Token | nodded |
Token ID | 14464 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
flower | +0.055 |
ble | +0.048 |
els | +0.046 |
cking | +0.046 |
ric | +0.045 |
Neg logit contributions | |
ives | -0.041 |
Enjoy | -0.037 |
Welcome | -0.036 |
ury | -0.036 |
Happy | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
ric | +0.024 |
flower | +0.024 |
cks | +0.023 |
cking | +0.023 |
els | +0.022 |
Neg logit contributions | |
Max | -0.007 |
And | -0.007 |
Happy | -0.006 |
hide | -0.005 |
ives | -0.005 |
Token | put |
Token ID | 1234 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
flower | +0.026 |
ble | +0.022 |
cking | +0.021 |
eled | +0.021 |
bery | +0.021 |
Neg logit contributions | |
ives | -0.026 |
Enjoy | -0.022 |
Welcome | -0.021 |
ury | -0.021 |
These | -0.021 |
Token | on |
Token ID | 319 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
flower | +0.030 |
ric | +0.028 |
ble | +0.027 |
cking | +0.027 |
mill | +0.025 |
Neg logit contributions | |
ives | -0.018 |
Max | -0.017 |
Enjoy | -0.016 |
Happy | -0.016 |
Now | -0.015 |
Token | their |
Token ID | 511 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
flower | +0.096 |
ble | +0.086 |
ric | +0.079 |
mill | +0.078 |
cker | +0.077 |
Neg logit contributions | |
Max | -0.074 |
Enjoy | -0.067 |
Happy | -0.067 |
ives | -0.067 |
And | -0.066 |
Token | rain |
Token ID | 6290 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
flower | +0.029 |
ble | +0.026 |
ric | +0.026 |
cking | +0.025 |
els | +0.024 |
Neg logit contributions | |
ives | -0.029 |
ury | -0.026 |
Welcome | -0.026 |
Happy | -0.026 |
Max | -0.026 |
Token | co |
Token ID | 1073 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
flower | +0.193 |
ble | +0.183 |
ric | +0.180 |
cking | +0.179 |
els | +0.174 |
Neg logit contributions | |
ives | -0.129 |
ury | -0.111 |
Max | -0.101 |
hide | -0.100 |
and | -0.095 |
Token | ats |
Token ID | 1381 |
Feature activation | +7.03e-02 |
Pos logit contributions | |
flower | +0.014 |
ble | +0.012 |
ric | +0.012 |
els | +0.012 |
cking | +0.012 |
Neg logit contributions | |
ives | -0.012 |
ury | -0.011 |
Enjoy | -0.011 |
Welcome | -0.010 |
Follow | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
flower | +0.003 |
ble | +0.003 |
els | +0.003 |
ric | +0.002 |
cking | +0.002 |
Neg logit contributions | |
ives | -0.003 |
Enjoy | -0.003 |
ury | -0.003 |
Welcome | -0.003 |
Follow | -0.002 |
Token | boots |
Token ID | 14412 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
flower | +0.039 |
ble | +0.034 |
ric | +0.033 |
els | +0.033 |
cking | +0.033 |
Neg logit contributions | |
ives | -0.051 |
ury | -0.046 |
Enjoy | -0.045 |
Welcome | -0.044 |
Follow | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
flower | +0.058 |
ble | +0.051 |
els | +0.048 |
ric | +0.048 |
cking | +0.048 |
Neg logit contributions | |
ives | -0.067 |
Enjoy | -0.064 |
ury | -0.062 |
Welcome | -0.062 |
Follow | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
ives | +0.000 |
ury | +0.000 |
Enjoy | +0.000 |
Welcome | +0.000 |
Follow | +0.000 |
Neg logit contributions | |
flower | -0.000 |
ble | -0.000 |
ric | -0.000 |
els | -0.000 |
cking | -0.000 |
Token | his |
Token ID | 465 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
ives | +0.002 |
ury | +0.002 |
Enjoy | +0.002 |
Max | +0.002 |
Welcome | +0.002 |
Neg logit contributions | |
flower | -0.002 |
ble | -0.002 |
cking | -0.002 |
ric | -0.002 |
els | -0.002 |
Token | dog |
Token ID | 3290 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
flower | +0.032 |
ble | +0.028 |
ric | +0.028 |
els | +0.027 |
cking | +0.027 |
Neg logit contributions | |
ives | -0.022 |
ury | -0.019 |
Enjoy | -0.018 |
Welcome | -0.018 |
Follow | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
flower | +0.026 |
ble | +0.023 |
ric | +0.023 |
els | +0.023 |
cking | +0.023 |
Neg logit contributions | |
ives | -0.025 |
ury | -0.022 |
Enjoy | -0.022 |
Welcome | -0.021 |
Follow | -0.021 |
Token | his |
Token ID | 465 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
flower | +0.022 |
ble | +0.019 |
ric | +0.019 |
cking | +0.019 |
els | +0.019 |
Neg logit contributions | |
ives | -0.021 |
ury | -0.019 |
Enjoy | -0.019 |
Welcome | -0.018 |
Max | -0.018 |
Token | sunset |
Token ID | 26428 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
flower | +0.062 |
ble | +0.055 |
ric | +0.054 |
els | +0.053 |
cking | +0.052 |
Neg logit contributions | |
ives | -0.043 |
ury | -0.037 |
Enjoy | -0.036 |
Follow | -0.034 |
Welcome | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
flower | +0.164 |
ble | +0.145 |
ric | +0.141 |
cking | +0.140 |
els | +0.140 |
Neg logit contributions | |
ives | -0.158 |
ury | -0.143 |
Enjoy | -0.140 |
Welcome | -0.136 |
Follow | -0.133 |
Token | He |
Token ID | 679 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ives | +0.009 |
ury | +0.008 |
Enjoy | +0.007 |
Welcome | +0.007 |
Follow | +0.007 |
Neg logit contributions | |
flower | -0.014 |
ric | -0.013 |
ble | -0.013 |
cks | -0.012 |
mill | -0.012 |
Token | says |
Token ID | 1139 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ives | +0.005 |
Enjoy | +0.004 |
ury | +0.004 |
Welcome | +0.003 |
Happy | +0.003 |
Neg logit contributions | |
flower | -0.012 |
ble | -0.011 |
ric | -0.011 |
cking | -0.011 |
els | -0.010 |
Token | he |
Token ID | 339 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
ives | +0.038 |
ury | +0.033 |
Enjoy | +0.031 |
Follow | +0.031 |
Welcome | +0.030 |
Neg logit contributions | |
flower | -0.048 |
ble | -0.044 |
ric | -0.042 |
els | -0.042 |
cking | -0.042 |
Token | does |
Token ID | 857 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
ives | +0.024 |
ury | +0.023 |
Welcome | +0.023 |
Happy | +0.023 |
and | +0.023 |
Neg logit contributions | |
flower | -0.032 |
ric | -0.029 |
els | -0.029 |
ble | -0.028 |
cks | -0.027 |
Token | him |
Token ID | 683 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
ives | +0.010 |
ury | +0.009 |
Enjoy | +0.008 |
Welcome | +0.008 |
Follow | +0.008 |
Neg logit contributions | |
flower | -0.011 |
ble | -0.010 |
els | -0.009 |
cking | -0.009 |
ric | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
flower | +0.020 |
ble | +0.018 |
ric | +0.018 |
cking | +0.018 |
els | +0.018 |
Neg logit contributions | |
ives | -0.013 |
ury | -0.011 |
Enjoy | -0.011 |
Max | -0.011 |
Welcome | -0.011 |
Token | Joe |
Token ID | 5689 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
flower | +0.038 |
ble | +0.035 |
ric | +0.034 |
cking | +0.033 |
els | +0.033 |
Neg logit contributions | |
ives | -0.030 |
ury | -0.026 |
Enjoy | -0.025 |
Welcome | -0.024 |
Follow | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
flower | +0.118 |
ble | +0.112 |
cking | +0.109 |
els | +0.108 |
ric | +0.108 |
Neg logit contributions | |
ives | -0.057 |
ury | -0.047 |
Max | -0.046 |
Enjoy | -0.045 |
Welcome | -0.045 |
Token | his |
Token ID | 465 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
flower | +0.050 |
ble | +0.046 |
ric | +0.045 |
cking | +0.045 |
els | +0.044 |
Neg logit contributions | |
ives | -0.036 |
ury | -0.032 |
Enjoy | -0.032 |
Welcome | -0.031 |
Happy | -0.030 |
Token | brick |
Token ID | 17214 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
flower | +0.075 |
ble | +0.068 |
ric | +0.066 |
cking | +0.066 |
els | +0.065 |
Neg logit contributions | |
ives | -0.062 |
ury | -0.056 |
Enjoy | -0.054 |
Welcome | -0.053 |
Happy | -0.051 |
Token | were |
Token ID | 547 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
cking | +0.191 |
cks | +0.190 |
flower | +0.190 |
ble | +0.190 |
ric | +0.185 |
Neg logit contributions | |
ives | -0.101 |
Sadly | -0.091 |
Max | -0.088 |
And | -0.086 |
People | -0.083 |
Token | best |
Token ID | 1266 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
flower | +0.049 |
ric | +0.046 |
els | +0.045 |
ble | +0.045 |
bery | +0.044 |
Neg logit contributions | |
ives | -0.017 |
Max | -0.017 |
Enjoy | -0.017 |
Happy | -0.016 |
Welcome | -0.016 |
Token | friends |
Token ID | 2460 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
ives | +0.009 |
ury | +0.007 |
Enjoy | +0.007 |
Welcome | +0.007 |
Follow | +0.007 |
Neg logit contributions | |
flower | -0.016 |
ble | -0.015 |
ric | -0.014 |
els | -0.014 |
cking | -0.014 |
Token | ! |
Token ID | 0 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
ives | +0.011 |
ury | +0.010 |
Enjoy | +0.010 |
Follow | +0.010 |
Welcome | +0.010 |
Neg logit contributions | |
flower | -0.011 |
ble | -0.009 |
ric | -0.009 |
cking | -0.009 |
els | -0.009 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
flower | +0.045 |
ble | +0.042 |
cking | +0.042 |
els | +0.041 |
ric | +0.041 |
Neg logit contributions | |
ives | -0.014 |
Enjoy | -0.011 |
ury | -0.011 |
Welcome | -0.011 |
Happy | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
flower | +0.029 |
ble | +0.025 |
ric | +0.025 |
els | +0.025 |
cking | +0.025 |
Neg logit contributions | |
ives | -0.021 |
ury | -0.019 |
Enjoy | -0.019 |
Welcome | -0.018 |
Follow | -0.018 |
Token | his |
Token ID | 465 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
flower | +0.013 |
ble | +0.011 |
cking | +0.011 |
ric | +0.011 |
els | +0.011 |
Neg logit contributions | |
ives | -0.010 |
ury | -0.009 |
Enjoy | -0.009 |
Max | -0.009 |
Welcome | -0.009 |
Token | dog |
Token ID | 3290 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
flower | +0.054 |
ble | +0.049 |
ric | +0.048 |
els | +0.047 |
cking | +0.047 |
Neg logit contributions | |
ives | -0.041 |
ury | -0.036 |
Enjoy | -0.035 |
Welcome | -0.034 |
Follow | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
flower | +0.045 |
ble | +0.039 |
ric | +0.039 |
els | +0.039 |
cking | +0.038 |
Neg logit contributions | |
ives | -0.042 |
ury | -0.038 |
Enjoy | -0.037 |
Welcome | -0.036 |
Follow | -0.036 |
Token | his |
Token ID | 465 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
flower | +0.030 |
ble | +0.027 |
ric | +0.026 |
els | +0.026 |
cking | +0.026 |
Neg logit contributions | |
ives | -0.032 |
ury | -0.029 |
Enjoy | -0.029 |
Welcome | -0.028 |
Follow | -0.027 |
Token | sunset |
Token ID | 26428 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
flower | +0.075 |
ble | +0.066 |
ric | +0.066 |
els | +0.065 |
cking | +0.063 |
Neg logit contributions | |
ives | -0.057 |
ury | -0.050 |
Enjoy | -0.048 |
Follow | -0.047 |
Welcome | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
flower | +0.167 |
ble | +0.151 |
ric | +0.149 |
cking | +0.148 |
els | +0.146 |
Neg logit contributions | |
ives | -0.147 |
ury | -0.131 |
Enjoy | -0.127 |
Welcome | -0.124 |
Happy | -0.122 |
Token | He |
Token ID | 679 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
flower | +0.008 |
ric | +0.008 |
ble | +0.008 |
els | +0.007 |
cks | +0.007 |
Neg logit contributions | |
ives | -0.004 |
ury | -0.004 |
Enjoy | -0.003 |
Follow | -0.003 |
Welcome | -0.003 |
Token | writes |
Token ID | 6797 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
flower | +0.010 |
ble | +0.009 |
cking | +0.009 |
ric | +0.009 |
els | +0.009 |
Neg logit contributions | |
ives | -0.005 |
ury | -0.005 |
Enjoy | -0.005 |
Welcome | -0.004 |
Happy | -0.004 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
ives | +0.055 |
ury | +0.049 |
Enjoy | +0.048 |
Welcome | +0.047 |
Follow | +0.047 |
Neg logit contributions | |
flower | -0.052 |
ble | -0.048 |
els | -0.046 |
ric | -0.045 |
cking | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
flower | +0.023 |
ble | +0.021 |
ric | +0.020 |
els | +0.020 |
cking | +0.020 |
Neg logit contributions | |
ives | -0.018 |
ury | -0.016 |
Enjoy | -0.016 |
Welcome | -0.015 |
Follow | -0.015 |
Token | shining |
Token ID | 22751 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
flower | +0.026 |
els | +0.025 |
ric | +0.024 |
bery | +0.024 |
cks | +0.024 |
Neg logit contributions | |
Enjoy | -0.013 |
Max | -0.013 |
Happy | -0.013 |
Welcome | -0.013 |
ives | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
flower | +0.079 |
ric | +0.074 |
cking | +0.072 |
ble | +0.072 |
els | +0.071 |
Neg logit contributions | |
ives | -0.048 |
ury | -0.041 |
Happy | -0.041 |
Welcome | -0.040 |
Enjoy | -0.040 |
Token | it |
Token ID | 340 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
flower | +0.037 |
ble | +0.034 |
ric | +0.033 |
cking | +0.033 |
els | +0.032 |
Neg logit contributions | |
ives | -0.031 |
ury | -0.028 |
Enjoy | -0.027 |
Welcome | -0.026 |
Follow | -0.025 |
Token | 's |
Token ID | 338 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
flower | +0.049 |
ble | +0.044 |
ric | +0.044 |
cking | +0.043 |
els | +0.043 |
Neg logit contributions | |
ives | -0.028 |
ury | -0.025 |
Enjoy | -0.025 |
Welcome | -0.022 |
Happy | -0.022 |
Token | not |
Token ID | 407 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
flower | +0.025 |
els | +0.023 |
ble | +0.023 |
ric | +0.022 |
cking | +0.022 |
Neg logit contributions | |
ives | -0.015 |
Enjoy | -0.014 |
Welcome | -0.014 |
ury | -0.013 |
Happy | -0.013 |
Token | raining |
Token ID | 43079 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
flower | +0.082 |
els | +0.076 |
ble | +0.074 |
ric | +0.074 |
cking | +0.072 |
Neg logit contributions | |
ives | -0.035 |
ury | -0.032 |
Max | -0.031 |
Welcome | -0.031 |
Enjoy | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
flower | +0.172 |
ble | +0.155 |
ric | +0.151 |
cking | +0.149 |
els | +0.148 |
Neg logit contributions | |
ives | -0.138 |
ury | -0.123 |
Enjoy | -0.122 |
Welcome | -0.116 |
Follow | -0.115 |
Token | okay |
Token ID | 8788 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
flower | +0.028 |
ble | +0.026 |
ric | +0.025 |
cking | +0.025 |
els | +0.025 |
Neg logit contributions | |
ives | -0.020 |
ury | -0.017 |
Enjoy | -0.017 |
Welcome | -0.016 |
Follow | -0.016 |
Token | ?" |
Token ID | 1701 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
cking | +0.049 |
flower | +0.049 |
cks | +0.048 |
els | +0.047 |
eled | +0.045 |
Neg logit contributions | |
Max | -0.031 |
Enjoy | -0.029 |
Welcome | -0.029 |
ury | -0.029 |
Happy | -0.028 |
Token | |
Token ID | 220 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
flower | +0.035 |
ble | +0.032 |
ric | +0.031 |
els | +0.031 |
cking | +0.031 |
Neg logit contributions | |
ives | -0.021 |
ury | -0.017 |
Enjoy | -0.017 |
Follow | -0.016 |
villains | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
flower | +0.103 |
ble | +0.095 |
ric | +0.093 |
cking | +0.093 |
els | +0.092 |
Neg logit contributions | |
ives | -0.042 |
ury | -0.035 |
Enjoy | -0.034 |
Welcome | -0.032 |
Follow | -0.030 |
Token | her |
Token ID | 607 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
flower | +0.046 |
ble | +0.041 |
ric | +0.040 |
els | +0.040 |
cking | +0.040 |
Neg logit contributions | |
ives | -0.049 |
ury | -0.044 |
Enjoy | -0.043 |
Welcome | -0.042 |
Follow | -0.041 |
Token | siblings |
Token ID | 20569 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
flower | +0.038 |
ble | +0.035 |
els | +0.033 |
ric | +0.033 |
cking | +0.032 |
Neg logit contributions | |
ives | -0.029 |
ury | -0.026 |
Enjoy | -0.025 |
Follow | -0.024 |
Welcome | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
flower | +0.025 |
ble | +0.022 |
ric | +0.022 |
cking | +0.022 |
els | +0.021 |
Neg logit contributions | |
ives | -0.018 |
ury | -0.016 |
Enjoy | -0.016 |
Welcome | -0.015 |
Happy | -0.015 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
flower | +0.038 |
ble | +0.034 |
ric | +0.033 |
els | +0.033 |
cking | +0.032 |
Neg logit contributions | |
ives | -0.027 |
ury | -0.023 |
Enjoy | -0.022 |
Welcome | -0.022 |
Follow | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
ives | +0.003 |
ury | +0.003 |
Follow | +0.002 |
Enjoy | +0.002 |
Welcome | +0.002 |
Neg logit contributions | |
flower | -0.008 |
ric | -0.008 |
ble | -0.008 |
els | -0.008 |
cking | -0.008 |
Token | trem |
Token ID | 10023 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
flower | +0.017 |
ble | +0.016 |
cking | +0.015 |
els | +0.015 |
ric | +0.015 |
Neg logit contributions | |
ives | -0.007 |
Enjoy | -0.006 |
ury | -0.006 |
Welcome | -0.006 |
Happy | -0.006 |
Token | ble |
Token ID | 903 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
flower | +0.051 |
ric | +0.035 |
els | +0.027 |
eled | +0.026 |
cking | +0.026 |
Neg logit contributions | |
ives | -0.228 |
ury | -0.219 |
People | -0.218 |
and | -0.217 |
hide | -0.216 |
Token | and |
Token ID | 290 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
flower | +0.074 |
ble | +0.067 |
els | +0.065 |
cking | +0.065 |
ric | +0.064 |
Neg logit contributions | |
ives | -0.066 |
ury | -0.060 |
Enjoy | -0.059 |
Welcome | -0.057 |
Follow | -0.056 |
Token | make |
Token ID | 787 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
flower | +0.047 |
ric | +0.042 |
ble | +0.042 |
cking | +0.041 |
els | +0.040 |
Neg logit contributions | |
ives | -0.034 |
ury | -0.029 |
Enjoy | -0.027 |
Welcome | -0.026 |
Follow | -0.026 |
Token | them |
Token ID | 606 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
flower | +0.081 |
ble | +0.072 |
ric | +0.071 |
els | +0.069 |
cking | +0.069 |
Neg logit contributions | |
ives | -0.073 |
ury | -0.065 |
Enjoy | -0.064 |
Welcome | -0.063 |
Happy | -0.062 |
Token | laugh |
Token ID | 6487 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
flower | +0.067 |
els | +0.064 |
eled | +0.062 |
ries | +0.060 |
ric | +0.060 |
Neg logit contributions | |
ives | -0.026 |
hide | -0.024 |
Welcome | -0.022 |
Happy | -0.021 |
Max | -0.021 |
Token | structure |
Token ID | 4645 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
ives | +0.003 |
ury | +0.003 |
Enjoy | +0.003 |
Welcome | +0.003 |
Follow | +0.003 |
Neg logit contributions | |
flower | -0.003 |
ble | -0.003 |
ric | -0.003 |
els | -0.003 |
cking | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
flower | +0.104 |
ble | +0.090 |
cking | +0.089 |
els | +0.089 |
ric | +0.087 |
Neg logit contributions | |
ives | -0.111 |
Enjoy | -0.104 |
ury | -0.103 |
Welcome | -0.098 |
Happy | -0.097 |
Token | ran |
Token ID | 4966 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
ives | +0.002 |
ury | +0.002 |
Enjoy | +0.002 |
Welcome | +0.002 |
These | +0.002 |
Neg logit contributions | |
flower | -0.002 |
ble | -0.002 |
cking | -0.002 |
els | -0.002 |
ric | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
flower | +0.007 |
ble | +0.006 |
cking | +0.006 |
els | +0.006 |
mill | +0.006 |
Neg logit contributions | |
ives | -0.004 |
ury | -0.004 |
Enjoy | -0.004 |
Welcome | -0.004 |
People | -0.004 |
Token | their |
Token ID | 511 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
flower | +0.004 |
ble | +0.003 |
cking | +0.003 |
ric | +0.003 |
els | +0.003 |
Neg logit contributions | |
ives | -0.007 |
ury | -0.006 |
Follow | -0.006 |
ave | -0.006 |
Enjoy | -0.006 |
Token | structures |
Token ID | 8573 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
ives | +0.003 |
ury | +0.002 |
Enjoy | +0.002 |
Welcome | +0.002 |
Happy | +0.002 |
Neg logit contributions | |
flower | -0.003 |
ble | -0.003 |
ric | -0.003 |
els | -0.003 |
cking | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
flower | +0.159 |
ble | +0.142 |
ric | +0.140 |
cking | +0.138 |
els | +0.137 |
Neg logit contributions | |
ives | -0.146 |
ury | -0.131 |
Enjoy | -0.128 |
Welcome | -0.124 |
Happy | -0.121 |
Token | But |
Token ID | 887 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
ives | +0.015 |
ury | +0.014 |
Enjoy | +0.013 |
Follow | +0.012 |
itt | +0.012 |
Neg logit contributions | |
flower | -0.015 |
ric | -0.015 |
cks | -0.015 |
mill | -0.014 |
els | -0.014 |
Token | they |
Token ID | 484 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
flower | +0.008 |
ble | +0.007 |
cking | +0.006 |
els | +0.006 |
mill | +0.006 |
Neg logit contributions | |
ives | -0.011 |
ury | -0.010 |
Enjoy | -0.010 |
Welcome | -0.009 |
Follow | -0.009 |
Token | were |
Token ID | 547 |
Feature activation | +5.59e-03 |
Pos logit contributions | |
ives | +0.042 |
Enjoy | +0.038 |
ury | +0.037 |
Welcome | +0.037 |
Happy | +0.037 |
Neg logit contributions | |
flower | -0.059 |
ble | -0.055 |
ric | -0.053 |
cking | -0.051 |
els | -0.051 |
Token | gone |
Token ID | 3750 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
flower | +0.000 |
ble | +0.000 |
ric | +0.000 |
cking | +0.000 |
els | +0.000 |
Neg logit contributions | |
ives | -0.000 |
ury | -0.000 |
Enjoy | -0.000 |
Welcome | -0.000 |
Happy | -0.000 |
Token | his |
Token ID | 465 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
flower | +0.014 |
ble | +0.012 |
ric | +0.012 |
cking | +0.012 |
els | +0.012 |
Neg logit contributions | |
ives | -0.009 |
ury | -0.008 |
Enjoy | -0.008 |
Welcome | -0.008 |
Follow | -0.007 |
Token | stomach |
Token ID | 11384 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
flower | +0.057 |
ble | +0.051 |
ric | +0.050 |
els | +0.049 |
cking | +0.049 |
Neg logit contributions | |
ives | -0.045 |
ury | -0.040 |
Enjoy | -0.039 |
Welcome | -0.038 |
Follow | -0.037 |
Token | was |
Token ID | 373 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
flower | +0.067 |
ric | +0.063 |
els | +0.062 |
cking | +0.061 |
ble | +0.060 |
Neg logit contributions | |
ives | -0.049 |
ury | -0.044 |
Max | -0.040 |
Enjoy | -0.039 |
Welcome | -0.038 |
Token | starting |
Token ID | 3599 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
flower | +0.040 |
els | +0.036 |
ble | +0.035 |
ric | +0.035 |
cking | +0.034 |
Neg logit contributions | |
ives | -0.021 |
Enjoy | -0.019 |
Max | -0.018 |
Welcome | -0.018 |
ury | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
flower | +0.103 |
ble | +0.096 |
ric | +0.096 |
els | +0.095 |
cking | +0.095 |
Neg logit contributions | |
ives | -0.014 |
Enjoy | -0.008 |
Welcome | -0.008 |
Sadly | -0.006 |
ury | -0.006 |
Token | trem |
Token ID | 10023 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
els | +0.009 |
flower | +0.009 |
lights | +0.008 |
ries | +0.008 |
cks | +0.008 |
Neg logit contributions | |
hide | -0.005 |
ives | -0.005 |
