Token | her |
Token ID | 607 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
Just | +0.003 |
ager | +0.003 |
age | +0.003 |
P | +0.003 |
sy | +0.003 |
Neg logit contributions | |
theirs | -0.003 |
rings | -0.003 |
wow | -0.002 |
what | -0.002 |
are | -0.002 |
Token | mom |
Token ID | 1995 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
theirs | +0.082 |
rings | +0.069 |
what | +0.064 |
are | +0.060 |
wow | +0.060 |
Neg logit contributions | |
Just | -0.087 |
ager | -0.081 |
age | -0.081 |
P | -0.078 |
bes | -0.076 |
Token | my |
Token ID | 1820 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
theirs | +0.077 |
rings | +0.065 |
what | +0.061 |
are | +0.058 |
wow | +0.057 |
Neg logit contributions | |
Just | -0.076 |
ager | -0.071 |
age | -0.071 |
P | -0.068 |
bes | -0.067 |
Token | watched |
Token ID | 7342 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
theirs | +0.070 |
rings | +0.060 |
what | +0.056 |
are | +0.053 |
wow | +0.052 |
Neg logit contributions | |
Just | -0.068 |
ager | -0.062 |
age | -0.062 |
P | -0.061 |
bes | -0.059 |
Token | in |
Token ID | 287 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
Just | +0.043 |
age | +0.040 |
ager | +0.040 |
bes | +0.039 |
P | +0.039 |
Neg logit contributions | |
theirs | -0.029 |
rings | -0.024 |
what | -0.020 |
wow | -0.020 |
are | -0.019 |
Token | amaz |
Token ID | 40642 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
theirs | +0.003 |
rings | +0.003 |
wow | +0.002 |
nam | +0.002 |
what | +0.002 |
Neg logit contributions | |
Just | -0.005 |
ager | -0.004 |
bes | -0.004 |
age | -0.004 |
rd | -0.004 |
Token | ement |
Token ID | 972 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
theirs | +0.424 |
rings | +0.365 |
what | +0.325 |
nam | +0.323 |
are | +0.318 |
Neg logit contributions | |
Just | -0.375 |
ager | -0.346 |
age | -0.337 |
P | -0.331 |
ivering | -0.323 |
Token | as |
Token ID | 355 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
theirs | +0.069 |
rings | +0.058 |
what | +0.053 |
wow | +0.051 |
are | +0.051 |
Neg logit contributions | |
Just | -0.067 |
age | -0.062 |
ager | -0.061 |
P | -0.059 |
bes | -0.059 |
Token | the |
Token ID | 262 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
theirs | +0.153 |
rings | +0.128 |
ours | +0.098 |
wow | +0.097 |
are | +0.095 |
Neg logit contributions | |
Just | -0.262 |
ager | -0.246 |
age | -0.241 |
Lu | -0.240 |
P | -0.240 |
Token | machine |
Token ID | 4572 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
theirs | +0.032 |
rings | +0.027 |
what | +0.026 |
wow | +0.024 |
are | +0.024 |
Neg logit contributions | |
Just | -0.033 |
age | -0.030 |
ager | -0.030 |
P | -0.029 |
bes | -0.029 |
Token | flew |
Token ID | 13112 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
theirs | +0.068 |
rings | +0.057 |
what | +0.053 |
are | +0.050 |
wow | +0.050 |
Neg logit contributions | |
Just | -0.068 |
ager | -0.063 |
age | -0.063 |
P | -0.061 |
bes | -0.060 |
Token | soon |
Token ID | 2582 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Just | +0.027 |
age | +0.026 |
ager | +0.025 |
ivering | +0.024 |
sy | +0.024 |
Neg logit contributions | |
theirs | -0.027 |
rings | -0.023 |
what | -0.020 |
wow | -0.020 |
are | -0.020 |
Token | nothing |
Token ID | 2147 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
Just | +0.137 |
age | +0.130 |
ager | +0.124 |
ivering | +0.121 |
bes | +0.119 |
Neg logit contributions | |
theirs | -0.149 |
rings | -0.128 |
what | -0.114 |
nam | -0.113 |
wow | -0.112 |
Token | but |
Token ID | 475 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
Just | +0.079 |
ager | +0.074 |
age | +0.073 |
P | +0.070 |
bes | +0.069 |
Neg logit contributions | |
theirs | -0.067 |
rings | -0.057 |
what | -0.051 |
wow | -0.048 |
are | -0.048 |
Token | a |
Token ID | 257 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
Just | +0.105 |
ager | +0.098 |
age | +0.095 |
sy | +0.091 |
bes | +0.089 |
Neg logit contributions | |
theirs | -0.071 |
rings | -0.064 |
nam | -0.053 |
ours | -0.048 |
angles | -0.046 |
Token | small |
Token ID | 1402 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
theirs | +0.001 |
rings | +0.001 |
what | +0.001 |
wow | +0.001 |
are | +0.001 |
Neg logit contributions | |
Just | -0.001 |
age | -0.001 |
ager | -0.001 |
bes | -0.001 |
P | -0.001 |
Token | spe |
Token ID | 693 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
Just | +0.017 |
age | +0.015 |
ager | +0.015 |
P | +0.015 |
bes | +0.014 |
Neg logit contributions | |
theirs | -0.020 |
rings | -0.017 |
what | -0.016 |
wow | -0.015 |
are | -0.015 |
Token | ck |
Token ID | 694 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
theirs | +0.305 |
rings | +0.235 |
what | +0.210 |
wow | +0.194 |
are | +0.190 |
Neg logit contributions | |
Just | -0.475 |
age | -0.443 |
ager | -0.443 |
P | -0.437 |
amas | -0.437 |
Token | in |
Token ID | 287 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
theirs | +0.073 |
rings | +0.062 |
what | +0.058 |
are | +0.056 |
wow | +0.055 |
Neg logit contributions | |
Just | -0.068 |
ager | -0.062 |
age | -0.062 |
bes | -0.061 |
P | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
Just | +0.052 |
P | +0.050 |
age | +0.049 |
ager | +0.048 |
Now | +0.048 |
Neg logit contributions | |
theirs | -0.028 |
rings | -0.028 |
ours | -0.021 |
nam | -0.020 |
wow | -0.019 |
Token | sky |
Token ID | 6766 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
Just | +0.016 |
ager | +0.015 |
age | +0.014 |
bes | +0.014 |
P | +0.014 |
Neg logit contributions | |
theirs | -0.017 |
rings | -0.015 |
what | -0.014 |
are | -0.014 |
wow | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
theirs | +0.041 |
rings | +0.035 |
what | +0.032 |
nam | +0.031 |
wow | +0.031 |
Neg logit contributions | |
Just | -0.036 |
age | -0.033 |
ager | -0.033 |
P | -0.031 |
bes | -0.031 |
Token | she |
Token ID | 673 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
theirs | +0.014 |
rings | +0.011 |
what | +0.009 |
wow | +0.009 |
nam | +0.009 |
Neg logit contributions | |
Just | -0.020 |
ager | -0.019 |
age | -0.019 |
bes | -0.018 |
P | -0.018 |
Token | had |
Token ID | 550 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
theirs | +0.003 |
what | +0.003 |
rings | +0.003 |
are | +0.003 |
wow | +0.003 |
Neg logit contributions | |
Just | -0.005 |
age | -0.005 |
amas | -0.005 |
ivering | -0.005 |
bes | -0.005 |
Token | with |
Token ID | 351 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
theirs | +0.035 |
what | +0.029 |
rings | +0.028 |
are | +0.026 |
their | +0.025 |
Neg logit contributions | |
Just | -0.039 |
age | -0.038 |
oster | -0.038 |
ivering | -0.038 |
amas | -0.037 |
Token | her |
Token ID | 607 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
theirs | +0.002 |
rings | +0.002 |
wow | +0.002 |
ours | +0.002 |
are | +0.001 |
Neg logit contributions | |
Just | -0.004 |
bes | -0.004 |
age | -0.004 |
ager | -0.004 |
P | -0.004 |
Token | or |
Token ID | 393 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
theirs | +0.042 |
rings | +0.035 |
what | +0.032 |
wow | +0.030 |
are | +0.030 |
Neg logit contributions | |
Just | -0.045 |
age | -0.042 |
ager | -0.042 |
P | -0.040 |
bes | -0.040 |
Token | nam |
Token ID | 7402 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
theirs | +0.026 |
rings | +0.021 |
wow | +0.018 |
what | +0.018 |
are | +0.017 |
Neg logit contributions | |
Just | -0.039 |
ager | -0.037 |
age | -0.037 |
P | -0.036 |
bes | -0.036 |
Token | ents |
Token ID | 658 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
theirs | +0.212 |
rings | +0.148 |
what | +0.127 |
wow | +0.113 |
are | +0.109 |
Neg logit contributions | |
Just | -0.571 |
age | -0.543 |
ager | -0.540 |
P | -0.528 |
bes | -0.522 |
Token | . |
Token ID | 13 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
theirs | +0.277 |
rings | +0.237 |
wow | +0.218 |
nam | +0.215 |
what | +0.215 |
Neg logit contributions | |
Just | -0.236 |
age | -0.234 |
ager | -0.219 |
sy | -0.210 |
bes | -0.209 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
theirs | +0.036 |
rings | +0.031 |
what | +0.028 |
wow | +0.027 |
are | +0.027 |
Neg logit contributions | |
Just | -0.034 |
age | -0.031 |
ager | -0.031 |
P | -0.030 |
bes | -0.029 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
theirs | +0.100 |
what | +0.082 |
rings | +0.082 |
are | +0.081 |
their | +0.072 |
Neg logit contributions | |
Just | -0.125 |
ager | -0.118 |
age | -0.116 |
ivering | -0.114 |
bes | -0.111 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
theirs | +0.102 |
rings | +0.090 |
wow | +0.084 |
nam | +0.080 |
flashes | +0.075 |
Neg logit contributions | |
Just | -0.091 |
year | -0.088 |
P | -0.085 |
eh | -0.083 |
Lu | -0.082 |
Token | the |
Token ID | 262 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
theirs | +0.019 |
rings | +0.018 |
wow | +0.014 |
nam | +0.014 |
ours | +0.013 |
Neg logit contributions | |
Just | -0.036 |
age | -0.035 |
ager | -0.034 |
sy | -0.033 |
bes | -0.033 |
Token | rest |
Token ID | 1334 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
theirs | +0.005 |
rings | +0.004 |
what | +0.004 |
wow | +0.004 |
are | +0.003 |
Neg logit contributions | |
Just | -0.005 |
age | -0.004 |
ager | -0.004 |
P | -0.004 |
bes | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Just | +0.006 |
age | +0.006 |
ager | +0.006 |
P | +0.006 |
bes | +0.006 |
Neg logit contributions | |
theirs | -0.005 |
rings | -0.004 |
what | -0.004 |
are | -0.004 |
wow | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
theirs | +0.073 |
rings | +0.070 |
wow | +0.052 |
are | +0.049 |
ours | +0.048 |
Neg logit contributions | |
Just | -0.137 |
bes | -0.135 |
P | -0.130 |
zer | -0.130 |
ager | -0.130 |
Token | or |
Token ID | 393 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
theirs | +0.013 |
rings | +0.011 |
what | +0.010 |
are | +0.010 |
nam | +0.010 |
Neg logit contributions | |
Just | -0.014 |
age | -0.012 |
ager | -0.012 |
P | -0.012 |
bes | -0.012 |
Token | nam |
Token ID | 7402 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
theirs | +0.012 |
rings | +0.010 |
wow | +0.009 |
ours | +0.008 |
are | +0.008 |
Neg logit contributions | |
Just | -0.015 |
ager | -0.014 |
age | -0.014 |
P | -0.013 |
fire | -0.013 |
Token | ents |
Token ID | 658 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
theirs | +0.223 |
rings | +0.157 |
what | +0.140 |
wow | +0.130 |
are | +0.122 |
Neg logit contributions | |
Just | -0.558 |
age | -0.529 |
ager | -0.526 |
P | -0.514 |
ivering | -0.507 |
Token | onto |
Token ID | 4291 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
theirs | +0.263 |
rings | +0.226 |
what | +0.210 |
wow | +0.205 |
nam | +0.202 |
Neg logit contributions | |
Just | -0.225 |
age | -0.215 |
ager | -0.208 |
bes | -0.197 |
sy | -0.196 |
Token | the |
Token ID | 262 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
theirs | +0.044 |
rings | +0.033 |
what | +0.028 |
wow | +0.025 |
are | +0.025 |
Neg logit contributions | |
Just | -0.097 |
age | -0.092 |
ager | -0.092 |
P | -0.090 |
bes | -0.089 |
Token | tree |
Token ID | 5509 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
theirs | +0.016 |
rings | +0.015 |
what | +0.014 |
nam | +0.013 |
are | +0.013 |
Neg logit contributions | |
Just | -0.016 |
ager | -0.015 |
P | -0.014 |
age | -0.014 |
ivering | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
theirs | +0.085 |
rings | +0.072 |
what | +0.067 |
are | +0.063 |
wow | +0.063 |
Neg logit contributions | |
Just | -0.085 |
ager | -0.079 |
age | -0.078 |
P | -0.076 |
bes | -0.074 |
Token | away |
Token ID | 1497 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
theirs | +0.100 |
rings | +0.087 |
what | +0.081 |
wow | +0.078 |
are | +0.077 |
Neg logit contributions | |
Just | -0.077 |
age | -0.071 |
ager | -0.069 |
P | -0.067 |
sy | -0.065 |
Token | , |
Token ID | 11 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Just | +0.174 |
ager | +0.163 |
age | +0.163 |
P | +0.159 |
bes | +0.154 |
Neg logit contributions | |
theirs | -0.177 |
rings | -0.150 |
what | -0.140 |
wow | -0.131 |
are | -0.131 |
Token | a |
Token ID | 257 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
theirs | +0.026 |
rings | +0.022 |
what | +0.020 |
are | +0.019 |
wow | +0.019 |
Neg logit contributions | |
Just | -0.023 |
age | -0.021 |
ager | -0.021 |
P | -0.020 |
bes | -0.020 |
Token | bright |
Token ID | 6016 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
theirs | +0.006 |
rings | +0.005 |
what | +0.005 |
wow | +0.005 |
are | +0.005 |
Neg logit contributions | |
Just | -0.007 |
ager | -0.006 |
age | -0.006 |
bes | -0.006 |
P | -0.006 |
Token | blue |
Token ID | 4171 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Just | +0.018 |
age | +0.017 |
ager | +0.017 |
P | +0.016 |
bes | +0.016 |
Neg logit contributions | |
theirs | -0.016 |
rings | -0.013 |
what | -0.012 |
wow | -0.011 |
are | -0.011 |
Token | spe |
Token ID | 693 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
theirs | +0.013 |
rings | +0.011 |
what | +0.010 |
wow | +0.009 |
are | +0.009 |
Neg logit contributions | |
Just | -0.012 |
age | -0.011 |
ager | -0.011 |
P | -0.011 |
bes | -0.010 |
Token | ck |
Token ID | 694 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
theirs | +0.328 |
rings | +0.260 |
what | +0.232 |
wow | +0.217 |
are | +0.213 |
Neg logit contributions | |
Just | -0.436 |
ager | -0.403 |
amas | -0.402 |
age | -0.399 |
P | -0.398 |
Token | in |
Token ID | 287 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
theirs | +0.092 |
rings | +0.079 |
what | +0.073 |
wow | +0.070 |
are | +0.069 |
Neg logit contributions | |
Just | -0.077 |
age | -0.071 |
ager | -0.071 |
P | -0.068 |
ivering | -0.066 |
Token | the |
Token ID | 262 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
Just | +0.035 |
P | +0.033 |
age | +0.033 |
entire | +0.032 |
Now | +0.032 |
Neg logit contributions | |
theirs | -0.022 |
rings | -0.022 |
ours | -0.017 |
nam | -0.017 |
maybe | -0.017 |
Token | sky |
Token ID | 6766 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
theirs | +0.006 |
rings | +0.005 |
what | +0.005 |
are | +0.005 |
wow | +0.005 |
Neg logit contributions | |
Just | -0.006 |
ager | -0.006 |
age | -0.005 |
bes | -0.005 |
P | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
theirs | +0.049 |
rings | +0.042 |
what | +0.039 |
wow | +0.037 |
nam | +0.037 |
Neg logit contributions | |
Just | -0.044 |
age | -0.041 |
ager | -0.040 |
P | -0.038 |
bes | -0.038 |
Token | eddy |
Token ID | 21874 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
Just | +0.051 |
ager | +0.048 |
bes | +0.045 |
age | +0.044 |
P | +0.043 |
Neg logit contributions | |
theirs | -0.066 |
rings | -0.063 |
what | -0.053 |
are | -0.050 |
nam | -0.049 |
Token | bear |
Token ID | 6842 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Just | +0.087 |
ager | +0.077 |
P | +0.073 |
ivering | +0.072 |
Days | +0.071 |
Neg logit contributions | |
theirs | -0.085 |
rings | -0.082 |
what | -0.079 |
are | -0.074 |
look | -0.069 |
Token | and |
Token ID | 290 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
theirs | +0.015 |
rings | +0.014 |
what | +0.013 |
are | +0.013 |
wow | +0.011 |
Neg logit contributions | |
Just | -0.015 |
ager | -0.014 |
P | -0.014 |
age | -0.013 |
ivering | -0.013 |
Token | watched |
Token ID | 7342 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
Just | +0.011 |
age | +0.011 |
ager | +0.010 |
bes | +0.010 |
P | +0.010 |
Neg logit contributions | |
theirs | -0.010 |
rings | -0.008 |
what | -0.007 |
wow | -0.007 |
are | -0.006 |
Token | in |
Token ID | 287 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Just | +0.118 |
age | +0.109 |
bes | +0.107 |
ze | +0.107 |
ager | +0.107 |
Neg logit contributions | |
theirs | -0.066 |
rings | -0.054 |
are | -0.044 |
wow | -0.043 |
nam | -0.042 |
Token | amaz |
Token ID | 40642 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
Just | +0.021 |
ager | +0.020 |
bes | +0.020 |
age | +0.020 |
rd | +0.019 |
Neg logit contributions | |
theirs | -0.015 |
rings | -0.014 |
wow | -0.011 |
nam | -0.011 |
ours | -0.010 |
Token | ement |
Token ID | 972 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
theirs | +0.396 |
rings | +0.338 |
what | +0.306 |
nam | +0.295 |
are | +0.294 |
Neg logit contributions | |
Just | -0.374 |
ager | -0.346 |
age | -0.341 |
P | -0.332 |
ivering | -0.323 |
Token | as |
Token ID | 355 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
theirs | +0.047 |
rings | +0.039 |
what | +0.036 |
wow | +0.036 |
are | +0.036 |
Neg logit contributions | |
Just | -0.041 |
age | -0.038 |
ager | -0.037 |
bes | -0.036 |
ivering | -0.035 |
Token | it |
Token ID | 340 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
theirs | +0.139 |
rings | +0.116 |
ours | +0.093 |
are | +0.089 |
wow | +0.088 |
Neg logit contributions | |
Just | -0.233 |
ager | -0.216 |
Lu | -0.213 |
sy | -0.213 |
P | -0.210 |
Token | shrunk |
Token ID | 38900 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
theirs | +0.052 |
rings | +0.044 |
what | +0.041 |
are | +0.039 |
wow | +0.038 |
Neg logit contributions | |
Just | -0.054 |
ager | -0.050 |
age | -0.050 |
P | -0.048 |
bes | -0.047 |
Token | an |
Token ID | 281 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
Just | +0.014 |
ager | +0.013 |
age | +0.013 |
P | +0.013 |
bes | +0.013 |
Neg logit contributions | |
theirs | -0.015 |
rings | -0.012 |
what | -0.012 |
are | -0.011 |
wow | -0.011 |
Token | around |
Token ID | 1088 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Just | +0.014 |
ager | +0.013 |
age | +0.013 |
P | +0.013 |
sy | +0.012 |
Neg logit contributions | |
theirs | -0.015 |
rings | -0.012 |
what | -0.011 |
wow | -0.011 |
nam | -0.010 |
Token | stopped |
Token ID | 5025 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
theirs | +0.075 |
rings | +0.059 |
wow | +0.049 |
nam | +0.048 |
what | +0.048 |
Neg logit contributions | |
Just | -0.127 |
age | -0.120 |
ager | -0.120 |
P | -0.117 |
bes | -0.116 |
Token | and |
Token ID | 290 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
theirs | +0.023 |
rings | +0.020 |
wow | +0.018 |
nam | +0.018 |
are | +0.018 |
Neg logit contributions | |
Just | -0.019 |
age | -0.016 |
ivering | -0.016 |
ager | -0.016 |
P | -0.015 |
Token | watched |
Token ID | 7342 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
theirs | +0.030 |
rings | +0.024 |
ours | +0.022 |
ours | +0.021 |
nam | +0.021 |
Neg logit contributions | |
Just | -0.026 |
age | -0.025 |
ager | -0.025 |
sy | -0.023 |
ce | -0.022 |
Token | in |
Token ID | 287 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Just | +0.120 |
age | +0.111 |
ze | +0.109 |
ager | +0.108 |
bes | +0.107 |
Neg logit contributions | |
theirs | -0.074 |
rings | -0.061 |
nam | -0.050 |
are | -0.049 |
ours | -0.048 |
Token | amaz |
Token ID | 40642 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
Just | +0.016 |
age | +0.015 |
ager | +0.015 |
entire | +0.015 |
bes | +0.015 |
Neg logit contributions | |
theirs | -0.010 |
rings | -0.010 |
ours | -0.008 |
nam | -0.007 |
wow | -0.007 |
Token | ement |
Token ID | 972 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
theirs | +0.406 |
rings | +0.351 |
what | +0.313 |
nam | +0.309 |
are | +0.303 |
Neg logit contributions | |
Just | -0.361 |
ager | -0.333 |
age | -0.324 |
P | -0.320 |
ivering | -0.311 |
Token | . |
Token ID | 13 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
theirs | +0.050 |
rings | +0.042 |
nam | +0.038 |
what | +0.038 |
wow | +0.038 |
Neg logit contributions | |
Just | -0.042 |
age | -0.038 |
ager | -0.037 |
bes | -0.035 |
ivering | -0.035 |
Token | They |
Token ID | 1119 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
theirs | +0.017 |
rings | +0.014 |
what | +0.013 |
are | +0.012 |
wow | +0.012 |
Neg logit contributions | |
Just | -0.018 |
age | -0.017 |
ager | -0.017 |
P | -0.016 |
bes | -0.016 |
Token | were |
Token ID | 547 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
theirs | +0.004 |
rings | +0.004 |
ours | +0.003 |
ours | +0.003 |
what | +0.003 |
Neg logit contributions | |
Just | -0.004 |
ager | -0.004 |
age | -0.004 |
sy | -0.004 |
P | -0.004 |
Token | so |
Token ID | 523 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
theirs | +0.116 |
rings | +0.101 |
what | +0.088 |
nam | +0.085 |
wow | +0.085 |
Neg logit contributions | |
Just | -0.116 |
age | -0.109 |
ager | -0.107 |
sy | -0.103 |
P | -0.102 |
Token | calmed |
Token ID | 49566 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
Just | +0.053 |
age | +0.050 |
ager | +0.050 |
P | +0.048 |
bes | +0.047 |
Neg logit contributions | |
theirs | -0.037 |
rings | -0.030 |
what | -0.027 |
wow | -0.025 |
are | -0.025 |
Token | down |
Token ID | 866 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
theirs | +0.061 |
rings | +0.052 |
wow | +0.047 |
nam | +0.045 |
what | +0.044 |
Neg logit contributions | |
Just | -0.059 |
age | -0.055 |
ager | -0.053 |
sy | -0.051 |
ivering | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
theirs | +0.009 |
rings | +0.008 |
what | +0.007 |
wow | +0.007 |
are | +0.007 |
Neg logit contributions | |
Just | -0.008 |
age | -0.007 |
ager | -0.007 |
P | -0.007 |
bes | -0.007 |
Token | watched |
Token ID | 7342 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
theirs | +0.025 |
rings | +0.021 |
what | +0.017 |
nam | +0.017 |
wow | +0.017 |
Neg logit contributions | |
Just | -0.026 |
ager | -0.025 |
age | -0.024 |
sy | -0.023 |
ce | -0.023 |
Token | in |
Token ID | 287 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Just | +0.120 |
age | +0.109 |
ager | +0.109 |
ze | +0.107 |
bes | +0.107 |
