Token | not |
Token ID | 407 |
Feature activation | +6.85e-03 |
Pos logit contributions | |
ind | +0.007 |
cha | +0.006 |
yacht | +0.006 |
re | +0.006 |
appearance | +0.006 |
Neg logit contributions | |
opener | -0.009 |
aver | -0.008 |
inda | -0.008 |
izzy | -0.008 |
Linda | -0.008 |
Token | bigger |
Token ID | 5749 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
opener | +0.014 |
aver | +0.013 |
inda | +0.012 |
eh | +0.012 |
Linda | +0.012 |
Neg logit contributions | |
ind | -0.010 |
cha | -0.009 |
bicycles | -0.009 |
yacht | -0.009 |
appearance | -0.009 |
Token | than |
Token ID | 621 |
Feature activation | +6.46e-03 |
Pos logit contributions | |
opener | +0.030 |
inda | +0.025 |
Jill | +0.025 |
Linda | +0.025 |
aver | +0.024 |
Neg logit contributions | |
ind | -0.028 |
cha | -0.027 |
yacht | -0.026 |
festival | -0.025 |
helicopter | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | +1.36e-03 |
Pos logit contributions | |
opener | +0.011 |
inda | +0.009 |
aver | +0.009 |
Jill | +0.009 |
Linda | +0.009 |
Neg logit contributions | |
ind | -0.012 |
cha | -0.011 |
bicycles | -0.010 |
helicopter | -0.010 |
ranch | -0.010 |
Token | fing |
Token ID | 8038 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
opener | +0.002 |
aver | +0.002 |
inda | +0.002 |
Linda | +0.002 |
eh | +0.002 |
Neg logit contributions | |
cha | -0.002 |
ind | -0.002 |
bicycles | -0.002 |
uted | -0.002 |
iling | -0.002 |
Token | ern |
Token ID | 1142 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
opener | +0.051 |
aver | +0.048 |
Linda | +0.045 |
lic | +0.044 |
inda | +0.044 |
Neg logit contributions | |
ind | -0.066 |
appearance | -0.062 |
cha | -0.060 |
iling | -0.056 |
strangers | -0.056 |
Token | ail |
Token ID | 603 |
Feature activation | +4.96e-02 |
Pos logit contributions | |
opener | +0.142 |
aver | +0.125 |
Linda | +0.112 |
lic | +0.112 |
avers | +0.111 |
Neg logit contributions | |
ind | -0.117 |
cha | -0.104 |
forever | -0.103 |
country | -0.102 |
mall | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | +4.46e-03 |
Pos logit contributions | |
opener | +0.076 |
aver | +0.065 |
inda | +0.065 |
Linda | +0.060 |
eh | +0.058 |
Neg logit contributions | |
ind | -0.099 |
cha | -0.094 |
bicycles | -0.090 |
yacht | -0.088 |
helicopter | -0.086 |
Token | They |
Token ID | 1119 |
Feature activation | -1.34e-03 |
Pos logit contributions | |
opener | +0.009 |
aver | +0.008 |
inda | +0.008 |
eh | +0.008 |
izzy | +0.007 |
Neg logit contributions | |
cha | -0.006 |
yacht | -0.006 |
bicycles | -0.006 |
ind | -0.006 |
ranch | -0.006 |
Token | also |
Token ID | 635 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
ind | +0.002 |
cha | +0.002 |
appearance | +0.002 |
bicycles | +0.002 |
yacht | +0.002 |
Neg logit contributions | |
opener | -0.002 |
aver | -0.002 |
inda | -0.002 |
Linda | -0.002 |
izzy | -0.002 |
Token | found |
Token ID | 1043 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
ind | +0.022 |
cha | +0.022 |
bicycles | +0.020 |
yacht | +0.020 |
helicopter | +0.020 |
Neg logit contributions | |
opener | -0.022 |
aver | -0.020 |
inda | -0.019 |
Linda | -0.018 |
eh | -0.018 |
Token | in |
Token ID | 287 |
Feature activation | -3.79e-03 |
Pos logit contributions | |
opener | +0.037 |
aver | +0.032 |
Jill | +0.030 |
inda | +0.030 |
eh | +0.029 |
Neg logit contributions | |
cha | -0.044 |
ind | -0.044 |
festival | -0.042 |
bicycles | -0.041 |
wedding | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
cha | +0.007 |
ind | +0.007 |
yacht | +0.007 |
bicycles | +0.007 |