Enjoy | -0.004 |
Welcome | -0.004 |
Max | -0.004 |
Token | ble |
Token ID | 903 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
flower | +0.055 |
ric | +0.052 |
cks | +0.041 |
els | +0.037 |
cking | +0.037 |
Neg logit contributions | |
ives | -0.205 |
ury | -0.201 |
and | -0.200 |
hide | -0.198 |
Give | -0.197 |
Token | . |
Token ID | 13 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
flower | +0.083 |
ric | +0.077 |
els | +0.074 |
ble | +0.073 |
cking | +0.073 |
Neg logit contributions | |
ives | -0.060 |
ury | -0.053 |
Enjoy | -0.051 |
Welcome | -0.050 |
Max | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
flower | +0.002 |
ble | +0.002 |
ric | +0.002 |
eled | +0.002 |
els | +0.002 |
Neg logit contributions | |
ives | -0.002 |
ury | -0.001 |
villains | -0.001 |
Enjoy | -0.001 |
hide | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
flower | +0.002 |
ble | +0.002 |
ric | +0.002 |
cking | +0.002 |
els | +0.002 |
Neg logit contributions | |
ives | -0.001 |
ury | -0.001 |
Enjoy | -0.001 |
Welcome | -0.001 |
Happy | -0.001 |
Token | His |
Token ID | 6653 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
flower | +0.013 |
ble | +0.011 |
ric | +0.011 |
els | +0.011 |
cking | +0.011 |
Neg logit contributions | |
ives | -0.013 |
ury | -0.012 |
Enjoy | -0.011 |
Welcome | -0.011 |
Follow | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
flower | +0.002 |
ble | +0.002 |
ric | +0.002 |
cking | +0.002 |
els | +0.002 |
Neg logit contributions | |
ives | -0.001 |
ury | -0.001 |
Enjoy | -0.001 |
Welcome | -0.001 |
Happy | -0.001 |
Token | his |
Token ID | 465 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
flower | +0.011 |
ble | +0.009 |
ric | +0.009 |
cking | +0.009 |
els | +0.009 |
Neg logit contributions | |
ives | -0.008 |
ury | -0.007 |
Enjoy | -0.007 |
Welcome | -0.007 |
Follow | -0.006 |
Token | phone |
Token ID | 3072 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
flower | +0.036 |
ble | +0.033 |
ric | +0.032 |
cking | +0.032 |
els | +0.032 |
Neg logit contributions | |
ives | -0.026 |
ury | -0.023 |
Enjoy | -0.022 |
Welcome | -0.021 |
Follow | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
flower | +0.043 |
ble | +0.039 |
cking | +0.038 |
ric | +0.038 |
els | +0.037 |
Neg logit contributions | |
ives | -0.035 |
ury | -0.031 |
Enjoy | -0.030 |
Welcome | -0.030 |
Happy | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
flower | +0.020 |
ble | +0.018 |
ric | +0.017 |
cking | +0.017 |
els | +0.017 |
Neg logit contributions | |
ives | -0.018 |
ury | -0.016 |
Enjoy | -0.016 |
Welcome | -0.016 |
Happy | -0.015 |
Token | fake |
Token ID | 8390 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
flower | +0.040 |
ble | +0.037 |
cking | +0.036 |
els | +0.036 |
ric | +0.036 |
Neg logit contributions | |
ives | -0.028 |
Enjoy | -0.025 |
Welcome | -0.025 |
ury | -0.024 |
Max | -0.024 |
Token | mustache |
Token ID | 49303 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
flower | +0.177 |
ble | +0.164 |
cking | +0.163 |
ric | +0.161 |
cks | +0.157 |
Neg logit contributions | |
ives | -0.118 |
ury | -0.103 |
Welcome | -0.099 |
Enjoy | -0.099 |
Happy | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
flower | +0.056 |
ble | +0.051 |
ric | +0.050 |
cking | +0.050 |
els | +0.049 |
Neg logit contributions | |
ives | -0.046 |
ury | -0.041 |
Enjoy | -0.039 |
Welcome | -0.039 |
Happy | -0.038 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
flower | +0.001 |
ble | +0.001 |
ric | +0.001 |
els | +0.001 |
cking | +0.001 |
Neg logit contributions | |
ives | -0.000 |
ury | -0.000 |
Enjoy | -0.000 |
Welcome | -0.000 |
Follow | -0.000 |
Token | L |
Token ID | 43 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ives | +0.023 |
ury | +0.021 |
Enjoy | +0.020 |
Welcome | +0.020 |
Follow | +0.020 |
Neg logit contributions | |
flower | -0.023 |
ble | -0.021 |
ric | -0.020 |
els | -0.020 |
cking | -0.019 |
Token | ily |
Token ID | 813 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
ives | +0.051 |
Enjoy | +0.042 |
ury | +0.042 |
Happy | +0.040 |
Welcome | +0.040 |
Neg logit contributions | |
flower | -0.085 |
ble | -0.076 |
ric | -0.076 |
cking | -0.076 |
els | -0.072 |
Token | sit |
Token ID | 1650 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
ives | +0.055 |
ury | +0.048 |
Enjoy | +0.047 |
Welcome | +0.045 |
Happy | +0.043 |
Neg logit contributions | |
flower | -0.093 |
ble | -0.085 |
ric | -0.083 |
cking | -0.083 |
els | -0.082 |
Token | down |
Token ID | 866 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
ives | +0.025 |
Max | +0.023 |
Enjoy | +0.022 |
ury | +0.022 |
Happy | +0.022 |
Neg logit contributions | |
flower | -0.042 |
ric | -0.041 |
cking | -0.040 |
cks | -0.039 |
els | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | +8.02e-02 |
Pos logit contributions | |
flower | +0.029 |
ble | +0.026 |
els | +0.025 |
ric | +0.025 |
cking | +0.025 |
Neg logit contributions | |
ives | -0.022 |
ury | -0.020 |
Enjoy | -0.019 |
Welcome | -0.018 |
Follow | -0.018 |
Token | do |
Token ID | 466 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
flower | +0.004 |
ric | +0.003 |
ble | +0.003 |
cking | +0.003 |
els | +0.003 |
Neg logit contributions | |
ives | -0.003 |
ury | -0.003 |
Enjoy | -0.002 |
and | -0.002 |
Follow | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
flower | +0.081 |
ble | +0.072 |
ric | +0.070 |
cking | +0.069 |
els | +0.068 |
Neg logit contributions | |
ives | -0.054 |
ury | -0.048 |
Enjoy | -0.047 |
Welcome | -0.045 |
People | -0.045 |
Token | math |
Token ID | 10688 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
flower | +0.055 |
ble | +0.051 |
ric | +0.049 |
els | +0.049 |
cking | +0.047 |
Neg logit contributions | |
ives | -0.044 |
ury | -0.039 |
Enjoy | -0.037 |
Welcome | -0.035 |
Follow | -0.035 |
Token | exercises |
Token ID | 13565 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
flower | +0.187 |
ble | +0.170 |
ric | +0.167 |
cking | +0.166 |
els | +0.165 |
Neg logit contributions | |
ives | -0.113 |
ury | -0.098 |
Enjoy | -0.096 |
Welcome | -0.092 |
Follow | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
flower | +0.131 |
ble | +0.119 |
ric | +0.118 |
cking | +0.116 |
els | +0.116 |
Neg logit contributions | |
ives | -0.090 |
ury | -0.079 |
Enjoy | -0.077 |
Welcome | -0.074 |
Happy | -0.073 |
Token | She |
Token ID | 1375 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
ives | +0.008 |
ury | +0.008 |
Enjoy | +0.007 |
villains | +0.007 |
Cop | +0.007 |
Neg logit contributions | |
flower | -0.013 |
els | -0.011 |
ric | -0.011 |
ble | -0.011 |
cks | -0.011 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
flower | +0.025 |
ble | +0.022 |
ric | +0.022 |
els | +0.022 |
cking | +0.022 |
Neg logit contributions | |
ives | -0.017 |
ury | -0.015 |
Enjoy | -0.014 |
Welcome | -0.014 |
Follow | -0.013 |
Token | finishing |
Token ID | 12848 |
Feature activation | +8.61e-02 |
Pos logit contributions | |
ives | +0.048 |
ury | +0.041 |
Follow | +0.040 |
Enjoy | +0.040 |
Sadly | +0.038 |
Neg logit contributions | |
flower | -0.074 |
els | -0.068 |
ric | -0.068 |
ble | -0.067 |
cking | -0.066 |
Token | cave |
Token ID | 11527 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
flower | +0.013 |
ble | +0.012 |
ric | +0.010 |
els | +0.010 |
cking | +0.010 |
Neg logit contributions | |
ives | -0.016 |
ury | -0.015 |
Enjoy | -0.014 |
enny | -0.013 |
and | -0.012 |
Token | started |
Token ID | 2067 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
flower | +0.002 |
ble | +0.001 |
els | +0.001 |
cking | +0.001 |
ric | +0.001 |
Neg logit contributions | |
ives | -0.001 |
Enjoy | -0.001 |
ury | -0.001 |
Welcome | -0.001 |
Happy | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
ives | +0.003 |
ury | +0.002 |
Welcome | +0.002 |
Enjoy | +0.002 |
Happy | +0.002 |
Neg logit contributions | |
flower | -0.010 |
ble | -0.009 |
ric | -0.009 |
cking | -0.009 |
els | -0.009 |
Token | shake |
Token ID | 13279 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
hide | +0.015 |
ives | +0.014 |
Welcome | +0.013 |
Max | +0.013 |
Happy | +0.013 |
Neg logit contributions | |
flower | -0.021 |
els | -0.020 |
ric | -0.019 |
ries | -0.019 |
cks | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
flower | +0.074 |
ric | +0.067 |
ble | +0.066 |
cking | +0.065 |
els | +0.064 |
Neg logit contributions | |
ives | -0.051 |
ury | -0.046 |
Max | -0.044 |
Happy | -0.043 |
Welcome | -0.043 |
Token | trem |
Token ID | 10023 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
flower | +0.014 |
ble | +0.013 |
ric | +0.012 |
cking | +0.012 |
els | +0.012 |
Neg logit contributions | |
ives | -0.013 |
ury | -0.011 |
Enjoy | -0.011 |
Welcome | -0.011 |
Happy | -0.011 |
Token | ble |
Token ID | 903 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
flower | +0.055 |
ric | +0.045 |
cking | +0.031 |
els | +0.030 |
ries | +0.030 |
Neg logit contributions | |
ives | -0.213 |
ury | -0.211 |
hide | -0.207 |
Follow | -0.205 |
Max | -0.205 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
flower | +0.082 |
ric | +0.073 |
ble | +0.072 |
els | +0.070 |
cking | +0.070 |
Neg logit contributions | |
ives | -0.067 |
ury | -0.060 |
Enjoy | -0.057 |
Welcome | -0.057 |
Max | -0.055 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
ble | +0.005 |
flower | +0.005 |
ric | +0.005 |
esh | +0.005 |
neath | +0.004 |
Neg logit contributions | |
ives | -0.005 |
ury | -0.004 |
Bye | -0.004 |
Enjoy | -0.004 |
and | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
flower | +0.031 |
ble | +0.030 |
els | +0.027 |
cking | +0.027 |
bery | +0.026 |
Neg logit contributions | |
ives | -0.031 |
Enjoy | -0.026 |
ury | -0.026 |
Welcome | -0.026 |
and | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
ives | +0.017 |
ury | +0.015 |
Enjoy | +0.014 |
Welcome | +0.014 |
Follow | +0.014 |
Neg logit contributions | |
flower | -0.020 |
ble | -0.020 |
cking | -0.018 |
ric | -0.018 |
els | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
flower | +0.017 |
ric | +0.016 |
ble | +0.016 |
els | +0.015 |
cking | +0.015 |
Neg logit contributions | |
ives | -0.008 |
ury | -0.007 |
Follow | -0.006 |
Welcome | -0.006 |
Enjoy | -0.006 |
Token | stay |
Token ID | 2652 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
ives | +0.006 |
ury | +0.005 |
Enjoy | +0.005 |
Welcome | +0.005 |
Happy | +0.005 |
Neg logit contributions | |
flower | -0.008 |
ble | -0.007 |
ric | -0.007 |
cking | -0.007 |
els | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
flower | +0.013 |
ric | +0.012 |
els | +0.011 |
ble | +0.011 |
ries | +0.011 |
Neg logit contributions | |
ives | -0.006 |
Max | -0.005 |
hide | -0.005 |
ury | -0.005 |
Enjoy | -0.005 |
Token | finish |
Token ID | 5461 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
flower | +0.022 |
ble | +0.021 |
ric | +0.020 |
cking | +0.019 |
mill | +0.019 |
Neg logit contributions | |
ives | -0.020 |
ury | -0.017 |
Enjoy | -0.016 |
Welcome | -0.016 |
Happy | -0.016 |
Token | his |
Token ID | 465 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
flower | +0.095 |
ric | +0.081 |
ble | +0.080 |
cking | +0.079 |
els | +0.078 |
Neg logit contributions | |
ives | -0.063 |
Enjoy | -0.059 |
ury | -0.058 |
Max | -0.058 |
Happy | -0.057 |
Token | math |
Token ID | 10688 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
flower | +0.020 |
ble | +0.019 |
els | +0.018 |
ric | +0.018 |
cking | +0.018 |
Neg logit contributions | |
ives | -0.018 |
ury | -0.016 |
Enjoy | -0.015 |
Welcome | -0.015 |
Follow | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
flower | +0.169 |
ble | +0.155 |
cking | +0.150 |
els | +0.150 |
ric | +0.148 |
Neg logit contributions | |
ives | -0.124 |
Enjoy | -0.112 |
ury | -0.110 |
Welcome | -0.106 |
Follow | -0.103 |
Token | So |
Token ID | 1406 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
ives | +0.000 |
ury | +0.000 |
Enjoy | +0.000 |
Welcome | +0.000 |
villains | +0.000 |
Neg logit contributions | |
flower | -0.001 |
ric | -0.001 |
els | -0.001 |
ble | -0.001 |
ries | -0.001 |
Token | Tim |
Token ID | 5045 |
Feature activation | -8.30e-01 |
Pos logit contributions | |
ives | +0.006 |
ury | +0.005 |
Enjoy | +0.005 |
Welcome | +0.005 |
Happy | +0.005 |
Neg logit contributions | |
flower | -0.012 |
ble | -0.011 |
ric | -0.011 |
cking | -0.011 |
els | -0.011 |
Token | my |
Token ID | 1820 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
ives | +0.032 |
ury | +0.029 |
Enjoy | +0.028 |
Welcome | +0.028 |
Happy | +0.027 |
Neg logit contributions | |
flower | -0.038 |
ble | -0.033 |
ric | -0.032 |
els | -0.032 |
cking | -0.032 |
Token | stayed |
Token ID | 9658 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
ives | +0.030 |
Enjoy | +0.027 |
Welcome | +0.027 |
ury | +0.027 |
Happy | +0.025 |
Neg logit contributions | |
flower | -0.037 |
ble | -0.034 |
els | -0.032 |
cking | -0.032 |
ric | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
flower | +0.002 |
ric | +0.001 |
cking | +0.001 |
cks | +0.001 |
els | +0.001 |
Neg logit contributions | |
ives | -0.001 |
Max | -0.001 |
ury | -0.001 |
Welcome | -0.001 |
Happy | -0.001 |
Token | quickly |
Token ID | 2952 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
flower | +0.021 |
ble | +0.019 |
ric | +0.019 |
els | +0.019 |
cking | +0.019 |
Neg logit contributions | |
ives | -0.017 |
ury | -0.015 |
Enjoy | -0.014 |
Welcome | -0.014 |
Happy | -0.014 |
Token | put |
Token ID | 1234 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
ives | +0.012 |
ury | +0.010 |
Enjoy | +0.010 |
Welcome | +0.009 |
Max | +0.009 |
Neg logit contributions | |
flower | -0.018 |
ric | -0.016 |
ble | -0.016 |
els | -0.015 |
cking | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
flower | +0.013 |
ric | +0.012 |
ble | +0.012 |
cking | +0.011 |
els | +0.011 |
Neg logit contributions | |
ives | -0.012 |
Enjoy | -0.011 |
Max | -0.011 |
Happy | -0.011 |
ury | -0.011 |
Token | his |
Token ID | 465 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
flower | +0.085 |
ble | +0.074 |
ric | +0.071 |
cking | +0.069 |
els | +0.067 |
Neg logit contributions | |
ives | -0.071 |
Enjoy | -0.065 |
Max | -0.065 |
Happy | -0.064 |
ury | -0.063 |
Token | rain |
Token ID | 6290 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
flower | +0.032 |
ric | +0.029 |
cking | +0.028 |
ble | +0.028 |
els | +0.027 |
Neg logit contributions | |
ives | -0.027 |
ury | -0.025 |
Enjoy | -0.024 |
Welcome | -0.024 |
Happy | -0.024 |
Token | coat |
Token ID | 31434 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
flower | +0.181 |
ble | +0.173 |
cking | +0.170 |
ric | +0.169 |
els | +0.166 |
Neg logit contributions | |
ives | -0.119 |
ury | -0.100 |
Max | -0.091 |
hide | -0.091 |
and | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
flower | +0.005 |
ble | +0.005 |
ric | +0.005 |
cking | +0.005 |
els | +0.005 |
Neg logit contributions | |
ives | -0.004 |
ury | -0.004 |
Enjoy | -0.004 |
Welcome | -0.003 |
Max | -0.003 |
Token | When |
Token ID | 1649 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
flower | +0.001 |
mill | +0.001 |
ric | +0.001 |
lights | +0.001 |
ble | +0.001 |
Neg logit contributions | |
ives | -0.001 |
ury | -0.001 |
Enjoy | -0.001 |
unn | -0.001 |
Follow | -0.001 |
Token | he |
Token ID | 339 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
flower | +0.045 |
ble | +0.041 |
cking | +0.040 |
ric | +0.040 |
els | +0.040 |
Neg logit contributions | |
ives | -0.035 |
ury | -0.030 |
Enjoy | -0.028 |
Follow | -0.027 |
Welcome | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ives | +0.024 |
ury | +0.022 |
Enjoy | +0.021 |
Welcome | +0.020 |
Follow | +0.020 |
Neg logit contributions | |
flower | -0.033 |
ble | -0.029 |
els | -0.028 |
ric | -0.028 |
cking | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
flower | +0.016 |
ble | +0.015 |
ric | +0.015 |
cking | +0.014 |
els | +0.014 |
Neg logit contributions | |
ives | -0.022 |
ury | -0.019 |
Follow | -0.018 |
Welcome | -0.018 |
Thank | -0.017 |
Token | hive |
Token ID | 35881 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
flower | +0.006 |
ble | +0.005 |
cking | +0.005 |
ric | +0.005 |
els | +0.004 |
Neg logit contributions | |
ives | -0.009 |
ury | -0.008 |
Enjoy | -0.008 |
Welcome | -0.008 |
Happy | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
flower | +0.036 |
ble | +0.032 |
ric | +0.031 |
els | +0.030 |
cking | +0.030 |
Neg logit contributions | |
ives | -0.028 |
Enjoy | -0.026 |
ury | -0.025 |
Welcome | -0.024 |
Happy | -0.023 |
Token | started |
Token ID | 2067 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
flower | +0.015 |
ble | +0.014 |
cking | +0.013 |
ric | +0.013 |
perched | +0.012 |
Neg logit contributions | |
ives | -0.015 |
Enjoy | -0.013 |
These | -0.012 |
ury | -0.012 |
People | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
flower | +0.051 |
ble | +0.048 |
ric | +0.047 |
els | +0.047 |
cking | +0.046 |
Neg logit contributions | |
ives | -0.013 |
ury | -0.010 |
Enjoy | -0.009 |
Welcome | -0.009 |
Happy | -0.008 |
Token | trem |
Token ID | 10023 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
flower | +0.001 |
ble | +0.001 |
ric | +0.001 |
cking | +0.001 |
els | +0.001 |
Neg logit contributions | |
ives | -0.001 |
ury | -0.000 |
Enjoy | -0.000 |
Welcome | -0.000 |
Happy | -0.000 |
Token | ble |
Token ID | 903 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
flower | +0.053 |
ric | +0.044 |
ries | +0.029 |
mill | +0.029 |
cking | +0.028 |
Neg logit contributions | |
ives | -0.211 |
hide | -0.210 |
ury | -0.210 |
Follow | -0.205 |
Max | -0.202 |
Token | with |
Token ID | 351 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
flower | +0.079 |
ble | +0.070 |
ric | +0.070 |
cking | +0.068 |
els | +0.068 |
Neg logit contributions | |
ives | -0.067 |
ury | -0.059 |
Enjoy | -0.057 |
Welcome | -0.057 |
Happy | -0.055 |
Token | excitement |
Token ID | 14067 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
flower | +0.009 |
ble | +0.009 |
cking | +0.008 |
els | +0.008 |
ric | +0.008 |
Neg logit contributions | |
ives | -0.012 |
ury | -0.011 |
Enjoy | -0.010 |
Welcome | -0.010 |
Follow | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
flower | +0.042 |
ric | +0.038 |
cking | +0.037 |
ble | +0.037 |
els | +0.036 |
Neg logit contributions | |
ives | -0.030 |
ury | -0.027 |
Max | -0.025 |
Happy | -0.025 |
Welcome | -0.025 |
Token | But |
Token ID | 887 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
flower | +0.007 |
ble | +0.007 |
ric | +0.007 |
esh | +0.006 |
mill | +0.006 |
Neg logit contributions | |
ives | -0.007 |
Enjoy | -0.005 |
itt | -0.005 |
ury | -0.005 |
and | -0.005 |
Token | make |
Token ID | 787 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ives | +0.015 |
ury | +0.013 |
Enjoy | +0.013 |
Welcome | +0.013 |
Happy | +0.012 |
Neg logit contributions | |
flower | -0.023 |
ble | -0.021 |
ric | -0.021 |
cking | -0.020 |
els | -0.020 |
Token | her |
Token ID | 607 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
flower | +0.043 |
ble | +0.038 |
ric | +0.037 |
cking | +0.037 |
els | +0.036 |
Neg logit contributions | |
ives | -0.045 |
ury | -0.040 |
Enjoy | -0.040 |
Welcome | -0.039 |
Happy | -0.038 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
flower | +0.066 |
ble | +0.061 |
ric | +0.060 |
cking | +0.059 |
els | +0.058 |
Neg logit contributions | |
ives | -0.045 |
ury | -0.038 |
Enjoy | -0.037 |
Welcome | -0.037 |
Max | -0.037 |
Token | angry |
Token ID | 7954 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
flower | +0.063 |
ble | +0.061 |
ric | +0.058 |
els | +0.057 |
cking | +0.055 |
Neg logit contributions | |
ives | -0.039 |
ury | -0.031 |
Max | -0.031 |
Welcome | -0.030 |
Many | -0.030 |
Token | or |
Token ID | 393 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
flower | +0.103 |
ble | +0.093 |
els | +0.089 |
ric | +0.089 |
cking | +0.088 |
Neg logit contributions | |
ives | -0.094 |
ury | -0.084 |
Enjoy | -0.084 |
Welcome | -0.080 |
Follow | -0.079 |
Token | sad |
Token ID | 6507 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
flower | +0.037 |
ble | +0.034 |
ric | +0.033 |
cking | +0.033 |
els | +0.033 |
Neg logit contributions | |
ives | -0.024 |
ury | -0.021 |
Enjoy | -0.021 |
Welcome | -0.020 |
Follow | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
flower | +0.168 |
ric | +0.151 |
ble | +0.150 |
cking | +0.148 |
els | +0.144 |
Neg logit contributions | |
ives | -0.129 |
ury | -0.113 |
Max | -0.108 |
Enjoy | -0.108 |
Welcome | -0.108 |
Token | She |
Token ID | 1375 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
ives | +0.006 |
ury | +0.005 |
Enjoy | +0.005 |
Follow | +0.004 |
Welcome | +0.004 |
Neg logit contributions | |
flower | -0.009 |
ble | -0.008 |
ric | -0.008 |
els | -0.008 |
mill | -0.008 |
Token | realized |
Token ID | 6939 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
flower | +0.023 |
ble | +0.021 |
els | +0.021 |
cking | +0.021 |
eled | +0.020 |
Neg logit contributions | |
ives | -0.021 |
Enjoy | -0.018 |
Welcome | -0.018 |
ury | -0.017 |
and | -0.017 |
Token | that |
Token ID | 326 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
Max | +0.002 |
ives | +0.001 |
Jack | +0.001 |
Happy | +0.001 |
Miss | +0.001 |
Neg logit contributions | |
flower | -0.008 |
ric | -0.007 |
cking | -0.007 |
eled | -0.007 |
cker | -0.007 |
Token | she |
Token ID | 673 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
ives | +0.033 |
ury | +0.029 |
Enjoy | +0.028 |
Follow | +0.027 |
Welcome | +0.027 |
Neg logit contributions | |
flower | -0.036 |
ble | -0.032 |
els | -0.031 |
ric | -0.031 |
cking | -0.031 |
Token | mom |
Token ID | 1995 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
flower | +0.063 |
cking | +0.059 |
ric | +0.059 |
ble | +0.058 |
els | +0.057 |
Neg logit contributions | |
ives | -0.031 |
Max | -0.030 |
Happy | -0.026 |
Sadly | -0.025 |
And | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
flower | +0.049 |
ble | +0.049 |
ric | +0.046 |
els | +0.045 |
cking | +0.043 |