Neg logit contributions | |
theirs | -0.079 |
rings | -0.068 |
nam | -0.055 |
are | -0.053 |
wow | -0.052 |
Token | amaz |
Token ID | 40642 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
Just | +0.030 |
ager | +0.028 |
age | +0.028 |
bes | +0.027 |
zer | +0.027 |
Neg logit contributions | |
theirs | -0.018 |
rings | -0.017 |
nam | -0.013 |
ours | -0.012 |
wow | -0.012 |
Token | ement |
Token ID | 972 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
theirs | +0.415 |
rings | +0.363 |
nam | +0.324 |
what | +0.320 |
are | +0.312 |
Neg logit contributions | |
Just | -0.350 |
ager | -0.322 |
age | -0.309 |
P | -0.305 |
ivering | -0.298 |
Token | as |
Token ID | 355 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
theirs | +0.051 |
rings | +0.043 |
nam | +0.039 |
wow | +0.038 |
what | +0.038 |
Neg logit contributions | |
Just | -0.046 |
age | -0.042 |
ager | -0.041 |
bes | -0.039 |
ivering | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
theirs | +0.145 |
rings | +0.141 |
ours | +0.115 |
endant | +0.103 |
nam | +0.095 |
Neg logit contributions | |
Just | -0.220 |
fire | -0.208 |
ager | -0.208 |
ce | -0.203 |
Lu | -0.200 |
Token | rainbow |
Token ID | 27223 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
theirs | +0.004 |
rings | +0.003 |
what | +0.003 |
wow | +0.003 |
are | +0.003 |
Neg logit contributions | |
Just | -0.004 |
ager | -0.004 |
age | -0.003 |
P | -0.003 |
bes | -0.003 |
Token | melted |
Token ID | 24178 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
theirs | +0.180 |
rings | +0.152 |
what | +0.141 |
wow | +0.134 |
nam | +0.133 |
Neg logit contributions | |
Just | -0.170 |
age | -0.160 |
ager | -0.158 |
P | -0.151 |
bes | -0.150 |
Token | the |
Token ID | 262 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
theirs | +0.023 |
rings | +0.021 |
are | +0.017 |
nam | +0.017 |
wow | +0.016 |
Neg logit contributions | |
Just | -0.034 |
ce | -0.030 |
sy | -0.030 |
ager | -0.030 |
zer | -0.029 |
Token | zipper |
Token ID | 48992 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
Just | +0.001 |
age | +0.001 |
ager | +0.001 |
P | +0.001 |
bes | +0.001 |
Neg logit contributions | |
theirs | -0.001 |
rings | -0.001 |
what | -0.001 |
wow | -0.001 |
are | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
theirs | +0.089 |
rings | +0.076 |
what | +0.072 |
wow | +0.069 |
are | +0.068 |
Neg logit contributions | |
Just | -0.066 |
age | -0.061 |
ager | -0.060 |
P | -0.057 |
bes | -0.057 |
Token | gasped |
Token ID | 45236 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
theirs | +0.010 |
rings | +0.008 |
what | +0.007 |
are | +0.007 |
wow | +0.007 |
Neg logit contributions | |
Just | -0.010 |
ager | -0.009 |
age | -0.009 |
P | -0.009 |
sy | -0.009 |
Token | with |
Token ID | 351 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
theirs | +0.053 |
rings | +0.045 |
what | +0.042 |
wow | +0.040 |
are | +0.040 |
Neg logit contributions | |
Just | -0.045 |
age | -0.042 |
ager | -0.041 |
P | -0.040 |
bes | -0.039 |
Token | amaz |
Token ID | 40642 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
Just | +0.009 |
ager | +0.009 |
age | +0.009 |
P | +0.009 |
sy | +0.008 |
Neg logit contributions | |
rings | -0.011 |
theirs | -0.011 |
ours | -0.009 |
nam | -0.008 |
angles | -0.008 |
Token | ement |
Token ID | 972 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
theirs | +0.401 |
rings | +0.346 |
what | +0.310 |
are | +0.302 |
nam | +0.301 |
Neg logit contributions | |
Just | -0.363 |
ager | -0.334 |
age | -0.328 |
P | -0.319 |
ivering | -0.314 |
Token | at |
Token ID | 379 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
theirs | +0.046 |
rings | +0.039 |
are | +0.036 |
nam | +0.036 |
wow | +0.035 |
Neg logit contributions | |
Just | -0.035 |
age | -0.032 |
ager | -0.032 |
sy | -0.030 |
ivering | -0.030 |
Token | all |
Token ID | 477 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
theirs | +0.095 |
rings | +0.086 |
nam | +0.065 |
wow | +0.064 |
are | +0.064 |
Neg logit contributions | |
Just | -0.151 |
ager | -0.143 |
bes | -0.141 |
zer | -0.140 |
age | -0.140 |
Token | the |
Token ID | 262 |
Feature activation | +7.42e-02 |
Pos logit contributions | |
theirs | +0.103 |
rings | +0.099 |
wow | +0.079 |
nam | +0.078 |
are | +0.068 |
Neg logit contributions | |
Just | -0.153 |
age | -0.147 |
ager | -0.147 |
sy | -0.145 |
ce | -0.142 |
Token | treasures |
Token ID | 29561 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
theirs | +0.007 |
rings | +0.005 |
what | +0.005 |
wow | +0.005 |
are | +0.005 |
Neg logit contributions | |
Just | -0.008 |
ager | -0.007 |
age | -0.007 |
P | -0.007 |
bes | -0.007 |
Token | time |
Token ID | 640 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
theirs | +0.038 |
rings | +0.032 |
what | +0.030 |
wow | +0.029 |
are | +0.028 |
Neg logit contributions | |
Just | -0.036 |
age | -0.033 |
ager | -0.033 |
P | -0.032 |
bes | -0.031 |
Token | playing |
Token ID | 2712 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
theirs | +0.004 |
rings | +0.004 |
what | +0.003 |
wow | +0.003 |
are | +0.003 |
Neg logit contributions | |
Just | -0.004 |
age | -0.004 |
ager | -0.004 |
P | -0.004 |
bes | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
Just | +0.044 |
ager | +0.040 |
age | +0.040 |
ivering | +0.038 |
sy | +0.036 |
Neg logit contributions | |
theirs | -0.058 |
what | -0.049 |
rings | -0.048 |
are | -0.046 |
their | -0.046 |
Token | her |
Token ID | 607 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
Just | +0.024 |
bes | +0.023 |
P | +0.023 |
age | +0.023 |
ager | +0.023 |
Neg logit contributions | |
theirs | -0.014 |
rings | -0.012 |
wow | -0.009 |
ours | -0.009 |
are | -0.009 |
Token | or |
Token ID | 393 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
theirs | +0.034 |
rings | +0.029 |
what | +0.027 |
wow | +0.025 |
are | +0.025 |
Neg logit contributions | |
Just | -0.032 |
age | -0.029 |
ager | -0.029 |
P | -0.028 |
bes | -0.028 |
Token | nam |
Token ID | 7402 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
theirs | +0.013 |
rings | +0.010 |
wow | +0.009 |
are | +0.009 |
what | +0.009 |
Neg logit contributions | |
Just | -0.016 |
age | -0.014 |
bes | -0.014 |
P | -0.014 |
ager | -0.014 |
Token | ents |
Token ID | 658 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
theirs | +0.227 |
rings | +0.165 |
what | +0.146 |
wow | +0.133 |
are | +0.128 |
Neg logit contributions | |
Just | -0.531 |
age | -0.503 |
ager | -0.501 |
P | -0.490 |
bes | -0.483 |
Token | and |
Token ID | 290 |
Feature activation | -6.96e-02 |
Pos logit contributions | |
theirs | +0.273 |
rings | +0.233 |
what | +0.218 |
wow | +0.213 |
nam | +0.206 |
Neg logit contributions | |
Just | -0.230 |
age | -0.219 |
ager | -0.213 |
P | -0.202 |
bes | -0.201 |
Token | making |
Token ID | 1642 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Just | +0.007 |
age | +0.007 |
ager | +0.006 |
P | +0.006 |
bes | +0.006 |
Neg logit contributions | |
theirs | -0.006 |
rings | -0.005 |
what | -0.005 |
wow | -0.004 |
are | -0.004 |
Token | her |
Token ID | 607 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
Just | +0.111 |
age | +0.106 |
ager | +0.105 |
bes | +0.103 |
P | +0.102 |
Neg logit contributions | |
theirs | -0.078 |
rings | -0.066 |
wow | -0.055 |
are | -0.054 |
what | -0.053 |
Token | special |
Token ID | 2041 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
theirs | +0.018 |
rings | +0.014 |
wow | +0.013 |
what | +0.013 |
ours | +0.012 |
Neg logit contributions | |
age | -0.019 |
Just | -0.019 |
bes | -0.018 |
ager | -0.018 |
ze | -0.018 |
Token | Tim |
Token ID | 5045 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
Just | +0.006 |
age | +0.005 |
ager | +0.005 |
P | +0.005 |
bes | +0.005 |
Neg logit contributions | |
theirs | -0.002 |
rings | -0.001 |
what | -0.001 |
wow | -0.001 |
are | -0.001 |
Token | watched |
Token ID | 7342 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
theirs | +0.038 |
what | +0.035 |
rings | +0.032 |
are | +0.029 |
Tom | +0.028 |
Neg logit contributions | |
fire | -0.088 |
bes | -0.087 |
Just | -0.086 |
oster | -0.086 |
ager | -0.085 |
Token | them |
Token ID | 606 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
Just | +0.147 |
age | +0.137 |
ager | +0.134 |
P | +0.131 |
bes | +0.131 |
Neg logit contributions | |
theirs | -0.091 |
rings | -0.076 |
what | -0.062 |
wow | -0.062 |
are | -0.061 |
Token | with |
Token ID | 351 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
Just | +0.027 |
age | +0.025 |
sy | +0.024 |
ager | +0.024 |
ivering | +0.023 |
Neg logit contributions | |
theirs | -0.033 |
rings | -0.029 |
nam | -0.026 |
wow | -0.026 |
what | -0.025 |
Token | pure |
Token ID | 5899 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
ze | +0.015 |
zer | +0.015 |
Just | +0.015 |
age | +0.015 |
bes | +0.015 |
Neg logit contributions | |
rings | -0.017 |
theirs | -0.016 |
ours | -0.015 |
angles | -0.013 |
endant | -0.013 |
Token | amaz |
Token ID | 40642 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
theirs | +0.078 |
rings | +0.067 |
what | +0.059 |
wow | +0.057 |
nam | +0.056 |
Neg logit contributions | |
Just | -0.093 |
age | -0.088 |
ager | -0.086 |
P | -0.084 |
bes | -0.083 |
Token | ement |
Token ID | 972 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
theirs | +0.340 |
rings | +0.272 |
what | +0.259 |
wow | +0.237 |
are | +0.233 |
Neg logit contributions | |
Just | -0.417 |
age | -0.396 |
ager | -0.391 |
P | -0.381 |
bes | -0.376 |
Token | , |
Token ID | 11 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
theirs | +0.047 |
rings | +0.040 |
what | +0.037 |
wow | +0.036 |
nam | +0.036 |
Neg logit contributions | |
Just | -0.044 |
age | -0.041 |
ager | -0.040 |
bes | -0.038 |
ivering | -0.038 |
Token | never |
Token ID | 1239 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
theirs | +0.035 |
rings | +0.030 |
what | +0.027 |
are | +0.026 |
nam | +0.026 |
Neg logit contributions | |
Just | -0.030 |
age | -0.027 |
ager | -0.026 |
bes | -0.026 |
P | -0.025 |
Token | t |
Token ID | 256 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
Just | +0.054 |
age | +0.048 |
ager | +0.048 |
ivering | +0.046 |
seek | +0.045 |
Neg logit contributions | |
theirs | -0.074 |
rings | -0.063 |
angles | -0.058 |
ours | -0.057 |
wow | -0.056 |
Token | iring |
Token ID | 3428 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Just | +0.073 |
ager | +0.067 |
age | +0.066 |
P | +0.063 |
bes | +0.063 |
Neg logit contributions | |
theirs | -0.113 |
rings | -0.100 |
what | -0.092 |
are | -0.088 |
wow | -0.087 |
Token | friends |
Token ID | 2460 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
theirs | +0.063 |
rings | +0.053 |
what | +0.048 |
wow | +0.045 |
are | +0.045 |
Neg logit contributions | |
Just | -0.073 |
age | -0.068 |
ager | -0.068 |
P | -0.066 |
bes | -0.065 |
Token | stopped |
Token ID | 5025 |
Feature activation | +9.65e-02 |
Pos logit contributions | |
Just | +0.067 |
age | +0.063 |
ager | +0.062 |
P | +0.061 |
bes | +0.060 |
Neg logit contributions | |
theirs | -0.052 |
rings | -0.043 |
what | -0.040 |
are | -0.037 |
wow | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
theirs | +0.009 |
rings | +0.008 |
what | +0.007 |
wow | +0.007 |
are | +0.007 |
Neg logit contributions | |
Just | -0.009 |
age | -0.008 |
ager | -0.008 |
P | -0.008 |
ivering | -0.008 |
Token | watched |
Token ID | 7342 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Just | +0.025 |
ager | +0.023 |
age | +0.022 |
P | +0.022 |
sy | +0.022 |
Neg logit contributions | |
theirs | -0.029 |
rings | -0.025 |
ours | -0.021 |
are | -0.021 |
what | -0.020 |
Token | in |
Token ID | 287 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
Just | +0.142 |
ager | +0.130 |
age | +0.130 |
bes | +0.127 |
P | +0.125 |
Neg logit contributions | |
theirs | -0.092 |
rings | -0.078 |
are | -0.064 |
what | -0.063 |
wow | -0.063 |
Token | amaz |
Token ID | 40642 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
Just | +0.040 |
ager | +0.038 |
age | +0.036 |
bes | +0.036 |
rd | +0.035 |
Neg logit contributions | |
theirs | -0.028 |
rings | -0.026 |
nam | -0.020 |
wow | -0.019 |
ours | -0.018 |
Token | ement |
Token ID | 972 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
theirs | +0.401 |
rings | +0.353 |
nam | +0.312 |
what | +0.310 |
are | +0.306 |
Neg logit contributions | |
Just | -0.348 |
ager | -0.321 |
age | -0.305 |
P | -0.304 |
ivering | -0.293 |
Token | . |
Token ID | 13 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
theirs | +0.027 |
rings | +0.022 |
what | +0.020 |
wow | +0.020 |
are | +0.020 |
Neg logit contributions | |
Just | -0.026 |
age | -0.023 |
ager | -0.023 |
bes | -0.022 |
ivering | -0.022 |
Token | The |
Token ID | 383 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
Just | +0.037 |
age | +0.034 |
ager | +0.034 |
P | +0.033 |
bes | +0.032 |
Neg logit contributions | |
theirs | -0.028 |
rings | -0.023 |
what | -0.020 |
are | -0.020 |
wow | -0.019 |
Token | dog |
Token ID | 3290 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
Just | +0.004 |
age | +0.004 |
ager | +0.004 |
P | +0.003 |
bes | +0.003 |
Neg logit contributions | |
theirs | -0.004 |
rings | -0.003 |
what | -0.003 |
wow | -0.003 |
are | -0.003 |
Token | too |
Token ID | 1165 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
Just | +0.018 |
age | +0.017 |
P | +0.017 |
ager | +0.017 |
amas | +0.016 |
Neg logit contributions | |
theirs | -0.016 |
rings | -0.013 |
what | -0.013 |
wow | -0.012 |
are | -0.012 |
Token | Wow |
Token ID | 22017 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
age | +0.003 |
Just | +0.003 |
ager | +0.003 |
ivering | +0.003 |
bes | +0.003 |
Neg logit contributions | |
theirs | -0.003 |
rings | -0.003 |
what | -0.003 |
wow | -0.003 |
nam | -0.002 |
Token | ," |
Token ID | 553 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
theirs | +0.144 |
rings | +0.123 |
what | +0.110 |
nam | +0.110 |
wow | +0.107 |
Neg logit contributions | |
Just | -0.096 |
ager | -0.088 |
age | -0.087 |
P | -0.084 |
sy | -0.082 |
Token | Emily |
Token ID | 17608 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
theirs | +0.078 |
rings | +0.063 |
what | +0.054 |
wow | +0.053 |
are | +0.052 |
Neg logit contributions | |
Just | -0.093 |
ager | -0.086 |
age | -0.086 |
P | -0.085 |
bes | -0.082 |
Token | gasped |
Token ID | 45236 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
theirs | +0.029 |
rings | +0.025 |
what | +0.023 |
are | +0.022 |
wow | +0.021 |
Neg logit contributions | |
Just | -0.050 |
P | -0.049 |
ivering | -0.049 |
age | -0.049 |
ager | -0.047 |
Token | in |
Token ID | 287 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
theirs | +0.043 |
rings | +0.037 |
what | +0.035 |
wow | +0.032 |
are | +0.032 |
Neg logit contributions | |
Just | -0.038 |
age | -0.036 |
ager | -0.036 |
P | -0.034 |
bes | -0.034 |
Token | amaz |
Token ID | 40642 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
Just | +0.047 |
ager | +0.044 |
age | +0.043 |
P | +0.042 |
bes | +0.041 |
Neg logit contributions | |
theirs | -0.032 |
rings | -0.028 |
what | -0.022 |
nam | -0.021 |
wow | -0.021 |
Token | ement |
Token ID | 972 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
theirs | +0.385 |
rings | +0.330 |
what | +0.298 |
are | +0.286 |
nam | +0.286 |
Neg logit contributions | |
Just | -0.366 |
ager | -0.338 |
age | -0.333 |
P | -0.325 |
ivering | -0.317 |
Token | . |
Token ID | 13 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
theirs | +0.027 |
rings | +0.023 |
what | +0.021 |
are | +0.020 |
wow | +0.020 |
Neg logit contributions | |
Just | -0.025 |
ager | -0.023 |
age | -0.023 |
P | -0.022 |
bes | -0.022 |
Token | She |
Token ID | 1375 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
theirs | +0.027 |
rings | +0.022 |
what | +0.021 |
wow | +0.019 |
maybe | +0.018 |
Neg logit contributions | |
Just | -0.042 |
ager | -0.042 |
age | -0.041 |
P | -0.040 |
ivering | -0.040 |
Token | realized |
Token ID | 6939 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
theirs | +0.006 |
what | +0.006 |
rings | +0.006 |
wow | +0.005 |
are | +0.005 |
Neg logit contributions | |
age | -0.008 |
P | -0.008 |
ivering | -0.008 |
Just | -0.008 |
amas | -0.008 |
Token | that |
Token ID | 326 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
theirs | +0.042 |
rings | +0.035 |
are | +0.030 |
nam | +0.029 |
ours | +0.029 |
Neg logit contributions | |
Just | -0.056 |
ager | -0.049 |
P | -0.049 |
age | -0.048 |
bes | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
theirs | +0.154 |
rings | +0.132 |
what | +0.122 |
wow | +0.117 |
are | +0.116 |
Neg logit contributions | |
Just | -0.135 |
age | -0.125 |
ager | -0.124 |
P | -0.119 |
bes | -0.118 |
Token |
|
Token ID | 198 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
ager | +0.033 |
age | +0.032 |
ivering | +0.032 |
bes | +0.031 |
amas | +0.031 |
Neg logit contributions | |
theirs | -0.021 |
what | -0.018 |
rings | -0.017 |
maybe | -0.016 |
Tom | -0.016 |
Token | Sarah |
Token ID | 29284 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
amas | +0.026 |
ager | +0.026 |
bes | +0.025 |
age | +0.024 |
ivering | +0.024 |
Neg logit contributions | |
theirs | -0.031 |
what | -0.028 |
rings | -0.026 |
their | -0.026 |
they | -0.025 |
Token | watched |
Token ID | 7342 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
P | +0.002 |
amas | +0.002 |
bes | +0.002 |
ager | +0.002 |
Just | +0.002 |
Neg logit contributions | |
theirs | -0.002 |
what | -0.001 |
rings | -0.001 |
are | -0.001 |
their | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
Just | +0.137 |
age | +0.125 |
ivering | +0.121 |
ze | +0.121 |
bes | +0.121 |
Neg logit contributions | |
theirs | -0.098 |
rings | -0.083 |
nam | -0.068 |
are | -0.067 |
wow | -0.067 |
Token | amaz |
Token ID | 40642 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
Just | +0.041 |
age | +0.039 |
ivering | +0.037 |
ager | +0.037 |
bes | +0.037 |
Neg logit contributions | |
theirs | -0.030 |
rings | -0.026 |
nam | -0.021 |
angles | -0.020 |
wow | -0.019 |
Token | ement |
Token ID | 972 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
theirs | +0.394 |
rings | +0.341 |
what | +0.303 |
nam | +0.299 |
are | +0.296 |
Neg logit contributions | |
Just | -0.358 |
ager | -0.327 |
age | -0.320 |
P | -0.314 |
ivering | -0.308 |
Token | as |
Token ID | 355 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
theirs | +0.033 |
rings | +0.027 |
are | +0.024 |
wow | +0.024 |
nam | +0.024 |
Neg logit contributions | |
Just | -0.035 |
age | -0.031 |
ager | -0.030 |
ivering | -0.030 |
bes | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
theirs | +0.141 |
rings | +0.125 |
ours | +0.101 |
ours | +0.093 |
angles | +0.093 |
Neg logit contributions | |
Just | -0.200 |
Lu | -0.186 |
Now | -0.179 |
ce | -0.176 |
B | -0.175 |
Token | water |
Token ID | 1660 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
Just | +0.003 |
ager | +0.003 |
age | +0.003 |
P | +0.003 |
ivering | +0.003 |
Neg logit contributions | |
theirs | -0.003 |
rings | -0.003 |
what | -0.003 |
wow | -0.002 |
are | -0.002 |
Token | became |
Token ID | 2627 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Just | +0.025 |
ager | +0.024 |
age | +0.024 |
P | +0.023 |
bes | +0.023 |
Neg logit contributions | |
theirs | -0.023 |
rings | -0.020 |
what | -0.019 |
are | -0.018 |
wow | -0.017 |
Token | were |
Token ID | 547 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Just | +0.094 |
age | +0.087 |
ager | +0.087 |
P | +0.084 |
bes | +0.083 |
Neg logit contributions | |
theirs | -0.080 |
rings | -0.067 |
what | -0.061 |
wow | -0.057 |
are | -0.057 |
Token | filled |
Token ID | 5901 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
theirs | +0.108 |
rings | +0.092 |
what | +0.083 |
wow | +0.079 |
are | +0.079 |
Neg logit contributions | |
Just | -0.112 |
age | -0.105 |
ager | -0.104 |
P | -0.100 |
bes | -0.099 |
Token | with |
Token ID | 351 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
theirs | +0.092 |
what | +0.076 |
their | +0.073 |
rings | +0.071 |
are | +0.068 |
Neg logit contributions | |
Just | -0.074 |
age | -0.069 |
ivering | -0.067 |
ager | -0.065 |
P | -0.064 |
Token | wonder |
Token ID | 4240 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
age | +0.015 |
Just | +0.015 |
ager | +0.015 |
sy | +0.014 |
entire | +0.014 |
Neg logit contributions | |
theirs | -0.018 |
rings | -0.018 |
ours | -0.015 |
wow | -0.014 |
angles | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
theirs | +0.236 |
rings | +0.208 |
nam | +0.184 |
wow | +0.182 |
ours | +0.176 |
Neg logit contributions | |
Just | -0.200 |
age | -0.185 |
ager | -0.182 |
sy | -0.172 |
bes | -0.171 |
Token | amaz |
Token ID | 40642 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
theirs | +0.007 |
rings | +0.006 |
ours | +0.005 |
nam | +0.005 |
wow | +0.005 |
Neg logit contributions | |
Just | -0.007 |
age | -0.006 |
ager | -0.006 |
sy | -0.006 |
fire | -0.006 |
Token | ement |
Token ID | 972 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
theirs | +0.382 |
rings | +0.329 |
what | +0.296 |
are | +0.285 |
nam | +0.284 |
Neg logit contributions | |
Just | -0.366 |
ager | -0.338 |
age | -0.334 |
P | -0.321 |
ivering | -0.315 |
Token | . |
Token ID | 13 |
Feature activation | +9.71e-02 |
Pos logit contributions | |
theirs | +0.036 |
rings | +0.030 |
nam | +0.028 |
are | +0.027 |
wow | +0.027 |
Neg logit contributions | |
Just | -0.032 |
age | -0.030 |
ager | -0.029 |
sy | -0.028 |
ivering | -0.027 |
Token | They |
Token ID | 1119 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
theirs | +0.008 |