ishly | +0.007 |
Neg logit contributions | |
opener | -0.005 |
aver | -0.004 |
inda | -0.004 |
Linda | -0.004 |
Jill | -0.004 |
Token | scary |
Token ID | 14343 |
Feature activation | +1.91e-03 |
Pos logit contributions | |
opener | +0.017 |
aver | +0.017 |
eh | +0.017 |
inda | +0.016 |
Linda | +0.016 |
Neg logit contributions | |
cha | -0.015 |
ind | -0.015 |
yacht | -0.015 |
uted | -0.015 |
bicycles | -0.015 |
Token | forest |
Token ID | 8222 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
opener | +0.003 |
aver | +0.003 |
eh | +0.003 |
inda | +0.003 |
Linda | +0.003 |
Neg logit contributions | |
cha | -0.003 |
aults | -0.003 |
ind | -0.003 |
uted | -0.003 |
yacht | -0.002 |
Token | " |
Token ID | 1 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
opener | +0.035 |
aver | +0.030 |
inda | +0.029 |
eh | +0.027 |
Jill | +0.026 |
Neg logit contributions | |
ind | -0.044 |
cha | -0.043 |
bicycles | -0.040 |
yacht | -0.039 |
appearance | -0.039 |
Token | |
Token ID | 220 |
Feature activation | +7.62e-02 |
Pos logit contributions | |
opener | +0.092 |
aver | +0.081 |
inda | +0.078 |
Linda | +0.074 |
izzy | +0.073 |
Neg logit contributions | |
ind | -0.081 |
cha | -0.078 |
yacht | -0.073 |
appearance | -0.073 |
bicycles | -0.071 |
Token |
|
Token ID | 198 |
Feature activation | +4.55e-03 |
Pos logit contributions | |
opener | +0.116 |
aver | +0.113 |
inda | +0.101 |
Linda | +0.101 |
Liz | +0.096 |
Neg logit contributions | |
ind | -0.125 |
cha | -0.110 |
aults | -0.106 |
uted | -0.105 |
forever | -0.103 |
Token |
|
Token ID | 198 |
Feature activation | +7.82e-06 |
Pos logit contributions | |
opener | +0.009 |
aver | +0.009 |
inda | +0.008 |
eh | +0.008 |
Linda | +0.008 |
Neg logit contributions | |
cha | -0.006 |
ind | -0.006 |
bicycles | -0.005 |
village | -0.005 |
forever | -0.005 |
Token | Just |
Token ID | 5703 |
Feature activation | +2.77e-02 |
Token | then |
Token ID | 788 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
opener | +0.063 |
aver | +0.057 |
inda | +0.056 |
izzy | +0.055 |
Linda | +0.053 |
Neg logit contributions | |
cha | -0.030 |
ind | -0.030 |
re | -0.028 |
yacht | -0.027 |
appearance | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
opener | +0.042 |
aver | +0.039 |
inda | +0.038 |
Linda | +0.036 |
eh | +0.035 |
Neg logit contributions | |
ind | -0.029 |
cha | -0.028 |
bicycles | -0.026 |
appearance | -0.025 |
yacht | -0.025 |
Token | " |
Token ID | 366 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
ind | +0.011 |
cha | +0.011 |
yacht | +0.010 |
bicycles | +0.010 |
appearance | +0.010 |
Neg logit contributions | |
opener | -0.012 |
aver | -0.011 |
inda | -0.011 |
Linda | -0.010 |
eh | -0.010 |
Token | What |
Token ID | 2061 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
ind | +0.024 |
cha | +0.024 |
bicycles | +0.022 |
yacht | +0.022 |
appearance | +0.022 |
Neg logit contributions | |
opener | -0.036 |
aver | -0.033 |
inda | -0.032 |
eh | -0.030 |
Linda | -0.030 |
Token | are |
Token ID | 389 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
ind | +0.039 |
cha | +0.035 |
ranch | +0.033 |
yacht | +0.032 |
appearance | +0.031 |
Neg logit contributions | |
opener | -0.057 |
aver | -0.049 |
inda | -0.048 |
izzy | -0.046 |
one | -0.046 |
Token | you |
Token ID | 345 |
Feature activation | +9.59e-03 |
Pos logit contributions | |
cha | +0.015 |
ind | +0.014 |
yacht | +0.013 |
bicycles | +0.012 |
helicopter | +0.012 |
Neg logit contributions | |
opener | -0.053 |
aver | -0.051 |
inda | -0.049 |
eh | -0.047 |
Linda | -0.046 |
Token | doing |