Neg logit contributions | |
ives | -0.031 |
Max | -0.025 |
and | -0.025 |
ury | -0.023 |
Many | -0.023 |
Token | dad |
Token ID | 9955 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
flower | +0.001 |
ble | +0.001 |
ric | +0.001 |
cking | +0.001 |
els | +0.001 |
Neg logit contributions | |
ives | -0.001 |
ury | -0.001 |
Enjoy | -0.001 |
Welcome | -0.001 |
Happy | -0.001 |
Token | angry |
Token ID | 7954 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
flower | +0.064 |
ble | +0.059 |
ric | +0.058 |
els | +0.057 |
cking | +0.056 |
Neg logit contributions | |
ives | -0.042 |
ury | -0.036 |
Enjoy | -0.034 |
Welcome | -0.034 |
Max | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
flower | +0.122 |
ble | +0.108 |
ric | +0.105 |
els | +0.104 |
cking | +0.104 |
Neg logit contributions | |
ives | -0.118 |
ury | -0.106 |
Enjoy | -0.104 |
Welcome | -0.101 |
Follow | -0.099 |
Token | sad |
Token ID | 6507 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
flower | +0.025 |
ble | +0.024 |
cking | +0.023 |
mill | +0.022 |
ric | +0.022 |
Neg logit contributions | |
ives | -0.020 |
ury | -0.017 |
Welcome | -0.016 |
Enjoy | -0.016 |
People | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
flower | +0.157 |
ble | +0.140 |
ric | +0.138 |
cking | +0.136 |
els | +0.135 |
Neg logit contributions | |
ives | -0.139 |
ury | -0.124 |
Enjoy | -0.121 |
Welcome | -0.118 |
Happy | -0.116 |
Token | She |
Token ID | 1375 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
ives | +0.002 |
ury | +0.002 |
Enjoy | +0.002 |
ival | +0.002 |
Follow | +0.002 |
Neg logit contributions | |
flower | -0.004 |
ble | -0.003 |
ric | -0.003 |
els | -0.003 |
mill | -0.003 |
Token | wanted |
Token ID | 2227 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
flower | +0.021 |
ble | +0.019 |
cking | +0.019 |
ric | +0.018 |
els | +0.018 |
Neg logit contributions | |
ives | -0.017 |
Welcome | -0.014 |
Enjoy | -0.014 |
ury | -0.014 |
and | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
flower | +0.004 |
els | +0.004 |
ble | +0.004 |
ric | +0.004 |
mill | +0.004 |
Neg logit contributions | |
ives | -0.003 |
ury | -0.002 |
Follow | -0.002 |
Welcome | -0.002 |
Enjoy | -0.002 |
Token | make |
Token ID | 787 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ives | +0.016 |
ury | +0.014 |
Enjoy | +0.014 |
Welcome | +0.013 |
Happy | +0.013 |
Neg logit contributions | |
flower | -0.030 |
ble | -0.028 |
ric | -0.027 |
cking | -0.027 |
els | -0.027 |
Token | excited |
Token ID | 6568 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
ives | +0.009 |
ury | +0.007 |
Enjoy | +0.007 |
Welcome | +0.007 |
Happy | +0.007 |
Neg logit contributions | |
flower | -0.017 |
ric | -0.015 |
ble | -0.015 |
els | -0.015 |
cking | -0.015 |
Token | about |
Token ID | 546 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
flower | +0.015 |
ble | +0.014 |
ric | +0.013 |
els | +0.013 |
cking | +0.013 |
Neg logit contributions | |
ives | -0.008 |
Enjoy | -0.007 |
ury | -0.007 |
Welcome | -0.007 |
Follow | -0.007 |
Token | r |
Token ID | 374 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
Max | +0.016 |
Jack | +0.015 |
Enjoy | +0.015 |
hide | +0.014 |
ives | +0.014 |
Neg logit contributions | |
flower | -0.026 |
ric | -0.022 |
bery | -0.022 |
cking | -0.022 |
ble | -0.022 |
Token | aking |
Token ID | 868 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
flower | +0.104 |
ric | +0.094 |
cking | +0.093 |
ble | +0.093 |
cks | +0.090 |
Neg logit contributions | |
ives | -0.097 |
ury | -0.081 |
Enjoy | -0.078 |
and | -0.077 |
People | -0.075 |
Token | and |
Token ID | 290 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
flower | +0.026 |
ric | +0.023 |
ble | +0.023 |
cking | +0.023 |
eled | +0.022 |
Neg logit contributions | |
ives | -0.017 |
Max | -0.015 |
People | -0.014 |
hide | -0.014 |
ury | -0.014 |
Token | r |
Token ID | 374 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
flower | +0.018 |
ble | +0.017 |
ric | +0.016 |
cking | +0.016 |
els | +0.016 |
Neg logit contributions | |
ives | -0.014 |
ury | -0.013 |
Enjoy | -0.012 |
Welcome | -0.012 |
Follow | -0.012 |
Token | aked |
Token ID | 4335 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
flower | +0.141 |
ble | +0.125 |
ric | +0.124 |
cking | +0.123 |
bery | +0.119 |
Neg logit contributions | |
ives | -0.149 |
ury | -0.125 |
Enjoy | -0.122 |
and | -0.121 |
Now | -0.119 |
Token | the |
Token ID | 262 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
flower | +0.068 |
ric | +0.061 |
ble | +0.061 |
cking | +0.058 |
els | +0.056 |
Neg logit contributions | |
ives | -0.054 |
ury | -0.047 |
Max | -0.046 |
Enjoy | -0.046 |
Happy | -0.045 |
Token | small |
Token ID | 1402 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
flower | +0.016 |
ble | +0.015 |
ric | +0.014 |
cking | +0.014 |
els | +0.014 |
Neg logit contributions | |
ives | -0.017 |
ury | -0.015 |
Enjoy | -0.015 |
Welcome | -0.014 |
Follow | -0.014 |
Token | piles |
Token ID | 30935 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
flower | +0.040 |
ble | +0.037 |
cking | +0.037 |
ric | +0.037 |
cks | +0.036 |
Neg logit contributions | |
ives | -0.037 |
ury | -0.034 |
Enjoy | -0.032 |
Welcome | -0.032 |
Max | -0.032 |
Token | too |
Token ID | 1165 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
flower | +0.104 |
ble | +0.096 |
ric | +0.095 |
cking | +0.094 |
els | +0.093 |
Neg logit contributions | |
ives | -0.051 |
ury | -0.043 |
Enjoy | -0.042 |
Welcome | -0.040 |
Happy | -0.039 |
Token | came |
Token ID | 1625 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ives | +0.011 |
helped | +0.009 |
Welcome | +0.009 |
t | +0.009 |
Give | +0.009 |
Neg logit contributions | |
els | -0.032 |
ric | -0.031 |
flower | -0.031 |
cking | -0.031 |
bery | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
ives | +0.029 |
ury | +0.025 |
Welcome | +0.024 |
Max | +0.024 |
Enjoy | +0.023 |
Neg logit contributions | |
flower | -0.063 |
ric | -0.058 |
cking | -0.058 |
ble | -0.057 |
els | -0.056 |
Token | blew |
Token ID | 17948 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
ives | +0.053 |
Max | +0.052 |
Happy | +0.049 |
Enjoy | +0.049 |
Welcome | +0.048 |
Neg logit contributions | |
flower | -0.053 |
ric | -0.049 |
ble | -0.048 |
els | -0.046 |
cking | -0.046 |
Token | away |
Token ID | 1497 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
flower | +0.014 |
ble | +0.013 |
els | +0.012 |
ric | +0.012 |
cking | +0.012 |
Neg logit contributions | |
ives | -0.013 |
ury | -0.012 |
Enjoy | -0.012 |
Welcome | -0.011 |
Follow | -0.011 |
Token | their |
Token ID | 511 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
flower | +0.011 |
cking | +0.010 |
ric | +0.010 |
eled | +0.009 |
ble | +0.009 |
Neg logit contributions | |
Max | -0.008 |
ives | -0.008 |
Happy | -0.008 |
Enjoy | -0.008 |
And | -0.008 |
Token | structures |
Token ID | 8573 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
ives | +0.007 |
ury | +0.006 |
Enjoy | +0.006 |
Welcome | +0.006 |
Happy | +0.006 |
Neg logit contributions | |
flower | -0.008 |
ble | -0.007 |
ric | -0.007 |
cking | -0.007 |
els | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
flower | +0.175 |
ric | +0.161 |
ble | +0.156 |
els | +0.153 |
cking | +0.153 |
Neg logit contributions | |
ives | -0.121 |
ury | -0.100 |
Max | -0.095 |
hide | -0.094 |
Welcome | -0.094 |
Token | The |
Token ID | 383 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
ives | +0.011 |
ury | +0.010 |
Follow | +0.009 |
Welcome | +0.009 |
Enjoy | +0.009 |
Neg logit contributions | |
flower | -0.020 |
ble | -0.020 |
ric | -0.019 |
els | -0.019 |
mill | -0.018 |
Token | sticks |
Token ID | 16461 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
ives | +0.031 |
ury | +0.028 |
Enjoy | +0.027 |
Welcome | +0.026 |
Happy | +0.026 |
Neg logit contributions | |
flower | -0.036 |
ble | -0.032 |
ric | -0.031 |
cking | -0.031 |
els | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
ives | +0.024 |
ury | +0.019 |
hide | +0.019 |
Max | +0.019 |
Welcome | +0.018 |
Neg logit contributions | |
flower | -0.034 |
ric | -0.031 |
els | -0.029 |
cking | -0.029 |
ble | -0.029 |
Token | stones |
Token ID | 14966 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
ives | +0.009 |
ury | +0.008 |
Enjoy | +0.008 |
Welcome | +0.008 |
Max | +0.008 |
Neg logit contributions | |
flower | -0.010 |
ble | -0.009 |
ric | -0.009 |
cking | -0.009 |
els | -0.009 |
Token | made |
Token ID | 925 |
Feature activation | -7.29e-02 |
Pos logit contributions | |
flower | +0.031 |
ble | +0.028 |
ric | +0.028 |
els | +0.028 |
cking | +0.027 |
Neg logit contributions | |
ives | -0.022 |
ury | -0.021 |
Welcome | -0.021 |
Enjoy | -0.021 |
Happy | -0.020 |
Token | him |
Token ID | 683 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
ives | +0.003 |
ury | +0.003 |
Follow | +0.003 |
Welcome | +0.003 |
Enjoy | +0.003 |
Neg logit contributions | |
flower | -0.003 |
ble | -0.003 |
els | -0.003 |
cking | -0.002 |
ric | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
ives | +0.008 |
hide | +0.007 |
Max | +0.006 |
ury | +0.006 |
Enjoy | +0.006 |
Neg logit contributions | |
flower | -0.017 |
els | -0.015 |
ric | -0.015 |
eled | -0.015 |
cking | -0.014 |
Token | his |
Token ID | 465 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
ives | +0.012 |
ury | +0.011 |
Enjoy | +0.010 |
Welcome | +0.010 |
Happy | +0.009 |
Neg logit contributions | |
flower | -0.022 |
ble | -0.020 |
ric | -0.020 |
els | -0.020 |
cking | -0.020 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
flower | +0.030 |
ble | +0.028 |
cking | +0.027 |
ric | +0.027 |
els | +0.026 |
Neg logit contributions | |
ives | -0.019 |
Max | -0.016 |
Enjoy | -0.016 |
ury | -0.016 |
Welcome | -0.016 |
Token | sad |
Token ID | 6507 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
flower | +0.067 |
ble | +0.061 |
ric | +0.060 |
els | +0.059 |
cking | +0.059 |
Neg logit contributions | |
ives | -0.040 |
ury | -0.034 |
Enjoy | -0.033 |
Welcome | -0.032 |
Follow | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -5.12e-02 |
Pos logit contributions | |
flower | +0.174 |
cking | +0.160 |
ric | +0.158 |
ble | +0.157 |
els | +0.155 |
Neg logit contributions | |
ives | -0.117 |
ury | -0.100 |
Enjoy | -0.097 |
Max | -0.095 |
Thank | -0.094 |
Token | You |
Token ID | 921 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
ives | +0.001 |
ury | +0.001 |
ival | +0.001 |
hide | +0.001 |
Enjoy | +0.001 |
Neg logit contributions | |
flower | -0.003 |
ric | -0.002 |
els | -0.002 |
ble | -0.002 |
cks | -0.002 |
Token | made |
Token ID | 925 |
Feature activation | +9.56e-02 |
Pos logit contributions | |
flower | +0.039 |
ric | +0.035 |
ble | +0.035 |
els | +0.034 |
cking | +0.033 |
Neg logit contributions | |
ury | -0.029 |
ives | -0.029 |
Welcome | -0.028 |
Enjoy | -0.028 |
Bye | -0.027 |
Token | me |
Token ID | 502 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
flower | +0.004 |
ble | +0.004 |
els | +0.004 |
ric | +0.004 |
cking | +0.003 |
Neg logit contributions | |
ives | -0.004 |
ury | -0.004 |
Follow | -0.003 |
Welcome | -0.003 |
Enjoy | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
ives | +0.032 |
Enjoy | +0.027 |
ury | +0.026 |
Max | +0.026 |
hide | +0.024 |
Neg logit contributions | |
flower | -0.056 |
els | -0.051 |
ric | -0.051 |
ble | -0.049 |
eled | -0.049 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ives | +0.006 |
ury | +0.006 |
Enjoy | +0.005 |
Welcome | +0.005 |
Follow | +0.005 |
Neg logit contributions | |
flower | -0.013 |
ble | -0.012 |
ric | -0.012 |
els | -0.011 |
cking | -0.011 |
Token | Jim |
Token ID | 18050 |
Feature activation | +8.66e-02 |
Pos logit contributions | |
flower | +0.006 |
ble | +0.005 |
ric | +0.005 |
els | +0.005 |
cks | +0.004 |
Neg logit contributions | |
ives | -0.005 |
ury | -0.004 |
Enjoy | -0.004 |
Follow | -0.004 |
Thank | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
cking | +0.005 |
flower | +0.005 |
ble | +0.005 |
ric | +0.005 |
cks | +0.005 |
Neg logit contributions | |
ives | -0.002 |
ury | -0.002 |
Enjoy | -0.002 |
Max | -0.002 |
Now | -0.001 |
Token | tired |
Token ID | 10032 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
flower | +0.026 |
ble | +0.023 |
ric | +0.023 |
cking | +0.023 |
els | +0.022 |
Neg logit contributions | |
ives | -0.017 |
ury | -0.015 |
Enjoy | -0.014 |
Welcome | -0.014 |
Follow | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
flower | +0.007 |
ble | +0.006 |
ric | +0.006 |
cking | +0.006 |
els | +0.006 |
Neg logit contributions | |
ives | -0.006 |
ury | -0.005 |
Enjoy | -0.005 |
Follow | -0.005 |
Welcome | -0.005 |
Token | frustrated |
Token ID | 14718 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
flower | +0.014 |
ble | +0.013 |
ric | +0.012 |
cking | +0.012 |
els | +0.012 |
Neg logit contributions | |
ives | -0.010 |
ury | -0.009 |
Enjoy | -0.008 |
Welcome | -0.008 |
Follow | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
flower | +0.159 |
ble | +0.144 |
ric | +0.140 |
els | +0.139 |
cking | +0.139 |
Neg logit contributions | |
ives | -0.132 |
ury | -0.117 |
Enjoy | -0.115 |
Welcome | -0.111 |
Follow | -0.109 |
Token | He |
Token ID | 679 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
ives | +0.002 |
ury | +0.002 |
Enjoy | +0.002 |
Welcome | +0.002 |
Follow | +0.001 |
Neg logit contributions | |
flower | -0.006 |
ble | -0.005 |
ric | -0.005 |
els | -0.005 |
cking | -0.005 |
Token | had |
Token ID | 550 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
flower | +0.015 |
ble | +0.014 |
ric | +0.014 |
els | +0.014 |
cking | +0.013 |
Neg logit contributions | |
ives | -0.013 |
ury | -0.011 |
Enjoy | -0.011 |
Welcome | -0.010 |
Follow | -0.010 |
Token | been |
Token ID | 587 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
flower | +0.009 |
ble | +0.008 |
els | +0.008 |
ric | +0.008 |
cking | +0.008 |
Neg logit contributions | |
ives | -0.004 |
ury | -0.004 |
Enjoy | -0.003 |
Welcome | -0.003 |
Max | -0.003 |
Token | walking |
Token ID | 6155 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
ives | +0.008 |
ury | +0.007 |
Enjoy | +0.006 |
Follow | +0.006 |
Welcome | +0.006 |
Neg logit contributions | |
flower | -0.010 |
ble | -0.009 |
cking | -0.009 |
ric | -0.009 |
els | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
flower | +0.018 |
ble | +0.016 |
els | +0.015 |
ric | +0.015 |
cking | +0.015 |
Neg logit contributions | |
ives | -0.017 |
ury | -0.015 |
Enjoy | -0.015 |
Welcome | -0.014 |
Follow | -0.014 |
Token | She |
Token ID | 1375 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
ives | +0.001 |
villains | +0.001 |
ury | +0.001 |
ave | +0.001 |
traitor | +0.001 |
Neg logit contributions | |
flower | -0.002 |
ric | -0.002 |
els | -0.002 |
ble | -0.002 |
ries | -0.001 |
Token | used |
Token ID | 973 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
flower | +0.023 |
els | +0.021 |
ble | +0.021 |
cking | +0.020 |
ric | +0.020 |
Neg logit contributions | |
ives | -0.020 |
Enjoy | -0.018 |
ury | -0.017 |
Welcome | -0.017 |
People | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ives | +0.076 |
Enjoy | +0.066 |
ury | +0.065 |
Max | +0.065 |
Happy | +0.064 |
Neg logit contributions | |
flower | -0.097 |
ble | -0.087 |
ric | -0.086 |
cking | -0.084 |
els | -0.081 |
Token | m |
Token ID | 285 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
ives | +0.034 |
ury | +0.030 |
Enjoy | +0.029 |
Welcome | +0.029 |
Happy | +0.028 |
Neg logit contributions | |
flower | -0.052 |
ble | -0.048 |
ric | -0.047 |
els | -0.047 |
cking | -0.047 |
Token | itt |
Token ID | 715 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
ives | +0.060 |
ury | +0.053 |
Enjoy | +0.052 |
Welcome | +0.051 |
Happy | +0.050 |
Neg logit contributions | |
flower | -0.084 |
ble | -0.077 |
ric | -0.075 |
els | -0.074 |
cking | -0.074 |
Token | to |
Token ID | 284 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
ives | +0.157 |
ury | +0.139 |
Enjoy | +0.137 |
Welcome | +0.132 |
Follow | +0.129 |
Neg logit contributions | |
flower | -0.259 |
ble | -0.236 |
ric | -0.231 |
cking | -0.231 |
els | -0.230 |
Token | take |
Token ID | 1011 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
ives | +0.025 |
ury | +0.022 |
Enjoy | +0.022 |
Max | +0.021 |
Welcome | +0.021 |
Neg logit contributions | |
flower | -0.033 |
ric | -0.029 |
ble | -0.029 |
cking | -0.028 |
els | -0.028 |
Token | out |
Token ID | 503 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
ives | +0.015 |
ury | +0.014 |
Follow | +0.013 |
villains | +0.013 |
Bye | +0.013 |
Neg logit contributions | |
flower | -0.011 |
els | -0.011 |
ble | -0.010 |
ries | -0.010 |
cking | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
ives | +0.021 |
ury | +0.018 |
Enjoy | +0.017 |
Happy | +0.017 |
Welcome | +0.017 |
Neg logit contributions | |
flower | -0.031 |
ble | -0.028 |
ric | -0.028 |
cking | -0.027 |
els | -0.026 |
Token | pan |
Token ID | 3425 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ives | +0.014 |
Enjoy | +0.012 |
ury | +0.012 |
Welcome | +0.012 |
Happy | +0.012 |
Neg logit contributions | |
flower | -0.017 |
ble | -0.016 |
ric | -0.016 |
cking | -0.015 |
els | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
ives | +0.037 |
ury | +0.033 |
Enjoy | +0.033 |
Welcome | +0.032 |
Happy | +0.032 |
Neg logit contributions | |
flower | -0.036 |
ble | -0.031 |
ric | -0.031 |
els | -0.030 |
cking | -0.030 |
Token | shore |
Token ID | 15191 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
ives | +0.028 |
ury | +0.025 |
Enjoy | +0.024 |
Welcome | +0.024 |
Follow | +0.023 |
Neg logit contributions | |
flower | -0.036 |
ble | -0.033 |
ric | -0.032 |
cking | -0.032 |
els | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
ives | +0.027 |
ury | +0.023 |
Enjoy | +0.022 |
Welcome | +0.021 |
Happy | +0.021 |
Neg logit contributions | |
flower | -0.044 |
ble | -0.040 |
ric | -0.040 |
cking | -0.039 |
els | -0.039 |
Token | They |
Token ID | 1119 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
flower | +0.010 |
ric | +0.010 |
ble | +0.009 |
els | +0.009 |
mill | +0.009 |
Neg logit contributions | |
ives | -0.005 |
ury | -0.004 |
Enjoy | -0.003 |
Follow | -0.003 |
villains | -0.003 |
Token | collected |
Token ID | 7723 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ives | +0.004 |
ury | +0.003 |
Enjoy | +0.003 |
Welcome | +0.003 |
Happy | +0.003 |
Neg logit contributions | |
flower | -0.008 |
ble | -0.007 |
els | -0.007 |
ric | -0.007 |
cking | -0.007 |
Token | seas |
Token ID | 21547 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
ives | +0.034 |
Enjoy | +0.029 |
Happy | +0.029 |
hide | +0.029 |
Max | +0.028 |
Neg logit contributions | |
flower | -0.052 |
ric | -0.046 |
ble | -0.046 |
cker | -0.044 |
cking | -0.044 |
Token | hell |
Token ID | 12758 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
ives | +0.169 |
ury | +0.144 |
Enjoy | +0.136 |
Welcome | +0.130 |
Happy | +0.129 |
Neg logit contributions | |
flower | -0.235 |
ble | -0.211 |
ric | -0.207 |
cking | -0.205 |
els | -0.204 |
Token | s |
Token ID | 82 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ives | +0.010 |
ury | +0.009 |
Enjoy | +0.008 |
Welcome | +0.008 |
Max | +0.008 |
Neg logit contributions | |
flower | -0.018 |
ric | -0.017 |
ble | -0.017 |
cking | -0.017 |
els | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
ives | +0.030 |
ury | +0.024 |
Enjoy | +0.024 |
Welcome | +0.022 |
Happy | +0.021 |
Neg logit contributions | |
flower | -0.055 |
ble | -0.051 |
cking | -0.051 |
ric | -0.049 |
els | -0.049 |
Token | built |
Token ID | 3170 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
flower | +0.002 |
ble | +0.002 |
ric | +0.002 |
els | +0.002 |
cking | +0.002 |
Neg logit contributions | |
ives | -0.001 |
ury | -0.001 |
Enjoy | -0.001 |
Welcome | -0.001 |
Follow | -0.001 |
Token | sand |
Token ID | 6450 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
flower | +0.016 |
ble | +0.014 |
ric | +0.014 |
els | +0.013 |
cker | +0.013 |
Neg logit contributions | |
ives | -0.010 |
hide | -0.009 |
Happy | -0.009 |
Enjoy | -0.009 |
Max | -0.009 |
Token | thought |
Token ID | 1807 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ives | +0.020 |
Enjoy | +0.019 |
Welcome | +0.018 |
ury | +0.017 |
Follow | +0.017 |
Neg logit contributions | |
flower | -0.025 |
ble | -0.022 |
els | -0.021 |
ric | -0.021 |
cking | -0.021 |
Token | they |
Token ID | 484 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
flower | +0.006 |
ble | +0.005 |
els | +0.005 |
cking | +0.005 |
ric | +0.005 |
Neg logit contributions | |
ives | -0.006 |
Enjoy | -0.005 |
Follow | -0.005 |
ury | -0.005 |
Sadly | -0.005 |
Token | looked |
Token ID | 3114 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
ives | +0.015 |
ury | +0.013 |
Enjoy | +0.013 |
Welcome | +0.012 |
Follow | +0.012 |
Neg logit contributions | |
flower | -0.024 |
ble | -0.022 |
ric | -0.021 |
els | -0.021 |
cking | -0.021 |
Token | like |
Token ID | 588 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
ives | +0.006 |
ury | +0.005 |
Enjoy | +0.005 |
Welcome | +0.005 |
Happy | +0.005 |
Neg logit contributions | |
flower | -0.011 |
ble | -0.010 |
ric | -0.010 |
els | -0.010 |
cking | -0.010 |
Token | ac |
Token ID | 936 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
ives | +0.008 |
ury | +0.007 |
Enjoy | +0.006 |
Follow | +0.006 |
Sadly | +0.006 |
Neg logit contributions | |
flower | -0.008 |
ble | -0.007 |
els | -0.007 |
ric | -0.007 |
mill | -0.007 |
Token | rob |
Token ID | 22609 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
Welcome | +0.029 |
Enjoy | +0.029 |
ives | +0.028 |
Follow | +0.028 |
Thank | +0.027 |
Neg logit contributions | |
flower | -0.027 |
ble | -0.024 |
cking | -0.023 |
els | -0.022 |
ric | -0.022 |
Token | ats |
Token ID | 1381 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
ives | +0.182 |
ury | +0.171 |
Welcome | +0.170 |
Enjoy | +0.166 |
Follow | +0.165 |
Neg logit contributions | |
flower | -0.186 |
els | -0.177 |
cking | -0.171 |