rings | +0.007 |
what | +0.006 |
are | +0.006 |
nam | +0.006 |
Neg logit contributions | |
Just | -0.010 |
age | -0.009 |
ager | -0.009 |
P | -0.009 |
bes | -0.009 |
Token | thanked |
Token ID | 26280 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
theirs | +0.002 |
rings | +0.002 |
what | +0.001 |
ours | +0.001 |
wow | +0.001 |
Neg logit contributions | |
Just | -0.002 |
ager | -0.002 |
age | -0.002 |
sy | -0.002 |
P | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
theirs | +0.040 |
rings | +0.035 |
ours | +0.026 |
nam | +0.026 |
wow | +0.025 |
Neg logit contributions | |
Just | -0.082 |
ager | -0.078 |
age | -0.076 |
P | -0.075 |
ce | -0.074 |
Token | they |
Token ID | 484 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
Just | +0.015 |
ager | +0.013 |
age | +0.013 |
bes | +0.013 |
sy | +0.013 |
Neg logit contributions | |
theirs | -0.012 |
rings | -0.011 |
what | -0.009 |
wow | -0.009 |
are | -0.009 |
Token | both |
Token ID | 1111 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
Just | +0.016 |
ager | +0.015 |
age | +0.015 |
P | +0.014 |
sy | +0.014 |
Neg logit contributions | |
theirs | -0.017 |
rings | -0.014 |
what | -0.012 |
wow | -0.012 |
nam | -0.012 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
theirs | +0.055 |
rings | +0.047 |
what | +0.043 |
wow | +0.041 |
nam | +0.040 |
Neg logit contributions | |
Just | -0.053 |
ager | -0.050 |
age | -0.049 |
P | -0.047 |
sy | -0.047 |
Token | around |
Token ID | 1088 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
Just | +0.011 |
ager | +0.010 |
sy | +0.010 |
age | +0.009 |
ivering | +0.009 |
Neg logit contributions | |
theirs | -0.011 |
rings | -0.011 |
nam | -0.008 |
wow | -0.008 |
are | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
theirs | +0.097 |
rings | +0.087 |
what | +0.075 |
wow | +0.075 |
nam | +0.074 |
Neg logit contributions | |
Just | -0.077 |
ager | -0.068 |
age | -0.066 |
P | -0.065 |
bes | -0.063 |
Token | amaz |
Token ID | 40642 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
Just | +0.034 |
rd | +0.031 |
ager | +0.031 |
entire | +0.031 |
P | +0.031 |
Neg logit contributions | |
rings | -0.021 |
theirs | -0.020 |
nam | -0.015 |
ours | -0.014 |
wow | -0.014 |
Token | ement |
Token ID | 972 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
theirs | +0.402 |
rings | +0.351 |
nam | +0.313 |
what | +0.313 |
are | +0.305 |
Neg logit contributions | |
Just | -0.342 |
ager | -0.315 |
age | -0.303 |
P | -0.300 |
ivering | -0.290 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
theirs | +0.024 |
rings | +0.020 |
what | +0.019 |
wow | +0.018 |
are | +0.018 |
Neg logit contributions | |
Just | -0.023 |
ager | -0.021 |
age | -0.021 |
P | -0.020 |
bes | -0.020 |
Token | The |
Token ID | 383 |
Feature activation | -7.60e-02 |
Pos logit contributions | |
Just | +0.014 |
age | +0.013 |
ager | +0.013 |
P | +0.012 |
bes | +0.012 |
Neg logit contributions | |
theirs | -0.011 |
rings | -0.009 |
what | -0.008 |
wow | -0.008 |
are | -0.008 |
Token | lake |
Token ID | 13546 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
Just | +0.007 |
age | +0.007 |
ager | +0.007 |
P | +0.006 |
bes | +0.006 |
Neg logit contributions | |
theirs | -0.007 |
rings | -0.006 |
what | -0.006 |
wow | -0.006 |
are | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
theirs | +0.028 |
rings | +0.025 |
what | +0.023 |
wow | +0.022 |
are | +0.022 |
Neg logit contributions | |
Just | -0.020 |
age | -0.019 |
ager | -0.019 |
P | -0.018 |
bes | -0.017 |
Token | seen |
Token ID | 1775 |
Feature activation | +7.48e-02 |
Pos logit contributions | |
Just | +0.027 |
ager | +0.025 |
age | +0.025 |
P | +0.024 |
bes | +0.024 |
Neg logit contributions | |
theirs | -0.027 |
rings | -0.023 |
what | -0.021 |
wow | -0.020 |
are | -0.020 |
Token | ! |
Token ID | 0 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
theirs | +0.007 |
rings | +0.006 |
what | +0.005 |
are | +0.005 |
wow | +0.005 |
Neg logit contributions | |
Just | -0.007 |
ager | -0.007 |
age | -0.007 |
P | -0.007 |
bes | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
Just | +0.013 |
age | +0.012 |
ager | +0.012 |
P | +0.012 |
bes | +0.012 |
Neg logit contributions | |
theirs | -0.012 |
rings | -0.010 |
what | -0.009 |
wow | -0.009 |
are | -0.009 |
Token | gasped |
Token ID | 45236 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
Just | +0.003 |
age | +0.003 |
ager | +0.003 |
ivering | +0.003 |
P | +0.003 |
Neg logit contributions | |
theirs | -0.003 |
rings | -0.003 |
what | -0.003 |
are | -0.002 |
wow | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
theirs | +0.039 |
rings | +0.034 |
what | +0.032 |
wow | +0.030 |
are | +0.030 |
Neg logit contributions | |
Just | -0.029 |
age | -0.027 |
ager | -0.027 |
P | -0.026 |
bes | -0.025 |
Token | amaz |
Token ID | 40642 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
Just | +0.048 |
ager | +0.045 |
age | +0.044 |
P | +0.044 |
bes | +0.043 |
Neg logit contributions | |
theirs | -0.034 |
rings | -0.030 |
ours | -0.023 |
nam | -0.022 |
maybe | -0.022 |
Token | ement |
Token ID | 972 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
theirs | +0.396 |
rings | +0.340 |
what | +0.305 |
nam | +0.299 |
are | +0.297 |
Neg logit contributions | |
Just | -0.353 |
ager | -0.326 |
age | -0.318 |
P | -0.312 |
ivering | -0.304 |
Token | , |
Token ID | 11 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
theirs | +0.022 |
rings | +0.018 |
what | +0.017 |
are | +0.016 |
wow | +0.016 |
Neg logit contributions | |
Just | -0.024 |
age | -0.022 |
ager | -0.022 |
ivering | -0.020 |
bes | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -8.75e-02 |
Pos logit contributions | |
theirs | +0.015 |
rings | +0.013 |
what | +0.012 |
are | +0.011 |
wow | +0.011 |
Neg logit contributions | |
Just | -0.014 |
age | -0.013 |
ager | -0.013 |
P | -0.012 |
bes | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
Just | +0.009 |
ager | +0.009 |
age | +0.009 |
P | +0.008 |
bes | +0.008 |
Neg logit contributions | |
theirs | -0.007 |
rings | -0.006 |
what | -0.005 |
are | -0.005 |
wow | -0.005 |
Token | tears |
Token ID | 10953 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
theirs | +0.003 |
rings | +0.002 |
what | +0.002 |
wow | +0.002 |
are | +0.002 |
Neg logit contributions | |
Just | -0.003 |
age | -0.003 |
ager | -0.003 |
P | -0.003 |
bes | -0.003 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
theirs | +0.029 |
rings | +0.023 |
ours | +0.021 |
endant | +0.021 |
aly | +0.020 |
Neg logit contributions | |
Just | -0.026 |
P | -0.026 |
Lu | -0.025 |
seek | -0.024 |
But | -0.024 |
Token | stopped |
Token ID | 5025 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
theirs | +0.022 |
rings | +0.021 |
what | +0.021 |
are | +0.019 |
their | +0.019 |
Neg logit contributions | |
age | -0.044 |
Just | -0.043 |
ager | -0.042 |
ivering | -0.042 |
amas | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
Just | +0.003 |
age | +0.003 |
P | +0.003 |
ager | +0.003 |
ivering | +0.003 |
Neg logit contributions | |
theirs | -0.003 |
rings | -0.003 |
wow | -0.003 |
are | -0.002 |
what | -0.002 |
Token | stared |
Token ID | 18484 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
theirs | +0.008 |
rings | +0.007 |
ours | +0.006 |
are | +0.006 |
bars | +0.006 |
Neg logit contributions | |
Just | -0.006 |
ager | -0.005 |
P | -0.005 |
ce | -0.005 |
bes | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
Just | +0.099 |
age | +0.089 |
ivering | +0.088 |
P | +0.088 |
ager | +0.087 |
Neg logit contributions | |
theirs | -0.096 |
rings | -0.081 |
are | -0.073 |
wow | -0.071 |
nam | -0.069 |
Token | amaz |
Token ID | 40642 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
Just | +0.035 |
entire | +0.033 |
Lu | +0.032 |
ager | +0.032 |
P | +0.032 |
Neg logit contributions | |
theirs | -0.029 |
rings | -0.028 |
angles | -0.022 |
ours | -0.021 |
bars | -0.021 |
Token | ement |
Token ID | 972 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
theirs | +0.392 |
rings | +0.335 |
what | +0.302 |
are | +0.294 |
nam | +0.293 |
Neg logit contributions | |
Just | -0.360 |
ager | -0.330 |
age | -0.325 |
P | -0.321 |
ivering | -0.312 |
Token | . |
Token ID | 13 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
theirs | +0.048 |
rings | +0.040 |
are | +0.038 |
wow | +0.037 |
what | +0.037 |
Neg logit contributions | |
Just | -0.041 |
age | -0.036 |
ager | -0.036 |
ivering | -0.035 |
bes | -0.034 |
Token | The |
Token ID | 383 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
Just | +0.003 |
age | +0.003 |
ager | +0.003 |
bes | +0.003 |
P | +0.003 |
Neg logit contributions | |
theirs | -0.003 |
rings | -0.002 |
what | -0.002 |
are | -0.002 |
wow | -0.002 |
Token | bush |
Token ID | 24484 |
Feature activation | -2.87e-03 |
Pos logit contributions | |
ager | +0.002 |
Just | +0.002 |
age | +0.002 |
bes | +0.002 |
oster | +0.002 |
Neg logit contributions | |
theirs | -0.002 |
what | -0.002 |
rings | -0.002 |
are | -0.002 |
look | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
Just | +0.000 |
ager | +0.000 |
age | +0.000 |
P | +0.000 |
bes | +0.000 |
Neg logit contributions | |
theirs | -0.000 |
rings | -0.000 |
what | -0.000 |
are | -0.000 |
wow | -0.000 |
Token | it |
Token ID | 340 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
Just | +0.033 |
age | +0.031 |
ager | +0.031 |
P | +0.031 |
ivering | +0.030 |
Neg logit contributions | |
theirs | -0.012 |
rings | -0.008 |
what | -0.007 |
wow | -0.006 |
are | -0.006 |
Token | often |
Token ID | 1690 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
theirs | +0.023 |
what | +0.019 |
rings | +0.017 |
are | +0.016 |
their | +0.015 |
Neg logit contributions | |
Just | -0.048 |
ivering | -0.046 |
P | -0.045 |
ager | -0.045 |
bes | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
Just | +0.001 |
ager | +0.001 |
age | +0.001 |
P | +0.001 |
ivering | +0.001 |
Neg logit contributions | |
theirs | -0.001 |
rings | -0.001 |
what | -0.001 |
are | -0.001 |
wow | -0.001 |
Token | watched |
Token ID | 7342 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
theirs | +0.028 |
rings | +0.024 |
what | +0.022 |
wow | +0.021 |
are | +0.021 |
Neg logit contributions | |
Just | -0.025 |
age | -0.023 |
ager | -0.023 |
P | -0.022 |
bes | -0.021 |
Token | in |
Token ID | 287 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
Just | +0.140 |
age | +0.131 |
ager | +0.129 |
ze | +0.127 |
bes | +0.126 |
Neg logit contributions | |
theirs | -0.079 |
rings | -0.069 |
nam | -0.054 |
are | -0.053 |
wow | -0.052 |
Token | amaz |
Token ID | 40642 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
Just | +0.027 |
age | +0.026 |
entire | +0.026 |
year | +0.025 |
ager | +0.025 |
Neg logit contributions | |
rings | -0.022 |
theirs | -0.021 |
ours | -0.017 |
wow | -0.017 |
nam | -0.016 |
Token | ement |
Token ID | 972 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
theirs | +0.390 |
rings | +0.338 |
what | +0.301 |
nam | +0.297 |
are | +0.292 |
Neg logit contributions | |
Just | -0.358 |
ager | -0.331 |
age | -0.324 |
P | -0.318 |
ivering | -0.309 |
Token | whenever |
Token ID | 8797 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
theirs | +0.031 |
rings | +0.026 |
what | +0.023 |
wow | +0.023 |
nam | +0.023 |
Neg logit contributions | |
Just | -0.028 |
age | -0.025 |
ager | -0.025 |
bes | -0.024 |
ivering | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +7.26e-02 |
Pos logit contributions | |
theirs | +0.105 |
rings | +0.091 |
ours | +0.079 |
endant | +0.072 |
ours | +0.070 |
Neg logit contributions | |
Just | -0.148 |
ager | -0.139 |
P | -0.137 |
seek | -0.136 |
fire | -0.133 |
Token | door |
Token ID | 3420 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
theirs | +0.007 |
what | +0.006 |
rings | +0.006 |
are | +0.005 |
nam | +0.005 |
Neg logit contributions | |
Just | -0.007 |
age | -0.006 |
ager | -0.006 |
P | -0.006 |
bes | -0.006 |
Token | opened |
Token ID | 4721 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
Just | +0.051 |
age | +0.047 |
ager | +0.046 |
bes | +0.043 |
P | +0.043 |
Neg logit contributions | |
theirs | -0.072 |
rings | -0.061 |
what | -0.057 |
wow | -0.056 |
nam | -0.056 |
Token | take |
Token ID | 1011 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
theirs | +0.036 |
rings | +0.029 |
what | +0.027 |
are | +0.026 |
wow | +0.024 |
Neg logit contributions | |
Just | -0.062 |
ager | -0.057 |
age | -0.057 |
P | -0.057 |
ivering | -0.056 |
Token | one |
Token ID | 530 |
Feature activation | +9.32e-02 |
Pos logit contributions | |
Just | +0.002 |
age | +0.002 |
ager | +0.002 |
P | +0.002 |
bes | +0.002 |
Neg logit contributions | |
theirs | -0.001 |
rings | -0.001 |
what | -0.001 |
wow | -0.001 |
are | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
theirs | +0.008 |
rings | +0.007 |
what | +0.006 |
are | +0.006 |
wow | +0.006 |
Neg logit contributions | |
Just | -0.009 |
ager | -0.009 |
age | -0.009 |
bes | -0.008 |
P | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
theirs | +0.072 |
rings | +0.065 |
wow | +0.051 |
are | +0.048 |
what | +0.048 |
Neg logit contributions | |
Just | -0.132 |
age | -0.125 |
ager | -0.125 |
P | -0.123 |
bes | -0.120 |
Token | or |
Token ID | 393 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
Just | +0.002 |
age | +0.002 |
ager | +0.002 |
P | +0.002 |
bes | +0.002 |
Neg logit contributions | |
theirs | -0.002 |
rings | -0.002 |
what | -0.002 |
wow | -0.002 |
are | -0.002 |
Token | nam |
Token ID | 7402 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
theirs | +0.002 |
rings | +0.002 |
wow | +0.001 |
are | +0.001 |
ours | +0.001 |
Neg logit contributions | |
Just | -0.004 |
age | -0.004 |
ager | -0.004 |
P | -0.004 |
bes | -0.003 |
Token | ents |
Token ID | 658 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
theirs | +0.209 |
rings | +0.145 |
what | +0.128 |
wow | +0.117 |
are | +0.111 |
Neg logit contributions | |
Just | -0.540 |
age | -0.512 |
ager | -0.509 |
P | -0.498 |
ivering | -0.491 |
Token | outside |
Token ID | 2354 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
theirs | +0.251 |
rings | +0.217 |
wow | +0.200 |
what | +0.197 |
nam | +0.195 |
Neg logit contributions | |
Just | -0.220 |
age | -0.217 |
ager | -0.204 |
sy | -0.194 |
P | -0.193 |
Token | for |
Token ID | 329 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Just | +0.014 |
age | +0.013 |
ager | +0.013 |
P | +0.012 |
bes | +0.012 |
Neg logit contributions | |
theirs | -0.014 |
rings | -0.012 |
what | -0.011 |
wow | -0.011 |
are | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
Just | +0.015 |
age | +0.014 |
ager | +0.014 |
P | +0.014 |
bes | +0.013 |
Neg logit contributions | |
theirs | -0.008 |
rings | -0.007 |
what | -0.006 |
wow | -0.005 |
are | -0.005 |
Token | walk |
Token ID | 2513 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
theirs | +0.018 |
rings | +0.016 |
what | +0.015 |
wow | +0.014 |
nam | +0.014 |
Neg logit contributions | |
Just | -0.018 |
age | -0.016 |
bes | -0.016 |
ager | -0.016 |
ivering | -0.016 |
Token | put |
Token ID | 1234 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Just | +0.029 |
age | +0.027 |
ager | +0.027 |
bes | +0.026 |
P | +0.026 |
Neg logit contributions | |
theirs | -0.031 |
rings | -0.027 |
what | -0.024 |
wow | -0.023 |
are | -0.023 |
Token | on |
Token ID | 319 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
P | +0.124 |
Just | +0.121 |
bes | +0.118 |
ers | +0.116 |
zer | +0.116 |
Neg logit contributions | |
theirs | -0.076 |
rings | -0.070 |
wow | -0.053 |
nam | -0.052 |
expect | -0.050 |
Token | their |
Token ID | 511 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
Just | +0.002 |
bes | +0.002 |
P | +0.002 |
zer | +0.002 |
ze | +0.002 |
Neg logit contributions | |
theirs | -0.001 |
rings | -0.001 |
wow | -0.000 |
are | -0.000 |
what | -0.000 |
Token | p |
Token ID | 279 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
Just | +0.067 |
age | +0.064 |
ager | +0.062 |
ivering | +0.061 |
sy | +0.059 |
Neg logit contributions | |
theirs | -0.049 |
rings | -0.039 |
what | -0.037 |
are | -0.034 |
wow | -0.034 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
Just | +0.054 |
ager | +0.049 |
age | +0.048 |
P | +0.046 |
bes | +0.045 |
Neg logit contributions | |
theirs | -0.091 |
rings | -0.081 |
what | -0.076 |
wow | -0.072 |
are | -0.072 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
ager | +0.125 |
Just | +0.111 |
eh | +0.107 |
oster | +0.099 |
P | +0.098 |
Neg logit contributions | |
theirs | -0.340 |
rings | -0.339 |
are | -0.306 |
what | -0.300 |
eyes | -0.299 |
Token | . |
Token ID | 13 |
Feature activation | -3.03e-03 |
Pos logit contributions | |
Just | +0.430 |
ager | +0.402 |
age | +0.395 |
P | +0.395 |
bes | +0.381 |
Neg logit contributions | |
theirs | -0.397 |
rings | -0.331 |
what | -0.307 |
are | -0.289 |
wow | -0.280 |
Token | They |
Token ID | 1119 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
Just | +0.000 |
age | +0.000 |
bes | +0.000 |
amas | +0.000 |
P | +0.000 |
Neg logit contributions | |
theirs | -0.000 |
rings | -0.000 |
nam | -0.000 |
wow | -0.000 |
are | -0.000 |
Token | said |
Token ID | 531 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Just | +0.026 |
ager | +0.024 |
age | +0.024 |
P | +0.023 |
sy | +0.023 |
Neg logit contributions | |
theirs | -0.032 |
rings | -0.027 |
what | -0.025 |
wow | -0.024 |
ours | -0.023 |
Token | good |
Token ID | 922 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
Just | +0.018 |
ze | +0.017 |
age | +0.016 |
ager | +0.016 |
bes | +0.016 |
Neg logit contributions | |
theirs | -0.018 |
rings | -0.016 |
nam | -0.014 |
ours | -0.013 |
angles | -0.013 |
Token | night |
Token ID | 1755 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Just | +0.154 |
age | +0.147 |
ager | +0.146 |
P | +0.139 |
bes | +0.131 |
Neg logit contributions | |
theirs | -0.182 |
rings | -0.154 |
nam | -0.140 |
what | -0.140 |
wow | -0.137 |
Token | put |
Token ID | 1234 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Just | +0.039 |
ager | +0.038 |
age | +0.038 |
sy | +0.038 |
bes | +0.037 |
Neg logit contributions | |
theirs | -0.032 |
rings | -0.024 |
wow | -0.020 |
what | -0.020 |
nam | -0.019 |
Token | on |
Token ID | 319 |
Feature activation | -4.43e-03 |
Pos logit contributions | |
P | +0.124 |
bes | +0.116 |
ers | +0.116 |
Just | +0.114 |
sy | +0.114 |
Neg logit contributions | |
theirs | -0.085 |
rings | -0.080 |
wow | -0.068 |
expect | -0.063 |
nam | -0.057 |
Token | their |
Token ID | 511 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
Just | +0.001 |
P | +0.001 |
bes | +0.001 |
ager | +0.001 |
zer | +0.001 |
Neg logit contributions | |
theirs | -0.000 |
rings | -0.000 |
wow | -0.000 |
maybe | -0.000 |
what | -0.000 |
Token | p |
Token ID | 279 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
Just | +0.064 |
age | +0.062 |
ager | +0.061 |
ivering | +0.058 |
sy | +0.058 |
Neg logit contributions | |
theirs | -0.048 |
rings | -0.040 |
what | -0.037 |
nam | -0.035 |
are | -0.035 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
Just | +0.046 |
ager | +0.042 |
age | +0.041 |
P | +0.039 |
ivering | +0.038 |
Neg logit contributions | |
theirs | -0.091 |
rings | -0.082 |
what | -0.077 |
wow | -0.073 |
are | -0.073 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
ager | +0.131 |
Just | +0.114 |
eh | +0.113 |
mer | +0.104 |
P | +0.103 |
Neg logit contributions | |
rings | -0.323 |
theirs | -0.317 |
are | -0.299 |
what | -0.294 |
eyes | -0.288 |
Token | and |
Token ID | 290 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
Just | +0.404 |
ager | +0.377 |
P | +0.374 |
age | +0.366 |
bes | +0.357 |
Neg logit contributions | |
theirs | -0.414 |
rings | -0.349 |
what | -0.329 |
are | -0.314 |
wow | -0.299 |
Token | get |
Token ID | 651 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
Just | +0.033 |
age | +0.031 |
bes | +0.031 |
P | +0.031 |
ager | +0.030 |
Neg logit contributions | |
theirs | -0.034 |
rings | -0.028 |
wow | -0.025 |
what | -0.024 |
nam | -0.023 |
Token | into |
Token ID | 656 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
Just | +0.035 |
P | +0.034 |
sy | +0.032 |
age | +0.032 |
ze | +0.032 |
Neg logit contributions | |
theirs | -0.029 |
rings | -0.025 |
wow | -0.024 |
Sof | -0.020 |
are | -0.020 |
Token | their |
Token ID | 511 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
Just | +0.063 |
bes | +0.061 |
P | +0.059 |
ce | +0.059 |
amas | +0.057 |
Neg logit contributions | |
theirs | -0.033 |
rings | -0.031 |
wow | -0.024 |
nam | -0.021 |
are | -0.019 |
Token | beds |
Token ID | 20237 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
Just | +0.044 |
ager | +0.040 |
age | +0.040 |
P | +0.038 |
ivering | +0.037 |
Neg logit contributions | |
theirs | -0.065 |
rings | -0.057 |
what | -0.054 |
are | -0.052 |
wow | -0.051 |
Token | put |
Token ID | 1234 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Just | +0.017 |
age | +0.016 |
ager | +0.016 |
bes | +0.015 |
P | +0.015 |
Neg logit contributions | |
theirs | -0.013 |
rings | -0.011 |
what | -0.009 |
wow | -0.009 |
nam | -0.009 |
Token | on |
Token ID | 319 |
Feature activation | +8.74e-03 |
Pos logit contributions | |
Just | +0.130 |
age | +0.123 |
P | +0.122 |
ager | +0.121 |
bes | +0.119 |
Neg logit contributions | |
theirs | -0.092 |
rings | -0.076 |
what | -0.065 |
wow | -0.065 |
are | -0.062 |
Token | your |
Token ID | 534 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
theirs | +0.001 |
rings | +0.001 |
what | +0.000 |
wow | +0.000 |
are | +0.000 |
Neg logit contributions | |
Just | -0.001 |
age | -0.001 |
ager | -0.001 |
