +0.218 |
ourke | +0.213 |
Vand | +0.206 |
$$ | +0.205 |
「 | +0.204 |
Neg logit contributions | |
ahime | -0.273 |
usterity | -0.270 |
Berks | -0.250 |
groupon | -0.244 |
Origin | -0.240 |
Token | onom |
Token ID | 6326 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
ahime | +2.966 |
usterity | +2.960 |
Berks | +2.726 |
groupon | +2.670 |
Origin | +2.647 |
Neg logit contributions | |
Deb | -2.016 |
Vand | -1.920 |
ourke | -1.916 |
$$ | -1.840 |
「 | -1.828 |
Token | icon |
Token ID | 4749 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
ahime | +0.913 |
usterity | +0.855 |
groupon | +0.600 |
Berks | +0.580 |
adobe | +0.517 |
Neg logit contributions | |
Deb | -4.638 |
Vand | -4.526 |
ourke | -4.468 |
$$ | -4.410 |
「 | -4.409 |
Token | , |
Token ID | 11 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
ahime | +2.397 |
usterity | +2.370 |
Berks | +2.181 |
groupon | +2.129 |
Origin | +2.098 |
Neg logit contributions | |
Deb | -2.376 |
ourke | -2.333 |
Vand | -2.268 |
$$ | -2.249 |
「 | -2.226 |
Token | for |
Token ID | 329 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
ahime | +1.407 |
usterity | +1.391 |
Berks | +1.284 |
groupon | +1.247 |
Origin | +1.226 |
Neg logit contributions | |
Deb | -1.373 |
ourke | -1.353 |
Vand | -1.315 |
$$ | -1.312 |
「 | -1.297 |
Token | example |
Token ID | 1672 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
Deb | +0.924 |
ourke | +0.882 |
Vand | +0.866 |
「 | +0.851 |
$$ | +0.848 |
Neg logit contributions | |
ahime | -1.515 |
usterity | -1.513 |
Berks | -1.398 |
groupon | -1.369 |
adobe | -1.351 |
Token | , |
Token ID | 11 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Deb | +2.054 |
ourke | +1.980 |
Vand | +1.961 |
「 | +1.950 |
$$ | +1.926 |
Neg logit contributions | |
usterity | -2.351 |
ahime | -2.339 |
Berks | -2.118 |
groupon | -2.068 |
adobe | -2.051 |
Token |
|
Token ID | 198 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
usterity | +2.034 |
ahime | +2.020 |
Berks | +1.906 |
groupon | +1.840 |
trust | +1.815 |
Neg logit contributions | |
ourke | -1.683 |
Deb | -1.662 |
「 | -1.591 |
Vand | -1.590 |
Sov | -1.568 |
Token |
|
Token ID | 198 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Deb | +0.416 |
ourke | +0.404 |
Vand | +0.394 |
$$ | +0.389 |
「 | +0.389 |
Neg logit contributions | |
ahime | -0.542 |
usterity | -0.540 |
Berks | -0.497 |
groupon | -0.487 |
Origin | -0.478 |
Token | pub |
Token ID | 12984 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
Deb | +0.087 |
ourke | +0.084 |
Vand | +0.082 |
「 | +0.081 |
$$ | +0.080 |
Neg logit contributions | |
ahime | -0.099 |
usterity | -0.099 |
Berks | -0.090 |
groupon | -0.089 |
Origin | -0.088 |
Token | struct |
Token ID | 2878 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
ahime | +2.845 |
usterity | +2.842 |
Berks | +2.634 |
groupon | +2.569 |
Origin | +2.548 |
Neg logit contributions | |
Deb | -2.037 |
ourke | -2.005 |
Vand | -1.924 |
「 | -1.913 |
$$ | -1.913 |
Token | Shared |
Token ID | 39403 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
ahime | +1.642 |
usterity | +1.621 |
Berks | +1.514 |
groupon | +1.448 |
Origin | +1.428 |
Neg logit contributions | |
ourke | -1.699 |
Deb | -1.673 |
$$ | -1.618 |
「 | -1.615 |
Sov | -1.595 |
Token | < |
Token ID | 1279 |
Feature activation | -6.16e+00 |
Pos logit contributions | |
ahime | +0.389 |
usterity | +0.386 |
Berks | +0.344 |
groupon | +0.332 |
Origin | +0.324 |
Neg logit contributions | |
Deb | -0.573 |
ourke | -0.559 |
Vand | -0.550 |
$$ | -0.546 |
「 | -0.545 |
Token | ' |
Token ID | 705 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
usterity | +4.006 |
ahime | +3.989 |
Berks | +3.768 |
Origin | +3.667 |
trust | +3.572 |
Neg logit contributions | |
ourke | -3.837 |
Deb | -3.772 |
「 | -3.715 |
Sov | -3.681 |
Vand | -3.651 |
Token | a |
Token ID | 64 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
ahime | +0.544 |
usterity | +0.539 |
Berks | +0.497 |
groupon | +0.494 |
Origin | +0.483 |
Neg logit contributions | |
Deb | -0.417 |
ourke | -0.406 |
Vand | -0.397 |
「 | -0.393 |
$$ | -0.387 |
Token | , |
Token ID | 837 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
ahime | +0.360 |
usterity | +0.356 |
Berks | +0.325 |
groupon | +0.317 |
adobe | +0.310 |
Neg logit contributions | |
Deb | -0.344 |
ourke | -0.333 |
Vand | -0.327 |
$$ | -0.324 |
「 | -0.322 |
Token | T |
Token ID | 309 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
ahime | +3.503 |
usterity | +3.492 |
Berks | +3.252 |
groupon | +3.113 |
Origin | +3.112 |
Neg logit contributions | |
Deb | -3.554 |
ourke | -3.547 |
「 | -3.406 |
$$ | -3.400 |
Vand | -3.393 |
Token | : |
Token ID | 1058 |
Feature activation | -6.62e+00 |
Pos logit contributions | |
ahime | +0.323 |
usterity | +0.321 |
Berks | +0.295 |
groupon | +0.288 |
adobe | +0.282 |
Neg logit contributions | |
Deb | -0.256 |
ourke | -0.248 |
Vand | -0.243 |
$$ | -0.240 |
「 | -0.239 |