cks | -0.166 |
ble | -0.166 |
Token | . |
Token ID | 13 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
ives | +0.064 |
ury | +0.056 |
Enjoy | +0.054 |
Welcome | +0.052 |
Happy | +0.051 |
Neg logit contributions | |
flower | -0.098 |
ble | -0.089 |
ric | -0.088 |
cking | -0.088 |
els | -0.087 |
Token | She |
Token ID | 1375 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
ives | +0.003 |
villains | +0.002 |
Enjoy | +0.002 |
traitor | +0.002 |
Cop | +0.002 |
Neg logit contributions | |
flower | -0.003 |
els | -0.002 |
ric | -0.002 |
mill | -0.002 |
ries | -0.002 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
flower | +0.016 |
ble | +0.014 |
ric | +0.014 |
els | +0.014 |
cking | +0.014 |
Neg logit contributions | |
ives | -0.011 |
Enjoy | -0.009 |
ury | -0.009 |
Welcome | -0.009 |
Follow | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ives | +0.038 |
ury | +0.033 |
Enjoy | +0.032 |
Welcome | +0.031 |
Follow | +0.030 |
Neg logit contributions | |
flower | -0.055 |
ble | -0.050 |
ric | -0.049 |
cking | -0.049 |
els | -0.048 |
Token | learn |
Token ID | 2193 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
ives | +0.022 |
ury | +0.020 |
Enjoy | +0.019 |
Welcome | +0.019 |
Happy | +0.018 |
Neg logit contributions | |
flower | -0.028 |
ble | -0.026 |
ric | -0.025 |
cking | -0.025 |
els | -0.024 |
Token | more |
Token ID | 517 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ives | +0.004 |
ury | +0.003 |
Enjoy | +0.003 |
Welcome | +0.003 |
Happy | +0.003 |
Neg logit contributions | |
flower | -0.006 |
ble | -0.005 |
ric | -0.005 |
cking | -0.005 |
els | -0.005 |
Token | about |
Token ID | 546 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
ives | +0.029 |
ury | +0.025 |
Enjoy | +0.024 |
Welcome | +0.023 |
Sadly | +0.022 |
Neg logit contributions | |
flower | -0.055 |
ble | -0.054 |
els | -0.052 |
ric | -0.051 |
cking | -0.051 |
Token | rh |
Token ID | 9529 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
ives | +0.031 |
ury | +0.027 |
Enjoy | +0.026 |
Follow | +0.026 |
Welcome | +0.025 |
Neg logit contributions | |
flower | -0.027 |
ric | -0.024 |
ble | -0.024 |
els | -0.023 |
cking | -0.023 |
Token | in |
Token ID | 259 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
ives | +0.112 |
ury | +0.105 |
Enjoy | +0.104 |
Welcome | +0.104 |
Thank | +0.103 |
Neg logit contributions | |
flower | -0.056 |
ble | -0.050 |
cking | -0.050 |
els | -0.050 |
ric | -0.047 |
Token | oc |
Token ID | 420 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
ives | +0.030 |
Enjoy | +0.027 |
ury | +0.027 |
Sadly | +0.026 |
Welcome | +0.026 |
Neg logit contributions | |
flower | -0.036 |
ble | -0.032 |
cking | -0.032 |
ric | -0.032 |
els | -0.032 |
Token | er |
Token ID | 263 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
ives | +0.221 |
Welcome | +0.212 |
ury | +0.211 |
Sadly | +0.203 |
Happy | +0.203 |
Neg logit contributions | |
els | -0.139 |
flower | -0.138 |
ries | -0.129 |
ric | -0.125 |
ble | -0.124 |
Token | oses |
Token ID | 4629 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
ives | +0.098 |
ury | +0.086 |
Enjoy | +0.082 |
Welcome | +0.080 |
Max | +0.078 |
Neg logit contributions | |
flower | -0.142 |
ble | -0.130 |
cking | -0.128 |
ric | -0.127 |
els | -0.126 |
Token | and |
Token ID | 290 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ives | +0.048 |
ury | +0.044 |
Enjoy | +0.043 |
Welcome | +0.042 |
Follow | +0.041 |
Neg logit contributions | |
flower | -0.062 |
ble | -0.055 |
ric | -0.054 |
els | -0.053 |
cking | -0.052 |
Token | respect |
Token ID | 2461 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
flower | +0.012 |
ric | +0.011 |
ble | +0.010 |
els | +0.010 |
cking | +0.010 |
Neg logit contributions | |
ives | -0.009 |
ury | -0.008 |
Enjoy | -0.008 |
Welcome | -0.008 |
Follow | -0.008 |
Token | them |
Token ID | 606 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
ives | +0.018 |
ury | +0.016 |
Enjoy | +0.016 |
Welcome | +0.015 |
Follow | +0.015 |
Neg logit contributions | |
flower | -0.017 |
ble | -0.015 |
els | -0.015 |
ric | -0.015 |
cking | -0.015 |
Token | didn |
Token ID | 1422 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
ives | +0.066 |
Enjoy | +0.058 |
ury | +0.057 |
Welcome | +0.056 |
Happy | +0.054 |
Neg logit contributions | |
flower | -0.088 |
ble | -0.081 |
cking | -0.078 |
els | -0.077 |
ric | -0.077 |
Token | 't |
Token ID | 470 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
flower | +0.005 |
cking | +0.004 |
ric | +0.004 |
els | +0.004 |
eled | +0.004 |
Neg logit contributions | |
ives | -0.001 |
ury | -0.001 |
Enjoy | -0.001 |
Max | -0.001 |
People | -0.000 |
Token | like |
Token ID | 588 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
ives | +0.014 |
ury | +0.012 |
Enjoy | +0.011 |
Welcome | +0.011 |
Happy | +0.010 |
Neg logit contributions | |
flower | -0.030 |
ble | -0.027 |
ric | -0.027 |
cking | -0.027 |
els | -0.027 |
Token | wet |
Token ID | 9583 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
ives | +0.024 |
ury | +0.022 |
Enjoy | +0.021 |
Welcome | +0.021 |
Happy | +0.020 |
Neg logit contributions | |
flower | -0.031 |
ble | -0.028 |
ric | -0.027 |
cking | -0.027 |
els | -0.027 |
Token | av |
Token ID | 1196 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
ives | +0.006 |
Max | +0.005 |
Enjoy | +0.005 |
ury | +0.005 |
Happy | +0.005 |
Neg logit contributions | |
flower | -0.008 |
ric | -0.007 |
ble | -0.007 |
cking | -0.007 |
cks | -0.007 |
Token | oc |
Token ID | 420 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
ives | +0.100 |
Welcome | +0.099 |
Enjoy | +0.095 |
ury | +0.094 |
People | +0.094 |
Neg logit contributions | |
flower | -0.131 |
cking | -0.117 |
els | -0.115 |
ric | -0.112 |
cks | -0.112 |
Token | ados |
Token ID | 22484 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
ives | +0.219 |
ury | +0.217 |
Welcome | +0.216 |
Follow | +0.209 |
Happy | +0.205 |
Neg logit contributions | |
flower | -0.130 |
els | -0.125 |
ries | -0.120 |
ble | -0.117 |
cking | -0.105 |
Token | , |
Token ID | 11 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
flower | +0.024 |
ble | +0.022 |
cking | +0.021 |
els | +0.021 |
ric | +0.021 |
Neg logit contributions | |
ives | -0.022 |
Enjoy | -0.021 |
Follow | -0.020 |
ury | -0.020 |
Welcome | -0.020 |
Token | so |
Token ID | 523 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
ives | +0.005 |
Max | +0.005 |
ury | +0.004 |
People | +0.004 |
Welcome | +0.004 |
Neg logit contributions | |
flower | -0.016 |
ble | -0.015 |
els | -0.014 |
cking | -0.014 |
ric | -0.014 |
Token | he |
Token ID | 339 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
flower | +0.017 |
ric | +0.016 |
els | +0.016 |
cks | +0.016 |
cking | +0.016 |
Neg logit contributions | |
Max | -0.005 |
ury | -0.004 |
Sadly | -0.004 |
Enjoy | -0.004 |
People | -0.004 |
Token | decided |
Token ID | 3066 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
ives | +0.029 |
ury | +0.025 |
Enjoy | +0.025 |
Welcome | +0.024 |
Happy | +0.023 |
Neg logit contributions | |
flower | -0.035 |
ble | -0.032 |
cking | -0.031 |
els | -0.031 |
ric | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
flower | +0.020 |
cker | +0.018 |
ble | +0.017 |
ric | +0.017 |
immer | +0.017 |
Neg logit contributions | |
hide | -0.008 |
Happy | -0.007 |
Max | -0.007 |
Welcome | -0.007 |
many | -0.006 |
Token | waves |
Token ID | 9813 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
ives | +0.026 |
Enjoy | +0.023 |
ury | +0.023 |
Welcome | +0.022 |
Happy | +0.022 |
Neg logit contributions | |
flower | -0.027 |
ble | -0.024 |
ric | -0.024 |
cking | -0.023 |
els | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -9.51e-02 |
Pos logit contributions | |
ives | +0.024 |
ury | +0.022 |
Enjoy | +0.021 |
Welcome | +0.021 |
Happy | +0.020 |
Neg logit contributions | |
flower | -0.028 |
ble | -0.025 |
ric | -0.025 |
cking | -0.025 |
els | -0.025 |
Token | They |
Token ID | 1119 |
Feature activation | +5.23e-03 |
Pos logit contributions | |
ives | +0.003 |
ury | +0.003 |
traitor | +0.002 |
villains | +0.002 |
Enjoy | +0.002 |
Neg logit contributions | |
flower | -0.004 |
ric | -0.004 |
els | -0.004 |
mill | -0.004 |
ble | -0.004 |
Token | gathered |
Token ID | 9272 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
flower | +0.000 |
ble | +0.000 |
ric | +0.000 |
cking | +0.000 |
els | +0.000 |
Neg logit contributions | |
ives | -0.000 |
ury | -0.000 |
Enjoy | -0.000 |
Welcome | -0.000 |
Follow | -0.000 |
Token | seas |
Token ID | 21547 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
ives | +0.038 |
Enjoy | +0.034 |
ury | +0.033 |
Happy | +0.032 |
Welcome | +0.032 |
Neg logit contributions | |
flower | -0.047 |
ric | -0.042 |
ble | -0.042 |
cking | -0.040 |
els | -0.039 |
Token | hell |
Token ID | 12758 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
ives | +0.160 |
ury | +0.140 |
Enjoy | +0.133 |
Welcome | +0.128 |
Happy | +0.126 |
Neg logit contributions | |
flower | -0.209 |
ble | -0.186 |
ric | -0.183 |
cking | -0.180 |
els | -0.180 |
Token | s |
Token ID | 82 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ives | +0.014 |
ury | +0.012 |
Enjoy | +0.012 |
Welcome | +0.012 |
Follow | +0.011 |
Neg logit contributions | |
flower | -0.021 |
ble | -0.019 |
ric | -0.019 |
cking | -0.018 |
els | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ives | +0.029 |
ury | +0.023 |
Enjoy | +0.022 |
Welcome | +0.020 |
Follow | +0.020 |
Neg logit contributions | |
flower | -0.064 |
cking | -0.059 |
ble | -0.059 |
ric | -0.058 |
els | -0.057 |
Token | filled |
Token ID | 5901 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
ives | +0.005 |
ury | +0.004 |
Enjoy | +0.004 |
Welcome | +0.004 |
Happy | +0.004 |
Neg logit contributions | |
flower | -0.005 |
ble | -0.004 |
ric | -0.004 |
cking | -0.004 |
els | -0.004 |
Token | their |
Token ID | 511 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
flower | +0.018 |
ric | +0.015 |
ble | +0.015 |
els | +0.015 |
cking | +0.015 |
Neg logit contributions | |
ives | -0.011 |
Enjoy | -0.011 |
Happy | -0.011 |
Welcome | -0.010 |
ury | -0.010 |
Token | They |
Token ID | 1119 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
ives | +0.015 |
ury | +0.013 |
ave | +0.012 |
Follow | +0.011 |
Enjoy | +0.011 |
Neg logit contributions | |
flower | -0.018 |
ric | -0.017 |
ble | -0.016 |
els | -0.016 |
lights | -0.016 |
Token | heard |
Token ID | 2982 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
ives | +0.018 |
ury | +0.016 |
Enjoy | +0.016 |
Welcome | +0.015 |
Follow | +0.015 |
Neg logit contributions | |
flower | -0.022 |
ble | -0.020 |
els | -0.019 |
ric | -0.019 |
cking | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ives | +0.073 |
ury | +0.066 |
Enjoy | +0.064 |
Follow | +0.062 |
Welcome | +0.061 |
Neg logit contributions | |
flower | -0.073 |
ble | -0.066 |
ric | -0.065 |
els | -0.064 |
cking | -0.064 |
Token | rh |
Token ID | 9529 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
ives | +0.051 |
ury | +0.047 |
Enjoy | +0.046 |
Follow | +0.043 |
Welcome | +0.042 |
Neg logit contributions | |
flower | -0.059 |
ble | -0.052 |
ric | -0.051 |
cking | -0.049 |
els | -0.049 |
Token | in |
Token ID | 259 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ives | +0.114 |
ury | +0.105 |
Enjoy | +0.103 |
Welcome | +0.102 |
Happy | +0.100 |
Neg logit contributions | |
flower | -0.064 |
ble | -0.054 |
ric | -0.052 |
cking | -0.052 |
els | -0.051 |
Token | oc |
Token ID | 420 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
ives | +0.034 |
ury | +0.031 |
Enjoy | +0.030 |
Welcome | +0.028 |
Follow | +0.028 |
Neg logit contributions | |
flower | -0.051 |
ric | -0.046 |
ble | -0.046 |
cking | -0.045 |
els | -0.044 |
Token | eros |
Token ID | 27498 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
ives | +0.228 |
ury | +0.212 |
Welcome | +0.207 |
Enjoy | +0.203 |
Follow | +0.200 |
Neg logit contributions | |
flower | -0.144 |
ble | -0.123 |
els | -0.120 |
ric | -0.118 |
cking | -0.112 |
Token | roar |
Token ID | 34532 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
ives | +0.030 |
ury | +0.026 |
Enjoy | +0.025 |
Welcome | +0.025 |
Happy | +0.024 |
Neg logit contributions | |
flower | -0.042 |
ble | -0.038 |
ric | -0.037 |
els | -0.037 |
cking | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
ives | +0.012 |
ury | +0.011 |
Welcome | +0.010 |
Happy | +0.010 |
Enjoy | +0.010 |
Neg logit contributions | |
flower | -0.018 |
ric | -0.016 |
ble | -0.016 |
els | -0.016 |
cking | -0.016 |
Token | They |
Token ID | 1119 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
ives | +0.014 |
ury | +0.011 |
Enjoy | +0.010 |
Follow | +0.010 |
Welcome | +0.010 |
Neg logit contributions | |
flower | -0.026 |
ble | -0.024 |
ric | -0.024 |
els | -0.023 |
cks | -0.023 |
Token | heard |
Token ID | 2982 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
ives | +0.017 |
ury | +0.015 |
Enjoy | +0.015 |
Welcome | +0.014 |
Follow | +0.014 |
Neg logit contributions | |
flower | -0.026 |
ble | -0.023 |
ric | -0.023 |
cking | -0.023 |
els | -0.022 |
Token | they |
Token ID | 484 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
ives | +0.024 |
ury | +0.021 |
Enjoy | +0.021 |
Welcome | +0.020 |
Follow | +0.020 |
Neg logit contributions | |
flower | -0.027 |
ble | -0.024 |
els | -0.023 |
cking | -0.023 |
ric | -0.023 |
Token | could |
Token ID | 714 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
ives | +0.025 |
ury | +0.021 |
Enjoy | +0.020 |
Welcome | +0.020 |
Happy | +0.019 |
Neg logit contributions | |
flower | -0.049 |
ble | -0.045 |
ric | -0.044 |
els | -0.044 |
cking | -0.044 |
Token | grow |
Token ID | 1663 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
ives | +0.017 |
Enjoy | +0.016 |
hide | +0.016 |
Welcome | +0.013 |
Max | +0.013 |
Neg logit contributions | |
flower | -0.042 |
els | -0.038 |
ric | -0.038 |
eled | -0.038 |
cking | -0.038 |
Token | more |
Token ID | 517 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
flower | +0.021 |
ric | +0.020 |
cking | +0.018 |
eled | +0.018 |
els | +0.018 |
Neg logit contributions | |
ives | -0.011 |
Enjoy | -0.010 |
Happy | -0.009 |
People | -0.009 |
Welcome | -0.009 |
Token | av |
Token ID | 1196 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
ives | +0.045 |
ury | +0.041 |
Enjoy | +0.040 |
Welcome | +0.039 |
Follow | +0.038 |
Neg logit contributions | |
flower | -0.045 |
ble | -0.040 |
els | -0.039 |
cking | -0.038 |
ric | -0.038 |
Token | oc |
Token ID | 420 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
Welcome | +0.099 |
ives | +0.099 |
People | +0.095 |
ury | +0.094 |
Enjoy | +0.093 |
Neg logit contributions | |
flower | -0.123 |
cking | -0.107 |
els | -0.106 |
cker | -0.102 |
cks | -0.102 |
Token | ados |
Token ID | 22484 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ives | +0.217 |
Welcome | +0.213 |
ury | +0.212 |
Happy | +0.202 |
Sadly | +0.202 |
Neg logit contributions | |
flower | -0.134 |
els | -0.129 |
ries | -0.123 |
ble | -0.122 |
cking | -0.113 |
Token | and |
Token ID | 290 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
flower | +0.059 |
ble | +0.053 |
els | +0.050 |
cking | +0.050 |
ric | +0.049 |
Neg logit contributions | |
ives | -0.049 |
Enjoy | -0.045 |
ury | -0.045 |
Welcome | -0.043 |
Sadly | -0.043 |
Token | share |
Token ID | 2648 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ives | +0.001 |
ury | +0.001 |
Enjoy | +0.001 |
Welcome | +0.001 |
Happy | +0.001 |
Neg logit contributions | |
flower | -0.002 |
ble | -0.001 |
ric | -0.001 |
cking | -0.001 |
els | -0.001 |
Token | them |
Token ID | 606 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
flower | +0.012 |
ric | +0.011 |
ble | +0.011 |
cking | +0.010 |
els | +0.010 |
Neg logit contributions | |
ives | -0.010 |
Enjoy | -0.009 |
ury | -0.009 |
Happy | -0.008 |
Welcome | -0.008 |
Token | with |
Token ID | 351 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
flower | +0.052 |
ric | +0.048 |
ble | +0.046 |
cking | +0.046 |
els | +0.046 |
Neg logit contributions | |
ives | -0.024 |
ury | -0.020 |
Enjoy | -0.020 |
Happy | -0.019 |
Welcome | -0.018 |
Token | had |
Token ID | 550 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
ives | +0.016 |
ury | +0.014 |
Enjoy | +0.014 |
Welcome | +0.013 |
Happy | +0.013 |
Neg logit contributions | |
flower | -0.027 |
ble | -0.024 |
ric | -0.023 |
cking | -0.023 |
els | -0.023 |
Token | discovered |
Token ID | 5071 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ives | +0.008 |
ury | +0.007 |
Enjoy | +0.007 |
Welcome | +0.007 |
Follow | +0.007 |
Neg logit contributions | |
flower | -0.013 |
ric | -0.012 |
ble | -0.012 |
cking | -0.011 |
els | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
ives | +0.047 |
Enjoy | +0.042 |
ury | +0.041 |
Max | +0.040 |
Welcome | +0.040 |
Neg logit contributions | |
flower | -0.072 |
ble | -0.064 |
ric | -0.063 |
cking | -0.063 |
els | -0.062 |
Token | rh |
Token ID | 9529 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
ives | +0.038 |
ury | +0.034 |
Enjoy | +0.032 |
Follow | +0.031 |
Welcome | +0.031 |
Neg logit contributions | |
flower | -0.044 |
ric | -0.039 |
ble | -0.039 |
cking | -0.037 |
els | -0.037 |
Token | in |
Token ID | 259 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ives | +0.114 |
ury | +0.106 |
Enjoy | +0.105 |
Welcome | +0.103 |
Happy | +0.102 |
Neg logit contributions | |
flower | -0.063 |
ble | -0.054 |
els | -0.051 |
ric | -0.051 |
cking | -0.051 |
Token | oc |
Token ID | 420 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
ives | +0.041 |
ury | +0.036 |
Enjoy | +0.035 |
Welcome | +0.034 |
Happy | +0.033 |
Neg logit contributions | |
flower | -0.060 |
ric | -0.054 |
ble | -0.053 |
els | -0.052 |
cking | -0.052 |
Token | eros |
Token ID | 27498 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
ives | +0.228 |
ury | +0.213 |
Welcome | +0.206 |
Max | +0.203 |
Enjoy | +0.203 |
Neg logit contributions | |
flower | -0.143 |
els | -0.122 |
ble | -0.120 |
ric | -0.120 |
cking | -0.111 |
Token | , |
Token ID | 11 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
ives | +0.033 |
ury | +0.029 |
Enjoy | +0.029 |
Welcome | +0.028 |
Happy | +0.027 |
Neg logit contributions | |
flower | -0.049 |
ble | -0.044 |
ric | -0.044 |
cking | -0.043 |
els | -0.043 |
Token | but |
Token ID | 475 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ives | +0.004 |
ury | +0.004 |
Enjoy | +0.004 |
Welcome | +0.004 |
Happy | +0.003 |
Neg logit contributions | |
flower | -0.007 |
ble | -0.006 |
ric | -0.006 |
cking | -0.006 |
els | -0.006 |
Token | they |
Token ID | 484 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
flower | +0.006 |
ble | +0.005 |
ric | +0.005 |
els | +0.005 |
cking | +0.005 |
Neg logit contributions | |
ives | -0.006 |
ury | -0.005 |
Enjoy | -0.005 |
Follow | -0.005 |
Welcome | -0.005 |
Token | had |
Token ID | 550 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
ives | +0.022 |
ury | +0.019 |
Enjoy | +0.019 |
Welcome | +0.018 |
Happy | +0.017 |
Neg logit contributions | |
flower | -0.039 |
ble | -0.036 |
ric | -0.035 |
cking | -0.035 |
els | -0.035 |
Token | They |
Token ID | 1119 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
ives | +0.019 |
ury | +0.016 |
Enjoy | +0.015 |
Follow | +0.014 |
ave | +0.014 |
Neg logit contributions | |
flower | -0.028 |
ble | -0.026 |
ric | -0.025 |
els | -0.024 |
cks | -0.024 |
Token | heard |
Token ID | 2982 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
ives | +0.021 |
ury | +0.018 |
Enjoy | +0.018 |
Welcome | +0.017 |
Follow | +0.017 |
Neg logit contributions | |
flower | -0.028 |
ble | -0.025 |
ric | -0.024 |
cking | -0.024 |
els | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ives | +0.077 |
ury | +0.069 |
Enjoy | +0.067 |
Follow | +0.065 |
Welcome | +0.065 |
Neg logit contributions | |
flower | -0.076 |
ble | -0.068 |
ric | -0.067 |
els | -0.066 |
cking | -0.066 |
Token | rh |
Token ID | 9529 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
ives | +0.056 |
ury | +0.051 |
Enjoy | +0.049 |
Follow | +0.047 |
enny | +0.046 |
Neg logit contributions | |
flower | -0.055 |
ric | -0.050 |
ble | -0.049 |
cking | -0.048 |
els | -0.046 |
Token | in |
Token ID | 259 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ives | +0.113 |
ury | +0.104 |
Enjoy | +0.102 |
Welcome | +0.100 |
Happy | +0.098 |
Neg logit contributions | |
flower | -0.066 |
ble | -0.055 |
ric | -0.054 |
cking | -0.053 |
els | -0.053 |
Token | oc |
Token ID | 420 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
ives | +0.031 |
ury | +0.027 |
Enjoy | +0.026 |
Welcome | +0.025 |
Follow | +0.024 |
Neg logit contributions | |
flower | -0.053 |
ble | -0.048 |
ric | -0.048 |
cking | -0.047 |
els | -0.047 |
Token | eros |
Token ID | 27498 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
ives | +0.227 |
ury | +0.209 |
Welcome | +0.204 |
Enjoy | +0.202 |
Follow | +0.198 |
Neg logit contributions | |
flower | -0.144 |
ble | -0.123 |
els | -0.120 |
ric | -0.119 |
cking | -0.114 |
Token | sn |
Token ID | 3013 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
ives | +0.030 |
ury | +0.027 |
Welcome | +0.026 |
Enjoy | +0.026 |
Happy | +0.025 |
Neg logit contributions | |
flower | -0.041 |
ble | -0.037 |
ric | -0.036 |
els | -0.036 |
cking | -0.036 |
Token | ore |
Token ID | 382 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
ives | +0.057 |
Welcome | +0.054 |
ury | +0.053 |
Happy | +0.053 |
villains | +0.050 |
Neg logit contributions | |
flower | -0.076 |
ble | -0.070 |
ric | -0.069 |
els | -0.068 |
cking | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
ives | +0.106 |
ury | +0.096 |
Enjoy | +0.095 |
Welcome | +0.092 |
Follow | +0.090 |
Neg logit contributions | |
flower | -0.107 |
ble | -0.097 |
ric | -0.094 |
cking | -0.093 |
els | -0.093 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ives | +0.018 |
ury | +0.015 |
Enjoy | +0.013 |
Follow | +0.013 |
Welcome | +0.012 |
Neg logit contributions | |
flower | -0.031 |