bes | -0.001 |
P | -0.001 |
Token | p |
Token ID | 279 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
Just | +0.079 |
ager | +0.078 |
ivering | +0.072 |
age | +0.072 |
sy | +0.072 |
Neg logit contributions | |
theirs | -0.051 |
rings | -0.043 |
what | -0.041 |
are | -0.038 |
nam | -0.038 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
Just | +0.043 |
ager | +0.039 |
age | +0.038 |
P | +0.036 |
ivering | +0.034 |
Neg logit contributions | |
theirs | -0.082 |
rings | -0.074 |
what | -0.069 |
are | -0.065 |
wow | -0.065 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
ager | +0.148 |
Just | +0.130 |
eh | +0.123 |
P | +0.123 |
oster | +0.121 |
Neg logit contributions | |
rings | -0.312 |
theirs | -0.310 |
are | -0.281 |
what | -0.278 |
eyes | -0.277 |
Token | ." |
Token ID | 526 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
Just | +0.429 |
ager | +0.411 |
P | +0.407 |
age | +0.391 |
bes | +0.390 |
Neg logit contributions | |
theirs | -0.386 |
rings | -0.322 |
what | -0.302 |
are | -0.290 |
their | -0.272 |
Token |
|
Token ID | 198 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
Just | +0.033 |
ager | +0.031 |
age | +0.031 |
P | +0.030 |
bes | +0.029 |
Neg logit contributions | |
theirs | -0.023 |
rings | -0.018 |
what | -0.017 |
are | -0.016 |
wow | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
ager | +0.084 |
age | +0.083 |
Just | +0.082 |
ivering | +0.081 |
bes | +0.081 |
Neg logit contributions | |
theirs | -0.063 |
what | -0.052 |
their | -0.049 |
are | -0.047 |
they | -0.046 |
Token | Tim |
Token ID | 14967 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
age | +0.057 |
amas | +0.056 |
bes | +0.055 |
lor | +0.055 |
ager | +0.054 |
Neg logit contributions | |
theirs | -0.092 |
what | -0.080 |
their | -0.079 |
they | -0.075 |
are | -0.075 |
Token | and |
Token ID | 290 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
Just | +0.066 |
age | +0.062 |
P | +0.062 |
ager | +0.061 |
ivering | +0.060 |
Neg logit contributions | |
theirs | -0.052 |
rings | -0.044 |
what | -0.043 |
are | -0.042 |
Tom | -0.038 |
Token | put |
Token ID | 1234 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Just | +0.011 |
age | +0.011 |
ager | +0.010 |
bes | +0.010 |
P | +0.010 |
Neg logit contributions | |
theirs | -0.009 |
rings | -0.007 |
what | -0.006 |
wow | -0.006 |
are | -0.006 |
Token | on |
Token ID | 319 |
Feature activation | +8.99e-02 |
Pos logit contributions | |
Just | +0.119 |
P | +0.115 |
age | +0.114 |
bes | +0.113 |
sy | +0.112 |
Neg logit contributions | |
theirs | -0.080 |
rings | -0.067 |
wow | -0.056 |
what | -0.054 |
are | -0.052 |
Token | their |
Token ID | 511 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
theirs | +0.005 |
rings | +0.004 |
wow | +0.003 |
what | +0.003 |
nam | +0.003 |
Neg logit contributions | |
Just | -0.011 |
bes | -0.011 |
P | -0.011 |
age | -0.011 |
zer | -0.010 |
Token | p |
Token ID | 279 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
Just | +0.069 |
ager | +0.065 |
age | +0.065 |
ivering | +0.063 |
P | +0.062 |
Neg logit contributions | |
theirs | -0.045 |
rings | -0.035 |
what | -0.034 |
are | -0.033 |
their | -0.032 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
Just | +0.041 |
ager | +0.037 |
age | +0.036 |
P | +0.035 |
ivering | +0.034 |
Neg logit contributions | |
theirs | -0.069 |
rings | -0.062 |
what | -0.057 |
are | -0.054 |
wow | -0.054 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
ager | +0.135 |
Just | +0.120 |
eh | +0.111 |
oster | +0.107 |
P | +0.104 |
Neg logit contributions | |
theirs | -0.314 |
rings | -0.310 |
are | -0.283 |
what | -0.280 |
eyes | -0.277 |
Token | first |
Token ID | 717 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Just | +0.442 |
ager | +0.417 |
P | +0.407 |
age | +0.405 |
bes | +0.396 |
Neg logit contributions | |
theirs | -0.374 |
rings | -0.306 |
what | -0.289 |
are | -0.270 |
their | -0.259 |
Token | . |
Token ID | 13 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
Just | +0.118 |
ager | +0.110 |
age | +0.109 |
P | +0.106 |
bes | +0.103 |
Neg logit contributions | |
theirs | -0.115 |
rings | -0.097 |
what | -0.090 |
are | -0.085 |
wow | -0.084 |
Token | They |
Token ID | 1119 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
Just | +0.006 |
age | +0.006 |
ager | +0.006 |
P | +0.006 |
bes | +0.006 |
Neg logit contributions | |
theirs | -0.004 |
rings | -0.003 |
what | -0.003 |
wow | -0.002 |
nam | -0.002 |
Token | do |
Token ID | 466 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
Just | +0.048 |
sy | +0.048 |
ager | +0.047 |
age | +0.047 |
ce | +0.045 |
Neg logit contributions | |
theirs | -0.048 |
rings | -0.037 |
wow | -0.032 |
nam | -0.031 |
what | -0.030 |
Token | what |
Token ID | 644 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
theirs | +0.038 |
rings | +0.033 |
what | +0.029 |
wow | +0.028 |
nam | +0.028 |
Neg logit contributions | |
Just | -0.036 |
age | -0.033 |
ager | -0.033 |
bes | -0.032 |
P | -0.032 |
Token | put |
Token ID | 1234 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Just | +0.024 |
bes | +0.022 |
age | +0.022 |
ager | +0.021 |
ze | +0.021 |
Neg logit contributions | |
theirs | -0.022 |
rings | -0.018 |
what | -0.015 |
wow | -0.015 |
ours | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
Just | +0.121 |
P | +0.120 |
bes | +0.119 |
age | +0.118 |
sy | +0.117 |
Neg logit contributions | |
theirs | -0.078 |
rings | -0.067 |
wow | -0.055 |
what | -0.051 |
nam | -0.050 |
Token | their |
Token ID | 511 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
theirs | +0.004 |
rings | +0.003 |
wow | +0.002 |
what | +0.002 |
nam | +0.002 |
Neg logit contributions | |
Just | -0.009 |
bes | -0.009 |
ze | -0.009 |
P | -0.009 |
ce | -0.009 |
Token | p |
Token ID | 279 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
Just | +0.062 |
age | +0.058 |
ager | +0.057 |
ivering | +0.056 |
P | +0.054 |
Neg logit contributions | |
theirs | -0.045 |
rings | -0.036 |
what | -0.034 |
are | -0.032 |
their | -0.032 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
Just | +0.042 |
ager | +0.038 |
age | +0.037 |
P | +0.036 |
ivering | +0.034 |
Neg logit contributions | |
theirs | -0.084 |
rings | -0.075 |
what | -0.070 |
wow | -0.067 |
are | -0.067 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
ager | +0.116 |
Just | +0.107 |
eh | +0.104 |
P | +0.095 |
oster | +0.090 |
Neg logit contributions | |
theirs | -0.324 |
rings | -0.317 |
are | -0.294 |
what | -0.288 |
their | -0.284 |
Token | . |
Token ID | 13 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Just | +0.438 |
ager | +0.413 |
P | +0.409 |
age | +0.399 |
bes | +0.392 |
Neg logit contributions | |
theirs | -0.373 |
rings | -0.307 |
what | -0.289 |
are | -0.271 |
their | -0.260 |
Token | They |
Token ID | 1119 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
Just | +0.016 |
age | +0.015 |
ager | +0.015 |
bes | +0.014 |
P | +0.014 |
Neg logit contributions | |
theirs | -0.011 |
rings | -0.009 |
what | -0.008 |
wow | -0.007 |
nam | -0.007 |
Token | hug |
Token ID | 16225 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Just | +0.040 |
age | +0.039 |
ager | +0.038 |
sy | +0.038 |
bes | +0.037 |
Neg logit contributions | |
theirs | -0.037 |
rings | -0.029 |
nam | -0.025 |
what | -0.024 |
wow | -0.024 |
Token | their |
Token ID | 511 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
theirs | +0.009 |
rings | +0.007 |
wow | +0.005 |
what | +0.005 |
nam | +0.005 |
Neg logit contributions | |
Just | -0.018 |
age | -0.017 |
ager | -0.017 |
bes | -0.016 |
P | -0.016 |
Token | mom |
Token ID | 1995 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
Just | +0.064 |
age | +0.060 |
ager | +0.059 |
P | +0.058 |
ivering | +0.057 |
Neg logit contributions | |
theirs | -0.047 |
rings | -0.039 |
what | -0.036 |
are | -0.034 |
wow | -0.034 |
Token | put |
Token ID | 1234 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
bes | +0.024 |
Just | +0.023 |
age | +0.023 |
ager | +0.023 |
P | +0.022 |
Neg logit contributions | |
theirs | -0.021 |
rings | -0.019 |
ours | -0.015 |
wow | -0.015 |
what | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
P | +0.116 |
ers | +0.112 |
Just | +0.108 |
bes | +0.108 |
co | +0.107 |
Neg logit contributions | |
theirs | -0.071 |
rings | -0.068 |
wow | -0.056 |
expect | -0.052 |
are | -0.050 |
Token | their |
Token ID | 511 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
theirs | +0.005 |
rings | +0.005 |
maybe | +0.004 |
wow | +0.004 |
are | +0.003 |
Neg logit contributions | |
Just | -0.010 |
bes | -0.009 |
P | -0.009 |
zer | -0.009 |
ze | -0.009 |
Token | p |
Token ID | 279 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
Just | +0.068 |
age | +0.064 |
ager | +0.063 |
ivering | +0.063 |
P | +0.061 |
Neg logit contributions | |
theirs | -0.042 |
rings | -0.031 |
what | -0.029 |
are | -0.027 |
their | -0.027 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
Just | +0.042 |
age | +0.038 |
ager | +0.037 |
P | +0.035 |
bes | +0.034 |
Neg logit contributions | |
theirs | -0.088 |
rings | -0.078 |
what | -0.074 |
wow | -0.071 |
are | -0.071 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
ager | +0.118 |
Just | +0.116 |
eh | +0.106 |
age | +0.094 |
P | +0.093 |
Neg logit contributions | |
theirs | -0.324 |
rings | -0.306 |
are | -0.289 |
what | -0.282 |
their | -0.279 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e-03 |
Pos logit contributions | |
Just | +0.450 |
ager | +0.423 |
P | +0.420 |
age | +0.410 |
bes | +0.403 |
Neg logit contributions | |
theirs | -0.358 |
rings | -0.291 |
what | -0.273 |
are | -0.255 |
their | -0.248 |
Token | They |
Token ID | 1119 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
Just | +0.000 |
age | +0.000 |
P | +0.000 |
bes | +0.000 |
ager | +0.000 |
Neg logit contributions | |
theirs | -0.000 |
rings | -0.000 |
what | -0.000 |
wow | -0.000 |
nam | -0.000 |
Token | hug |
Token ID | 16225 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
ager | +0.036 |
age | +0.036 |
sy | +0.036 |
Just | +0.036 |
oster | +0.035 |
Neg logit contributions | |
theirs | -0.031 |
rings | -0.026 |
nam | -0.021 |
wow | -0.020 |
ours | -0.020 |
Token | their |
Token ID | 511 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
theirs | +0.012 |
rings | +0.009 |
what | +0.008 |
wow | +0.008 |
are | +0.007 |
Neg logit contributions | |
Just | -0.020 |
age | -0.019 |
ager | -0.019 |
P | -0.019 |
bes | -0.018 |
Token | mom |
Token ID | 1995 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
Just | +0.066 |
age | +0.063 |
ager | +0.061 |
ivering | +0.060 |
P | +0.060 |
Neg logit contributions | |
theirs | -0.045 |
rings | -0.035 |
what | -0.034 |
are | -0.031 |
their | -0.031 |
Token | them |
Token ID | 606 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
theirs | +0.005 |
rings | +0.004 |
wow | +0.004 |
nam | +0.003 |
what | +0.003 |
Neg logit contributions | |
Just | -0.010 |
age | -0.010 |
P | -0.010 |
ager | -0.009 |
sy | -0.009 |
Token | towels |
Token ID | 38494 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
Just | +0.065 |
ager | +0.061 |
age | +0.061 |
P | +0.061 |
sy | +0.058 |
Neg logit contributions | |
theirs | -0.045 |
rings | -0.039 |
wow | -0.033 |
what | -0.032 |
nam | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
Just | +0.141 |
age | +0.129 |
ager | +0.129 |
P | +0.124 |
bes | +0.121 |
Neg logit contributions | |
theirs | -0.195 |
rings | -0.169 |
what | -0.158 |
are | -0.151 |
wow | -0.151 |
Token | p |
Token ID | 279 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
Just | +0.031 |
bes | +0.029 |
age | +0.028 |
P | +0.028 |
ager | +0.028 |
Neg logit contributions | |
theirs | -0.034 |
rings | -0.030 |
wow | -0.026 |
what | -0.025 |
nam | -0.024 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
Just | +0.073 |
bes | +0.072 |
co | +0.071 |
amas | +0.070 |
ivering | +0.069 |
Neg logit contributions | |
theirs | -0.050 |
rings | -0.041 |
wow | -0.040 |
nam | -0.039 |
maybe | -0.037 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
eh | +0.116 |
ager | +0.112 |
Just | +0.112 |
P | +0.107 |
age | +0.098 |
Neg logit contributions | |
theirs | -0.347 |
rings | -0.321 |
are | -0.318 |
what | -0.308 |
their | -0.299 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Just | +0.393 |
ager | +0.364 |
age | +0.360 |
P | +0.355 |
bes | +0.343 |
Neg logit contributions | |
theirs | -0.411 |
rings | -0.346 |
what | -0.324 |
are | -0.308 |
wow | -0.302 |
Token | They |
Token ID | 1119 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
Just | +0.012 |
age | +0.011 |
P | +0.011 |
ager | +0.011 |
bes | +0.011 |
Neg logit contributions | |
theirs | -0.009 |
rings | -0.008 |
what | -0.007 |
wow | -0.007 |
nam | -0.007 |
Token | give |
Token ID | 1577 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
ager | +0.024 |
Just | +0.023 |
age | +0.023 |
sy | +0.023 |
bes | +0.023 |
Neg logit contributions | |
theirs | -0.019 |
rings | -0.016 |
nam | -0.013 |
wow | -0.012 |
what | -0.012 |
Token | them |
Token ID | 606 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
theirs | +0.003 |
rings | +0.002 |
wow | +0.002 |
what | +0.002 |
nam | +0.002 |
Neg logit contributions | |
Just | -0.006 |
age | -0.006 |
P | -0.005 |
ager | -0.005 |
sy | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
Just | +0.065 |
P | +0.061 |
age | +0.061 |
ager | +0.061 |
sy | +0.059 |
Neg logit contributions | |
theirs | -0.048 |
rings | -0.041 |
wow | -0.035 |
what | -0.034 |
nam | -0.034 |
Token | puts |
Token ID | 7584 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
theirs | +0.007 |
rings | +0.006 |
what | +0.005 |
are | +0.005 |
wow | +0.005 |
Neg logit contributions | |
Just | -0.010 |
age | -0.010 |
ager | -0.010 |
P | -0.009 |
bes | -0.009 |
Token | on |
Token ID | 319 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
P | +0.024 |
Just | +0.024 |
age | +0.022 |
bes | +0.021 |
ager | +0.021 |
Neg logit contributions | |
theirs | -0.030 |
rings | -0.026 |
wow | -0.024 |
what | -0.023 |
are | -0.023 |
Token | her |
Token ID | 607 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
theirs | +0.003 |
rings | +0.002 |
wow | +0.002 |
what | +0.002 |
are | +0.002 |
Neg logit contributions | |
Just | -0.005 |
P | -0.005 |
bes | -0.005 |
age | -0.004 |
ager | -0.004 |
Token | p |
Token ID | 279 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
Just | +0.025 |
ager | +0.024 |
age | +0.024 |
ivering | +0.023 |
sy | +0.023 |
Neg logit contributions | |
theirs | -0.020 |
rings | -0.017 |
what | -0.016 |
are | -0.015 |
nam | -0.015 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
Just | +0.043 |
ager | +0.039 |
age | +0.038 |
P | +0.036 |
bes | +0.035 |
Neg logit contributions | |
theirs | -0.087 |
rings | -0.078 |
what | -0.073 |
wow | -0.070 |
are | -0.070 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
ager | +0.125 |
mer | +0.108 |
eh | +0.108 |
oster | +0.104 |
fire | +0.100 |
Neg logit contributions | |
rings | -0.313 |
theirs | -0.306 |
what | -0.285 |
are | -0.284 |
eyes | -0.277 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Just | +0.381 |
ager | +0.360 |
P | +0.349 |
age | +0.348 |
bes | +0.338 |
Neg logit contributions | |
theirs | -0.414 |
rings | -0.354 |
what | -0.334 |
are | -0.316 |
wow | -0.306 |
Token | They |
Token ID | 1119 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
theirs | +0.010 |
rings | +0.008 |
what | +0.007 |
wow | +0.007 |
nam | +0.007 |
Neg logit contributions | |
Just | -0.012 |
age | -0.011 |
amas | -0.011 |
bes | -0.011 |
P | -0.011 |
Token | are |
Token ID | 389 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
age | +0.013 |
Just | +0.012 |
sy | +0.012 |
P | +0.012 |
bes | +0.012 |
Neg logit contributions | |
theirs | -0.015 |
rings | -0.011 |
wow | -0.010 |
what | -0.010 |
nam | -0.010 |
Token | tight |
Token ID | 5381 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
theirs | +0.147 |
rings | +0.124 |
what | +0.112 |
wow | +0.107 |
are | +0.106 |
Neg logit contributions | |
Just | -0.168 |
age | -0.157 |
ager | -0.155 |
P | -0.152 |
bes | -0.150 |
Token | and |
Token ID | 290 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
theirs | +0.004 |
rings | +0.003 |
what | +0.003 |
are | +0.003 |
their | +0.003 |
Neg logit contributions | |
Just | -0.004 |
ager | -0.004 |
P | -0.004 |
age | -0.003 |
oster | -0.003 |
Token | put |
Token ID | 1234 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
theirs | +0.001 |
rings | +0.001 |
what | +0.001 |
wow | +0.001 |
are | +0.001 |
Neg logit contributions | |
Just | -0.001 |
age | -0.001 |
ager | -0.001 |
bes | -0.001 |
P | -0.001 |
Token | on |
Token ID | 319 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
Just | +0.128 |
P | +0.123 |
age | +0.122 |
ager | +0.119 |
bes | +0.118 |
Neg logit contributions | |
theirs | -0.069 |
rings | -0.054 |
wow | -0.044 |
what | -0.043 |
nam | -0.041 |
Token | your |
Token ID | 534 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
theirs | +0.014 |
rings | +0.011 |
what | +0.010 |
wow | +0.009 |
are | +0.009 |
Neg logit contributions | |
Just | -0.018 |
age | -0.017 |
ager | -0.016 |
P | -0.016 |
bes | -0.016 |
Token | p |
Token ID | 279 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
Just | +0.057 |
ager | +0.054 |
age | +0.053 |
P | +0.051 |
sy | +0.050 |
Neg logit contributions | |
theirs | -0.045 |
rings | -0.037 |
what | -0.035 |
are | -0.033 |
nam | -0.032 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
Just | +0.036 |
ager | +0.032 |
age | +0.032 |
P | +0.030 |
bes | +0.029 |
Neg logit contributions | |
theirs | -0.075 |
rings | -0.067 |
what | -0.063 |
wow | -0.061 |
are | -0.061 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
ager | +0.138 |
Just | +0.125 |
eh | +0.122 |
oster | +0.115 |
P | +0.114 |
Neg logit contributions | |
rings | -0.294 |
theirs | -0.285 |
are | -0.265 |
eyes | -0.254 |
look | -0.253 |
Token | ." |
Token ID | 526 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Just | +0.429 |
ager | +0.408 |
P | +0.405 |
bes | +0.391 |
age | +0.390 |
Neg logit contributions | |
theirs | -0.373 |
rings | -0.304 |
what | -0.289 |
are | -0.278 |
their | -0.262 |
Token |
|
Token ID | 198 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
Just | +0.016 |
ager | +0.015 |
age | +0.015 |
P | +0.015 |
bes | +0.014 |
Neg logit contributions | |
theirs | -0.010 |
rings | -0.008 |
what | -0.007 |
are | -0.006 |
wow | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
Just | +0.041 |
ager | +0.039 |
age | +0.039 |
P | +0.037 |
ivering | +0.037 |
Neg logit contributions | |
theirs | -0.040 |
rings | -0.033 |
what | -0.032 |
are | -0.030 |
wow | -0.029 |
Token | L |
Token ID | 43 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
age | +0.038 |
ager | +0.036 |
lor | +0.035 |
amas | +0.034 |
unk | +0.034 |
Neg logit contributions | |
theirs | -0.047 |
what | -0.043 |
are | -0.041 |
their | -0.041 |
nam | -0.040 |
Token | ily |
Token ID | 813 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
theirs | +0.113 |
rings | +0.089 |
what | +0.088 |
are | +0.083 |
wow | +0.078 |
Neg logit contributions | |
Just | -0.118 |
age | -0.112 |
ager | -0.108 |
P | -0.105 |
bes | -0.105 |
Token | They |
Token ID | 1119 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
theirs | +0.005 |
rings | +0.004 |
what | +0.004 |
wow | +0.004 |
nam | +0.004 |
Neg logit contributions | |
Just | -0.006 |
age | -0.005 |
ager | -0.005 |
P | -0.005 |
bes | -0.005 |
Token | were |
Token ID | 547 |
Feature activation | +9.19e-01 |
Pos logit contributions | |
Just | +0.011 |
age | +0.011 |
ager | +0.011 |
sy | +0.011 |
co | +0.010 |
Neg logit contributions | |
theirs | -0.011 |
rings | -0.009 |
wow | -0.008 |
ours | -0.008 |
ours | -0.008 |
Token | wearing |
Token ID | 5762 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
theirs | +0.084 |
rings | +0.076 |
wow | +0.069 |
are | +0.066 |
what | +0.066 |
Neg logit contributions | |
Just | -0.080 |
age | -0.074 |
bes | -0.072 |
sy | -0.072 |
ivering | -0.072 |
Token | p |
Token ID | 279 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
bes | +0.078 |
Just | +0.073 |
ze | +0.072 |
age | +0.071 |
P | +0.070 |
Neg logit contributions | |
theirs | -0.058 |
rings | -0.053 |
ours | -0.043 |
wow | -0.043 |
maybe | -0.041 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
Just | +0.041 |
bes | +0.036 |
ager | +0.035 |
age | +0.035 |
ivering | +0.035 |
Neg logit contributions | |
theirs | -0.079 |
rings | -0.068 |
what | -0.065 |
wow | -0.065 |
are | -0.064 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
ager | +0.106 |
Just | +0.097 |
eh | +0.093 |
oster | +0.092 |
age | +0.092 |
Neg logit contributions | |
theirs | -0.332 |
rings | -0.320 |
are | -0.307 |
what | -0.302 |
wow | -0.293 |
Token | . |
Token ID | 13 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
Just | +0.404 |
ager | +0.376 |
P | +0.370 |
age | +0.369 |
bes | +0.352 |
Neg logit contributions | |
theirs | -0.395 |
rings | -0.331 |
what | -0.312 |
are | -0.296 |
wow | -0.286 |
Token | And |
Token ID | 843 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
theirs | +0.002 |
rings | +0.001 |
what | +0.001 |
wow | +0.001 |
nam | +0.001 |
Neg logit contributions | |
Just | -0.002 |
age | -0.001 |
ager | -0.001 |
P | -0.001 |
bes | -0.001 |
Token | they |
Token ID | 484 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
theirs | +0.001 |
rings | +0.001 |
wow | +0.001 |
nam | +0.001 |
ours | +0.001 |
Neg logit contributions | |
Just | -0.002 |
bes | -0.002 |
ager | -0.002 |
age | -0.002 |
rd | -0.002 |
Token | were |
Token ID | 547 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
Just | +0.026 |
ager | +0.025 |
age | +0.025 |
sy | +0.024 |
P | +0.024 |
Neg logit contributions | |
theirs | -0.024 |
rings | -0.020 |
what | -0.017 |
wow | -0.017 |
nam | -0.016 |
Token | not |
Token ID | 407 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
theirs | +0.080 |
rings | +0.067 |
what | +0.061 |
wow | +0.058 |
are | +0.058 |
Neg logit contributions | |
Just | -0.089 |
age | -0.083 |
ager | -0.083 |
P | -0.080 |
bes | -0.079 |
Token | put |
Token ID | 1234 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Just | +0.012 |
age | +0.012 |
bes | +0.011 |
ager | +0.011 |
P | +0.011 |
Neg logit contributions | |
theirs | -0.013 |
rings | -0.011 |
what | -0.010 |
wow | -0.010 |
are | -0.010 |
Token | on |
Token ID | 319 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
bes | +0.112 |
age | +0.111 |
Just | +0.110 |
ers | +0.110 |
P | +0.109 |
Neg logit contributions | |
theirs | -0.065 |
rings | -0.057 |
wow | -0.046 |
nam | -0.043 |
expect | -0.041 |
Token | their |
Token ID | 511 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
theirs | +0.010 |
rings | +0.008 |
wow | +0.005 |
what | +0.005 |
nam | +0.005 |
Neg logit contributions | |
Just | -0.027 |
bes | -0.027 |
age | -0.026 |
ze | -0.026 |
zer | -0.026 |
Token | p |
Token ID | 279 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
Just | +0.036 |
ager | +0.034 |
age | +0.033 |
P | +0.032 |
ivering | +0.032 |
Neg logit contributions | |
theirs | -0.031 |
rings | -0.025 |
what | -0.024 |
are | -0.023 |
wow | -0.022 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
Just | +0.038 |
ager | +0.035 |
age | +0.033 |
P | +0.033 |
ivering | +0.031 |
Neg logit contributions | |
theirs | -0.066 |
rings | -0.059 |
what | -0.055 |
wow | -0.052 |
are | -0.052 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
ager | +0.134 |
Just | +0.122 |
eh | +0.114 |
P | +0.113 |
oster | +0.102 |
Neg logit contributions | |
theirs | -0.316 |
rings | -0.314 |
are | -0.288 |
what | -0.279 |
their | -0.273 |
Token | . |
Token ID | 13 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
Just | +0.414 |
ager | +0.389 |
P | +0.381 |
age | +0.375 |
bes | +0.366 |
Neg logit contributions | |
theirs | -0.382 |
rings | -0.320 |
what | -0.299 |
are | -0.282 |
their | -0.269 |
Token | They |
Token ID | 1119 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
theirs | +0.006 |
rings | +0.005 |
wow | +0.004 |
what | +0.004 |
nam | +0.004 |
Neg logit contributions | |
Just | -0.008 |
age | -0.007 |
bes | -0.007 |
P | -0.007 |
amas | -0.007 |
Token | climbed |
Token ID | 19952 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
Just | +0.016 |
age | +0.015 |
ager | +0.015 |
sy | +0.015 |
P | +0.015 |
Neg logit contributions | |
theirs | -0.019 |
rings | -0.016 |
what | -0.014 |
wow | -0.014 |
ours | -0.013 |
Token | into |
Token ID | 656 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
theirs | +0.047 |
rings | +0.040 |
what | +0.037 |
wow | +0.035 |
are | +0.035 |
Neg logit contributions | |
Just | -0.042 |
age | -0.039 |
ager | -0.039 |
P | -0.037 |
bes | -0.037 |
Token | their |
Token ID | 511 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
bes | +0.044 |
Just | +0.043 |
ce | +0.041 |
Lu | +0.041 |
co | +0.040 |
Neg logit contributions | |
theirs | -0.029 |
rings | -0.027 |
wow | -0.022 |
ours | -0.018 |
nam | -0.018 |
Token | put |
Token ID | 1234 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
bes | +0.021 |
Just | +0.021 |
age | +0.020 |
ager | +0.019 |
P | +0.019 |
Neg logit contributions | |
theirs | -0.022 |
rings | -0.018 |
what | -0.016 |
ours | -0.016 |
wow | -0.016 |
Token | on |
Token ID | 319 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
P | +0.111 |
ers | +0.108 |
bes | +0.107 |
sy | +0.103 |
age | +0.101 |
Neg logit contributions | |
theirs | -0.068 |
rings | -0.065 |
wow | -0.057 |
expect | -0.053 |
bars | -0.051 |
Token | their |
Token ID | 511 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
theirs | +0.006 |
rings | +0.006 |
expect | +0.004 |
wow | +0.004 |
maybe | +0.004 |
Neg logit contributions | |
bes | -0.013 |
P | -0.012 |
Just | -0.012 |
zer | -0.012 |
ze | -0.012 |
Token | p |
Token ID | 279 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
Just | +0.053 |
ager | +0.050 |
age | +0.050 |
P | +0.048 |
ivering | +0.048 |
Neg logit contributions | |
theirs | -0.038 |
rings | -0.031 |
what | -0.028 |
are | -0.026 |
wow | -0.026 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
Just | +0.038 |
age | +0.035 |
ager | +0.034 |
bes | +0.033 |
P | +0.033 |
Neg logit contributions | |
theirs | -0.066 |
rings | -0.057 |
what | -0.055 |
wow | -0.053 |
are | -0.052 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
ager | +0.121 |
Just | +0.112 |
oster | +0.093 |
eh | +0.092 |
P | +0.088 |
Neg logit contributions | |
rings | -0.337 |
theirs | -0.336 |
are | -0.303 |
look | -0.294 |
what | -0.293 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Just | +0.435 |
ager | +0.409 |
P | +0.403 |
age | +0.397 |
bes | +0.390 |
Neg logit contributions | |
theirs | -0.361 |
rings | -0.300 |
what | -0.277 |
are | -0.261 |
their | -0.251 |
Token | They |
Token ID | 1119 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
Just | +0.018 |
age | +0.017 |
ager | +0.017 |
P | +0.016 |
bes | +0.016 |
Neg logit contributions | |
theirs | -0.010 |
rings | -0.008 |
what | -0.007 |
wow | -0.007 |
nam | -0.007 |
Token | each |
Token ID | 1123 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
Just | +0.037 |
sy | +0.036 |
ager | +0.036 |
age | +0.035 |
bes | +0.034 |
Neg logit contributions | |
theirs | -0.038 |
rings | -0.029 |
wow | -0.025 |
what | -0.024 |
nam | -0.024 |
Token | pick |
Token ID | 2298 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
Just | +0.059 |
age | +0.055 |
ager | +0.055 |
P | +0.053 |
bes | +0.052 |
Neg logit contributions | |
theirs | -0.046 |
rings | -0.038 |
what | -0.034 |
wow | -0.033 |
nam | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
P | +0.007 |
Just | +0.007 |
age | +0.007 |
sy | +0.007 |
ager | +0.007 |
Neg logit contributions | |
theirs | -0.009 |
rings | -0.008 |
nam | -0.007 |
wow | -0.007 |
what | -0.007 |
Token | put |
Token ID | 1234 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Just | +0.015 |
age | +0.014 |
ager | +0.014 |
P | +0.014 |
bes | +0.014 |
Neg logit contributions | |
theirs | -0.015 |
rings | -0.012 |
what | -0.011 |
wow | -0.011 |
are | -0.011 |
Token | on |
Token ID | 319 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Just | +0.131 |
P | +0.127 |
age | +0.125 |
bes | +0.123 |
sy | +0.119 |
Neg logit contributions | |
theirs | -0.073 |
rings | -0.058 |
wow | -0.048 |
what | -0.046 |
are | -0.045 |
Token | her |
Token ID | 607 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
theirs | +0.007 |
rings | +0.005 |
what | +0.004 |
wow | +0.004 |
are | +0.004 |
Neg logit contributions | |
Just | -0.013 |
bes | -0.012 |
P | -0.012 |
age | -0.012 |
ager | -0.012 |
Token | p |
Token ID | 279 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
Just | +0.034 |
ager | +0.032 |
age | +0.031 |
ivering | +0.030 |
sy | +0.030 |
Neg logit contributions | |
theirs | -0.024 |
rings | -0.020 |
what | -0.019 |
are | -0.018 |
nam | -0.018 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
Just | +0.035 |
ager | +0.032 |
age | +0.031 |
P | +0.030 |
bes | +0.028 |
Neg logit contributions | |
theirs | -0.072 |
rings | -0.064 |
what | -0.060 |
wow | -0.058 |
are | -0.057 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
ager | +0.132 |
Just | +0.117 |
eh | +0.107 |
P | +0.103 |
oster | +0.100 |
Neg logit contributions | |
rings | -0.311 |
theirs | -0.306 |
are | -0.277 |
what | -0.269 |
eyes | -0.269 |
Token | . |
Token ID | 13 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
Just | +0.429 |
ager | +0.408 |
P | +0.396 |
age | +0.393 |
bes | +0.386 |
Neg logit contributions | |
theirs | -0.359 |
rings | -0.302 |
what | -0.280 |
are | -0.260 |
their | -0.247 |
Token | Mom |
Token ID | 11254 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
Just | +0.023 |
age | +0.021 |
P | +0.021 |
amas | +0.021 |
bes | +0.020 |
Neg logit contributions | |
theirs | -0.018 |
rings | -0.015 |
wow | -0.013 |
what | -0.013 |
nam | -0.013 |
Token | my |
Token ID | 1820 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
Just | +0.019 |
ager | +0.017 |
age | +0.017 |
P | +0.017 |
bes | +0.017 |
Neg logit contributions | |
theirs | -0.016 |
rings | -0.014 |
what | -0.013 |
are | -0.012 |
wow | -0.012 |
Token | read |
Token ID | 1100 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
Just | +0.026 |
P | +0.025 |
ager | +0.024 |
age | +0.024 |
ivering | +0.024 |
Neg logit contributions | |
theirs | -0.020 |
rings | -0.017 |
what | -0.016 |
are | -0.015 |
wow | -0.014 |
Token | her |
Token ID | 607 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
theirs | +0.019 |
rings | +0.016 |
wow | +0.013 |
nam | +0.012 |
what | +0.012 |
Neg logit contributions | |
Just | -0.033 |
age | -0.031 |
P | -0.031 |
bes | -0.031 |
co | -0.030 |
Token | put |
Token ID | 1234 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Just | +0.015 |
age | +0.014 |
ager | +0.013 |
bes | +0.013 |
P | +0.013 |
Neg logit contributions | |
theirs | -0.015 |
rings | -0.013 |
what | -0.012 |
wow | -0.011 |
are | -0.011 |
Token | on |
Token ID | 319 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Just | +0.115 |
age | +0.112 |
P | +0.112 |
bes | +0.109 |
sy | +0.107 |
Neg logit contributions | |
theirs | -0.082 |
rings | -0.069 |
wow | -0.059 |
what | -0.055 |
nam | -0.054 |
Token | their |
Token ID | 511 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
theirs | +0.008 |
rings | +0.006 |
wow | +0.004 |
what | +0.004 |
nam | +0.004 |
Neg logit contributions | |
Just | -0.019 |
bes | -0.019 |
age | -0.018 |
P | -0.018 |
ze | -0.018 |
Token | p |
Token ID | 279 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
Just | +0.054 |
ager | +0.052 |
age | +0.051 |
ivering | +0.049 |
P | +0.049 |
Neg logit contributions | |
theirs | -0.036 |
rings | -0.029 |
what | -0.028 |
are | -0.027 |
their | -0.026 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
Just | +0.044 |
ager | +0.042 |
age | +0.039 |
P | +0.039 |
sy | +0.037 |
Neg logit contributions | |
theirs | -0.073 |
rings | -0.066 |
what | -0.061 |
ours | -0.058 |
are | -0.057 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
ager | +0.137 |
Just | +0.116 |
mer | +0.113 |
eh | +0.112 |
P | +0.111 |
Neg logit contributions | |
rings | -0.297 |
theirs | -0.293 |
are | -0.270 |
what | -0.267 |
eyes | -0.263 |
Token | . |
Token ID | 13 |
Feature activation | +2.08e-04 |
Pos logit contributions | |
Just | +0.425 |
ager | +0.401 |
P | +0.396 |
age | +0.387 |
ivering | +0.378 |
Neg logit contributions | |
theirs | -0.368 |
rings | -0.306 |
what | -0.286 |
are | -0.269 |
their | -0.257 |
Token | Their |
Token ID | 5334 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
theirs | +0.000 |
rings | +0.000 |
nam | +0.000 |
wow | +0.000 |
are | +0.000 |
Neg logit contributions | |
Just | -0.000 |
age | -0.000 |
bes | -0.000 |
amas | -0.000 |
P | -0.000 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
Just | +0.038 |
ager | +0.036 |
age | +0.036 |
P | +0.035 |
ivering | +0.034 |
Neg logit contributions | |
theirs | -0.023 |
rings | -0.019 |
what | -0.017 |
are | -0.016 |
wow | -0.015 |
Token | tucked |
Token ID | 29779 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
theirs | +0.003 |
rings | +0.002 |
what | +0.002 |
are | +0.002 |
wow | +0.002 |
Neg logit contributions | |
Just | -0.004 |
P | -0.004 |
age | -0.004 |
ager | -0.004 |
ivering | -0.004 |
Token | them |
Token ID | 606 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
theirs | +0.013 |
rings | +0.011 |
wow | +0.009 |
are | +0.008 |
what | +0.008 |
Neg logit contributions | |
Just | -0.028 |
P | -0.027 |
age | -0.026 |
ager | -0.026 |
bes | -0.026 |
Token | put |
Token ID | 1234 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Just | +0.024 |
bes | +0.023 |
age | +0.023 |
ager | +0.022 |
ze | +0.022 |
Neg logit contributions | |
theirs | -0.021 |
rings | -0.018 |
what | -0.015 |
wow | -0.015 |
ours | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Just | +0.120 |
P | +0.120 |
bes | +0.119 |
age | +0.118 |
co | +0.118 |
Neg logit contributions | |
theirs | -0.073 |
rings | -0.063 |
wow | -0.053 |
what | -0.049 |
nam | -0.046 |
Token | their |
Token ID | 511 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
theirs | +0.006 |
rings | +0.005 |
wow | +0.003 |
maybe | +0.003 |
what | +0.003 |
Neg logit contributions | |
Just | -0.013 |
bes | -0.013 |
P | -0.012 |
co | -0.012 |
ze | -0.012 |
Token | p |
Token ID | 279 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
Just | +0.040 |
age | +0.037 |
ager | +0.037 |
P | +0.036 |
ivering | +0.035 |
Neg logit contributions | |
theirs | -0.032 |
rings | -0.026 |
what | -0.024 |
are | -0.023 |
wow | -0.023 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
Just | +0.036 |
age | +0.032 |
ager | +0.032 |
P | +0.030 |
bes | +0.029 |
Neg logit contributions | |
theirs | -0.079 |
rings | -0.071 |
what | -0.067 |
wow | -0.064 |
are | -0.064 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
ager | +0.118 |
Just | +0.109 |
eh | +0.105 |
P | +0.098 |
oster | +0.088 |
Neg logit contributions | |
theirs | -0.326 |
rings | -0.318 |
are | -0.298 |
what | -0.289 |
their | -0.285 |
Token | . |
Token ID | 13 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
Just | +0.423 |
ager | +0.399 |
P | +0.391 |
age | +0.386 |
bes | +0.375 |
Neg logit contributions | |
theirs | -0.371 |
rings | -0.306 |
what | -0.287 |
are | -0.269 |
their | -0.260 |
Token | They |
Token ID | 1119 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
theirs | +0.007 |
rings | +0.007 |
nam | +0.006 |
what | +0.006 |
wow | +0.005 |
Neg logit contributions | |
Just | -0.010 |
age | -0.009 |
bes | -0.008 |
P | -0.008 |
ager | -0.008 |
Token | get |
Token ID | 651 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
age | +0.015 |
Just | +0.015 |
sy | +0.015 |
ager | +0.015 |
bes | +0.014 |
Neg logit contributions | |
theirs | -0.014 |
rings | -0.011 |
wow | -0.010 |
nam | -0.010 |
what | -0.009 |
Token | into |
Token ID | 656 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
Just | +0.024 |
P | +0.022 |
age | +0.022 |
sy | +0.022 |
ze | +0.021 |
Neg logit contributions | |
theirs | -0.026 |
rings | -0.023 |
wow | -0.022 |
what | -0.019 |
Sof | -0.019 |
Token | their |
Token ID | 511 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
Just | +0.040 |
bes | +0.040 |
amas | +0.037 |
ce | +0.037 |
Now | +0.037 |
Neg logit contributions | |
theirs | -0.039 |
rings | -0.038 |
wow | -0.033 |
nam | -0.028 |
angles | -0.027 |
Token | put |
Token ID | 1234 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Just | +0.008 |
age | +0.008 |
ager | +0.008 |
P | +0.007 |
bes | +0.007 |
Neg logit contributions | |
theirs | -0.007 |
rings | -0.005 |
what | -0.005 |
wow | -0.005 |
are | -0.005 |
Token | on |
Token ID | 319 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Just | +0.135 |
P | +0.127 |
ager | +0.127 |
age | +0.127 |
bes | +0.125 |
Neg logit contributions | |
theirs | -0.060 |
rings | -0.045 |
what | -0.035 |
wow | -0.034 |
nam | -0.032 |
Token | your |
Token ID | 534 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
theirs | +0.008 |
rings | +0.007 |
what | +0.006 |
wow | +0.005 |
are | +0.005 |
Neg logit contributions | |
Just | -0.017 |
age | -0.016 |
ager | -0.016 |
P | -0.015 |
bes | -0.015 |
Token | p |
Token ID | 279 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
Just | +0.057 |
age | +0.057 |
ager | +0.057 |
lor | +0.052 |
ivering | +0.052 |
Neg logit contributions | |
theirs | -0.037 |
their | -0.029 |
what | -0.029 |
are | -0.028 |
look | -0.027 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
Just | +0.043 |
ager | +0.041 |
age | +0.039 |
P | +0.037 |
ivering | +0.035 |
Neg logit contributions | |
theirs | -0.069 |
rings | -0.062 |
what | -0.057 |
ours | -0.056 |
are | -0.054 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
ager | +0.143 |
Just | +0.127 |
eh | +0.127 |
age | +0.113 |
oster | +0.107 |
Neg logit contributions | |
theirs | -0.280 |
rings | -0.267 |
are | -0.255 |
ours | -0.251 |
eyes | -0.250 |
Token | . |
Token ID | 13 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
Just | +0.451 |
ager | +0.433 |
P | +0.419 |
bes | +0.411 |
age | +0.411 |
Neg logit contributions | |
theirs | -0.339 |
rings | -0.270 |
what | -0.262 |
are | -0.250 |
their | -0.233 |
Token | OK |
Token ID | 7477 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
theirs | +0.020 |
rings | +0.017 |
what | +0.015 |
wow | +0.014 |
are | +0.014 |
Neg logit contributions | |
Just | -0.026 |
ager | -0.025 |
age | -0.024 |
P | -0.024 |
bes | -0.023 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Just | +0.138 |
ager | +0.132 |
age | +0.128 |
bes | +0.128 |
P | +0.127 |
Neg logit contributions | |
theirs | -0.099 |
what | -0.082 |
rings | -0.082 |
are | -0.074 |
wow | -0.068 |
Token |
|
Token ID | 198 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
theirs | +0.019 |
rings | +0.017 |
what | +0.015 |
wow | +0.015 |
are | +0.014 |
Neg logit contributions | |
Just | -0.016 |
ager | -0.014 |
age | -0.014 |
P | -0.014 |
bes | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
Just | +0.043 |
age | +0.040 |
ager | +0.040 |
P | +0.038 |
bes | +0.038 |
Neg logit contributions | |
theirs | -0.044 |
rings | -0.037 |
what | -0.035 |
are | -0.033 |
wow | -0.033 |
Token | on |
Token ID | 319 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
P | +0.089 |
Just | +0.089 |
bes | +0.089 |
age | +0.087 |
sy | +0.085 |
Neg logit contributions | |
theirs | -0.116 |
rings | -0.107 |
wow | -0.096 |
what | -0.088 |
nam | -0.087 |
Token | their |
Token ID | 511 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
theirs | +0.002 |
rings | +0.002 |
nam | +0.001 |
wow | +0.001 |
maybe | +0.001 |
Neg logit contributions | |
Just | -0.006 |
bes | -0.006 |
ager | -0.006 |
P | -0.006 |
age | -0.006 |
Token | warm |
Token ID | 5814 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
Just | +0.034 |
ager | +0.033 |
age | +0.033 |
ivering | +0.031 |
P | +0.031 |
Neg logit contributions | |
theirs | -0.024 |
rings | -0.019 |
what | -0.018 |
their | -0.017 |
are | -0.017 |
Token | p |
Token ID | 279 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
Just | +0.091 |
ager | +0.089 |
P | +0.082 |
ivering | +0.081 |
age | +0.081 |
Neg logit contributions | |
theirs | -0.071 |
rings | -0.059 |
what | -0.056 |
their | -0.053 |
are | -0.052 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
Just | +0.041 |
ager | +0.037 |
age | +0.036 |
P | +0.035 |
bes | +0.033 |
Neg logit contributions | |
theirs | -0.079 |
rings | -0.071 |
what | -0.066 |
are | -0.063 |
wow | -0.063 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
ager | +0.124 |
Just | +0.115 |
eh | +0.111 |
oster | +0.100 |
P | +0.098 |
Neg logit contributions | |
theirs | -0.326 |
rings | -0.325 |
are | -0.301 |
their | -0.288 |
eyes | -0.287 |
Token | and |
Token ID | 290 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
Just | +0.378 |
ager | +0.354 |
P | +0.346 |
age | +0.343 |
bes | +0.335 |
Neg logit contributions | |
theirs | -0.409 |
rings | -0.347 |
what | -0.327 |
are | -0.312 |
wow | -0.297 |
Token | crawl |
Token ID | 27318 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
Just | +0.036 |
age | +0.034 |
bes | +0.033 |
ager | +0.033 |
P | +0.032 |
Neg logit contributions | |
theirs | -0.040 |
rings | -0.034 |
wow | -0.030 |
what | -0.029 |
nam | -0.027 |
Token | into |
Token ID | 656 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
theirs | +0.022 |
rings | +0.019 |
what | +0.018 |
are | +0.017 |
wow | +0.017 |
Neg logit contributions | |
Just | -0.021 |
ager | -0.019 |
age | -0.019 |
P | -0.018 |
bes | -0.018 |
Token | their |
Token ID | 511 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
bes | +0.042 |
Just | +0.042 |
ce | +0.040 |
Lu | +0.040 |
P | +0.039 |
Neg logit contributions | |
rings | -0.030 |
theirs | -0.030 |
wow | -0.025 |
angles | -0.021 |
endant | -0.021 |
Token | sleeping |
Token ID | 11029 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Just | +0.031 |
ager | +0.029 |
age | +0.028 |
P | +0.027 |
ivering | +0.026 |
Neg logit contributions | |
theirs | -0.028 |
rings | -0.024 |
what | -0.023 |
are | -0.022 |
their | -0.021 |
Token | pair |
Token ID | 5166 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
Just | +0.012 |
age | +0.011 |
ager | +0.011 |
P | +0.010 |
bes | +0.010 |
Neg logit contributions | |
theirs | -0.010 |
rings | -0.009 |
what | -0.008 |
are | -0.007 |
wow | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
Just | +0.048 |
age | +0.046 |
ager | +0.045 |
sy | +0.041 |
bes | +0.041 |
Neg logit contributions | |
theirs | -0.052 |
rings | -0.044 |
nam | -0.041 |
what | -0.040 |
wow | -0.039 |
Token | matching |
Token ID | 12336 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
theirs | +0.075 |
rings | +0.063 |
what | +0.053 |
ours | +0.053 |
wow | +0.052 |
Neg logit contributions | |
Just | -0.083 |
ager | -0.078 |
age | -0.077 |
P | -0.076 |
sy | -0.073 |
Token | p |
Token ID | 279 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
Just | +0.046 |
ager | +0.044 |
age | +0.043 |
bes | +0.042 |
P | +0.041 |
Neg logit contributions | |
theirs | -0.046 |
rings | -0.038 |
what | -0.034 |
nam | -0.034 |
wow | -0.034 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