ble | -0.028 |
ric | -0.028 |
els | -0.027 |
cks | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
ives | +0.020 |
ury | +0.016 |
Enjoy | +0.016 |
Welcome | +0.015 |
Max | +0.014 |
Neg logit contributions | |
flower | -0.065 |
ble | -0.059 |
els | -0.058 |
ric | -0.058 |
cking | -0.058 |
Token | They |
Token ID | 2990 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
ives | +0.025 |
ury | +0.024 |
Enjoy | +0.023 |
Follow | +0.022 |
Welcome | +0.022 |
Neg logit contributions | |
flower | -0.030 |
ric | -0.026 |
els | -0.025 |
ble | -0.025 |
cking | -0.024 |
Token | get |
Token ID | 651 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
flower | +0.035 |
ble | +0.032 |
ric | +0.032 |
cking | +0.031 |
els | +0.031 |
Neg logit contributions | |
ives | -0.022 |
Enjoy | -0.019 |
ury | -0.019 |
Welcome | -0.018 |
Happy | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
flower | +0.007 |
ric | +0.006 |
ble | +0.006 |
cking | +0.006 |
els | +0.006 |
Neg logit contributions | |
ives | -0.004 |
Enjoy | -0.004 |
Happy | -0.003 |
Welcome | -0.003 |
Max | -0.003 |
Token | m |
Token ID | 285 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ives | +0.036 |
ury | +0.032 |
Enjoy | +0.032 |
Welcome | +0.031 |
Happy | +0.030 |
Neg logit contributions | |
flower | -0.042 |
ble | -0.038 |
ric | -0.038 |
els | -0.038 |
cking | -0.038 |
Token | itt |
Token ID | 715 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
ives | +0.052 |
ury | +0.046 |
Enjoy | +0.045 |
Welcome | +0.043 |
Follow | +0.042 |
Neg logit contributions | |
flower | -0.057 |
ble | -0.050 |
ric | -0.050 |
cking | -0.049 |
els | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
ives | +0.154 |
ury | +0.133 |
Enjoy | +0.128 |
Welcome | +0.124 |
Happy | +0.121 |
Neg logit contributions | |
flower | -0.208 |
ble | -0.187 |
ric | -0.186 |
els | -0.181 |
cking | -0.180 |
Token | a |
Token ID | 257 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
ives | +0.013 |
Enjoy | +0.011 |
ury | +0.011 |
Happy | +0.011 |
Welcome | +0.011 |
Neg logit contributions | |
flower | -0.020 |
ble | -0.018 |
ric | -0.017 |
cking | -0.017 |
els | -0.017 |
Token | spat |
Token ID | 15246 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
ives | +0.002 |
ury | +0.002 |
Enjoy | +0.002 |
Welcome | +0.002 |
Happy | +0.002 |
Neg logit contributions | |
flower | -0.003 |
ble | -0.002 |
els | -0.002 |
ric | -0.002 |
cking | -0.002 |
Token | ula |
Token ID | 4712 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
flower | +0.019 |
ric | +0.017 |
cking | +0.017 |
els | +0.017 |
ble | +0.016 |
Neg logit contributions | |
ives | -0.013 |
ury | -0.011 |
Enjoy | -0.011 |
Welcome | -0.010 |
Happy | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
flower | +0.060 |
ric | +0.056 |
cking | +0.056 |
ble | +0.054 |
els | +0.054 |
Neg logit contributions | |
ives | -0.041 |
ury | -0.035 |
Enjoy | -0.034 |
Thank | -0.031 |
Welcome | -0.031 |
Token | that |
Token ID | 326 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ives | +0.039 |
Enjoy | +0.035 |
ury | +0.035 |
Welcome | +0.033 |
Max | +0.033 |
Neg logit contributions | |
flower | -0.051 |
ble | -0.045 |
cking | -0.044 |
ric | -0.044 |
els | -0.044 |
Token | boss |
Token ID | 6478 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
ives | +0.046 |
ury | +0.040 |
Enjoy | +0.037 |
Follow | +0.035 |
Welcome | +0.035 |
Neg logit contributions | |
flower | -0.054 |
ble | -0.049 |
cking | -0.047 |
ric | -0.047 |
els | -0.045 |
Token | y |
Token ID | 88 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
ives | +0.024 |
ury | +0.022 |
Enjoy | +0.022 |
Welcome | +0.021 |
Happy | +0.021 |
Neg logit contributions | |
flower | -0.019 |
ble | -0.017 |
ric | -0.016 |
cking | -0.016 |
els | -0.016 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
ives | +0.009 |
ury | +0.008 |
Enjoy | +0.008 |
Welcome | +0.007 |
Happy | +0.007 |
Neg logit contributions | |
flower | -0.013 |
ble | -0.012 |
ric | -0.012 |
cking | -0.012 |
els | -0.012 |
Token | in |
Token ID | 259 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ives | +0.110 |
ury | +0.102 |
Enjoy | +0.101 |
Welcome | +0.099 |
Happy | +0.098 |
Neg logit contributions | |
flower | -0.056 |
ble | -0.048 |
ric | -0.045 |
cking | -0.045 |
els | -0.045 |
Token | oc |
Token ID | 420 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
ives | +0.038 |
ury | +0.034 |
Enjoy | +0.033 |
Welcome | +0.032 |
Happy | +0.031 |
Neg logit contributions | |
flower | -0.060 |
ble | -0.055 |
ric | -0.054 |
cking | -0.053 |
els | -0.053 |
Token | eros |
Token ID | 27498 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
ives | +0.229 |
ury | +0.215 |
Welcome | +0.212 |
Sadly | +0.207 |
Enjoy | +0.205 |
Neg logit contributions | |
flower | -0.129 |
els | -0.120 |
ble | -0.115 |
ries | -0.109 |
ric | -0.109 |
Token | . |
Token ID | 13 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
ives | +0.040 |
ury | +0.035 |
Enjoy | +0.034 |
Welcome | +0.033 |
Follow | +0.031 |
Neg logit contributions | |
flower | -0.064 |
ble | -0.058 |
ric | -0.057 |
cking | -0.057 |
els | -0.057 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
ives | +0.000 |
ury | +0.000 |
hide | +0.000 |
villains | +0.000 |
Welcome | +0.000 |
Neg logit contributions | |
flower | -0.001 |
ric | -0.001 |
ble | -0.001 |
els | -0.001 |
mill | -0.000 |
Token | D |
Token ID | 35 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ives | +0.016 |
ury | +0.015 |
Enjoy | +0.014 |
Follow | +0.013 |
Welcome | +0.013 |
Neg logit contributions | |
flower | -0.017 |
ble | -0.015 |
ric | -0.015 |
els | -0.014 |
cks | -0.014 |
Token | ee |
Token ID | 1453 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
ives | +0.052 |
Enjoy | +0.046 |
ury | +0.045 |
Welcome | +0.042 |
People | +0.041 |
Neg logit contributions | |
flower | -0.066 |
cking | -0.059 |
ble | -0.059 |
els | -0.058 |
ric | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
ives | +0.007 |
ury | +0.006 |
Enjoy | +0.006 |
Welcome | +0.006 |
Follow | +0.006 |
Neg logit contributions | |
flower | -0.009 |
ble | -0.009 |
cking | -0.008 |
els | -0.008 |
ric | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
ives | +0.007 |
Enjoy | +0.006 |
ury | +0.006 |
Follow | +0.006 |
Welcome | +0.006 |
Neg logit contributions | |
flower | -0.010 |
ble | -0.009 |
mill | -0.009 |
ric | -0.009 |
cking | -0.009 |
Token | I |
Token ID | 40 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
ives | +0.004 |
ury | +0.004 |
Enjoy | +0.004 |
Welcome | +0.004 |
Follow | +0.004 |
Neg logit contributions | |
flower | -0.007 |
ric | -0.006 |
ble | -0.006 |
els | -0.006 |
cking | -0.006 |
Token | love |
Token ID | 1842 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
flower | +0.023 |
ble | +0.020 |
ric | +0.020 |
els | +0.019 |
cking | +0.019 |
Neg logit contributions | |
ives | -0.016 |
ury | -0.014 |
Welcome | -0.014 |
Happy | -0.014 |
People | -0.014 |
Token | av |
Token ID | 1196 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
ives | +0.047 |
ury | +0.041 |
Follow | +0.039 |
Welcome | +0.038 |
Enjoy | +0.038 |
Neg logit contributions | |
flower | -0.061 |
ble | -0.055 |
ric | -0.054 |
els | -0.054 |
cking | -0.053 |
Token | oc |
Token ID | 420 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
Welcome | +0.108 |
ives | +0.107 |
ury | +0.103 |
People | +0.102 |
Bye | +0.101 |
Neg logit contributions | |
flower | -0.127 |
els | -0.111 |
cking | -0.109 |
ric | -0.104 |
cks | -0.103 |
Token | ados |
Token ID | 22484 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
ives | +0.220 |
ury | +0.218 |
Welcome | +0.216 |
Happy | +0.204 |
Follow | +0.203 |
Neg logit contributions | |
flower | -0.131 |
els | -0.123 |
ries | -0.119 |
ble | -0.110 |
cking | -0.102 |
Token | ! |
Token ID | 0 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
flower | +0.035 |
ble | +0.031 |
ric | +0.030 |
els | +0.030 |
mill | +0.029 |
Neg logit contributions | |
ives | -0.028 |
ury | -0.025 |
Enjoy | -0.025 |
Welcome | -0.025 |
Sadly | -0.025 |
Token | They |
Token ID | 1119 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
flower | +0.032 |
ric | +0.028 |
ble | +0.028 |
mill | +0.027 |
els | +0.026 |
Neg logit contributions | |
ives | -0.015 |
ury | -0.012 |
villains | -0.011 |
hide | -0.011 |
and | -0.011 |
Token | are |
Token ID | 389 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
flower | +0.015 |
ble | +0.014 |
ric | +0.014 |
cking | +0.014 |
els | +0.014 |
Neg logit contributions | |
ives | -0.009 |
ury | -0.008 |
Enjoy | -0.008 |
Welcome | -0.008 |
Happy | -0.007 |
Token | so |
Token ID | 523 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ives | +0.011 |
Enjoy | +0.010 |
ury | +0.010 |
Welcome | +0.009 |
Happy | +0.009 |
Neg logit contributions | |
flower | -0.022 |
ble | -0.020 |
ric | -0.019 |
cking | -0.019 |
els | -0.019 |
Token | It |
Token ID | 632 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
ives | +0.017 |
ury | +0.015 |
ave | +0.014 |
Cop | +0.014 |
villains | +0.014 |
Neg logit contributions | |
ble | -0.021 |
flower | -0.020 |
ric | -0.019 |
cks | -0.019 |
els | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
ives | +0.015 |
Max | +0.014 |
ury | +0.014 |
Welcome | +0.014 |
hide | +0.013 |
Neg logit contributions | |
flower | -0.037 |
ric | -0.035 |
ble | -0.035 |
els | -0.034 |
cking | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
ives | +0.022 |
Max | +0.021 |
Enjoy | +0.020 |
Welcome | +0.020 |
ury | +0.020 |
Neg logit contributions | |
flower | -0.042 |
ric | -0.037 |
els | -0.037 |
ble | -0.037 |
cking | -0.036 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
ives | +0.035 |
Enjoy | +0.031 |
ury | +0.031 |
Welcome | +0.030 |
Happy | +0.029 |
Neg logit contributions | |
flower | -0.043 |
cking | -0.039 |
els | -0.039 |
ble | -0.039 |
ric | -0.038 |
Token | in |
Token ID | 259 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
ives | +0.099 |
ury | +0.091 |
Enjoy | +0.089 |
Welcome | +0.088 |
Happy | +0.086 |
Neg logit contributions | |
flower | -0.055 |
ble | -0.047 |
ric | -0.046 |
cking | -0.045 |
els | -0.044 |
Token | oc |
Token ID | 420 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
ives | +0.033 |
ury | +0.030 |
Welcome | +0.028 |
Enjoy | +0.028 |
Follow | +0.027 |
Neg logit contributions | |
flower | -0.042 |
els | -0.037 |
ric | -0.037 |
ble | -0.037 |
cking | -0.037 |
Token | eros |
Token ID | 27498 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
ives | +0.222 |
ury | +0.206 |
Welcome | +0.200 |
Enjoy | +0.198 |
Max | +0.194 |
Neg logit contributions | |
flower | -0.144 |
ble | -0.129 |
els | -0.122 |
ric | -0.119 |
cking | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
ives | +0.029 |
ury | +0.026 |
Enjoy | +0.025 |
Welcome | +0.024 |
Happy | +0.023 |
Neg logit contributions | |
flower | -0.039 |
ble | -0.035 |
ric | -0.035 |
els | -0.034 |
cking | -0.034 |
Token | It |
Token ID | 632 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
ives | +0.018 |
ury | +0.015 |
ave | +0.014 |
Cop | +0.013 |
villains | +0.013 |
Neg logit contributions | |
flower | -0.022 |
ble | -0.022 |
ric | -0.021 |
cks | -0.020 |
els | -0.019 |
Token | lifted |
Token ID | 13663 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
ives | +0.016 |
ury | +0.014 |
Welcome | +0.014 |
Max | +0.014 |
Follow | +0.014 |
Neg logit contributions | |
flower | -0.038 |
ble | -0.035 |
ric | -0.035 |
els | -0.035 |
cking | -0.034 |
Token | its |
Token ID | 663 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
ives | +0.042 |
ury | +0.038 |
Enjoy | +0.037 |
Welcome | +0.036 |
Follow | +0.035 |
Neg logit contributions | |
flower | -0.030 |
ble | -0.027 |
els | -0.026 |
ric | -0.025 |
cking | -0.025 |
Token | have |
Token ID | 423 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
flower | +0.008 |
ble | +0.008 |
ric | +0.007 |
cking | +0.007 |
els | +0.007 |
Neg logit contributions | |
ives | -0.005 |
ury | -0.005 |
Enjoy | -0.005 |
Welcome | -0.004 |
Follow | -0.004 |
Token | stopped |
Token ID | 5025 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
ives | +0.004 |
ury | +0.004 |
Enjoy | +0.004 |
Follow | +0.004 |
Welcome | +0.004 |
Neg logit contributions | |
flower | -0.006 |
ric | -0.005 |
ble | -0.005 |
cking | -0.005 |
els | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ives | +0.011 |
ury | +0.010 |
Enjoy | +0.010 |
Welcome | +0.010 |
Happy | +0.009 |
Neg logit contributions | |
flower | -0.019 |
ble | -0.017 |
ric | -0.017 |
cking | -0.017 |
els | -0.017 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
ives | +0.046 |
ury | +0.041 |
Enjoy | +0.038 |
Follow | +0.037 |
enny | +0.037 |
Neg logit contributions | |
flower | -0.043 |
ric | -0.037 |
ble | -0.036 |
cking | -0.035 |
els | -0.034 |
Token | in |
Token ID | 259 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
ives | +0.105 |
ury | +0.097 |
Enjoy | +0.095 |
Welcome | +0.093 |
Happy | +0.091 |
Neg logit contributions | |
flower | -0.061 |
ble | -0.051 |
ric | -0.050 |
cking | -0.049 |
els | -0.049 |
Token | oc |
Token ID | 420 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
ives | +0.022 |
ury | +0.019 |
Enjoy | +0.019 |
Welcome | +0.018 |
Follow | +0.017 |
Neg logit contributions | |
flower | -0.034 |
ric | -0.030 |
ble | -0.030 |
cking | -0.029 |
els | -0.029 |
Token | eros |
Token ID | 27498 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
ives | +0.217 |
ury | +0.200 |
Welcome | +0.195 |
Enjoy | +0.193 |
Follow | +0.190 |
Neg logit contributions | |
flower | -0.143 |
ble | -0.121 |
els | -0.120 |
ric | -0.119 |
cking | -0.113 |
Token | . |
Token ID | 13 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
ives | +0.028 |
ury | +0.025 |
Enjoy | +0.025 |
Welcome | +0.024 |
People | +0.023 |
Neg logit contributions | |
flower | -0.027 |
ble | -0.024 |
ric | -0.023 |
cking | -0.023 |
els | -0.023 |
Token | He |
Token ID | 679 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
ives | +0.012 |
ury | +0.010 |
and | +0.009 |
enny | +0.009 |
hide | +0.009 |
Neg logit contributions | |
flower | -0.019 |
ric | -0.018 |
ble | -0.017 |
els | -0.016 |
cks | -0.016 |
Token | is |
Token ID | 318 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
ives | +0.007 |
ury | +0.006 |
Enjoy | +0.006 |
and | +0.006 |
Welcome | +0.006 |
Neg logit contributions | |
flower | -0.009 |
ric | -0.008 |
els | -0.008 |
ble | -0.008 |
cking | -0.008 |
Token | sleeping |
Token ID | 11029 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
ives | +0.031 |
ury | +0.027 |
Enjoy | +0.026 |
Welcome | +0.025 |
Follow | +0.024 |
Neg logit contributions | |
flower | -0.043 |
ble | -0.039 |
ric | -0.038 |
cking | -0.038 |
els | -0.038 |
Token | She |
Token ID | 1375 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
ives | +0.016 |
ury | +0.014 |
Enjoy | +0.013 |
Follow | +0.013 |
Welcome | +0.012 |
Neg logit contributions | |
flower | -0.025 |
ble | -0.023 |
ric | -0.022 |
els | -0.022 |
mill | -0.022 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
flower | +0.006 |
ble | +0.005 |
els | +0.005 |
cking | +0.005 |
ric | +0.005 |
Neg logit contributions | |
ives | -0.004 |
Enjoy | -0.004 |
ury | -0.004 |
Welcome | -0.004 |
Happy | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ives | +0.058 |
ury | +0.051 |
Enjoy | +0.051 |
Max | +0.049 |
Welcome | +0.049 |
Neg logit contributions | |
flower | -0.075 |
ble | -0.067 |
ric | -0.066 |
cking | -0.065 |
els | -0.064 |
Token | rh |
Token ID | 9529 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
ives | +0.049 |
ury | +0.044 |
Enjoy | +0.042 |
Welcome | +0.041 |
Follow | +0.040 |
Neg logit contributions | |
flower | -0.058 |
ble | -0.052 |
ric | -0.051 |
cking | -0.050 |
els | -0.050 |
Token | in |
Token ID | 259 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ives | +0.112 |
ury | +0.103 |
Enjoy | +0.102 |
Welcome | +0.100 |
Happy | +0.098 |
Neg logit contributions | |
flower | -0.064 |
ble | -0.054 |
ric | -0.052 |
cking | -0.051 |
els | -0.051 |
Token | oc |
Token ID | 420 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
ives | +0.030 |
ury | +0.025 |
Enjoy | +0.024 |
Welcome | +0.023 |
Follow | +0.022 |
Neg logit contributions | |
flower | -0.070 |
ble | -0.065 |
els | -0.064 |
ric | -0.064 |
cking | -0.064 |
Token | eros |
Token ID | 27498 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ives | +0.222 |
ury | +0.205 |
Welcome | +0.199 |
Enjoy | +0.197 |
Happy | +0.193 |
Neg logit contributions | |
flower | -0.141 |
ble | -0.120 |
els | -0.119 |
ric | -0.116 |
cking | -0.112 |
Token | coming |
Token ID | 2406 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
ives | +0.031 |
ury | +0.027 |
Welcome | +0.026 |
Max | +0.026 |
hide | +0.025 |
Neg logit contributions | |
flower | -0.054 |
ble | -0.050 |
ric | -0.050 |
els | -0.048 |
cking | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
ives | +0.003 |
ury | +0.003 |
Welcome | +0.003 |
Enjoy | +0.003 |
Max | +0.003 |
Neg logit contributions | |
flower | -0.004 |
ric | -0.003 |
ble | -0.003 |
cking | -0.003 |
els | -0.003 |
Token | It |
Token ID | 632 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
ives | +0.011 |
ury | +0.009 |
Enjoy | +0.009 |
Follow | +0.008 |
Welcome | +0.008 |
Neg logit contributions | |
flower | -0.019 |
ble | -0.018 |
ric | -0.017 |
els | -0.017 |
mill | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
ives | +0.022 |
ury | +0.020 |
Welcome | +0.019 |
Max | +0.019 |
Enjoy | +0.019 |
Neg logit contributions | |
flower | -0.041 |
ble | -0.038 |
ric | -0.038 |
els | -0.037 |
cking | -0.037 |
Token | I |
Token ID | 40 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
ives | +0.003 |
ury | +0.003 |
Enjoy | +0.003 |
Welcome | +0.002 |
Follow | +0.002 |
Neg logit contributions | |
flower | -0.004 |
ble | -0.003 |
ric | -0.003 |
cking | -0.003 |
els | -0.003 |
Token | will |
Token ID | 481 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
flower | +0.019 |
ric | +0.016 |
ble | +0.016 |
els | +0.015 |
cking | +0.015 |
Neg logit contributions | |
ives | -0.015 |
People | -0.013 |
ury | -0.013 |
Welcome | -0.012 |
Happy | -0.012 |
Token | buy |
Token ID | 2822 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
ives | +0.042 |
ury | +0.036 |
Enjoy | +0.035 |
Welcome | +0.034 |
Happy | +0.032 |
Neg logit contributions | |
flower | -0.083 |
ble | -0.075 |
ric | -0.075 |
cking | -0.074 |
els | -0.074 |
Token | more |
Token ID | 517 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
flower | +0.015 |
els | +0.014 |
ble | +0.014 |
ries | +0.014 |
cking | +0.013 |
Neg logit contributions | |
ives | -0.011 |
ury | -0.010 |
Follow | -0.009 |
Welcome | -0.009 |
Sadly | -0.009 |
Token | av |
Token ID | 1196 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
ives | +0.026 |
ury | +0.022 |
Enjoy | +0.022 |
Welcome | +0.021 |
Happy | +0.021 |
Neg logit contributions | |
flower | -0.041 |
ble | -0.037 |
ric | -0.037 |
cking | -0.036 |
els | -0.036 |
Token | oc |
Token ID | 420 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
Welcome | +0.087 |
ives | +0.087 |
ury | +0.084 |
People | +0.082 |
Bye | +0.081 |
Neg logit contributions | |
flower | -0.109 |
els | -0.097 |
cking | -0.094 |
cks | -0.090 |
cker | -0.090 |
Token | ados |
Token ID | 22484 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
ives | +0.216 |
Welcome | +0.216 |
ury | +0.214 |
Sadly | +0.205 |
Max | +0.204 |
Neg logit contributions | |
els | -0.123 |
flower | -0.121 |
ries | -0.117 |
ble | -0.104 |
cking | -0.100 |
Token | tomorrow |
Token ID | 9439 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
flower | +0.072 |
ble | +0.065 |
ric | +0.063 |
els | +0.063 |
cking | +0.062 |
Neg logit contributions | |
ives | -0.049 |
ury | -0.044 |
Enjoy | -0.043 |
Welcome | -0.041 |
Follow | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
ives | +0.018 |
Enjoy | +0.016 |
ury | +0.016 |
Welcome | +0.016 |
Sadly | +0.016 |
Neg logit contributions | |
flower | -0.019 |
ble | -0.017 |
els | -0.016 |
ric | -0.016 |
mill | -0.016 |
Token | You |
Token ID | 921 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
flower | +0.002 |
ric | +0.002 |
els | +0.002 |
ble | +0.002 |
mill | +0.002 |
Neg logit contributions | |
ives | -0.001 |
and | -0.001 |
ave | -0.001 |
villains | -0.001 |
ury | -0.001 |
Token | can |
Token ID | 460 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
flower | +0.034 |
ble | +0.030 |
ric | +0.030 |
els | +0.029 |
cking | +0.028 |
Neg logit contributions | |
ives | -0.021 |
ury | -0.019 |
and | -0.018 |
Welcome | -0.017 |
Bye | -0.017 |
Token | vegetables |
Token ID | 13701 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
ives | +0.009 |
ury | +0.009 |
Enjoy | +0.008 |
Welcome | +0.008 |
Follow | +0.008 |
Neg logit contributions | |
flower | -0.010 |
ble | -0.009 |
els | -0.009 |
ric | -0.009 |
cking | -0.009 |
Token | ! |
Token ID | 0 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
ives | +0.003 |
ury | +0.003 |
Enjoy | +0.003 |
Welcome | +0.003 |
Max | +0.003 |
Neg logit contributions | |
flower | -0.005 |
ric | -0.005 |
ble | -0.005 |
els | -0.005 |
cking | -0.005 |
Token | All |
Token ID | 1439 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
flower | +0.018 |
ric | +0.016 |
ble | +0.016 |
els | +0.016 |
cks | +0.015 |
Neg logit contributions | |
ives | -0.010 |
ury | -0.009 |
Enjoy | -0.008 |
villains | -0.007 |
Welcome | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
flower | +0.010 |
ble | +0.009 |
ric | +0.009 |
cking | +0.009 |
els | +0.008 |
Neg logit contributions | |
ives | -0.005 |
Max | -0.004 |
Happy | -0.004 |
Welcome | -0.004 |
ury | -0.004 |
Token | b |
Token ID | 275 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
ives | +0.057 |
ury | +0.051 |
Enjoy | +0.049 |
Follow | +0.048 |
Welcome | +0.047 |
Neg logit contributions | |
flower | -0.062 |
els | -0.055 |
ble | -0.053 |
cking | -0.053 |
ric | -0.052 |
Token | unn |
Token ID | 20935 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
ives | +0.043 |