Just | +0.046 |
ager | +0.043 |
age | +0.043 |
bes | +0.041 |
sy | +0.041 |
Neg logit contributions | |
theirs | -0.055 |
rings | -0.045 |
what | -0.043 |
nam | -0.042 |
wow | -0.042 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
Just | +0.122 |
ager | +0.120 |
P | +0.111 |
eh | +0.111 |
oster | +0.109 |
Neg logit contributions | |
theirs | -0.321 |
rings | -0.317 |
what | -0.289 |
are | -0.283 |
wow | -0.279 |
Token | with |
Token ID | 351 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
Just | +0.384 |
age | +0.356 |
ager | +0.356 |
P | +0.343 |
bes | +0.337 |
Neg logit contributions | |
theirs | -0.395 |
rings | -0.335 |
what | -0.310 |
wow | -0.293 |
are | -0.292 |
Token | com |
Token ID | 401 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
Just | +0.041 |
bes | +0.041 |
ers | +0.039 |
sy | +0.039 |
ze | +0.039 |
Neg logit contributions | |
theirs | -0.036 |
rings | -0.031 |
ours | -0.030 |
wow | -0.027 |
nam | -0.026 |
Token | ets |
Token ID | 1039 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
theirs | +0.106 |
rings | +0.091 |
what | +0.085 |
wow | +0.082 |
are | +0.081 |
Neg logit contributions | |
Just | -0.082 |
ager | -0.076 |
age | -0.076 |
P | -0.072 |
bes | -0.071 |
Token | on |
Token ID | 319 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
theirs | +0.040 |
rings | +0.034 |
nam | +0.032 |
what | +0.031 |
wow | +0.030 |
Neg logit contributions | |
Just | -0.033 |
age | -0.031 |
ager | -0.030 |
bes | -0.029 |
sy | -0.028 |
Token | them |
Token ID | 606 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
theirs | +0.013 |
rings | +0.010 |
wow | +0.008 |
nam | +0.008 |
ours | +0.008 |
Neg logit contributions | |
Just | -0.027 |
bes | -0.025 |
age | -0.024 |
ce | -0.024 |
ager | -0.024 |
Token | put |
Token ID | 1234 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Just | +0.021 |
age | +0.019 |
ager | +0.019 |
bes | +0.018 |
P | +0.018 |
Neg logit contributions | |
theirs | -0.023 |
rings | -0.020 |
what | -0.018 |
wow | -0.017 |
are | -0.017 |
Token | on |
Token ID | 319 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Just | +0.111 |
P | +0.108 |
age | +0.107 |
ager | +0.105 |
bes | +0.104 |
Neg logit contributions | |
theirs | -0.073 |
rings | -0.061 |
wow | -0.051 |
what | -0.047 |
nam | -0.047 |
Token | their |
Token ID | 511 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
theirs | +0.012 |
rings | +0.010 |
wow | +0.007 |
what | +0.007 |
are | +0.007 |
Neg logit contributions | |
Just | -0.027 |
bes | -0.026 |
age | -0.026 |
P | -0.026 |
ager | -0.025 |
Token | p |
Token ID | 279 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
Just | +0.042 |
age | +0.040 |
ager | +0.040 |
P | +0.038 |
ivering | +0.038 |
Neg logit contributions | |
theirs | -0.031 |
rings | -0.025 |
what | -0.024 |
are | -0.022 |
wow | -0.022 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
Just | +0.040 |
ager | +0.037 |
age | +0.035 |
P | +0.035 |
ivering | +0.033 |
Neg logit contributions | |
theirs | -0.068 |
rings | -0.061 |
what | -0.056 |
wow | -0.053 |
are | -0.053 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
ager | +0.121 |
eh | +0.113 |
P | +0.110 |
Just | +0.110 |
oster | +0.103 |
Neg logit contributions | |
theirs | -0.295 |
rings | -0.295 |
what | -0.268 |
are | -0.265 |
wow | -0.260 |
Token | . |
Token ID | 13 |
Feature activation | +8.06e-02 |
Pos logit contributions | |
Just | +0.411 |
ager | +0.387 |
P | +0.381 |
age | +0.374 |
bes | +0.365 |
Neg logit contributions | |
theirs | -0.371 |
rings | -0.311 |
what | -0.290 |
are | -0.272 |
wow | -0.261 |
Token | They |
Token ID | 1119 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
theirs | +0.007 |
rings | +0.006 |
wow | +0.005 |
nam | +0.005 |
are | +0.005 |
Neg logit contributions | |
Just | -0.009 |
age | -0.008 |
bes | -0.007 |
amas | -0.007 |
ager | -0.007 |
Token | climbed |
Token ID | 19952 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
Just | +0.013 |
age | +0.012 |
ager | +0.012 |
P | +0.012 |
sy | +0.012 |
Neg logit contributions | |
theirs | -0.015 |
rings | -0.013 |
what | -0.012 |
wow | -0.011 |
nam | -0.011 |
Token | into |
Token ID | 656 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
theirs | +0.045 |
rings | +0.038 |
what | +0.035 |
are | +0.033 |
wow | +0.033 |
Neg logit contributions | |
Just | -0.045 |
ager | -0.042 |
age | -0.042 |
P | -0.040 |
ivering | -0.040 |
Token | their |
Token ID | 511 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
Just | +0.046 |
bes | +0.045 |
ce | +0.043 |
Lu | +0.043 |
amas | +0.043 |
Neg logit contributions | |
theirs | -0.028 |
rings | -0.026 |
wow | -0.022 |
ours | -0.018 |
angles | -0.017 |
Token | put |
Token ID | 1234 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Just | +0.045 |
age | +0.043 |
bes | +0.042 |
ager | +0.041 |
P | +0.040 |
Neg logit contributions | |
theirs | -0.048 |
rings | -0.041 |
what | -0.036 |
wow | -0.035 |
are | -0.033 |
Token | on |
Token ID | 319 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
Just | +0.124 |
P | +0.123 |
bes | +0.123 |
age | +0.122 |
ers | +0.121 |
Neg logit contributions | |
theirs | -0.075 |
rings | -0.067 |
wow | -0.056 |
nam | -0.051 |
expect | -0.049 |
Token | their |
Token ID | 511 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
theirs | +0.005 |
rings | +0.004 |
wow | +0.003 |
what | +0.003 |
are | +0.003 |
Neg logit contributions | |
Just | -0.011 |
bes | -0.011 |
age | -0.010 |
P | -0.010 |
zer | -0.010 |
Token | p |
Token ID | 279 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
Just | +0.038 |
age | +0.036 |
ager | +0.036 |
P | +0.035 |
ivering | +0.034 |
Neg logit contributions | |
theirs | -0.032 |
rings | -0.027 |
what | -0.024 |
are | -0.023 |
wow | -0.023 |
Token | aj |
Token ID | 1228 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
Just | +0.045 |
ager | +0.040 |
age | +0.039 |
P | +0.038 |
ivering | +0.036 |
Neg logit contributions | |
theirs | -0.089 |
rings | -0.080 |
what | -0.075 |
wow | -0.072 |
are | -0.072 |
Token | amas |
Token ID | 17485 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
ager | +0.132 |
Just | +0.123 |
eh | +0.104 |
P | +0.102 |
oster | +0.095 |
Neg logit contributions | |
theirs | -0.340 |
rings | -0.336 |
are | -0.310 |
their | -0.295 |
what | -0.294 |
Token | . |
Token ID | 13 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Just | +0.420 |
ager | +0.397 |
P | +0.389 |
age | +0.384 |
ivering | +0.372 |
Neg logit contributions | |
theirs | -0.364 |
rings | -0.300 |
what | -0.280 |
are | -0.262 |
their | -0.253 |
Token | They |
Token ID | 1119 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
Just | +0.023 |
age | +0.021 |
bes | +0.020 |
P | +0.020 |
ager | +0.020 |
Neg logit contributions | |
theirs | -0.019 |
rings | -0.016 |
nam | -0.014 |
what | -0.014 |
wow | -0.013 |
Token | hugged |
Token ID | 41130 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
Just | +0.026 |
ager | +0.025 |
age | +0.024 |
P | +0.024 |
sy | +0.024 |
Neg logit contributions | |
theirs | -0.031 |
rings | -0.026 |
what | -0.024 |
wow | -0.023 |
ours | -0.022 |
Token | their |
Token ID | 511 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
Just | +0.033 |
age | +0.031 |
co | +0.030 |
bes | +0.030 |
ze | +0.029 |
Neg logit contributions | |
theirs | -0.021 |
rings | -0.018 |
wow | -0.016 |
ours | -0.015 |
ours | -0.014 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Just | +0.035 |
age | +0.033 |
ager | +0.033 |
P | +0.031 |
bes | +0.031 |
Neg logit contributions | |
theirs | -0.032 |
rings | -0.027 |
what | -0.025 |
wow | -0.024 |
are | -0.023 |
Token | He |
Token ID | 679 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
theirs | +0.023 |
rings | +0.019 |
what | +0.017 |
are | +0.016 |
wow | +0.016 |
Neg logit contributions | |
Just | -0.034 |
ager | -0.032 |
age | -0.032 |
P | -0.031 |
ivering | -0.031 |
Token | looked |
Token ID | 3114 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
theirs | +0.008 |
rings | +0.007 |
what | +0.007 |
are | +0.006 |
wow | +0.006 |
Neg logit contributions | |
Just | -0.010 |
age | -0.009 |
ivering | -0.009 |
P | -0.009 |
amas | -0.009 |
Token | at |
Token ID | 379 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Just | +0.024 |
ager | +0.021 |
age | +0.021 |
sy | +0.021 |
ivering | +0.021 |
Neg logit contributions | |
theirs | -0.028 |
rings | -0.025 |
wow | -0.021 |
are | -0.021 |
nam | -0.021 |
Token | it |
Token ID | 340 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
theirs | +0.073 |
rings | +0.060 |
wow | +0.048 |
ours | +0.042 |
are | +0.041 |
Neg logit contributions | |
Just | -0.143 |
ager | -0.135 |
bes | -0.133 |
age | -0.133 |
zer | -0.131 |
Token | with |
Token ID | 351 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
theirs | +0.023 |
rings | +0.019 |
what | +0.018 |
are | +0.017 |
wow | +0.017 |
Neg logit contributions | |
Just | -0.020 |
ager | -0.019 |
age | -0.019 |
P | -0.018 |
bes | -0.017 |
Token | amaz |
Token ID | 40642 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
Just | +0.031 |
age | +0.028 |
ager | +0.027 |
ze | +0.027 |
P | +0.027 |
Neg logit contributions | |
theirs | -0.026 |
rings | -0.025 |
ours | -0.021 |
nam | -0.019 |
angles | -0.019 |
Token | ement |
Token ID | 972 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
theirs | +0.354 |
rings | +0.299 |
what | +0.274 |
wow | +0.261 |
are | +0.259 |
Neg logit contributions | |
Just | -0.365 |
age | -0.338 |
ager | -0.338 |
P | -0.326 |
bes | -0.321 |
Token | and |
Token ID | 290 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
theirs | +0.020 |
rings | +0.017 |
nam | +0.015 |
are | +0.015 |
wow | +0.015 |
Neg logit contributions | |
Just | -0.016 |
age | -0.015 |
ager | -0.014 |
bes | -0.014 |
ivering | -0.014 |
Token | said |
Token ID | 531 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
theirs | +0.003 |
rings | +0.002 |
what | +0.002 |
are | +0.002 |
wow | +0.002 |
Neg logit contributions | |
Just | -0.003 |
ager | -0.002 |
age | -0.002 |
bes | -0.002 |
P | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
Just | +0.001 |
age | +0.001 |
ager | +0.001 |
P | +0.001 |
sy | +0.001 |
Neg logit contributions | |
theirs | -0.001 |
rings | -0.001 |
nam | -0.001 |
what | -0.001 |
are | -0.001 |
Token | " |
Token ID | 366 |
Feature activation | -2.36e-04 |
Pos logit contributions | |
theirs | +0.018 |
rings | +0.014 |
what | +0.014 |
wow | +0.013 |
are | +0.012 |
Neg logit contributions | |
Just | -0.027 |
ager | -0.027 |
age | -0.027 |
P | -0.026 |
ivering | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Just | +0.015 |
age | +0.014 |
ager | +0.014 |
P | +0.013 |
bes | +0.013 |
Neg logit contributions | |
theirs | -0.015 |
rings | -0.013 |
what | -0.012 |
are | -0.011 |
wow | -0.011 |
Token | He |
Token ID | 679 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
theirs | +0.014 |
rings | +0.012 |
what | +0.011 |
nam | +0.010 |
wow | +0.010 |
Neg logit contributions | |
Just | -0.014 |
age | -0.013 |
ager | -0.013 |
P | -0.012 |
bes | -0.012 |
Token | always |
Token ID | 1464 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
theirs | +0.011 |
what | +0.009 |
are | +0.009 |
rings | +0.008 |
their | +0.008 |
Neg logit contributions | |
Just | -0.013 |
ivering | -0.012 |
amas | -0.012 |
age | -0.012 |
P | -0.012 |
Token | used |
Token ID | 973 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
Just | +0.072 |
age | +0.067 |
ager | +0.067 |
P | +0.064 |
bes | +0.063 |
Neg logit contributions | |
theirs | -0.082 |
rings | -0.070 |
what | -0.065 |
wow | -0.062 |
are | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
Just | +0.057 |
age | +0.054 |
bes | +0.052 |
ager | +0.051 |
sy | +0.051 |
Neg logit contributions | |
theirs | -0.041 |
rings | -0.037 |
wow | -0.032 |
ours | -0.032 |
nam | -0.030 |
Token | loop |
Token ID | 9052 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
Just | +0.012 |
age | +0.011 |
ager | +0.011 |
P | +0.011 |
bes | +0.011 |
Neg logit contributions | |
theirs | -0.014 |
rings | -0.012 |
what | -0.012 |
wow | -0.011 |
are | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
theirs | +0.217 |
rings | +0.183 |
what | +0.169 |
are | +0.159 |
wow | +0.158 |
Neg logit contributions | |
Just | -0.230 |
ager | -0.214 |
age | -0.211 |
P | -0.208 |
bes | -0.203 |
Token | lead |
Token ID | 1085 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
theirs | +0.042 |
rings | +0.037 |
wow | +0.032 |
what | +0.031 |
ours | +0.031 |
Neg logit contributions | |
Just | -0.045 |
age | -0.044 |
ager | -0.042 |
bes | -0.041 |
sy | -0.040 |
Token | them |
Token ID | 606 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
theirs | +0.114 |
rings | +0.085 |
what | +0.075 |
are | +0.066 |
wow | +0.065 |
Neg logit contributions | |
Just | -0.247 |
ager | -0.234 |
age | -0.234 |
P | -0.228 |
bes | -0.226 |
Token | back |
Token ID | 736 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
Just | +0.037 |
ager | +0.034 |
age | +0.034 |
P | +0.033 |
bes | +0.033 |
Neg logit contributions | |
theirs | -0.032 |
rings | -0.026 |
what | -0.024 |
are | -0.023 |
wow | -0.022 |
Token | home |
Token ID | 1363 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Just | +0.034 |
ager | +0.032 |
P | +0.032 |
ivering | +0.032 |
age | +0.031 |
Neg logit contributions | |
theirs | -0.024 |
rings | -0.018 |
what | -0.018 |
their | -0.016 |
are | -0.016 |
Token | feel |
Token ID | 1254 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
theirs | +0.055 |
rings | +0.046 |
what | +0.040 |
wow | +0.038 |
are | +0.037 |
Neg logit contributions | |
Just | -0.074 |
age | -0.070 |
ager | -0.069 |
P | -0.067 |
bes | -0.067 |
Token | calm |
Token ID | 9480 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
theirs | +0.123 |
rings | +0.107 |
wow | +0.088 |
what | +0.088 |
nam | +0.086 |
Neg logit contributions | |
Just | -0.149 |
age | -0.139 |
ager | -0.137 |
P | -0.135 |
ivering | -0.133 |
Token | ", |
Token ID | 1600 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
theirs | +0.068 |
rings | +0.057 |
what | +0.054 |
are | +0.051 |
wow | +0.050 |
Neg logit contributions | |
Just | -0.067 |
ager | -0.063 |
age | -0.061 |
P | -0.061 |
bes | -0.060 |
Token | or |
Token ID | 393 |
Feature activation | +9.66e-02 |
Pos logit contributions | |
theirs | +0.031 |
rings | +0.025 |
what | +0.022 |
wow | +0.021 |
are | +0.020 |
Neg logit contributions | |
Just | -0.051 |
age | -0.048 |
ager | -0.048 |
P | -0.046 |
bes | -0.046 |
Token | " |
Token ID | 366 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
theirs | +0.007 |
rings | +0.006 |
wow | +0.005 |
are | +0.005 |
what | +0.004 |
Neg logit contributions | |
Just | -0.011 |
age | -0.010 |
ager | -0.010 |
P | -0.010 |
bes | -0.010 |
Token | Sm |
Token ID | 7556 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
Just | +0.001 |
ager | +0.001 |
age | +0.001 |
bes | +0.001 |
ivering | +0.001 |
Neg logit contributions | |
theirs | -0.002 |
rings | -0.001 |
what | -0.001 |
are | -0.001 |
nam | -0.001 |
Token | ile |
Token ID | 576 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
theirs | +0.265 |
rings | +0.228 |
what | +0.218 |
are | +0.208 |
wow | +0.203 |
Neg logit contributions | |
Just | -0.175 |
age | -0.158 |
ager | -0.154 |
bes | -0.150 |
P | -0.149 |
Token | and |
Token ID | 290 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
theirs | +0.023 |
rings | +0.019 |
what | +0.019 |
are | +0.018 |
wow | +0.017 |
Neg logit contributions | |
Just | -0.027 |
ager | -0.025 |
P | -0.025 |
age | -0.025 |
bes | -0.024 |
Token | let |
Token ID | 1309 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
theirs | +0.001 |
rings | +0.001 |
what | +0.001 |
wow | +0.001 |
nam | +0.001 |
Neg logit contributions | |
Just | -0.002 |
age | -0.002 |
ager | -0.002 |
P | -0.002 |
bes | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
theirs | +0.032 |
what | +0.028 |
are | +0.027 |
rings | +0.026 |
their | +0.025 |
Neg logit contributions | |
Just | -0.030 |
ager | -0.027 |
bes | -0.027 |
ivering | -0.025 |
ider | -0.025 |
Token | sadness |
Token ID | 25303 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
theirs | +0.012 |
rings | +0.010 |
what | +0.010 |
are | +0.009 |
wow | +0.009 |
Neg logit contributions | |
Just | -0.013 |
ager | -0.012 |
age | -0.012 |
bes | -0.011 |
P | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
Just | +0.010 |
age | +0.010 |
ager | +0.009 |
bes | +0.009 |
P | +0.009 |
Neg logit contributions | |
theirs | -0.013 |
rings | -0.011 |
nam | -0.011 |
what | -0.010 |
wow | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
Just | +0.056 |
age | +0.052 |
ager | +0.051 |
P | +0.049 |
bes | +0.048 |
Neg logit contributions | |
theirs | -0.065 |
rings | -0.056 |
what | -0.052 |
wow | -0.050 |
are | -0.049 |
Token | One |
Token ID | 3198 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Just | +0.054 |
ager | +0.051 |
age | +0.050 |
ivering | +0.049 |
bes | +0.049 |
Neg logit contributions | |
theirs | -0.067 |
rings | -0.057 |
what | -0.054 |
are | -0.052 |
wow | -0.052 |
Token | day |
Token ID | 1110 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
theirs | +0.011 |
what | +0.009 |
rings | +0.009 |
are | +0.008 |
their | +0.008 |
Neg logit contributions | |
Just | -0.010 |
bes | -0.009 |
ager | -0.009 |
age | -0.009 |
amas | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
Just | +0.086 |
age | +0.080 |
ager | +0.079 |
P | +0.077 |
bes | +0.075 |
Neg logit contributions | |
theirs | -0.088 |
rings | -0.075 |
what | -0.068 |
wow | -0.065 |
nam | -0.064 |
Token | Zig |
Token ID | 24992 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
theirs | +0.001 |
rings | +0.001 |
ours | +0.001 |
nam | +0.001 |
ours | +0.001 |
Neg logit contributions | |
Just | -0.001 |
P | -0.001 |
age | -0.001 |
ager | -0.001 |
B | -0.001 |
Token | gy |
Token ID | 1360 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
theirs | +0.275 |
rings | +0.254 |
what | +0.230 |
are | +0.216 |
their | +0.211 |
Neg logit contributions | |
Just | -0.140 |
P | -0.139 |
ager | -0.138 |
Now | -0.131 |
amas | -0.128 |
Token | 's |
Token ID | 338 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
Just | +0.188 |
P | +0.184 |
bes | +0.181 |
ivering | +0.181 |
amas | +0.179 |
Neg logit contributions | |
theirs | -0.123 |
are | -0.114 |
Tom | -0.110 |
they | -0.106 |
what | -0.106 |
Token | friend |
Token ID | 1545 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
theirs | +0.070 |
rings | +0.061 |
what | +0.058 |
are | +0.055 |
wow | +0.052 |
Neg logit contributions | |
Just | -0.060 |
ager | -0.056 |
bes | -0.055 |
age | -0.053 |
ivering | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
Just | +0.082 |
ager | +0.076 |
age | +0.076 |
bes | +0.075 |
ivering | +0.073 |
Neg logit contributions | |
theirs | -0.058 |
rings | -0.047 |
what | -0.046 |
are | -0.042 |
wow | -0.041 |
Token | a |
Token ID | 257 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
theirs | +0.004 |
rings | +0.003 |
nam | +0.003 |
ours | +0.003 |
wow | +0.003 |
Neg logit contributions | |
Just | -0.006 |
P | -0.005 |
ager | -0.005 |
age | -0.005 |
sy | -0.005 |
Token | had |
Token ID | 550 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
amas | +0.011 |
ivering | +0.010 |
Just | +0.010 |
age | +0.010 |
lor | +0.010 |
Neg logit contributions | |
theirs | -0.006 |
are | -0.005 |
what | -0.005 |
their | -0.005 |
they | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
Just | +0.037 |
ager | +0.036 |
age | +0.035 |
ivering | +0.035 |
bes | +0.035 |
Neg logit contributions | |
theirs | -0.017 |
rings | -0.013 |
what | -0.012 |
are | -0.011 |
wow | -0.010 |
Token | big |
Token ID | 1263 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Just | +0.032 |
ager | +0.030 |
bes | +0.029 |
age | +0.029 |
ivering | +0.029 |
Neg logit contributions | |
theirs | -0.020 |
rings | -0.016 |
what | -0.016 |
wow | -0.014 |
look | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
Just | +0.124 |
ager | +0.114 |
age | +0.112 |
P | +0.109 |
bes | +0.108 |
Neg logit contributions | |
theirs | -0.110 |
rings | -0.091 |
what | -0.086 |
are | -0.083 |
wow | -0.082 |
Token | bus |
Token ID | 1323 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
theirs | +0.002 |
rings | +0.002 |
what | +0.002 |
wow | +0.001 |
are | +0.001 |
Neg logit contributions | |
Just | -0.003 |
ager | -0.003 |
age | -0.003 |
P | -0.003 |
bes | -0.003 |
Token | hy |
Token ID | 12114 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
theirs | +0.029 |
rings | +0.025 |
what | +0.023 |
are | +0.022 |
wow | +0.021 |
Neg logit contributions | |
Just | -0.038 |
P | -0.036 |
ager | -0.035 |
ivering | -0.035 |
bes | -0.034 |
Token | tail |
Token ID | 7894 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
theirs | +0.247 |
rings | +0.210 |
what | +0.205 |
are | +0.196 |
wow | +0.196 |
Neg logit contributions | |
Just | -0.202 |
ager | -0.189 |
sy | -0.182 |
age | -0.178 |
rd | -0.175 |
Token | and |
Token ID | 290 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Just | +0.044 |
ager | +0.042 |
P | +0.042 |
amas | +0.041 |
age | +0.040 |
Neg logit contributions | |
theirs | -0.031 |
rings | -0.027 |
what | -0.025 |
are | -0.023 |
wow | -0.022 |
Token | sharp |
Token ID | 7786 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
Just | +0.019 |
ager | +0.018 |
age | +0.018 |
ivering | +0.017 |
bes | +0.017 |
Neg logit contributions | |
theirs | -0.014 |
rings | -0.012 |
what | -0.011 |
wow | -0.010 |
nam | -0.010 |
Token | teeth |
Token ID | 9941 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
Just | +0.020 |
ager | +0.019 |
P | +0.019 |
age | +0.019 |
ivering | +0.018 |
Neg logit contributions | |
theirs | -0.015 |
rings | -0.012 |
what | -0.011 |
are | -0.010 |
wow | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
theirs | +0.050 |
rings | +0.042 |
what | +0.039 |
are | +0.037 |
wow | +0.036 |
Neg logit contributions | |
Just | -0.050 |
ager | -0.047 |
age | -0.047 |
P | -0.045 |
bes | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
theirs | +0.102 |
rings | +0.086 |
what | +0.081 |
are | +0.076 |
wow | +0.075 |
Neg logit contributions | |
Just | -0.096 |
ager | -0.089 |
age | -0.088 |
P | -0.086 |
bes | -0.084 |
Token | but |
Token ID | 475 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
theirs | +0.031 |
rings | +0.026 |
what | +0.025 |
wow | +0.023 |
nam | +0.023 |
Neg logit contributions | |
Just | -0.032 |
ager | -0.032 |
age | -0.031 |
P | -0.031 |
ivering | -0.029 |
Token | it |
Token ID | 340 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
Just | +0.101 |
ager | +0.093 |
age | +0.092 |
P | +0.090 |
bes | +0.089 |
Neg logit contributions | |
theirs | -0.059 |
rings | -0.048 |
wow | -0.038 |
what | -0.038 |
are | -0.037 |
Token | was |
Token ID | 373 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
theirs | +0.026 |
rings | +0.022 |
are | +0.021 |
what | +0.021 |
maybe | +0.020 |
Neg logit contributions | |
Just | -0.027 |
ager | -0.026 |
age | -0.024 |
P | -0.024 |
bes | -0.024 |
Token | hard |
Token ID | 1327 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
Just | +0.015 |
age | +0.014 |
ager | +0.013 |
sy | +0.013 |
ivering | +0.013 |
Neg logit contributions | |
theirs | -0.014 |
rings | -0.012 |
wow | -0.011 |
what | -0.011 |
are | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
theirs | +0.002 |
rings | +0.001 |
what | +0.001 |
wow | +0.001 |
nam | +0.001 |
Neg logit contributions | |
Just | -0.002 |
age | -0.002 |
ager | -0.002 |
P | -0.001 |
bes | -0.001 |
Token | drink |
Token ID | 4144 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
theirs | +0.043 |
rings | +0.035 |
what | +0.032 |
wow | +0.030 |
are | +0.030 |
Neg logit contributions | |
Just | -0.054 |
age | -0.051 |
ager | -0.051 |
P | -0.049 |
bes | -0.049 |
Token | as |
Token ID | 355 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Just | +0.073 |
age | +0.069 |
ager | +0.067 |
P | +0.066 |
bes | +0.065 |
Neg logit contributions | |
theirs | -0.076 |
rings | -0.066 |
what | -0.059 |
wow | -0.058 |
nam | -0.056 |
Token | his |
Token ID | 465 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
theirs | +0.153 |
rings | +0.142 |
wow | +0.119 |
are | +0.114 |
what | +0.109 |
Neg logit contributions | |
Just | -0.193 |
ager | -0.174 |
P | -0.172 |
sy | -0.170 |
age | -0.166 |
Token | throat |
Token ID | 13589 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
theirs | +0.037 |
rings | +0.031 |
what | +0.029 |
are | +0.027 |
their | +0.026 |
Neg logit contributions | |
Just | -0.050 |
ager | -0.048 |
P | -0.046 |
age | -0.046 |
ivering | -0.045 |
Token | was |
Token ID | 373 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Just | +0.021 |
ager | +0.019 |
age | +0.019 |
P | +0.019 |
bes | +0.018 |
Neg logit contributions | |
theirs | -0.020 |
rings | -0.017 |
what | -0.016 |
are | -0.015 |
wow | -0.015 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Just | +0.090 |
age | +0.084 |
ager | +0.084 |
P | +0.081 |
bes | +0.081 |
Neg logit contributions | |
theirs | -0.067 |
rings | -0.055 |
what | -0.049 |
wow | -0.046 |
are | -0.046 |
Token | hugged |
Token ID | 41130 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
Just | +0.014 |
P | +0.013 |
age | +0.013 |
bes | +0.013 |
amas | +0.013 |
Neg logit contributions | |
theirs | -0.009 |
what | -0.009 |
are | -0.008 |
rings | -0.008 |
maybe | -0.007 |
Token | them |
Token ID | 606 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
Just | +0.037 |
P | +0.036 |
age | +0.034 |
B | +0.034 |
co | +0.034 |
Neg logit contributions | |
theirs | -0.024 |
rings | -0.022 |
wow | -0.020 |
nam | -0.018 |
endant | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
Just | +0.050 |
age | +0.046 |
ager | +0.046 |
P | +0.045 |
bes | +0.044 |
Neg logit contributions | |
theirs | -0.062 |
rings | -0.053 |
what | -0.051 |
are | -0.048 |
wow | -0.047 |
Token | said |
Token ID | 531 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
Just | +0.014 |
ager | +0.013 |
P | +0.012 |
bes | +0.012 |
age | +0.012 |
Neg logit contributions | |
theirs | -0.017 |
rings | -0.015 |
wow | -0.012 |
ours | -0.012 |
nam | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
Just | +0.029 |
age | +0.025 |
ze | +0.024 |
ager | +0.024 |
ce | +0.024 |
Neg logit contributions | |
theirs | -0.028 |
rings | -0.024 |
nam | -0.021 |
ours | -0.020 |
angles | -0.020 |
Token | " |
Token ID | 366 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
theirs | +0.003 |
rings | +0.003 |
what | +0.003 |
wow | +0.002 |
are | +0.002 |
Neg logit contributions | |
Just | -0.005 |
ager | -0.005 |
age | -0.005 |
P | -0.005 |
ivering | -0.004 |
Token | I |
Token ID | 40 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
Just | +0.019 |
age | +0.019 |
ager | +0.018 |
bes | +0.018 |
ivering | +0.018 |
Neg logit contributions | |
theirs | -0.024 |
rings | -0.021 |
what | -0.020 |
are | -0.019 |
wow | -0.018 |
Token | know |
Token ID | 760 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Just | +0.015 |
age | +0.014 |
ager | +0.014 |
P | +0.014 |
sy | +0.013 |
Neg logit contributions | |
theirs | -0.015 |
rings | -0.013 |
what | -0.011 |
wow | -0.011 |
nam | -0.011 |
Token | you |
Token ID | 345 |
Feature activation | -1.52e-04 |
Pos logit contributions | |
theirs | +0.193 |
rings | +0.162 |
nam | +0.147 |
ours | +0.134 |
wow | +0.134 |
Neg logit contributions | |
Just | -0.147 |
ager | -0.131 |
P | -0.120 |
bes | -0.120 |
rd | -0.119 |
Token | want |
Token ID | 765 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
ager | +0.000 |
Just | +0.000 |
sy | +0.000 |
age | +0.000 |
bes | +0.000 |
Neg logit contributions | |
theirs | -0.000 |
rings | -0.000 |
wow | -0.000 |
nam | -0.000 |
ours | -0.000 |
Token | The |
Token ID | 464 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
amas | +0.025 |
bes | +0.024 |
ivering | +0.024 |
age | +0.024 |
ager | +0.023 |
Neg logit contributions | |
theirs | -0.028 |
what | -0.024 |
wow | -0.022 |
rings | -0.022 |
their | -0.021 |
Token | goat |
Token ID | 26917 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
theirs | +0.009 |
what | +0.007 |
rings | +0.007 |
are | +0.007 |
wow | +0.007 |
Neg logit contributions | |
Just | -0.008 |
bes | -0.008 |
age | -0.008 |
ager | -0.008 |
ivering | -0.007 |
Token | quickly |
Token ID | 2952 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
theirs | +0.004 |
what | +0.004 |
rings | +0.004 |
are | +0.004 |
wow | +0.003 |
Neg logit contributions | |
Just | -0.005 |
P | -0.005 |
bes | -0.005 |
amas | -0.005 |
ager | -0.005 |
Token | ran |
Token ID | 4966 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
Just | +0.075 |
age | +0.069 |
ager | +0.069 |
amas | +0.069 |
bes | +0.068 |
Neg logit contributions | |
theirs | -0.067 |
rings | -0.056 |
what | -0.054 |
are | -0.051 |
wow | -0.051 |
Token | out |
Token ID | 503 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
Just | +0.043 |
ager | +0.041 |
age | +0.040 |
bes | +0.040 |
P | +0.040 |
Neg logit contributions | |
theirs | -0.039 |
rings | -0.031 |
what | -0.031 |
their | -0.028 |
wow | -0.027 |
Token | of |
Token ID | 286 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
theirs | +0.075 |
rings | +0.062 |
what | +0.057 |
wow | +0.054 |
are | +0.053 |
Neg logit contributions | |
Just | -0.091 |
age | -0.085 |
ager | -0.085 |
P | -0.082 |
bes | -0.081 |
Token | the |
Token ID | 262 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
theirs | +0.070 |
rings | +0.066 |
wow | +0.050 |
are | +0.048 |
what | +0.045 |
Neg logit contributions | |
Just | -0.132 |
P | -0.127 |
bes | -0.125 |
ager | -0.125 |
age | -0.125 |
Token | shed |
Token ID | 14999 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Just | +0.002 |
ager | +0.002 |
age | +0.002 |
bes | +0.002 |
ivering | +0.002 |
Neg logit contributions | |
theirs | -0.002 |
rings | -0.002 |
what | -0.001 |
are | -0.001 |
their | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -7.08e-02 |
Pos logit contributions | |
theirs | +0.027 |
rings | +0.023 |
what | +0.022 |
are | +0.020 |
wow | +0.020 |
Neg logit contributions | |
Just | -0.024 |
P | -0.022 |
ager | -0.022 |
age | -0.022 |
bes | -0.021 |
Token | back |
Token ID | 736 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
Just | +0.007 |
age | +0.006 |
ager | +0.006 |
P | +0.006 |
ivering | +0.006 |
Neg logit contributions | |
theirs | -0.007 |
rings | -0.006 |
what | -0.005 |
wow | -0.005 |
are | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
Just | +0.017 |
age | +0.016 |
ager | +0.016 |
P | +0.015 |
bes | +0.015 |
Neg logit contributions | |
theirs | -0.016 |
rings | -0.014 |
what | -0.013 |
wow | -0.012 |
are | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
Just | +0.077 |
age | +0.070 |
ager | +0.070 |
P | +0.067 |
bes | +0.066 |
Neg logit contributions | |
theirs | -0.106 |
rings | -0.092 |
what | -0.086 |
wow | -0.082 |
are | -0.082 |
Token | fast |
Token ID | 3049 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
theirs | +0.011 |
rings | +0.011 |
wow | +0.009 |
what | +0.009 |
ours | +0.009 |
Neg logit contributions | |
Just | -0.009 |
sy | -0.009 |
P | -0.009 |
age | -0.008 |
oster | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
Just | +0.002 |
age | +0.002 |
ager | +0.002 |
bes | +0.002 |
P | +0.002 |
Neg logit contributions | |
theirs | -0.003 |
rings | -0.003 |
what | -0.002 |
wow | -0.002 |
nam | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
theirs | +0.004 |
rings | +0.003 |
what | +0.003 |
wow | +0.002 |
nam | +0.002 |
Neg logit contributions | |
Just | -0.006 |
age | -0.005 |
ager | -0.005 |
P | -0.005 |
bes | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
Just | +0.055 |
age | +0.053 |
ager | +0.053 |
ivering | +0.051 |
P | +0.051 |
Neg logit contributions | |
theirs | -0.048 |
rings | -0.040 |
what | -0.039 |
are | -0.037 |
wow | -0.035 |
Token | One |
Token ID | 3198 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
age | +0.048 |
amas | +0.046 |
ager | +0.046 |
bes | +0.046 |
Just | +0.046 |
Neg logit contributions | |
theirs | -0.053 |
what | -0.046 |
are | -0.046 |
rings | -0.045 |
wow | -0.044 |
Token | day |
Token ID | 1110 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
theirs | +0.026 |
rings | +0.023 |
what | +0.021 |
wow | +0.020 |
are | +0.020 |
Neg logit contributions | |
Just | -0.017 |
age | -0.016 |
ager | -0.016 |
P | -0.015 |
bes | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Just | +0.068 |
P | +0.061 |
ager | +0.061 |
age | +0.060 |
bes | +0.056 |
Neg logit contributions | |
theirs | -0.090 |
rings | -0.077 |
nam | -0.067 |
what | -0.066 |
wow | -0.065 |
Token | man |
Token ID | 582 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Just | +0.012 |
age | +0.011 |
bes | +0.011 |
ager | +0.010 |
ivering | +0.010 |
Neg logit contributions | |
theirs | -0.013 |
what | -0.011 |
rings | -0.010 |
wow | -0.010 |
are | -0.010 |
Token | told |
Token ID | 1297 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
theirs | +0.021 |
rings | +0.018 |
what | +0.017 |
are | +0.016 |
wow | +0.016 |
Neg logit contributions | |
Just | -0.022 |
age | -0.021 |
ager | -0.020 |
bes | -0.020 |
P | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
Just | +0.063 |
ager | +0.059 |
P | +0.059 |
age | +0.059 |
zer | +0.059 |
Neg logit contributions | |
theirs | -0.037 |
rings | -0.036 |
nam | -0.029 |
wow | -0.026 |
ours | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
theirs | +0.128 |
rings | +0.111 |
wow | +0.105 |
nam | +0.102 |
what | +0.101 |
Neg logit contributions | |
Just | -0.088 |
age | -0.080 |
ager | -0.075 |
P | -0.075 |
bes | -0.074 |
Token |
|
Token ID | 198 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
age | +0.060 |
ager | +0.059 |
Just | +0.058 |
ivering | +0.057 |
bes | +0.057 |
Neg logit contributions | |
theirs | -0.050 |
rings | -0.041 |
what | -0.041 |
are | -0.036 |
maybe | -0.035 |
Token | She |
Token ID | 3347 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
age | +0.048 |
amas | +0.047 |
ager | +0.047 |
bes | +0.047 |
ivering | +0.045 |
Neg logit contributions | |
theirs | -0.053 |
rings | -0.046 |
what | -0.046 |
nam | -0.042 |
are | -0.041 |
Token | took |
Token ID | 1718 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
Just | +0.001 |
age | +0.001 |
ivering | +0.001 |
ager | +0.001 |
P | +0.001 |
Neg logit contributions | |
theirs | -0.001 |
rings | -0.001 |
what | -0.001 |
wow | -0.001 |
are | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
Just | +0.035 |
P | +0.033 |
age | +0.033 |
ce | +0.032 |
ager | +0.032 |
Neg logit contributions | |
theirs | -0.025 |
rings | -0.019 |
nam | -0.017 |
are | -0.016 |
wow | -0.016 |
Token | frame |
Token ID | 5739 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Just | +0.032 |
age | +0.030 |
ager | +0.030 |
P | +0.029 |
bes | +0.028 |
Neg logit contributions | |
theirs | -0.032 |
rings | -0.026 |
what | -0.024 |
wow | -0.023 |
are | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
theirs | +0.117 |
rings | +0.100 |
what | +0.092 |
are | +0.086 |
wow | +0.085 |
Neg logit contributions | |
Just | -0.118 |
ager | -0.109 |
age | -0.107 |
P | -0.106 |
ivering | -0.104 |
Token | put |
Token ID | 1234 |
Feature activation | -9.78e-01 |
Pos logit contributions | |
Just | +0.022 |
ager | +0.020 |
age | +0.019 |
bes | +0.019 |
P | +0.019 |
Neg logit contributions | |
theirs | -0.030 |
rings | -0.023 |
what | -0.022 |
wow | -0.021 |
are | -0.021 |
Token | it |
Token ID | 340 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
Just | +0.107 |
P | +0.099 |
bes | +0.099 |
Now | +0.099 |
age | +0.099 |
Neg logit contributions | |
theirs | -0.069 |
rings | -0.052 |
nam | -0.045 |
ours | -0.042 |
wow | -0.040 |
Token | up |
Token ID | 510 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
theirs | +0.003 |
rings | +0.003 |
what | +0.002 |
are | +0.002 |
wow | +0.002 |
Neg logit contributions | |
Just | -0.003 |
ager | -0.002 |
age | -0.002 |
P | -0.002 |
ivering | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
Just | +0.011 |
age | +0.010 |
ager | +0.010 |
P | +0.009 |
bes | +0.009 |
Neg logit contributions | |
theirs | -0.013 |
rings | -0.012 |
what | -0.011 |
wow | -0.010 |
are | -0.010 |
Token | night |
Token ID | 3847 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
theirs | +0.129 |
rings | +0.111 |
what | +0.106 |
wow | +0.103 |
are | +0.102 |
Neg logit contributions | |
Just | -0.100 |
age | -0.089 |
ager | -0.088 |
bes | -0.087 |
P | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
Just | +0.167 |
P | +0.157 |
ager | +0.156 |
bes | +0.151 |
age | +0.147 |
Neg logit contributions | |
theirs | -0.114 |
what | -0.095 |
rings | -0.093 |
wow | -0.088 |
are | -0.085 |
Token | car |
Token ID | 1097 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
theirs | +0.026 |
rings | +0.022 |
what | +0.019 |
nam | +0.018 |
wow | +0.017 |
Neg logit contributions | |
Just | -0.034 |
age | -0.032 |
ager | -0.032 |
P | -0.031 |
bes | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
theirs | +0.058 |
rings | +0.050 |
what | +0.048 |
are | +0.048 |
wow | +0.046 |
Neg logit contributions | |
Just | -0.060 |
P | -0.055 |
ager | -0.053 |
bes | -0.052 |
age | -0.052 |
Token | I |
Token ID | 314 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
theirs | +0.031 |
rings | +0.026 |
what | +0.024 |
wow | +0.023 |
are | +0.023 |
Neg logit contributions | |
Just | -0.043 |
ager | -0.042 |
P | -0.041 |
age | -0.040 |
bes | -0.040 |
Token | love |
Token ID | 1842 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
theirs | +0.027 |
rings | +0.021 |
are | +0.020 |
what | +0.020 |
wow | +0.018 |
Neg logit contributions | |
Just | -0.044 |
P | -0.041 |
ager | -0.041 |
bes | -0.040 |
age | -0.040 |
Token | you |
Token ID | 345 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Just | +0.031 |
age | +0.029 |
ager | +0.029 |
P | +0.028 |
bes | +0.028 |
Neg logit contributions | |
theirs | -0.029 |
rings | -0.024 |
what | -0.022 |
wow | -0.021 |
are | -0.021 |
Token | ." |
Token ID | 526 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
theirs | +0.021 |
rings | +0.017 |
what | +0.017 |
are | +0.016 |
wow | +0.015 |
Neg logit contributions | |
Just | -0.022 |
ager | -0.021 |
P | -0.021 |
age | -0.020 |
bes | -0.020 |
Token | And |
Token ID | 843 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
theirs | +0.006 |
rings | +0.005 |
what | +0.004 |
wow | +0.004 |
are | +0.004 |
Neg logit contributions | |
Just | -0.007 |
ager | -0.007 |
age | -0.007 |
P | -0.007 |
ivering | -0.007 |
Token | they |
Token ID | 484 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
theirs | +0.012 |
rings | +0.010 |
what | +0.008 |
wow | +0.008 |
nam | +0.008 |
Neg logit contributions | |
Just | -0.019 |
age | -0.018 |
ager | -0.018 |
P | -0.017 |
bes | -0.017 |
Token | both |
Token ID | 1111 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
Just | +0.002 |
age | +0.002 |
sy | +0.002 |
ager | +0.002 |
P | +0.002 |
Neg logit contributions | |
theirs | -0.002 |
rings | -0.002 |
what | -0.002 |
ours | -0.001 |
nam | -0.001 |
Token | 's |
Token ID | 338 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
theirs | +0.001 |
rings | +0.001 |
what | +0.001 |
wow | +0.001 |
nam | +0.001 |
Neg logit contributions | |
Just | -0.001 |
age | -0.001 |
ager | -0.001 |
P | -0.001 |
bes | -0.001 |
Token | words |
Token ID | 2456 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
theirs | +0.105 |
rings | +0.088 |
what | +0.088 |
are | +0.081 |
wow | +0.078 |
Neg logit contributions | |
Just | -0.093 |
P | -0.088 |
ager | -0.086 |
age | -0.083 |
eh | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
theirs | +0.102 |
rings | +0.088 |
what | +0.080 |
wow | +0.078 |
nam | +0.077 |
Neg logit contributions | |
Just | -0.087 |
age | -0.081 |
ager | -0.080 |
bes | -0.075 |
P | -0.075 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
theirs | +0.020 |
rings | +0.016 |
what | +0.015 |
are | +0.014 |
wow | +0.014 |
Neg logit contributions | |
Just | -0.021 |
ager | -0.020 |
age | -0.020 |
P | -0.020 |
ivering | -0.019 |
Token | Once |
Token ID | 7454 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
theirs | +0.067 |
are | +0.054 |
what | +0.054 |
rings | +0.052 |
their | +0.049 |
Neg logit contributions | |
Just | -0.098 |
ager | -0.094 |
age | -0.092 |
ivering | -0.092 |
bes | -0.088 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
theirs | +0.084 |
rings | +0.077 |
wow | +0.071 |
nam | +0.071 |
flashes | +0.062 |
Neg logit contributions | |
Just | -0.081 |
P | -0.075 |
year | -0.074 |
eh | -0.072 |
Lu | -0.071 |
Token | a |
Token ID | 257 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Just | +0.028 |
ager | +0.025 |
age | +0.025 |
P | +0.025 |
bes | +0.024 |
Neg logit contributions | |
theirs | -0.020 |
rings | -0.018 |
ours | -0.015 |
wow | -0.014 |
nam | -0.014 |
Token | time |
Token ID | 640 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
age | +0.013 |
Just | +0.013 |
amas | +0.012 |
bes | +0.012 |
ager | +0.012 |
Neg logit contributions | |
theirs | -0.013 |
what | -0.012 |
are | -0.011 |
their | -0.011 |
look | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
Just | +0.004 |
ager | +0.003 |
age | +0.003 |
P | +0.003 |
bes | +0.003 |
Neg logit contributions | |
theirs | -0.004 |
rings | -0.003 |
what | -0.003 |
nam | -0.003 |
wow | -0.003 |
Token | there |
Token ID | 612 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
theirs | +0.017 |
rings | +0.015 |
wow | +0.012 |
nam | +0.012 |
what | +0.011 |
Neg logit contributions | |
Just | -0.017 |
P | -0.016 |
ager | -0.015 |
sy | -0.015 |
age | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Just | +0.024 |
age | +0.021 |
ager | +0.021 |
P | +0.020 |
bes | +0.020 |
Neg logit contributions | |
theirs | -0.049 |
rings | -0.044 |
what | -0.040 |
nam | -0.039 |
wow | -0.039 |
Token | - |
Token ID | 12 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Just | +0.002 |
age | +0.002 |
lor | +0.002 |
amas | +0.002 |
ager | +0.002 |
Neg logit contributions | |
theirs | -0.004 |
what | -0.004 |
are | -0.003 |
their | -0.003 |
rings | -0.003 |
Token | years |
Token ID | 19002 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Just | +0.012 |
age | +0.011 |
ager | +0.011 |
P | +0.011 |
bes | +0.010 |
Neg logit contributions | |
theirs | -0.011 |
rings | -0.009 |
what | -0.008 |
wow | -0.008 |
are | -0.008 |
Token | old |
Token ID | 1468 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
theirs | +0.164 |
rings | +0.141 |
what | +0.136 |
are | +0.129 |
their | +0.127 |
Neg logit contributions | |
Just | -0.074 |
bes | -0.062 |
Now | -0.060 |
age | -0.059 |
P | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
theirs | +0.109 |
rings | +0.095 |
what | +0.094 |
are | +0.087 |
their | +0.083 |
Neg logit contributions | |
Just | -0.124 |
age | -0.117 |
ager | -0.116 |
oster | -0.113 |
bes | -0.112 |
Token | One |
Token ID | 1881 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
Just | +0.004 |
age | +0.003 |
P | +0.003 |
ager | +0.003 |
Lu | +0.003 |
Neg logit contributions | |
theirs | -0.003 |
rings | -0.003 |
nam | -0.002 |
wow | -0.002 |
what | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