Welcome | +0.042 |
Happy | +0.042 |
Max | +0.041 |
Cop | +0.041 |
Neg logit contributions | |
flower | -0.114 |
els | -0.106 |
ble | -0.105 |
cking | -0.104 |
ric | -0.104 |
Token | ies |
Token ID | 444 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
ives | +0.287 |
ury | +0.269 |
Enjoy | +0.269 |
Welcome | +0.264 |
Follow | +0.261 |
Neg logit contributions | |
flower | -0.068 |
ble | -0.047 |
ric | -0.043 |
cking | -0.042 |
els | -0.042 |
Token | were |
Token ID | 547 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
ives | +0.016 |
ury | +0.014 |
Enjoy | +0.013 |
Welcome | +0.013 |
Happy | +0.013 |
Neg logit contributions | |
flower | -0.029 |
ric | -0.026 |
ble | -0.026 |
els | -0.026 |
cking | -0.026 |
Token | over |
Token ID | 625 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
ives | +0.013 |
ury | +0.011 |
Enjoy | +0.010 |
Welcome | +0.010 |
Happy | +0.010 |
Neg logit contributions | |
flower | -0.026 |
ric | -0.024 |
ble | -0.024 |
els | -0.023 |
cking | -0.023 |
Token | joy |
Token ID | 2633 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
flower | +0.017 |
ble | +0.016 |
ric | +0.016 |
cking | +0.015 |
els | +0.015 |
Neg logit contributions | |
ives | -0.010 |
ury | -0.009 |
Enjoy | -0.009 |
Welcome | -0.009 |
Happy | -0.008 |
Token | ed |
Token ID | 276 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
ives | +0.073 |
Enjoy | +0.070 |
ury | +0.067 |
Sadly | +0.066 |
Welcome | +0.064 |
Neg logit contributions | |
flower | -0.122 |
els | -0.105 |
ble | -0.104 |
ric | -0.102 |
cking | -0.101 |
Token | He |
Token ID | 679 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
flower | +0.007 |
ric | +0.007 |
ble | +0.007 |
mill | +0.006 |
els | +0.006 |
Neg logit contributions | |
ives | -0.004 |
ury | -0.003 |
Enjoy | -0.003 |
hide | -0.003 |
Follow | -0.003 |
Token | had |
Token ID | 550 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
flower | +0.018 |
ble | +0.016 |
ric | +0.016 |
cking | +0.016 |
els | +0.016 |
Neg logit contributions | |
ives | -0.010 |
ury | -0.009 |
Enjoy | -0.009 |
Welcome | -0.008 |
Follow | -0.008 |
Token | taught |
Token ID | 7817 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
flower | +0.007 |
ble | +0.006 |
ric | +0.006 |
cking | +0.006 |
els | +0.006 |
Neg logit contributions | |
ives | -0.005 |
ury | -0.004 |
Enjoy | -0.004 |
Welcome | -0.004 |
Follow | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
ives | +0.062 |
ury | +0.056 |
Enjoy | +0.053 |
Follow | +0.053 |
Welcome | +0.052 |
Neg logit contributions | |
flower | -0.061 |
ric | -0.056 |
ble | -0.056 |
els | -0.055 |
cking | -0.053 |
Token | b |
Token ID | 275 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
ives | +0.010 |
ury | +0.009 |
Enjoy | +0.008 |
Welcome | +0.008 |
Follow | +0.008 |
Neg logit contributions | |
flower | -0.014 |
ble | -0.013 |
ric | -0.012 |
cking | -0.012 |
els | -0.012 |
Token | unn |
Token ID | 20935 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
ives | +0.044 |
ury | +0.038 |
Max | +0.037 |
Happy | +0.037 |
Enjoy | +0.037 |
Neg logit contributions | |
flower | -0.116 |
ble | -0.107 |
ric | -0.105 |
els | -0.105 |
cking | -0.103 |
Token | ies |
Token ID | 444 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
ives | +0.264 |
ury | +0.245 |
Enjoy | +0.239 |
Welcome | +0.237 |
Happy | +0.233 |
Neg logit contributions | |
flower | -0.088 |
ble | -0.071 |
ric | -0.068 |
cking | -0.067 |
els | -0.065 |
Token | to |
Token ID | 284 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
ives | +0.014 |
Enjoy | +0.012 |
ury | +0.012 |
Welcome | +0.011 |
Happy | +0.011 |
Neg logit contributions | |
flower | -0.024 |
cking | -0.022 |
ble | -0.022 |
els | -0.021 |
eled | -0.021 |
Token | be |
Token ID | 307 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
ives | +0.010 |
ury | +0.009 |
Enjoy | +0.008 |
Welcome | +0.008 |
Follow | +0.008 |
Neg logit contributions | |
flower | -0.014 |
ble | -0.012 |
ric | -0.012 |
cking | -0.012 |
els | -0.012 |
Token | friendly |
Token ID | 8030 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
flower | +0.052 |
ric | +0.049 |
ble | +0.049 |
els | +0.047 |
cking | +0.046 |
Neg logit contributions | |
ives | -0.022 |
Enjoy | -0.018 |
ury | -0.018 |
Max | -0.018 |
Happy | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ives | +0.030 |
ury | +0.027 |
Enjoy | +0.026 |
Welcome | +0.025 |
Follow | +0.025 |
Neg logit contributions | |
flower | -0.037 |
ble | -0.033 |
ric | -0.032 |
els | -0.032 |
cking | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
ives | +0.002 |
Enjoy | +0.002 |
Max | +0.002 |
hide | +0.001 |
ury | +0.001 |
Neg logit contributions | |
flower | -0.002 |
els | -0.002 |
ble | -0.002 |
cking | -0.002 |
ric | -0.002 |
Token | top |
Token ID | 1353 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
ives | +0.001 |
Enjoy | +0.001 |
Welcome | +0.001 |
hide | +0.001 |
ury | +0.001 |
Neg logit contributions | |
flower | -0.002 |
els | -0.002 |
cks | -0.002 |
cking | -0.002 |
ric | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
flower | +0.047 |
ble | +0.045 |
els | +0.044 |
ric | +0.044 |
cking | +0.044 |
Neg logit contributions | |
ives | -0.020 |
ury | -0.017 |
Welcome | -0.015 |
Max | -0.015 |
Enjoy | -0.015 |
Token | The |
Token ID | 383 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
flower | +0.011 |
ric | +0.011 |
ble | +0.010 |
els | +0.010 |
eled | +0.010 |
Neg logit contributions | |
ives | -0.006 |
ury | -0.005 |
Enjoy | -0.004 |
villains | -0.004 |
Welcome | -0.004 |
Token | b |
Token ID | 275 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
ives | +0.014 |
Enjoy | +0.013 |
Welcome | +0.013 |
Happy | +0.012 |
ury | +0.012 |
Neg logit contributions | |
flower | -0.022 |
cks | -0.021 |
ric | -0.020 |
els | -0.020 |
cking | -0.020 |
Token | unn |
Token ID | 20935 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
ives | +0.037 |
ury | +0.030 |
Enjoy | +0.028 |
Welcome | +0.027 |
Happy | +0.026 |
Neg logit contributions | |
flower | -0.111 |
ble | -0.103 |
ric | -0.101 |
els | -0.100 |
cking | -0.100 |
Token | ies |
Token ID | 444 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ives | +0.260 |
ury | +0.241 |
Enjoy | +0.235 |
Welcome | +0.232 |
Follow | +0.229 |
Neg logit contributions | |
flower | -0.085 |
ble | -0.070 |
ric | -0.069 |
cking | -0.067 |
els | -0.065 |
Token | settled |
Token ID | 10282 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ives | +0.005 |
ury | +0.004 |
Welcome | +0.004 |
Enjoy | +0.004 |
Follow | +0.004 |
Neg logit contributions | |
flower | -0.010 |
ric | -0.009 |
ble | -0.009 |
els | -0.009 |
cking | -0.009 |
Token | in |
Token ID | 287 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
ives | +0.049 |
ury | +0.044 |
Max | +0.043 |
Enjoy | +0.043 |
Happy | +0.042 |
Neg logit contributions | |
flower | -0.068 |
ric | -0.063 |
cking | -0.062 |
els | -0.062 |
ble | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Enjoy | +0.016 |
ives | +0.015 |
Happy | +0.015 |
Max | +0.015 |
Welcome | +0.015 |
Neg logit contributions | |
flower | -0.031 |
ble | -0.029 |
ric | -0.028 |
els | -0.028 |
cking | -0.028 |
Token | soon |
Token ID | 2582 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
ives | +0.008 |
ury | +0.007 |
Enjoy | +0.007 |
People | +0.007 |
Welcome | +0.007 |
Neg logit contributions | |
flower | -0.009 |
ble | -0.007 |
cking | -0.007 |
ric | -0.007 |
mill | -0.007 |
Token | one |
Token ID | 530 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
flower | +0.023 |
ble | +0.022 |
cking | +0.021 |
cks | +0.021 |
ric | +0.021 |
Neg logit contributions | |
Max | -0.015 |
ives | -0.015 |
Enjoy | -0.014 |
ury | -0.014 |
Welcome | -0.014 |
Token | day |
Token ID | 1110 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
ives | +0.014 |
ury | +0.012 |
Enjoy | +0.012 |
Welcome | +0.012 |
Happy | +0.011 |
Neg logit contributions | |
flower | -0.031 |
ble | -0.029 |
ric | -0.028 |
els | -0.028 |
cking | -0.028 |
Token | it |
Token ID | 340 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
ives | +0.008 |
ury | +0.007 |
Enjoy | +0.007 |
Max | +0.007 |
Welcome | +0.007 |
Neg logit contributions | |
flower | -0.017 |
ric | -0.016 |
ble | -0.015 |
cking | -0.015 |
els | -0.015 |
Token | started |
Token ID | 2067 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
ives | +0.031 |
ury | +0.027 |
Max | +0.026 |
Sadly | +0.025 |
Welcome | +0.025 |
Neg logit contributions | |
flower | -0.050 |
ric | -0.047 |
els | -0.046 |
cking | -0.046 |
cks | -0.045 |
Token | to |
Token ID | 284 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
ives | +0.005 |
ury | +0.003 |
Max | +0.003 |
Welcome | +0.003 |
Sadly | +0.003 |
Neg logit contributions | |
flower | -0.025 |
ble | -0.023 |
els | -0.023 |
cks | -0.023 |
cking | -0.023 |
Token | rain |
Token ID | 6290 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
hide | +0.012 |
Max | +0.011 |
rest | +0.010 |
you | +0.009 |
Sadly | +0.009 |
Neg logit contributions | |
els | -0.027 |
cks | -0.026 |
eled | -0.026 |
flower | -0.026 |
ries | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
flower | +0.080 |
els | +0.076 |
ble | +0.074 |
cking | +0.074 |
eled | +0.073 |
Neg logit contributions | |
ives | -0.048 |
ury | -0.042 |
Max | -0.040 |
hide | -0.039 |
t | -0.037 |
Token | The |
Token ID | 383 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
ives | +0.003 |
ury | +0.003 |
villains | +0.003 |
Enjoy | +0.002 |
Cop | +0.002 |
Neg logit contributions | |
flower | -0.004 |
ric | -0.004 |
ble | -0.003 |
els | -0.003 |
ries | -0.003 |
Token | little |
Token ID | 1310 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
ives | +0.010 |
ury | +0.009 |
Enjoy | +0.009 |
Welcome | +0.009 |
Happy | +0.008 |
Neg logit contributions | |
flower | -0.014 |
ble | -0.013 |
ric | -0.013 |
cking | -0.013 |
els | -0.012 |
Token | girl |
Token ID | 2576 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
ives | +0.013 |
ury | +0.012 |
Welcome | +0.011 |
Max | +0.011 |
Happy | +0.011 |
Neg logit contributions | |
flower | -0.022 |
ric | -0.021 |
cking | -0.021 |
cks | -0.021 |
ble | -0.021 |
Token | started |
Token ID | 2067 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
ives | +0.014 |
Enjoy | +0.013 |
ury | +0.012 |
Welcome | +0.012 |
Happy | +0.012 |
Neg logit contributions | |
flower | -0.017 |
ble | -0.014 |
cking | -0.014 |
ric | -0.014 |
els | -0.014 |
Token | boy |
Token ID | 2933 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
flower | +0.005 |
ble | +0.004 |
ric | +0.004 |
mill | +0.004 |
els | +0.004 |
Neg logit contributions | |
ives | -0.005 |
ury | -0.005 |
Enjoy | -0.005 |
Sadly | -0.004 |
People | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
ives | +0.003 |
ury | +0.003 |
Enjoy | +0.003 |
Welcome | +0.003 |
Follow | +0.002 |
Neg logit contributions | |
flower | -0.006 |
ble | -0.005 |
ric | -0.005 |
els | -0.005 |
cking | -0.005 |
Token | He |
Token ID | 679 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
ives | +0.003 |
ury | +0.003 |
Enjoy | +0.002 |
Follow | +0.002 |
Welcome | +0.002 |
Neg logit contributions | |
flower | -0.006 |
ric | -0.006 |
ble | -0.006 |
els | -0.006 |
mill | -0.006 |
Token | liked |
Token ID | 8288 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
flower | +0.044 |
ble | +0.040 |
ric | +0.040 |
cking | +0.039 |
els | +0.039 |
Neg logit contributions | |
ives | -0.019 |
ury | -0.016 |
Enjoy | -0.016 |
Welcome | -0.015 |
Happy | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
ives | +0.013 |
ury | +0.011 |
Enjoy | +0.010 |
Welcome | +0.009 |
Follow | +0.009 |
Neg logit contributions | |
flower | -0.038 |
ble | -0.035 |
ric | -0.035 |
cking | -0.035 |
els | -0.035 |
Token | climb |
Token ID | 12080 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ives | +0.013 |
Enjoy | +0.012 |
hide | +0.011 |
ury | +0.011 |
Welcome | +0.011 |
Neg logit contributions | |
flower | -0.029 |
cking | -0.026 |
ble | -0.026 |
ric | -0.026 |
els | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
flower | +0.093 |
cking | +0.083 |
ble | +0.082 |
eled | +0.081 |
ric | +0.081 |
Neg logit contributions | |
Max | -0.044 |
ives | -0.041 |
Happy | -0.039 |
hide | -0.039 |
People | -0.039 |
Token | He |
Token ID | 679 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
ives | +0.005 |
ury | +0.005 |
Enjoy | +0.004 |
Follow | +0.004 |
Welcome | +0.004 |
Neg logit contributions | |
flower | -0.008 |
ric | -0.008 |
ble | -0.008 |
els | -0.007 |
cks | -0.007 |
Token | climbed |
Token ID | 19952 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
flower | +0.021 |
ble | +0.020 |
ric | +0.019 |
cking | +0.019 |
els | +0.019 |
Neg logit contributions | |
ives | -0.011 |
ury | -0.009 |
Enjoy | -0.009 |
Welcome | -0.009 |
Follow | -0.009 |
Token | on |
Token ID | 319 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
flower | +0.037 |
cking | +0.034 |
ric | +0.033 |
eled | +0.033 |
els | +0.032 |
Neg logit contributions | |
Max | -0.016 |
ives | -0.016 |
Happy | -0.015 |
hide | -0.015 |
Now | -0.015 |
Token | his |
Token ID | 465 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
ives | +0.020 |
ury | +0.018 |
Enjoy | +0.017 |
Welcome | +0.017 |
Follow | +0.016 |
Neg logit contributions | |
flower | -0.022 |
ble | -0.020 |
ric | -0.019 |
cking | -0.019 |
els | -0.019 |
Token | 's |
Token ID | 338 |
Feature activation | -3.02e-03 |
Pos logit contributions | |
flower | +0.002 |
ble | +0.002 |
ric | +0.002 |
cking | +0.002 |
els | +0.002 |
Neg logit contributions | |
ives | -0.001 |
ury | -0.001 |
Enjoy | -0.001 |
Welcome | -0.001 |
Follow | -0.001 |
Token | not |
Token ID | 407 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
Max | +0.000 |
ives | +0.000 |
ury | +0.000 |
Enjoy | +0.000 |
hide | +0.000 |
Neg logit contributions | |
flower | -0.000 |
ble | -0.000 |
els | -0.000 |
ric | -0.000 |
eled | -0.000 |
Token | safe |
Token ID | 3338 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
flower | +0.046 |
els | +0.042 |
ble | +0.041 |
ric | +0.041 |
cking | +0.041 |
Neg logit contributions | |
ives | -0.023 |
ury | -0.021 |
Max | -0.020 |
Enjoy | -0.020 |
Welcome | -0.019 |
Token | ," |
Token ID | 553 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ives | +0.020 |
ury | +0.018 |
Enjoy | +0.017 |
Welcome | +0.016 |
Max | +0.016 |
Neg logit contributions | |
flower | -0.030 |
ric | -0.027 |
ble | -0.027 |
cking | -0.027 |
els | -0.026 |
Token | replied |
Token ID | 8712 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
flower | +0.007 |
ble | +0.006 |
ric | +0.006 |
els | +0.006 |
cking | +0.006 |
Neg logit contributions | |
ives | -0.003 |
ury | -0.003 |
Enjoy | -0.003 |
Welcome | -0.002 |
Follow | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
flower | +0.070 |
ble | +0.064 |
ric | +0.063 |
cking | +0.063 |
els | +0.062 |
Neg logit contributions | |
ives | -0.038 |
ury | -0.033 |
Enjoy | -0.032 |
Welcome | -0.031 |
Happy | -0.030 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
flower | +0.086 |
ric | +0.078 |
cking | +0.078 |
ble | +0.077 |
els | +0.076 |
Neg logit contributions | |
ives | -0.062 |
ury | -0.056 |
Max | -0.053 |
Enjoy | -0.053 |
Welcome | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
flower | +0.060 |
ble | +0.050 |
els | +0.050 |
cking | +0.049 |
ric | +0.048 |
Neg logit contributions | |
ives | -0.069 |
Enjoy | -0.065 |
ury | -0.062 |
Welcome | -0.061 |
People | -0.060 |
Token | " |
Token ID | 366 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
flower | +0.045 |
ric | +0.039 |
ble | +0.038 |
mill | +0.038 |
els | +0.036 |
Neg logit contributions | |
ives | -0.033 |
Enjoy | -0.028 |
ury | -0.027 |
villains | -0.027 |
Follow | -0.025 |
Token | You |
Token ID | 1639 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
flower | +0.009 |
ble | +0.008 |
ric | +0.008 |
cking | +0.008 |
els | +0.008 |
Neg logit contributions | |
ives | -0.009 |
ury | -0.008 |
Enjoy | -0.008 |
Welcome | -0.007 |
Happy | -0.007 |
Token | need |
Token ID | 761 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
flower | +0.062 |
ble | +0.058 |
ric | +0.056 |
els | +0.055 |
cking | +0.053 |
Neg logit contributions | |
ives | -0.040 |
and | -0.037 |
ury | -0.037 |
Enjoy | -0.036 |
Welcome | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
ives | +0.026 |
Enjoy | +0.024 |
ury | +0.023 |
Welcome | +0.022 |
People | +0.022 |
Neg logit contributions | |
flower | -0.035 |
ble | -0.030 |
ric | -0.030 |
els | -0.029 |
cking | -0.029 |
Token | Ben |
Token ID | 3932 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
ives | +0.008 |
ury | +0.007 |
Enjoy | +0.006 |
Welcome | +0.006 |
Follow | +0.006 |
Neg logit contributions | |
flower | -0.021 |
ble | -0.019 |
els | -0.019 |
ric | -0.019 |
cking | -0.019 |
Token | smiled |
Token ID | 13541 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
flower | +0.002 |
ble | +0.002 |
ric | +0.002 |
els | +0.002 |
cking | +0.002 |
Neg logit contributions | |
ives | -0.001 |
ury | -0.001 |
Enjoy | -0.001 |
Welcome | -0.001 |
Happy | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
ives | +0.012 |
Happy | +0.010 |
Max | +0.010 |
And | +0.010 |
ury | +0.010 |
Neg logit contributions | |
flower | -0.030 |
ric | -0.029 |
cking | -0.029 |
els | -0.029 |
cks | -0.028 |
Token | looked |
Token ID | 3114 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
flower | +0.012 |
ble | +0.010 |
cking | +0.010 |
ric | +0.010 |
cks | +0.010 |
Neg logit contributions | |
ives | -0.010 |
ury | -0.009 |
Enjoy | -0.009 |
These | -0.008 |
People | -0.008 |
Token | at |
Token ID | 379 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
flower | +0.024 |
ble | +0.022 |
ric | +0.022 |
els | +0.021 |
cking | +0.021 |
Neg logit contributions | |
ives | -0.013 |
ury | -0.012 |
Enjoy | -0.011 |
Welcome | -0.011 |
Happy | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
flower | +0.069 |
ble | +0.061 |
ric | +0.060 |
cking | +0.059 |
els | +0.057 |
Neg logit contributions | |
ives | -0.061 |
Enjoy | -0.055 |
ury | -0.054 |
Max | -0.054 |
Welcome | -0.053 |
Token | with |
Token ID | 351 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
flower | +0.017 |
ric | +0.016 |
ble | +0.015 |
els | +0.015 |
cking | +0.015 |
Neg logit contributions | |
ives | -0.011 |
ury | -0.009 |
Welcome | -0.009 |
Max | -0.009 |
Happy | -0.009 |
Token | wonder |
Token ID | 4240 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
ives | +0.006 |
Enjoy | +0.006 |
ury | +0.006 |
Welcome | +0.006 |
Happy | +0.005 |
Neg logit contributions | |
flower | -0.009 |
ble | -0.008 |
ric | -0.008 |
cking | -0.008 |
els | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
ives | +0.005 |
ury | +0.004 |
Happy | +0.004 |
Enjoy | +0.004 |
Max | +0.004 |
Neg logit contributions | |
flower | -0.009 |
ric | -0.008 |
ble | -0.008 |
cking | -0.008 |
eled | -0.008 |
Token | They |
Token ID | 1119 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
ives | +0.008 |
ury | +0.007 |
villains | +0.006 |
Cop | +0.006 |
Enjoy | +0.006 |
Neg logit contributions | |
flower | -0.010 |
ric | -0.010 |
ble | -0.009 |
cks | -0.009 |
els | -0.009 |
Token | family |
Token ID | 1641 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
ives | +0.029 |
ury | +0.025 |
Enjoy | +0.025 |
Welcome | +0.024 |
Happy | +0.023 |
Neg logit contributions | |
flower | -0.042 |
ble | -0.038 |
cking | -0.038 |
ric | -0.038 |
els | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
ives | +0.018 |
ury | +0.015 |
Welcome | +0.015 |
Enjoy | +0.015 |
Happy | +0.015 |
Neg logit contributions | |
flower | -0.035 |
ble | -0.033 |
cking | -0.033 |
ric | -0.033 |
cks | -0.032 |
Token | with |
Token ID | 351 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
flower | +0.019 |
ble | +0.018 |
cking | +0.017 |
ric | +0.017 |
els | +0.017 |
Neg logit contributions | |
ives | -0.009 |
ury | -0.008 |
Enjoy | -0.008 |
Welcome | -0.007 |
Max | -0.007 |
Token | Mom |
Token ID | 11254 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ives | +0.012 |
ury | +0.011 |
Enjoy | +0.011 |
Welcome | +0.010 |
Follow | +0.010 |
Neg logit contributions | |
flower | -0.015 |
ble | -0.013 |
ric | -0.013 |
els | -0.013 |
cking | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
flower | +0.070 |
ble | +0.067 |
cking | +0.065 |
ric | +0.064 |
els | +0.063 |
Neg logit contributions | |
ives | -0.040 |
ury | -0.035 |
Max | -0.034 |
Happy | -0.033 |
Enjoy | -0.033 |
Token | Dad |
Token ID | 17415 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
flower | +0.017 |
ble | +0.016 |
ric | +0.016 |
cking | +0.015 |
els | +0.015 |
Neg logit contributions | |
ives | -0.010 |
Enjoy | -0.009 |
ury | -0.009 |
Happy | -0.008 |
Welcome | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
flower | +0.107 |
ble | +0.098 |
ric | +0.096 |
cking | +0.095 |
els | +0.094 |
Neg logit contributions | |
ives | -0.075 |
ury | -0.066 |
Enjoy | -0.064 |
Welcome | -0.064 |
Happy | -0.062 |
Token | his |
Token ID | 465 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
flower | +0.045 |
ble | +0.041 |
ric | +0.040 |
cking | +0.040 |
els | +0.040 |
Neg logit contributions | |
ives | -0.030 |
ury | -0.026 |
Enjoy | -0.025 |
Welcome | -0.025 |
Follow | -0.024 |
Token | two |
Token ID | 734 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
flower | +0.067 |
ble | +0.061 |
ric | +0.060 |
els | +0.059 |
cking | +0.058 |
Neg logit contributions | |
ives | -0.049 |
ury | -0.043 |
Enjoy | -0.042 |
Welcome | -0.041 |
Follow | -0.040 |
Token | brothers |
Token ID | 9397 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
flower | +0.126 |
ble | +0.113 |
ric | +0.111 |
els | +0.111 |
cking | +0.111 |
Neg logit contributions | |
ives | -0.102 |
ury | -0.091 |
Enjoy | -0.090 |
Welcome | -0.086 |
Follow | -0.085 |
Token | , |
Token ID | 11 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
flower | +0.083 |
ble | +0.076 |
ric | +0.074 |
cking | +0.074 |
els | +0.073 |
Neg logit contributions | |
ives | -0.062 |
ury | -0.054 |
Enjoy | -0.053 |