theirs | +0.098 |
rings | +0.082 |
what | +0.080 |
are | +0.077 |
wow | +0.074 |
Neg logit contributions | |
Just | -0.080 |
ager | -0.072 |
age | -0.072 |
bes | -0.071 |
P | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
Just | +0.081 |
P | +0.073 |
ager | +0.073 |
age | +0.072 |
ivering | +0.068 |
Neg logit contributions | |
theirs | -0.092 |
rings | -0.079 |
what | -0.069 |
nam | -0.068 |
wow | -0.068 |
Token | Sally |
Token ID | 25737 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
theirs | +0.004 |
rings | +0.003 |
wow | +0.003 |
ours | +0.002 |
what | +0.002 |
Neg logit contributions | |
Just | -0.006 |
P | -0.005 |
ager | -0.005 |
eh | -0.005 |
Lu | -0.005 |
Token | went |
Token ID | 1816 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
theirs | +0.023 |
are | +0.021 |
what | +0.020 |
rings | +0.020 |
their | +0.019 |
Neg logit contributions | |
Just | -0.039 |
bes | -0.036 |
age | -0.036 |
oster | -0.036 |
ivering | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
theirs | +0.036 |
rings | +0.029 |
what | +0.028 |
are | +0.025 |
their | +0.024 |
Neg logit contributions | |
Just | -0.050 |
ager | -0.047 |
age | -0.047 |
ivering | -0.045 |
bes | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
theirs | +0.026 |
rings | +0.023 |
wow | +0.019 |
ours | +0.018 |
bars | +0.018 |
Neg logit contributions | |
Just | -0.034 |
P | -0.033 |
ager | -0.032 |
Lu | -0.031 |
seek | -0.031 |
Token | seeing |
Token ID | 4379 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
theirs | +0.041 |
rings | +0.035 |
wow | +0.030 |
nam | +0.029 |
are | +0.029 |
Neg logit contributions | |
Just | -0.050 |
ager | -0.046 |
age | -0.045 |
P | -0.044 |
bes | -0.044 |
Token | all |
Token ID | 477 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Just | +0.020 |
bes | +0.019 |
ze | +0.019 |
zer | +0.019 |
P | +0.019 |
Neg logit contributions | |
theirs | -0.012 |
rings | -0.010 |
wow | -0.009 |
ours | -0.008 |
are | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
theirs | +0.086 |
rings | +0.081 |
wow | +0.070 |
nam | +0.060 |
ours | +0.058 |
Neg logit contributions | |
age | -0.135 |
eh | -0.134 |
Just | -0.133 |
ager | -0.131 |
Lu | -0.129 |
Token | people |
Token ID | 661 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
Just | +0.029 |
age | +0.027 |
ager | +0.026 |
bes | +0.026 |
P | +0.025 |
Neg logit contributions | |
theirs | -0.026 |
rings | -0.021 |
what | -0.021 |
are | -0.019 |
nam | -0.018 |
Token | go |
Token ID | 467 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
Just | +0.014 |
age | +0.013 |
ivering | +0.013 |
ager | +0.013 |
bes | +0.012 |
Neg logit contributions | |
theirs | -0.020 |
rings | -0.017 |
wow | -0.016 |
what | -0.015 |
nam | -0.014 |
Token | hungry |
Token ID | 14720 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
theirs | +0.094 |
rings | +0.078 |
what | +0.074 |
are | +0.069 |
their | +0.067 |
Neg logit contributions | |
Just | -0.095 |
ager | -0.088 |
age | -0.088 |
P | -0.084 |
bes | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Just | +0.065 |
age | +0.060 |
ager | +0.060 |
P | +0.059 |
bes | +0.057 |
Neg logit contributions | |
theirs | -0.057 |
rings | -0.046 |
what | -0.044 |
are | -0.042 |
their | -0.039 |
Token | She |
Token ID | 1375 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
theirs | +0.008 |
rings | +0.006 |
what | +0.006 |
are | +0.005 |
wow | +0.005 |
Neg logit contributions | |
Just | -0.016 |
ager | -0.015 |
age | -0.015 |
P | -0.015 |
ivering | -0.015 |
Token | had |
Token ID | 550 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
Just | +0.008 |
age | +0.008 |
ivering | +0.008 |
amas | +0.008 |
bes | +0.008 |
Neg logit contributions | |
theirs | -0.005 |
what | -0.004 |
rings | -0.004 |
are | -0.004 |
their | -0.004 |
Token | an |
Token ID | 281 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
Just | +0.020 |
age | +0.019 |
ager | +0.019 |
P | +0.018 |
bes | +0.018 |
Neg logit contributions | |
theirs | -0.014 |
rings | -0.012 |
what | -0.011 |
wow | -0.010 |
are | -0.010 |
Token | idea |
Token ID | 2126 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
Just | +0.040 |
age | +0.038 |
ager | +0.037 |
P | +0.036 |
bes | +0.036 |
Neg logit contributions | |
theirs | -0.033 |
rings | -0.028 |
what | -0.025 |
wow | -0.024 |
are | -0.024 |
Token | 3 |
Token ID | 513 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
Just | +0.072 |
age | +0.070 |
ager | +0.069 |
P | +0.063 |
ivering | +0.062 |
Neg logit contributions | |
theirs | -0.117 |
rings | -0.103 |
what | -0.093 |
nam | -0.090 |
are | -0.090 |
Token | year |
Token ID | 614 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
Just | +0.017 |
amas | +0.016 |
ivering | +0.014 |
P | +0.014 |
lor | +0.013 |
Neg logit contributions | |
theirs | -0.034 |
what | -0.032 |
are | -0.029 |
their | -0.029 |
it | -0.028 |
Token | old |
Token ID | 1468 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Just | +0.094 |
age | +0.088 |
ager | +0.087 |
P | +0.084 |
bes | +0.083 |
Neg logit contributions | |
theirs | -0.077 |
rings | -0.064 |
what | -0.058 |
wow | -0.055 |
are | -0.054 |
Token | named |
Token ID | 3706 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
theirs | +0.121 |
rings | +0.104 |
what | +0.097 |
wow | +0.092 |
are | +0.092 |
Neg logit contributions | |
Just | -0.101 |
age | -0.093 |
ager | -0.093 |
P | -0.089 |
bes | -0.088 |
Token | Tommy |
Token ID | 19919 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
theirs | +0.060 |
rings | +0.047 |
what | +0.041 |
wow | +0.038 |
are | +0.038 |
Neg logit contributions | |
Just | -0.104 |
age | -0.098 |
ager | -0.098 |
P | -0.095 |
bes | -0.094 |
Token | wanted |
Token ID | 2227 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
theirs | +0.064 |
rings | +0.054 |
what | +0.050 |
wow | +0.048 |
are | +0.047 |
Neg logit contributions | |
Just | -0.058 |
age | -0.054 |
ager | -0.054 |
P | -0.052 |
bes | -0.051 |
Token | to |
Token ID | 284 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
Just | +0.049 |
age | +0.046 |
ager | +0.045 |
P | +0.043 |
sy | +0.042 |
Neg logit contributions | |
theirs | -0.053 |
rings | -0.046 |
wow | -0.042 |
are | -0.040 |
nam | -0.040 |
Token | open |
Token ID | 1280 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
theirs | +0.033 |
rings | +0.027 |
what | +0.024 |
wow | +0.024 |
nam | +0.023 |
Neg logit contributions | |
Just | -0.038 |
age | -0.037 |
ager | -0.036 |
P | -0.034 |
bes | -0.033 |
Token | it |
Token ID | 340 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
theirs | +0.005 |
rings | +0.004 |
wow | +0.004 |
ours | +0.004 |
are | +0.004 |
Neg logit contributions | |
Just | -0.005 |
zer | -0.005 |
bes | -0.005 |
ers | -0.005 |
ce | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
theirs | +0.020 |
rings | +0.017 |
what | +0.015 |
wow | +0.015 |
are | +0.015 |
Neg logit contributions | |
Just | -0.019 |
age | -0.017 |
ager | -0.017 |
P | -0.016 |
bes | -0.016 |
Token | but |
Token ID | 475 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
theirs | +0.018 |
rings | +0.016 |
ours | +0.014 |
wow | +0.014 |
angles | +0.014 |
Neg logit contributions | |
Just | -0.012 |
age | -0.010 |
ager | -0.009 |
sy | -0.009 |
bes | -0.009 |
Token | label |
Token ID | 6167 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
Just | +0.030 |
age | +0.028 |
ager | +0.027 |
bes | +0.026 |
P | +0.026 |
Neg logit contributions | |
theirs | -0.029 |
rings | -0.024 |
what | -0.022 |
wow | -0.021 |
are | -0.021 |
Token | that |
Token ID | 326 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
theirs | +0.028 |
rings | +0.023 |
what | +0.021 |
wow | +0.021 |
nam | +0.020 |
Neg logit contributions | |
Just | -0.028 |
age | -0.027 |
ager | -0.026 |
P | -0.025 |
bes | -0.025 |
Token | said |
Token ID | 531 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
theirs | +0.017 |
rings | +0.014 |
what | +0.013 |
wow | +0.013 |
nam | +0.012 |
Neg logit contributions | |
Just | -0.017 |
ager | -0.015 |
age | -0.015 |
P | -0.015 |
bes | -0.015 |
Token | " |
Token ID | 366 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
Just | +0.021 |
age | +0.020 |
bes | +0.018 |
ager | +0.018 |
ze | +0.018 |
Neg logit contributions | |
theirs | -0.024 |
rings | -0.020 |
nam | -0.020 |
ours | -0.018 |
angles | -0.017 |
Token | del |
Token ID | 12381 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Just | +0.022 |
ager | +0.021 |
age | +0.020 |
ivering | +0.019 |
bes | +0.019 |
Neg logit contributions | |
theirs | -0.032 |
rings | -0.029 |
what | -0.026 |
are | -0.025 |
nam | -0.025 |
Token | iver |
Token ID | 1428 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
Just | +0.095 |
ager | +0.091 |
bes | +0.088 |
P | +0.085 |
age | +0.083 |
Neg logit contributions | |
theirs | -0.177 |
rings | -0.157 |
what | -0.142 |
are | -0.141 |
angles | -0.137 |
Token | to |
Token ID | 284 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
Just | +0.233 |
ager | +0.206 |
P | +0.198 |
bes | +0.195 |
age | +0.192 |
Neg logit contributions | |
theirs | -0.332 |
what | -0.286 |
rings | -0.282 |
are | -0.274 |
wow | -0.257 |
Token | Mr |
Token ID | 1770 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
theirs | +0.030 |
rings | +0.025 |
what | +0.022 |
wow | +0.022 |
are | +0.021 |
Neg logit contributions | |
Just | -0.033 |
age | -0.031 |
ager | -0.030 |
P | -0.029 |
bes | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
theirs | +0.161 |
rings | +0.136 |
what | +0.126 |
are | +0.118 |
wow | +0.115 |
Neg logit contributions | |
Just | -0.169 |
ager | -0.155 |
age | -0.155 |
P | -0.149 |
bes | -0.148 |
Token | Smith |
Token ID | 4176 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
theirs | +0.031 |
rings | +0.027 |
what | +0.025 |
wow | +0.023 |
are | +0.023 |
Neg logit contributions | |
Just | -0.039 |
ager | -0.037 |
age | -0.036 |
P | -0.036 |
ivering | -0.035 |
Token | ". |
Token ID | 1911 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
Just | +0.057 |
age | +0.051 |
ager | +0.051 |
P | +0.049 |
bes | +0.048 |
Neg logit contributions | |
theirs | -0.087 |
rings | -0.076 |
what | -0.072 |
are | -0.069 |
wow | -0.068 |
Token | Then |
Token ID | 3244 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
Just | +0.052 |
age | +0.049 |
ager | +0.048 |
P | +0.047 |
bes | +0.046 |
Neg logit contributions | |
theirs | -0.037 |
rings | -0.030 |
what | -0.027 |
wow | -0.025 |
are | -0.025 |
Token | she |
Token ID | 673 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
Just | +0.069 |
age | +0.065 |
ager | +0.065 |
P | +0.064 |
bes | +0.062 |
Neg logit contributions | |
theirs | -0.040 |
rings | -0.031 |
what | -0.025 |
nam | -0.025 |
wow | -0.024 |
Token | went |
Token ID | 1816 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
Just | +0.066 |
age | +0.061 |
ager | +0.061 |
P | +0.059 |
bes | +0.058 |
Neg logit contributions | |
theirs | -0.061 |
rings | -0.052 |
what | -0.049 |
are | -0.046 |
wow | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
theirs | +0.041 |
rings | +0.034 |
what | +0.033 |
their | +0.029 |
wow | +0.028 |
Neg logit contributions | |
Just | -0.051 |
ager | -0.049 |
age | -0.047 |
P | -0.046 |
ivering | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
theirs | +0.001 |
rings | +0.001 |
wow | +0.001 |
nam | +0.001 |
ours | +0.001 |
Neg logit contributions | |
Just | -0.002 |
age | -0.002 |
ager | -0.002 |
bes | -0.002 |
P | -0.002 |
Token | kitchen |
Token ID | 9592 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Just | +0.029 |
ager | +0.027 |
age | +0.026 |
ivering | +0.025 |
bes | +0.025 |
Neg logit contributions | |
theirs | -0.033 |
rings | -0.030 |
what | -0.029 |
are | -0.027 |
wow | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Just | +0.220 |
P | +0.208 |
age | +0.207 |
ager | +0.206 |
oster | +0.200 |
Neg logit contributions | |
theirs | -0.196 |
rings | -0.163 |
what | -0.160 |
their | -0.146 |
are | -0.146 |
Token | get |
Token ID | 651 |
Feature activation | +9.82e-03 |
Pos logit contributions | |
theirs | +0.012 |
rings | +0.011 |
wow | +0.009 |
what | +0.008 |
nam | +0.008 |
Neg logit contributions | |
Just | -0.016 |
age | -0.015 |
ager | -0.015 |
P | -0.014 |
bes | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
theirs | +0.001 |
rings | +0.001 |
wow | +0.001 |
are | +0.001 |
angles | +0.001 |
Neg logit contributions | |
Just | -0.001 |
P | -0.001 |
sy | -0.001 |
age | -0.001 |
ager | -0.001 |
Token | snack |
Token ID | 26906 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
Just | +0.011 |
age | +0.010 |
ager | +0.010 |
P | +0.010 |
sy | +0.009 |
Neg logit contributions | |
theirs | -0.011 |
rings | -0.010 |
what | -0.008 |
nam | -0.008 |
wow | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Just | +0.053 |
ager | +0.049 |
age | +0.047 |
ivering | +0.047 |
P | +0.047 |
Neg logit contributions | |
theirs | -0.042 |
rings | -0.035 |
what | -0.032 |
are | -0.032 |
their | -0.029 |
Token | They |
Token ID | 1119 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
Just | +0.027 |
ager | +0.024 |
age | +0.024 |
bes | +0.023 |
P | +0.023 |
Neg logit contributions | |
theirs | -0.018 |
rings | -0.016 |
nam | -0.014 |
wow | -0.013 |
what | -0.013 |
Token | could |
Token ID | 714 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
Just | +0.029 |
ager | +0.027 |
age | +0.026 |
P | +0.026 |
bes | +0.026 |
Neg logit contributions | |
theirs | -0.032 |
rings | -0.027 |
wow | -0.024 |
what | -0.023 |
ours | -0.023 |
Token | see |
Token ID | 766 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
theirs | +0.038 |
rings | +0.035 |
nam | +0.031 |
wow | +0.030 |
ours | +0.030 |
Neg logit contributions | |
Just | -0.030 |
age | -0.027 |
ager | -0.026 |
bes | -0.026 |
ze | -0.025 |
Token | it |
Token ID | 340 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
rings | +0.040 |
theirs | +0.039 |
nam | +0.034 |
wow | +0.029 |
bars | +0.029 |
Neg logit contributions | |
ers | -0.055 |
fire | -0.055 |
zer | -0.055 |
ze | -0.055 |
Just | -0.055 |
Token | sailing |
Token ID | 28499 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Just | +0.009 |
age | +0.008 |
ze | +0.008 |
ager | +0.008 |
fire | +0.008 |
Neg logit contributions | |
theirs | -0.012 |
rings | -0.011 |
nam | -0.011 |
wow | -0.009 |
ours | -0.009 |
Token | away |
Token ID | 1497 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
theirs | +0.100 |
rings | +0.091 |
what | +0.080 |
wow | +0.079 |
nam | +0.078 |
Neg logit contributions | |
Just | -0.085 |
age | -0.080 |
ager | -0.079 |
P | -0.075 |
bes | -0.074 |
Token | in |
Token ID | 287 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
Just | +0.197 |
age | +0.181 |
ager | +0.181 |
P | +0.173 |
bes | +0.172 |
Neg logit contributions | |
theirs | -0.224 |
rings | -0.193 |
what | -0.176 |
wow | -0.171 |
are | -0.167 |
Token | the |
Token ID | 262 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
Just | +0.082 |
P | +0.078 |
bes | +0.078 |
ager | +0.077 |
fire | +0.076 |
Neg logit contributions | |
theirs | -0.046 |
rings | -0.045 |
wow | -0.034 |
ours | -0.032 |
nam | -0.030 |
Token | distance |
Token ID | 5253 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Just | +0.038 |
age | +0.035 |
ager | +0.035 |
P | +0.034 |
bes | +0.034 |
Neg logit contributions | |
theirs | -0.031 |
rings | -0.025 |
what | -0.023 |
are | -0.022 |
wow | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
theirs | +0.128 |
rings | +0.110 |
what | +0.100 |
wow | +0.098 |
nam | +0.097 |
Neg logit contributions | |
Just | -0.110 |
age | -0.102 |
ager | -0.101 |
P | -0.095 |
bes | -0.095 |
Token | They |
Token ID | 1119 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
Just | +0.023 |
ager | +0.020 |
age | +0.020 |
P | +0.019 |
bes | +0.019 |
Neg logit contributions | |
theirs | -0.024 |
rings | -0.021 |
nam | -0.019 |
wow | -0.018 |
what | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
Just | +0.206 |
ager | +0.195 |
age | +0.194 |
P | +0.187 |
bes | +0.183 |
Neg logit contributions | |
theirs | -0.226 |
rings | -0.189 |
what | -0.184 |
are | -0.171 |
wow | -0.166 |
Token | said |
Token ID | 531 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
Just | +0.031 |
age | +0.028 |
ager | +0.028 |
P | +0.027 |
bes | +0.027 |
Neg logit contributions | |
theirs | -0.031 |
rings | -0.026 |
what | -0.022 |
wow | -0.022 |
are | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
Just | +0.030 |
age | +0.027 |
P | +0.025 |
ze | +0.025 |
ager | +0.024 |
Neg logit contributions | |
theirs | -0.045 |
rings | -0.039 |
nam | -0.036 |
ours | -0.035 |
angles | -0.034 |
Token | " |
Token ID | 366 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
theirs | +0.002 |
rings | +0.002 |
what | +0.002 |
wow | +0.002 |
are | +0.002 |
Neg logit contributions | |
Just | -0.003 |
age | -0.003 |
ager | -0.003 |
P | -0.003 |
bes | -0.003 |
Token | Go |
Token ID | 5247 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
sy | +0.027 |
age | +0.027 |
ager | +0.026 |
amas | +0.026 |
bes | +0.025 |
Neg logit contributions | |
theirs | -0.026 |
rings | -0.024 |
are | -0.023 |
Tom | -0.021 |
what | -0.021 |
Token | away |
Token ID | 1497 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
theirs | +0.038 |
what | +0.035 |
are | +0.033 |
look | +0.031 |
their | +0.030 |
Neg logit contributions | |
Just | -0.044 |
bes | -0.044 |
amas | -0.040 |
ager | -0.040 |
rd | -0.040 |
Token | ! |
Token ID | 0 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Just | +0.287 |
age | +0.266 |
ager | +0.264 |
P | +0.261 |
bes | +0.259 |
Neg logit contributions | |
theirs | -0.134 |
what | -0.131 |
are | -0.114 |
their | -0.105 |
Tom | -0.102 |
Token | Anna |
Token ID | 11735 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Just | +0.015 |
age | +0.014 |
ager | +0.014 |
P | +0.013 |
bes | +0.013 |
Neg logit contributions | |
theirs | -0.015 |
rings | -0.013 |
what | -0.012 |
wow | -0.011 |
are | -0.011 |
Token | is |
Token ID | 318 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
Just | +0.029 |
age | +0.026 |
P | +0.026 |
ager | +0.026 |
bes | +0.025 |
Neg logit contributions | |
theirs | -0.020 |
are | -0.018 |
what | -0.017 |
rings | -0.016 |
their | -0.014 |
Token | mine |
Token ID | 6164 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
theirs | +0.042 |
rings | +0.035 |
what | +0.032 |
wow | +0.030 |
are | +0.030 |
Neg logit contributions | |
Just | -0.048 |
age | -0.045 |
ager | -0.045 |
P | -0.043 |
bes | -0.043 |
Token | now |
Token ID | 783 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
Just | +0.114 |
age | +0.111 |
P | +0.109 |
ager | +0.107 |
oster | +0.105 |
Neg logit contributions | |
theirs | -0.116 |
what | -0.099 |
rings | -0.095 |
are | -0.094 |
wow | -0.086 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
theirs | +0.128 |
rings | +0.106 |
what | +0.101 |
are | +0.099 |
wow | +0.092 |
Neg logit contributions | |
Just | -0.155 |
ager | -0.144 |
age | -0.143 |
P | -0.141 |
bes | -0.139 |
Token | Anna |
Token ID | 11735 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
Just | +0.144 |
ager | +0.139 |
age | +0.138 |
ivering | +0.134 |
bes | +0.133 |
Neg logit contributions | |
theirs | -0.075 |
rings | -0.058 |
what | -0.053 |
are | -0.048 |
wow | -0.047 |
Token | said |
Token ID | 531 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
Just | +0.072 |
age | +0.068 |
ager | +0.067 |
P | +0.066 |
bes | +0.065 |
Neg logit contributions | |
theirs | -0.048 |
rings | -0.039 |
what | -0.035 |
wow | -0.033 |
are | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
Just | +0.039 |
age | +0.036 |
ager | +0.035 |
P | +0.034 |
bes | +0.034 |
Neg logit contributions | |
theirs | -0.042 |
rings | -0.036 |
what | -0.033 |
wow | -0.031 |
are | -0.031 |
Token | " |
Token ID | 366 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
Just | +0.049 |
age | +0.045 |
ager | +0.044 |
P | +0.044 |
bes | +0.043 |
Neg logit contributions | |
theirs | -0.041 |
rings | -0.034 |
what | -0.031 |
wow | -0.029 |
are | -0.029 |
Token | But |
Token ID | 1537 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
Just | +0.041 |
age | +0.039 |
ager | +0.039 |
ivering | +0.038 |
bes | +0.038 |
Neg logit contributions | |
theirs | -0.062 |
rings | -0.054 |
what | -0.050 |
are | -0.049 |
wow | -0.049 |
Token | can |
Token ID | 460 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
Just | +0.234 |
ager | +0.209 |
age | +0.208 |
P | +0.207 |
bes | +0.207 |
Neg logit contributions | |
theirs | -0.199 |
rings | -0.161 |
nam | -0.131 |
wow | -0.123 |
what | -0.120 |
Token | you |
Token ID | 345 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
theirs | +0.071 |
rings | +0.057 |
wow | +0.051 |
what | +0.051 |
nam | +0.048 |
Neg logit contributions | |
Just | -0.068 |
age | -0.062 |
bes | -0.061 |
P | -0.060 |
ager | -0.060 |
Token | number |
Token ID | 1271 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Just | +0.035 |
ager | +0.033 |
age | +0.032 |
bes | +0.032 |
P | +0.032 |
Neg logit contributions | |
theirs | -0.020 |
rings | -0.016 |
what | -0.015 |
are | -0.015 |
wow | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
Just | +0.115 |
co | +0.105 |
P | +0.105 |
age | +0.103 |
ce | +0.103 |
Neg logit contributions | |
theirs | -0.088 |
rings | -0.067 |
wow | -0.062 |
nam | -0.056 |
maybe | -0.052 |
Token | flowers |
Token ID | 12734 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
Just | +0.043 |
ager | +0.040 |
age | +0.040 |
P | +0.038 |
bes | +0.038 |
Neg logit contributions | |
theirs | -0.040 |
rings | -0.034 |
what | -0.031 |
are | -0.029 |
wow | -0.029 |