Welcome | -0.052 |
Happy | -0.050 |
Token | quickly |
Token ID | 2952 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
flower | +0.021 |
ble | +0.019 |
ric | +0.018 |
cking | +0.018 |
els | +0.018 |
Neg logit contributions | |
ives | -0.013 |
ury | -0.011 |
Enjoy | -0.011 |
Welcome | -0.011 |
Happy | -0.010 |
Token | took |
Token ID | 1718 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
ives | +0.050 |
Enjoy | +0.045 |
ury | +0.044 |
Welcome | +0.043 |
Happy | +0.042 |
Neg logit contributions | |
flower | -0.060 |
ble | -0.055 |
cking | -0.054 |
els | -0.053 |
ric | -0.052 |
Token | out |
Token ID | 503 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
flower | +0.001 |
els | +0.001 |
ble | +0.001 |
cking | +0.000 |
eled | +0.000 |
Neg logit contributions | |
ives | -0.001 |
ury | -0.001 |
villains | -0.001 |
Welcome | -0.001 |
Bye | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
ives | +0.023 |
Enjoy | +0.020 |
Happy | +0.020 |
Max | +0.019 |
Welcome | +0.019 |
Neg logit contributions | |
flower | -0.030 |
ble | -0.028 |
ric | -0.027 |
cking | -0.026 |
cks | -0.025 |
Token | shining |
Token ID | 22751 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
ives | +0.023 |
ury | +0.021 |
Enjoy | +0.020 |
Welcome | +0.020 |
Happy | +0.019 |
Neg logit contributions | |
flower | -0.020 |
ble | -0.017 |
ric | -0.017 |
cking | -0.017 |
els | -0.017 |
Token | coal |
Token ID | 5655 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
flower | +0.031 |
cking | +0.030 |
ric | +0.029 |
cks | +0.029 |
ble | +0.028 |
Neg logit contributions | |
ives | -0.025 |
Enjoy | -0.023 |
ury | -0.022 |
Welcome | -0.021 |
Happy | -0.021 |
Token | from |
Token ID | 422 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
ives | +0.010 |
ury | +0.009 |
Enjoy | +0.008 |
Welcome | +0.008 |
Max | +0.008 |
Neg logit contributions | |
flower | -0.016 |
ric | -0.015 |
ble | -0.015 |
cking | -0.015 |
els | -0.015 |
Token | her |
Token ID | 607 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
flower | +0.007 |
ric | +0.006 |
ble | +0.006 |
cking | +0.006 |
els | +0.006 |
Neg logit contributions | |
ives | -0.006 |
Enjoy | -0.006 |
Max | -0.005 |
Welcome | -0.005 |
ury | -0.005 |
Token | pocket |
Token ID | 10000 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
flower | +0.038 |
ble | +0.034 |
ric | +0.033 |
cking | +0.033 |
els | +0.033 |
Neg logit contributions | |
ives | -0.029 |
ury | -0.026 |
Enjoy | -0.025 |
Welcome | -0.025 |
Happy | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
ives | +0.005 |
Enjoy | +0.004 |
ury | +0.004 |
Welcome | +0.004 |
Happy | +0.004 |
Neg logit contributions | |
flower | -0.006 |
ble | -0.005 |
els | -0.005 |
ric | -0.005 |
cking | -0.005 |
Token | placed |
Token ID | 4624 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
flower | +0.021 |
ble | +0.019 |
els | +0.018 |
cking | +0.018 |
ric | +0.017 |
Neg logit contributions | |
ives | -0.017 |
ury | -0.015 |
Enjoy | -0.015 |
Welcome | -0.014 |
People | -0.014 |
Token | Thank |
Token ID | 10449 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
flower | +0.015 |
ble | +0.013 |
ric | +0.013 |
cking | +0.013 |
els | +0.013 |
Neg logit contributions | |
ives | -0.011 |
ury | -0.009 |
Enjoy | -0.009 |
Welcome | -0.009 |
Happy | -0.009 |
Token | you |
Token ID | 345 |
Feature activation | +3.95e-02 |
Pos logit contributions | |
flower | +0.033 |
ble | +0.033 |
els | +0.032 |
cks | +0.031 |
ries | +0.031 |
Neg logit contributions | |
ives | -0.022 |
Sadly | -0.019 |
ury | -0.018 |
ave | -0.016 |
Enjoy | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
flower | +0.002 |
ble | +0.001 |
ric | +0.001 |
els | +0.001 |
bery | +0.001 |
Neg logit contributions | |
ives | -0.002 |
ury | -0.001 |
Enjoy | -0.001 |
Welcome | -0.001 |
Follow | -0.001 |
Token | now |
Token ID | 783 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
flower | +0.008 |
ble | +0.008 |
ric | +0.007 |
mill | +0.007 |
els | +0.007 |
Neg logit contributions | |
ives | -0.008 |
ury | -0.006 |
ave | -0.006 |
and | -0.006 |
Enjoy | -0.006 |
Token | I |
Token ID | 314 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
ives | +0.001 |
ury | +0.001 |
and | +0.001 |
Enjoy | +0.001 |
Sadly | +0.001 |
Neg logit contributions | |
flower | -0.002 |
ble | -0.002 |
cking | -0.001 |
ric | -0.001 |
els | -0.001 |
Token | can |
Token ID | 460 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
flower | +0.003 |
ble | +0.002 |
ric | +0.002 |
els | +0.002 |
cking | +0.002 |
Neg logit contributions | |
ives | -0.002 |
ury | -0.002 |
Enjoy | -0.002 |
People | -0.002 |
Cop | -0.002 |
Token | work |
Token ID | 670 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
ives | +0.002 |
ury | +0.002 |
Enjoy | +0.002 |
Welcome | +0.002 |
Happy | +0.002 |
Neg logit contributions | |
flower | -0.005 |
ble | -0.005 |
ric | -0.004 |
cking | -0.004 |
els | -0.004 |
Token | again |
Token ID | 757 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
flower | +0.026 |
ble | +0.024 |
cking | +0.023 |
els | +0.023 |
ric | +0.023 |
Neg logit contributions | |
ives | -0.022 |
ury | -0.020 |
Enjoy | -0.019 |
Follow | -0.018 |
Welcome | -0.018 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
ives | +0.014 |
ury | +0.012 |
Enjoy | +0.012 |
Welcome | +0.011 |
Follow | +0.011 |
Neg logit contributions | |
flower | -0.016 |
ble | -0.014 |
ric | -0.014 |
cking | -0.014 |
els | -0.014 |
Token | |
Token ID | 220 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
flower | +0.007 |
ric | +0.007 |
ble | +0.007 |
els | +0.006 |
mill | +0.006 |
Neg logit contributions | |
ives | -0.003 |
ury | -0.003 |
Welcome | -0.003 |
Enjoy | -0.003 |
villains | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
flower | +0.056 |
ble | +0.054 |
ric | +0.052 |
cking | +0.050 |
els | +0.050 |
Neg logit contributions | |
ives | -0.027 |
ury | -0.024 |
Enjoy | -0.022 |
Welcome | -0.022 |
Happy | -0.021 |
Token | my |
Token ID | 1820 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
flower | +0.013 |
ble | +0.012 |
ric | +0.012 |
cking | +0.012 |
els | +0.012 |
Neg logit contributions | |
ives | -0.009 |
ury | -0.008 |
Enjoy | -0.008 |
Welcome | -0.008 |
Happy | -0.007 |
Token | smiled |
Token ID | 13541 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
flower | +0.005 |
ble | +0.005 |
ric | +0.005 |
cking | +0.005 |
els | +0.005 |
Neg logit contributions | |
ives | -0.003 |
ury | -0.003 |
Enjoy | -0.003 |
Welcome | -0.003 |
Happy | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ives | +0.017 |
Max | +0.016 |
ury | +0.015 |
And | +0.015 |
Happy | +0.015 |
Neg logit contributions | |
ric | -0.056 |
cks | -0.055 |
flower | -0.054 |
cking | -0.054 |
els | -0.053 |
Token | felt |
Token ID | 2936 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
flower | +0.006 |
ble | +0.005 |
cking | +0.005 |
mill | +0.005 |
els | +0.005 |
Neg logit contributions | |
ives | -0.004 |
ury | -0.003 |
Enjoy | -0.003 |
Welcome | -0.003 |
People | -0.003 |
Token | much |
Token ID | 881 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
flower | +0.063 |
ric | +0.058 |
els | +0.057 |
ble | +0.056 |
cking | +0.055 |
Neg logit contributions | |
ives | -0.025 |
Enjoy | -0.022 |
Happy | -0.020 |
ury | -0.020 |
Welcome | -0.020 |
Token | better |
Token ID | 1365 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
flower | +0.033 |
ble | +0.030 |
cking | +0.029 |
els | +0.029 |
ric | +0.028 |
Neg logit contributions | |
ives | -0.025 |
ury | -0.023 |
Enjoy | -0.022 |
Welcome | -0.021 |
Follow | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
flower | +0.008 |
ble | +0.007 |
cking | +0.007 |
mill | +0.006 |
els | +0.006 |
Neg logit contributions | |
ives | -0.008 |
Enjoy | -0.007 |
People | -0.007 |
ury | -0.007 |
Follow | -0.007 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
flower | +0.011 |
ric | +0.010 |
mill | +0.009 |
eled | +0.009 |
els | +0.009 |
Neg logit contributions | |
ives | -0.007 |
ury | -0.006 |
Cop | -0.006 |
villains | -0.006 |
Enjoy | -0.006 |
Token | learned |
Token ID | 4499 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
ives | +0.015 |
ury | +0.013 |
Enjoy | +0.013 |
Welcome | +0.012 |
Happy | +0.012 |
Neg logit contributions | |
flower | -0.023 |
ble | -0.021 |
ric | -0.020 |
els | -0.020 |
cking | -0.020 |
Token | that |
Token ID | 326 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ives | +0.026 |
ury | +0.023 |
Enjoy | +0.023 |
Welcome | +0.022 |
Happy | +0.021 |
Neg logit contributions | |
flower | -0.039 |
ble | -0.035 |
ric | -0.035 |
cking | -0.034 |
els | -0.034 |
Token | sometimes |
Token ID | 3360 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
ives | +0.063 |
ury | +0.057 |
Follow | +0.052 |
Enjoy | +0.051 |
ave | +0.050 |
Neg logit contributions | |
flower | -0.048 |
ble | -0.043 |
els | -0.039 |
mill | -0.039 |
cking | -0.039 |
Token | " |
Token ID | 366 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
flower | +0.001 |
ble | +0.001 |
ric | +0.001 |
cking | +0.001 |
els | +0.001 |
Neg logit contributions | |
ives | -0.000 |
ury | -0.000 |
Enjoy | -0.000 |
Follow | -0.000 |
Welcome | -0.000 |
Token | Hi |
Token ID | 17250 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
ives | +0.011 |
ury | +0.010 |
Enjoy | +0.009 |
Welcome | +0.009 |
Happy | +0.009 |
Neg logit contributions | |
flower | -0.017 |
ble | -0.016 |
ric | -0.016 |
els | -0.016 |
cking | -0.016 |
Token | ! |
Token ID | 0 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
flower | +0.018 |
ble | +0.016 |
els | +0.016 |
ric | +0.015 |
ries | +0.015 |
Neg logit contributions | |
ives | -0.016 |
Enjoy | -0.014 |
ury | -0.013 |
Sadly | -0.013 |
Follow | -0.013 |
Token | My |
Token ID | 2011 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
flower | +0.043 |
ric | +0.039 |
mill | +0.036 |
ble | +0.035 |
els | +0.035 |
Neg logit contributions | |
ives | -0.022 |
ury | -0.016 |
Sadly | -0.015 |
Enjoy | -0.015 |
and | -0.014 |
Token | name |
Token ID | 1438 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
ives | +0.023 |
ury | +0.020 |
Enjoy | +0.020 |
Sadly | +0.019 |
Follow | +0.019 |
Neg logit contributions | |
flower | -0.022 |
ble | -0.019 |
ric | -0.019 |
els | -0.018 |
mill | -0.016 |
Token | is |
Token ID | 318 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
flower | +0.046 |
ble | +0.042 |
ric | +0.042 |
cking | +0.041 |
els | +0.041 |
Neg logit contributions | |
ives | -0.026 |
ury | -0.023 |
Enjoy | -0.022 |
Welcome | -0.021 |
Happy | -0.021 |
Token | Sue |
Token ID | 26089 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
flower | +0.046 |
ble | +0.042 |
ric | +0.042 |
els | +0.041 |
cks | +0.041 |
Neg logit contributions | |
ives | -0.021 |
ury | -0.016 |
Enjoy | -0.015 |
Sadly | -0.014 |
Follow | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
flower | +0.052 |
ble | +0.048 |
cking | +0.048 |
ric | +0.047 |
els | +0.047 |
Neg logit contributions | |
ives | -0.040 |
ury | -0.036 |
Enjoy | -0.034 |
Welcome | -0.034 |
Happy | -0.033 |
Token | This |
Token ID | 770 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
flower | +0.016 |
ric | +0.014 |
els | +0.013 |
mill | +0.013 |
ble | +0.013 |
Neg logit contributions | |
ives | -0.008 |
ury | -0.006 |
Sadly | -0.005 |
ave | -0.005 |
Enjoy | -0.005 |
Token | is |
Token ID | 318 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
flower | +0.060 |
ble | +0.052 |
ric | +0.051 |
els | +0.050 |
cks | +0.047 |
Neg logit contributions | |
ives | -0.053 |
ury | -0.048 |
Enjoy | -0.046 |
Sadly | -0.046 |
and | -0.045 |
Token | Fl |
Token ID | 1610 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
flower | +0.006 |
ble | +0.005 |
ric | +0.005 |
cking | +0.005 |
els | +0.005 |
Neg logit contributions | |
ives | -0.003 |
ury | -0.003 |
Enjoy | -0.003 |
Welcome | -0.003 |
Happy | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
ives | +0.028 |
ury | +0.024 |
Welcome | +0.023 |
Follow | +0.023 |
Happy | +0.023 |
Neg logit contributions | |
flower | -0.048 |
ble | -0.044 |
ric | -0.044 |
cking | -0.043 |
els | -0.043 |
Token | very |
Token ID | 845 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
Max | +0.021 |
ives | +0.019 |
Happy | +0.018 |
hide | +0.018 |
Welcome | +0.018 |
Neg logit contributions | |
flower | -0.047 |
ric | -0.042 |
ble | -0.041 |
els | -0.041 |
cking | -0.041 |
Token | dark |
Token ID | 3223 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
ives | +0.036 |
ury | +0.031 |
Enjoy | +0.030 |
Welcome | +0.029 |
Cop | +0.028 |
Neg logit contributions | |
flower | -0.044 |
ble | -0.042 |
cking | -0.040 |
els | -0.039 |
ric | -0.039 |
Token | inside |
Token ID | 2641 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
ives | +0.018 |
ury | +0.016 |
Enjoy | +0.016 |
Welcome | +0.015 |
Follow | +0.015 |
Neg logit contributions | |
flower | -0.028 |
ble | -0.025 |
ric | -0.025 |
els | -0.024 |
cking | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
ives | +0.034 |
ury | +0.030 |
Enjoy | +0.029 |
Welcome | +0.029 |
Happy | +0.028 |
Neg logit contributions | |
flower | -0.044 |
ble | -0.040 |
ric | -0.039 |
cking | -0.039 |
els | -0.038 |
Token | but |
Token ID | 475 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
ives | +0.009 |
ury | +0.008 |
Enjoy | +0.008 |
Welcome | +0.007 |
Follow | +0.007 |
Neg logit contributions | |
flower | -0.013 |
ble | -0.012 |
ric | -0.012 |
cking | -0.012 |
els | -0.012 |
Token | they |
Token ID | 484 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
flower | +0.008 |
ble | +0.007 |
cking | +0.007 |
els | +0.007 |
ric | +0.007 |
Neg logit contributions | |
ives | -0.009 |
ury | -0.008 |
Enjoy | -0.008 |
Welcome | -0.007 |
Follow | -0.007 |
Token | didn |
Token ID | 1422 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
ives | +0.018 |
ury | +0.015 |
Enjoy | +0.015 |
Welcome | +0.014 |
Follow | +0.014 |
Neg logit contributions | |
flower | -0.036 |
ble | -0.033 |
ric | -0.033 |
cking | -0.033 |
els | -0.032 |
Token | 't |
Token ID | 470 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
flower | +0.041 |
cking | +0.037 |
ric | +0.037 |
els | +0.037 |
eled | +0.036 |
Neg logit contributions | |
ives | -0.006 |
Max | -0.004 |
Welcome | -0.004 |
ury | -0.004 |
Enjoy | -0.004 |
Token | mind |
Token ID | 2000 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
ives | +0.004 |
ury | +0.003 |
Enjoy | +0.003 |
Welcome | +0.003 |
Happy | +0.003 |
Neg logit contributions | |
flower | -0.008 |
ble | -0.007 |
ric | -0.007 |
cking | -0.007 |
els | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Max | +0.010 |
ives | +0.008 |
ury | +0.008 |
Happy | +0.008 |
Welcome | +0.008 |
Neg logit contributions | |
flower | -0.020 |
ble | -0.017 |
eled | -0.017 |
cking | -0.017 |
cker | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
ives | +0.001 |
ury | +0.001 |
Enjoy | +0.001 |
Welcome | +0.001 |
Follow | +0.001 |
Neg logit contributions | |
flower | -0.003 |
ble | -0.002 |
ric | -0.002 |
els | -0.002 |
cking | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
flower | +0.031 |
ble | +0.030 |
ric | +0.029 |
els | +0.029 |
cking | +0.028 |
Neg logit contributions | |
ives | -0.016 |
ury | -0.014 |
Enjoy | -0.013 |
Welcome | -0.013 |
Follow | -0.013 |
Token | They |
Token ID | 2990 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
flower | +0.030 |
ric | +0.027 |
cking | +0.026 |
els | +0.026 |
ries | +0.025 |
Neg logit contributions | |
ives | -0.024 |
ury | -0.022 |
Enjoy | -0.021 |
Now | -0.020 |
Follow | -0.020 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
flower | +0.057 |
ble | +0.051 |
ric | +0.050 |
cking | +0.050 |
els | +0.050 |
Neg logit contributions | |
ives | -0.040 |
ury | -0.035 |
Enjoy | -0.034 |
Welcome | -0.033 |
Happy | -0.032 |
Token | at |
Token ID | 379 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ives | +0.006 |
ury | +0.005 |
Enjoy | +0.005 |
Welcome | +0.005 |
Happy | +0.005 |
Neg logit contributions | |
flower | -0.010 |
ble | -0.009 |
ric | -0.009 |
cking | -0.009 |
els | -0.009 |
Token | each |
Token ID | 1123 |
Feature activation | -9.65e-01 |
Pos logit contributions | |
flower | +0.054 |
ble | +0.048 |
ric | +0.047 |
cking | +0.047 |
mill | +0.045 |
Neg logit contributions | |
Max | -0.032 |
ives | -0.032 |
Enjoy | -0.030 |
Jack | -0.029 |
Happy | -0.029 |
Token | other |
Token ID | 584 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ives | +0.022 |
ury | +0.017 |
Enjoy | +0.017 |
Welcome | +0.016 |
Happy | +0.015 |
Neg logit contributions | |
flower | -0.059 |
ble | -0.054 |
ric | -0.054 |
cking | -0.053 |
els | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
ives | +0.037 |
ury | +0.033 |
Enjoy | +0.031 |
Welcome | +0.031 |
Max | +0.030 |
Neg logit contributions | |
flower | -0.051 |
ble | -0.046 |
ric | -0.046 |
cking | -0.045 |
els | -0.044 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
flower | +0.021 |
cking | +0.018 |
ble | +0.018 |
els | +0.018 |
ric | +0.017 |
Neg logit contributions | |
ives | -0.020 |
Enjoy | -0.017 |
ury | -0.017 |
Welcome | -0.016 |
Follow | -0.016 |
Token | their |
Token ID | 511 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
ives | +0.007 |
Max | +0.006 |
Enjoy | +0.006 |
Happy | +0.005 |
People | +0.005 |
Neg logit contributions | |
flower | -0.014 |
ric | -0.013 |
cking | -0.012 |
ble | -0.012 |
cker | -0.012 |
Token | wide |
Token ID | 3094 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
ives | +0.022 |
ury | +0.020 |
Enjoy | +0.019 |
Welcome | +0.019 |
Happy | +0.018 |
Neg logit contributions | |
flower | -0.026 |
ble | -0.023 |
ric | -0.023 |
cking | -0.023 |
els | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Max | +0.020 |
Happy | +0.018 |
ives | +0.017 |
Jack | +0.017 |
ury | +0.016 |
Neg logit contributions | |
flower | -0.030 |
ric | -0.028 |
cking | -0.026 |
ble | -0.025 |
cker | -0.024 |
Token | eyes |
Token ID | 2951 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
flower | +0.008 |
ble | +0.007 |
cking | +0.007 |
ric | +0.007 |
els | +0.006 |
Neg logit contributions | |
ives | -0.007 |
ury | -0.006 |
Enjoy | -0.006 |
Welcome | -0.006 |
Max | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
Enjoy | +0.010 |
ives | +0.010 |
Welcome | +0.010 |
ury | +0.010 |
Cop | +0.010 |
Neg logit contributions | |
flower | -0.008 |
ble | -0.007 |
els | -0.007 |
cking | -0.006 |
bery | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
ives | +0.021 |
ury | +0.018 |
Enjoy | +0.017 |
Welcome | +0.016 |
Follow | +0.016 |
Neg logit contributions | |
flower | -0.030 |
ble | -0.029 |
els | -0.028 |
ric | -0.028 |
cks | -0.026 |
Token | heard |
Token ID | 2982 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
flower | +0.003 |
ble | +0.003 |
els | +0.002 |
ric | +0.002 |
cking | +0.002 |
Neg logit contributions | |
ives | -0.002 |
Enjoy | -0.002 |
Welcome | -0.002 |
ury | -0.002 |
These | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ives | +0.076 |
ury | +0.067 |
Enjoy | +0.066 |
Welcome | +0.064 |
Follow | +0.063 |
Neg logit contributions | |
flower | -0.094 |
ble | -0.085 |
ric | -0.083 |
els | -0.082 |
cking | -0.082 |
Token | crash |
Token ID | 7014 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
ives | +0.040 |
ury | +0.036 |
Enjoy | +0.034 |
Welcome | +0.034 |
Happy | +0.033 |
Neg logit contributions | |
flower | -0.060 |
ble | -0.053 |
els | -0.053 |
ric | -0.053 |
cking | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
flower | +0.047 |
ric | +0.044 |
cking | +0.042 |
ble | +0.041 |
eled | +0.041 |
Neg logit contributions | |
ives | -0.028 |
Max | -0.024 |
ury | -0.024 |
Welcome | -0.022 |
Happy | -0.022 |
Token | She |
Token ID | 1375 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
ives | +0.026 |
ury | +0.022 |
Enjoy | +0.022 |
Follow | +0.021 |
Welcome | +0.020 |
Neg logit contributions | |
flower | -0.038 |
ble | -0.037 |
els | -0.035 |
ric | -0.035 |
cks | -0.033 |
Token | felt |
Token ID | 2936 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
ives | +0.002 |
Enjoy | +0.002 |
ury | +0.002 |
Welcome | +0.002 |
Happy | +0.002 |
Neg logit contributions | |
flower | -0.003 |
ble | -0.002 |
els | -0.002 |
cking | -0.002 |
ric | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
ives | +0.008 |
Max | +0.007 |
hide | +0.007 |
Enjoy | +0.007 |
People | +0.006 |
Neg logit contributions | |
flower | -0.015 |
ric | -0.013 |
els | -0.013 |
mill | -0.013 |
cking | -0.013 |
Token | down |
Token ID | 866 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
flower | +0.005 |
ric | +0.005 |
cking | +0.005 |
els | +0.005 |
ble | +0.005 |
Neg logit contributions | |
ives | -0.002 |
Happy | -0.002 |
Welcome | -0.002 |
Enjoy | -0.002 |
Max | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
flower | +0.044 |
cking | +0.039 |
ble | +0.039 |
ric | +0.039 |
els | +0.038 |
Neg logit contributions | |
ives | -0.032 |
Happy | -0.030 |
Enjoy | -0.030 |
Max | -0.030 |
Welcome | -0.029 |
Token | street |
Token ID | 4675 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
ives | +0.011 |
ury | +0.010 |
Enjoy | +0.009 |
Welcome | +0.009 |
Happy | +0.009 |
Neg logit contributions | |
flower | -0.020 |
ble | -0.019 |
ric | -0.018 |
els | -0.018 |
cking | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
flower | +0.016 |
ble | +0.014 |
ric | +0.014 |
cking | +0.013 |
els | +0.013 |
Neg logit contributions | |
ives | -0.014 |
ury | -0.012 |
Enjoy | -0.012 |
Welcome | -0.011 |
Follow | -0.011 |
Token | He |
Token ID | 679 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
ives | +0.005 |
ury | +0.004 |
Enjoy | +0.003 |
Welcome | +0.003 |
Follow | +0.003 |
Neg logit contributions | |
flower | -0.010 |
ble | -0.009 |
ric | -0.009 |
els | -0.009 |
cking | -0.009 |
Token | saw |
Token ID | 2497 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
flower | +0.015 |
ble | +0.013 |
ric | +0.013 |
cking | +0.013 |
els | +0.013 |
Neg logit contributions | |
ives | -0.011 |
Enjoy | -0.009 |
ury | -0.009 |
Welcome | -0.008 |
Follow | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
ives | +0.032 |
ury | +0.028 |
Enjoy | +0.028 |
Welcome | +0.027 |
Happy | +0.026 |
Neg logit contributions | |
flower | -0.043 |
ble | -0.039 |
ric | -0.038 |
cking | -0.038 |
els | -0.038 |
Token | flag |
Token ID | 6056 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ives | +0.024 |
ury | +0.021 |
Enjoy | +0.021 |
Welcome | +0.020 |
Follow | +0.020 |
Neg logit contributions | |
flower | -0.033 |
ble | -0.030 |
ric | -0.029 |
cking | -0.029 |
els | -0.029 |
Token | that |
Token ID | 326 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
Max | +0.023 |
Welcome | +0.022 |
hide | +0.021 |
ives | +0.021 |
ury | +0.020 |
Neg logit contributions | |
flower | -0.053 |
ric | -0.053 |
cking | -0.053 |
els | -0.053 |
eled | -0.052 |
Token | was |
Token ID | 373 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
ives | +0.036 |
Enjoy | +0.031 |
ury | +0.031 |
Follow | +0.029 |
Welcome | +0.028 |
Neg logit contributions | |
flower | -0.040 |
ble | -0.036 |
ric | -0.034 |
els | -0.034 |
cking | -0.033 |
Token | waving |
Token ID | 25849 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
flower | +0.022 |
ric | +0.020 |
els | +0.020 |
bery | +0.019 |
ries | +0.019 |
Neg logit contributions | |
hide | -0.009 |
Max | -0.008 |
long | -0.008 |
Welcome | -0.008 |
to | -0.008 |
Token | got |
Token ID | 1392 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
flower | +0.015 |
ble | +0.013 |
cking | +0.013 |
ric | +0.013 |
els | +0.013 |
Neg logit contributions | |
ives | -0.010 |
ury | -0.008 |
Enjoy | -0.008 |
Welcome | -0.007 |
Follow | -0.007 |
Token | scared |
Token ID | 12008 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
flower | +0.040 |
ble | +0.036 |
cking | +0.036 |
els | +0.035 |
ric | +0.035 |
Neg logit contributions | |
ives | -0.032 |
ury | -0.029 |
Enjoy | -0.027 |
Welcome | -0.026 |
Follow | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +2.07e-03 |
Pos logit contributions | |
flower | +0.055 |
ble | +0.049 |
ric | +0.048 |
cking | +0.048 |
els | +0.047 |
Neg logit contributions | |
ives | -0.051 |
ury | -0.046 |
Enjoy | -0.045 |
Welcome | -0.043 |
Follow | -0.042 |
Token | She |
Token ID | 1375 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
flower | +0.000 |
ble | +0.000 |
ries | +0.000 |
ric | +0.000 |
els | +0.000 |
Neg logit contributions | |
ives | -0.000 |
Enjoy | -0.000 |
ury | -0.000 |
villains | -0.000 |
ival | -0.000 |
Token | ran |
Token ID | 4966 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
flower | +0.021 |
ble | +0.019 |
ric | +0.018 |
els | +0.018 |
cking | +0.018 |
Neg logit contributions | |
ives | -0.020 |
Enjoy | -0.018 |
ury | -0.017 |
Welcome | -0.016 |
These | -0.016 |
Token | away |
Token ID | 1497 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ives | +0.025 |
ury | +0.022 |
Enjoy | +0.021 |
People | +0.021 |
Welcome | +0.021 |
Neg logit contributions | |
flower | -0.034 |
ble | -0.030 |
cking | -0.029 |
mill | -0.029 |
els | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
ives | +0.035 |
ury | +0.031 |
Enjoy | +0.030 |
Welcome | +0.029 |
Happy | +0.028 |
Neg logit contributions | |
flower | -0.056 |
ric | -0.051 |
ble | -0.051 |
els | -0.050 |
cking | -0.050 |
Token | leaving |
Token ID | 4305 |
Feature activation | -9.89e-02 |
Pos logit contributions | |
ives | +0.021 |
Enjoy | +0.018 |
ury | +0.018 |
People | +0.017 |
Follow | +0.017 |
Neg logit contributions | |
flower | -0.026 |
cking | -0.023 |
ric | -0.023 |
ble | -0.023 |
cks | -0.021 |
Token | her |
Token ID | 607 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
ives | +0.005 |
ury | +0.004 |
Follow | +0.004 |
Enjoy | +0.004 |
Welcome | +0.004 |
Neg logit contributions | |
flower | -0.003 |
els | -0.003 |
ble | -0.003 |
ries | -0.003 |
ric | -0.003 |
Token | toys |
Token ID | 14958 |
Feature activation | +9.47e-02 |
Pos logit contributions | |
flower | +0.002 |
ble | +0.002 |
ric | +0.002 |
cking | +0.002 |
els | +0.002 |
Neg logit contributions | |
ives | -0.001 |
ury | -0.001 |
Enjoy | -0.001 |
Welcome | -0.001 |
Max | -0.001 |
Token | behind |
Token ID | 2157 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
flower | +0.005 |
ble | +0.004 |
cking | +0.004 |
ric | +0.004 |
els | +0.004 |
Neg logit contributions | |
ives | -0.003 |
ury | -0.003 |
Enjoy | -0.003 |
Welcome | -0.003 |
Happy | -0.003 |
Token | day |
Token ID | 1110 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
flower | +0.021 |
ble | +0.019 |
ric | +0.019 |
cking | +0.019 |
els | +0.019 |
Neg logit contributions | |
ives | -0.011 |
ury | -0.009 |
Enjoy | -0.009 |
Welcome | -0.008 |
Happy | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
ives | +0.021 |
ury | +0.018 |
Enjoy | +0.017 |
Welcome | +0.017 |
Happy | +0.016 |
Neg logit contributions | |
flower | -0.038 |
ble | -0.035 |
ric | -0.035 |
cking | -0.035 |
els | -0.034 |
Token | she |
Token ID | 673 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
ives | +0.019 |
ury | +0.017 |
Enjoy | +0.017 |
Max | +0.016 |
Happy | +0.016 |
Neg logit contributions | |
flower | -0.040 |
ric | -0.037 |
ble | -0.037 |
cking | -0.037 |
els | -0.036 |
Token | found |
Token ID | 1043 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
ives | +0.014 |
Enjoy | +0.012 |
ury | +0.012 |
Welcome | +0.011 |
Happy | +0.011 |
Neg logit contributions | |
flower | -0.019 |
ble | -0.017 |
els | -0.017 |
ric | -0.016 |
cking | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
ives | +0.034 |
ury | +0.030 |
Enjoy | +0.029 |
Welcome | +0.028 |
Max | +0.028 |
Neg logit contributions | |
flower | -0.048 |
ric | -0.043 |
ble | -0.043 |
cking | -0.043 |
els | -0.042 |
Token | card |
Token ID | 2657 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
ives | +0.022 |
ury | +0.019 |
Enjoy | +0.019 |
Follow | +0.018 |
Welcome | +0.018 |
Neg logit contributions | |
flower | -0.027 |
ble | -0.024 |
ric | -0.024 |
cking | -0.023 |
els | -0.023 |
Token | with |
Token ID | 351 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
ives | +0.023 |
ury | +0.019 |
Max | +0.018 |
Welcome | +0.018 |
Enjoy | +0.018 |
Neg logit contributions | |
flower | -0.048 |
ric | -0.048 |
cking | -0.047 |
els | -0.045 |
eled | -0.045 |
Token | a |
Token ID | 257 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
ives | +0.032 |
ury | +0.029 |
Enjoy | +0.028 |
Welcome | +0.027 |
Follow | +0.027 |
Neg logit contributions | |
flower | -0.038 |
ble | -0.034 |
els | -0.034 |
ric | -0.034 |
cking | -0.034 |
Token | yellow |
Token ID | 7872 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
ives | +0.011 |
ury | +0.010 |
Enjoy | +0.010 |
Welcome | +0.009 |
Follow | +0.009 |
Neg logit contributions | |
flower | -0.012 |
ble | -0.011 |
ric | -0.011 |
cking | -0.011 |
els | -0.011 |
Token | fruit |
Token ID | 8234 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
cking | +0.015 |
flower | +0.014 |
ric | +0.014 |
ble | +0.014 |
cks | +0.013 |
Neg logit contributions | |
ives | -0.011 |
Enjoy | -0.010 |
ury | -0.009 |
Thank | -0.009 |
Welcome | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
flower | +0.036 |
ric | +0.034 |
cking | +0.033 |
ble | +0.033 |
els | +0.031 |
Neg logit contributions | |
ives | -0.026 |
ury | -0.022 |
Enjoy | -0.021 |
Welcome | -0.021 |
Max | -0.020 |
Token | she |
Token ID | 673 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
ives | +0.005 |
ury | +0.004 |
Enjoy | +0.004 |
Welcome | +0.004 |
Happy | +0.004 |
Neg logit contributions | |
flower | -0.006 |
ble | -0.005 |
ric | -0.005 |
cking | -0.005 |
els | -0.005 |
Token | saw |
Token ID | 2497 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
ives | +0.013 |
ury | +0.012 |
Enjoy | +0.012 |
Welcome | +0.011 |
Happy | +0.011 |
Neg logit contributions | |
flower | -0.019 |
ble | -0.017 |
ric | -0.016 |
els | -0.016 |
cking | -0.016 |
Token | another |
Token ID | 1194 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
ives | +0.033 |
ury | +0.030 |
Enjoy | +0.029 |
Welcome | +0.028 |
Happy | +0.028 |
Neg logit contributions | |
flower | -0.039 |
ble | -0.035 |
ric | -0.034 |
cking | -0.034 |
els | -0.034 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
ives | +0.007 |
ury | +0.006 |
Welcome | +0.006 |
Enjoy | +0.006 |
Max | +0.006 |
Neg logit contributions | |
flower | -0.009 |
ble | -0.009 |
els | -0.009 |
cking | -0.009 |
ric | -0.009 |
Token | in |
Token ID | 259 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
ives | +0.100 |
ury | +0.092 |
Enjoy | +0.091 |
Welcome | +0.090 |
Happy | +0.088 |
Neg logit contributions | |
flower | -0.054 |
ble | -0.045 |
ric | -0.043 |
cking | -0.043 |
els | -0.043 |
Token | oc |
Token ID | 420 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
ives | +0.026 |
ury | +0.023 |
Enjoy | +0.022 |
Welcome | +0.021 |
Follow | +0.020 |
Neg logit contributions | |
flower | -0.053 |
ble | -0.049 |
ric | -0.048 |
els | -0.048 |
cking | -0.048 |
Token | eros |
Token ID | 27498 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
ives | +0.213 |
ury | +0.199 |
Welcome | +0.195 |
Enjoy | +0.192 |
Happy | +0.190 |
Neg logit contributions | |
flower | -0.135 |
els | -0.115 |
ble | -0.115 |
ric | -0.109 |
cking | -0.106 |
Token | coming |
Token ID | 2406 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
ives | +0.028 |
ury | +0.025 |
Welcome | +0.024 |
Enjoy | +0.024 |
Max | +0.023 |
Neg logit contributions | |
flower | -0.035 |
ble | -0.032 |
ric | -0.032 |
els | -0.031 |
cking | -0.031 |
Token | towards |
Token ID | 3371 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
flower | +0.020 |
ric | +0.019 |
els | +0.018 |
cking | +0.018 |
ble | +0.018 |
Neg logit contributions | |
ives | -0.012 |
Welcome | -0.011 |
ury | -0.011 |
Max | -0.011 |
Enjoy | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
flower | +0.029 |
ble | +0.026 |
ric | +0.025 |
cking | +0.025 |
els | +0.025 |
Neg logit contributions | |
ives | -0.033 |
ury | -0.030 |
Enjoy | -0.030 |
Welcome | -0.029 |
Happy | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
flower | +0.022 |
ble | +0.020 |
cking | +0.020 |
els | +0.019 |
ric | +0.019 |
Neg logit contributions | |
ives | -0.018 |
ury | -0.016 |
Enjoy | -0.015 |
Welcome | -0.015 |
Max | -0.014 |
Token | fun |
Token ID | 1257 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ives | +0.023 |
ury | +0.020 |
Follow | +0.018 |
Enjoy | +0.018 |
Welcome | +0.018 |
Neg logit contributions | |
flower | -0.025 |
ble | -0.024 |
cking | -0.023 |
ric | -0.023 |
cks | -0.022 |
Token | in |
Token ID | 287 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
ives | +0.064 |
ury | +0.057 |
Enjoy | +0.055 |
Welcome | +0.054 |
Sadly | +0.053 |
Neg logit contributions | |
flower | -0.069 |
ble | -0.063 |
cking | -0.062 |
els | -0.060 |
ric | -0.059 |
Token | the |
Token ID | 262 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
ives | +0.024 |
ury | +0.022 |
Enjoy | +0.022 |
Welcome | +0.021 |
Happy | +0.021 |
Neg logit contributions | |
flower | -0.026 |
ble | -0.023 |
ric | -0.022 |
els | -0.022 |
cking | -0.022 |
Token | sky |
Token ID | 6766 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
ives | +0.023 |
ury | +0.021 |
Enjoy | +0.020 |
Welcome | +0.019 |
Happy | +0.019 |
Neg logit contributions | |
flower | -0.028 |
ble | -0.025 |
ric | -0.025 |
cking | -0.024 |
els | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
ives | +0.013 |
ury | +0.012 |
Enjoy | +0.011 |
Welcome | +0.011 |
Happy | +0.011 |
Neg logit contributions | |
flower | -0.017 |
ble | -0.015 |
ric | -0.015 |
cking | -0.015 |
els | -0.015 |
Token | Enjoy |
Token ID | 18179 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
ives | +0.014 |
boards | +0.012 |
and | +0.011 |
ival | +0.011 |
ury | +0.011 |
Neg logit contributions | |
flower | -0.025 |
ric | -0.023 |
ble | -0.020 |
esh | -0.020 |
cks | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
ives | +0.109 |
Enjoy | +0.097 |
ury | +0.096 |
Happy | +0.091 |
Welcome | +0.090 |
Neg logit contributions | |
flower | -0.166 |
ble | -0.147 |
ric | -0.146 |
cking | -0.144 |
els | -0.143 |
Token | season |
Token ID | 1622 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
ives | +0.063 |
ury | +0.057 |
Enjoy | +0.056 |
Welcome | +0.054 |
Follow | +0.053 |
Neg logit contributions | |
flower | -0.063 |
ble | -0.055 |
ric | -0.054 |
cking | -0.053 |
els | -0.053 |
Token | ," |
Token ID | 553 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
ives | +0.022 |
ury | +0.020 |
Enjoy | +0.020 |
Welcome | +0.019 |
Follow | +0.018 |
Neg logit contributions | |
flower | -0.026 |
ble | -0.023 |
ric | -0.022 |
els | -0.022 |
cking | -0.022 |
Token | Tom |
Token ID | 4186 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
ives | +0.013 |
ury | +0.011 |
Enjoy | +0.011 |
Welcome | +0.010 |
Follow | +0.010 |
Neg logit contributions | |
flower | -0.022 |
ble | -0.020 |
els | -0.020 |
ric | -0.020 |
cking | -0.020 |
Token | says |
Token ID | 1139 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
flower | +0.044 |
ble | +0.040 |
els | +0.039 |
ric | +0.039 |
cking | +0.039 |
Neg logit contributions | |
ives | -0.023 |
ury | -0.021 |
Enjoy | -0.020 |
Welcome | -0.019 |
Happy | -0.018 |
Token | He |
Token ID | 679 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
flower | +0.022 |
ble | +0.020 |
ric | +0.019 |
els | +0.019 |
eled | +0.018 |
Neg logit contributions | |
ives | -0.014 |
ury | -0.012 |
Enjoy | -0.011 |
Bye | -0.010 |
and | -0.010 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
flower | +0.019 |
ble | +0.017 |
eled | +0.016 |
ric | +0.016 |
els | +0.016 |
Neg logit contributions | |
ives | -0.016 |
ury | -0.013 |
Enjoy | -0.013 |
Welcome | -0.013 |
People | -0.012 |
Token | some |
Token ID | 617 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
ives | +0.046 |
ury | +0.042 |
Welcome | +0.040 |
Enjoy | +0.039 |
Follow | +0.039 |
Neg logit contributions | |
flower | -0.045 |
ble | -0.042 |
els | -0.040 |
cking | -0.040 |
ric | -0.039 |
Token | lovely |
Token ID | 14081 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
ives | +0.014 |
ury | +0.013 |
Enjoy | +0.012 |
Welcome | +0.012 |
Follow | +0.012 |
Neg logit contributions | |
flower | -0.019 |
ble | -0.017 |
els | -0.017 |
cking | -0.017 |
ric | -0.017 |
Token | sa |
Token ID | 473 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
ives | +0.008 |
ury | +0.007 |
Enjoy | +0.007 |
Happy | +0.007 |
Welcome | +0.007 |
Neg logit contributions | |
flower | -0.012 |
ble | -0.011 |
ric | -0.011 |
cking | -0.011 |
cks | -0.011 |
Token | us |
Token ID | 385 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
ives | +0.068 |
ury | +0.061 |
Welcome | +0.061 |
Enjoy | +0.059 |
Follow | +0.058 |
Neg logit contributions | |
flower | -0.093 |
ble | -0.085 |
ric | -0.081 |
els | -0.081 |
cking | -0.080 |
Token | ages |
Token ID | 1095 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
ives | +0.112 |
Enjoy | +0.103 |
Welcome | +0.101 |
Follow | +0.098 |
ury | +0.098 |
Neg logit contributions | |
flower | -0.172 |
ble | -0.161 |
cking | -0.156 |
ric | -0.156 |
els | -0.153 |
Token | on |
Token ID | 319 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
ives | +0.011 |
ury | +0.009 |
Enjoy | +0.009 |
Welcome | +0.009 |
Happy | +0.009 |
Neg logit contributions | |
flower | -0.017 |
ble | -0.015 |
ric | -0.015 |
cking | -0.015 |
els | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
flower | +0.028 |
ble | +0.025 |
ric | +0.025 |
cking | +0.025 |
els | +0.024 |
Neg logit contributions | |
ives | -0.021 |
Max | -0.020 |
Enjoy | -0.020 |
Happy | -0.019 |
ury | -0.019 |
Token | shelf |
Token ID | 18316 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
ives | +0.016 |
ury | +0.014 |
Enjoy | +0.014 |
Follow | +0.013 |
Welcome | +0.013 |
Neg logit contributions | |
flower | -0.019 |
ble | -0.017 |
ric | -0.017 |
els | -0.016 |
cking | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
flower | +0.035 |
ble | +0.031 |
els | +0.030 |
ric | +0.030 |
cking | +0.029 |
Neg logit contributions | |
ives | -0.028 |
Enjoy | -0.025 |
ury | -0.025 |
Welcome | -0.024 |
Follow | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
ives | +0.015 |
Enjoy | +0.013 |
ury | +0.013 |
Welcome | +0.012 |
Happy | +0.012 |
Neg logit contributions | |
flower | -0.027 |
ble | -0.024 |
els | -0.024 |
ric | -0.024 |
cking | -0.024 |
Token | very |
Token ID | 845 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
ives | +0.016 |
ury | +0.014 |
Enjoy | +0.013 |
Welcome | +0.013 |
Follow | +0.012 |
Neg logit contributions | |
flower | -0.032 |
ble | -0.029 |
ric | -0.028 |
cking | -0.028 |
els | -0.028 |
Token | clever |
Token ID | 14169 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
ives | +0.033 |
boards | +0.026 |
Sadly | +0.025 |
and | +0.025 |
Did | +0.024 |
Neg logit contributions | |
ble | -0.028 |
flower | -0.027 |
cking | -0.025 |
cker | -0.024 |
cks | -0.024 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
ives | +0.033 |
ury | +0.029 |
Enjoy | +0.028 |
Welcome | +0.027 |
Follow | +0.027 |
Neg logit contributions | |
flower | -0.042 |
ble | -0.037 |
els | -0.035 |
ric | -0.035 |
mill | -0.035 |
Token | in |
Token ID | 259 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
ives | +0.092 |
ury | +0.086 |
Sadly | +0.086 |
Enjoy | +0.085 |
Welcome | +0.085 |
Neg logit contributions | |
flower | -0.037 |
ble | -0.031 |
cking | -0.027 |
els | -0.027 |
mill | -0.026 |
Token | oc |
Token ID | 420 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
ives | +0.026 |
ury | +0.022 |
Enjoy | +0.022 |
Sadly | +0.022 |
Welcome | +0.021 |
Neg logit contributions | |
flower | -0.034 |
ble | -0.030 |
mill | -0.028 |
ric | -0.028 |
cker | -0.027 |
Token | eros |
Token ID | 27498 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
ives | +0.216 |
Welcome | +0.207 |
Sadly | +0.206 |
ury | +0.203 |
Enjoy | +0.199 |
Neg logit contributions | |
flower | -0.112 |
ble | -0.097 |
els | -0.094 |
mill | -0.087 |
ries | -0.086 |
Token | ." |
Token ID | 526 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
ives | +0.031 |
ury | +0.027 |
Enjoy | +0.027 |
Sadly | +0.026 |
Welcome | +0.026 |
Neg logit contributions | |
flower | -0.033 |
ble | -0.029 |
ric | -0.027 |
els | -0.027 |
cking | -0.027 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
ives | +0.013 |
ury | +0.011 |
Enjoy | +0.010 |
Welcome | +0.010 |
Follow | +0.010 |
Neg logit contributions | |
flower | -0.024 |
ric | -0.022 |
ble | -0.021 |
mill | -0.020 |
els | -0.020 |
Token | Once |
Token ID | 7454 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
flower | +0.003 |
ble | +0.002 |
ric | +0.002 |
els | +0.002 |
cks | +0.002 |
Neg logit contributions | |
ives | -0.002 |
ury | -0.002 |
Enjoy | -0.002 |
Follow | -0.002 |
Welcome | -0.002 |
Token | upon |
Token ID | 2402 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
flower | +0.040 |
cking | +0.035 |
ble | +0.035 |
ric | +0.034 |
els | +0.034 |
Neg logit contributions | |
ives | -0.040 |
Max | -0.037 |
ury | -0.037 |
Welcome | -0.036 |
Enjoy | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
flower | +0.018 |
ble | +0.017 |
cking | +0.016 |
ric | +0.016 |
els | +0.015 |
Neg logit contributions | |
ives | -0.013 |
Happy | -0.013 |
Welcome | -0.012 |
Enjoy | -0.012 |
Max | -0.012 |
Token | tree |
Token ID | 5509 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ives | +0.004 |
ury | +0.004 |
Enjoy | +0.004 |
Welcome | +0.004 |
Happy | +0.003 |
Neg logit contributions | |
flower | -0.006 |
ble | -0.005 |
ric | -0.005 |
cking | -0.005 |
els | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
flower | +0.005 |
ble | +0.005 |
ric | +0.005 |
els | +0.005 |
cking | +0.005 |
Neg logit contributions | |
ives | -0.004 |
ury | -0.004 |
Enjoy | -0.004 |
Welcome | -0.004 |
Happy | -0.004 |
Token | Both |
Token ID | 5747 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
flower | +0.020 |
ric | +0.018 |
ble | +0.018 |
els | +0.017 |
mill | +0.017 |
Neg logit contributions | |
ives | -0.011 |
ury | -0.009 |
Enjoy | -0.008 |
villains | -0.008 |
hide | -0.008 |
Token | b |
Token ID | 275 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
flower | +0.059 |
els | +0.053 |
ble | +0.053 |
ric | +0.052 |
cking | +0.052 |
Neg logit contributions | |
ives | -0.035 |
ury | -0.030 |
Enjoy | -0.030 |
Follow | -0.028 |
Welcome | -0.028 |
Token | unn |
Token ID | 20935 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
ives | +0.035 |
Max | +0.032 |
ury | +0.032 |
Welcome | +0.032 |
Cop | +0.032 |
Neg logit contributions | |
flower | -0.097 |
els | -0.089 |
ric | -0.088 |
ble | -0.088 |
cking | -0.088 |
Token | ies |
Token ID | 444 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
ives | +0.264 |
ury | +0.247 |
Enjoy | +0.244 |
Welcome | +0.240 |
Happy | +0.237 |
Neg logit contributions | |
flower | -0.072 |
ble | -0.054 |
ric | -0.051 |
cking | -0.049 |
els | -0.048 |
Token | agreed |
Token ID | 4987 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
ives | +0.011 |
ury | +0.009 |
Enjoy | +0.009 |
Welcome | +0.009 |
Happy | +0.008 |
Neg logit contributions | |
flower | -0.020 |
ble | -0.019 |
ric | -0.019 |
els | -0.018 |
cking | -0.018 |
Token | that |
Token ID | 326 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
ives | +0.007 |
ury | +0.006 |
Enjoy | +0.006 |
Welcome | +0.006 |
Happy | +0.006 |
Neg logit contributions | |
flower | -0.015 |
ble | -0.014 |
ric | -0.014 |
els | -0.014 |
cking | -0.014 |
Token | it |
Token ID | 340 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
ives | +0.014 |
ury | +0.012 |
Enjoy | +0.012 |
Follow | +0.011 |
Welcome | +0.011 |
Neg logit contributions | |
flower | -0.015 |
ble | -0.013 |
els | -0.013 |
ric | -0.013 |
cking | -0.013 |
Token | had |
Token ID | 550 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
ives | +0.014 |
ury | +0.012 |
Enjoy | +0.012 |
Welcome | +0.011 |
Happy | +0.011 |
Neg logit contributions | |
flower | -0.019 |
ble | -0.017 |
ric | -0.017 |
els | -0.017 |
cking | -0.017 |