Token ID | 1804 |
Feature activation | +8.34e-03 |
Pos logit contributions | |
opener | +0.021 |
aver | +0.020 |
inda | +0.019 |
Linda | +0.018 |
eh | +0.018 |
Neg logit contributions | |
cha | -0.012 |
ind | -0.012 |
bicycles | -0.011 |
helicopter | -0.010 |
yacht | -0.009 |
Token | |
Token ID | 220 |
Feature activation | +7.58e-02 |
Pos logit contributions | |
opener | +0.012 |
aver | +0.009 |
inda | +0.009 |
Linda | +0.009 |
Jill | +0.008 |
Neg logit contributions | |
ind | -0.017 |
cha | -0.017 |
bicycles | -0.016 |
appearance | -0.016 |
re | -0.015 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.28e-03 |
Pos logit contributions | |
aver | +0.121 |
opener | +0.119 |
inda | +0.110 |
Jen | +0.107 |
Linda | +0.107 |
Neg logit contributions | |
ind | -0.119 |
cha | -0.104 |
festival | -0.101 |
world | -0.100 |
mall | -0.099 |
Token | The |
Token ID | 383 |
Feature activation | -4.10e-03 |
Pos logit contributions | |
opener | +0.004 |
aver | +0.004 |
inda | +0.004 |
eh | +0.004 |
izzy | +0.004 |
Neg logit contributions | |
cha | -0.003 |
helicopter | -0.003 |
yacht | -0.003 |
billboard | -0.003 |
bicycles | -0.003 |
Token | tube |
Token ID | 12403 |
Feature activation | -5.79e-03 |
Pos logit contributions | |
yacht | +0.005 |
cha | +0.005 |
ind | +0.005 |
bicycles | +0.004 |
helicopter | +0.004 |
Neg logit contributions | |
opener | -0.009 |
aver | -0.008 |
inda | -0.008 |
eh | -0.008 |
avers | -0.008 |
Token | didn |
Token ID | 1422 |
Feature activation | -8.60e-04 |
Pos logit contributions | |
ind | +0.012 |
cha | +0.011 |
appearance | +0.011 |
bicycles | +0.010 |
ponies | +0.010 |
Neg logit contributions | |
opener | -0.008 |
aver | -0.008 |
inda | -0.007 |
Linda | -0.007 |
eh | -0.006 |
Token | 't |
Token ID | 470 |
Feature activation | +9.72e-03 |
Pos logit contributions | |
ind | +0.001 |
cha | +0.001 |
yacht | +0.001 |
helicopter | +0.001 |
festival | +0.001 |
Neg logit contributions | |
opener | -0.002 |
aver | -0.001 |
inda | -0.001 |
eh | -0.001 |
Linda | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.57e-03 |
Pos logit contributions | |
ind | +0.004 |
cha | +0.004 |
yacht | +0.004 |
bicycles | +0.004 |
helicopter | +0.004 |
Neg logit contributions | |
opener | -0.006 |
aver | -0.006 |
inda | -0.006 |
eh | -0.005 |
Linda | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
ind | +0.003 |
cha | +0.003 |
appearance | +0.003 |
bicycles | +0.003 |
yacht | +0.003 |
Neg logit contributions | |
opener | -0.002 |
aver | -0.002 |
inda | -0.002 |
Linda | -0.002 |
eh | -0.002 |
Token | Ready |
Token ID | 35474 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
ind | +0.027 |
cha | +0.026 |
bicycles | +0.024 |
re | +0.023 |
festival | +0.023 |
Neg logit contributions | |
opener | -0.044 |
aver | -0.040 |
inda | -0.040 |
Linda | -0.038 |
eh | -0.037 |
Token | for |
Token ID | 329 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
opener | +0.022 |
aver | +0.020 |
inda | +0.019 |
Linda | +0.018 |
eh | +0.018 |
Neg logit contributions | |
ind | -0.016 |
cha | -0.015 |
bicycles | -0.014 |
yacht | -0.014 |
appearance | -0.014 |
Token | take |
Token ID | 1011 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
cha | +0.018 |
ind | +0.017 |
re | +0.017 |
bicycles | +0.017 |
festival | +0.017 |
Neg logit contributions | |
opener | -0.020 |
aver | -0.019 |
inda | -0.018 |
izzy | -0.017 |
eh | -0.017 |
Token | - |
Token ID | 12 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
opener | +0.039 |
aver | +0.036 |
inda | +0.036 |
Linda | +0.034 |
eh | +0.034 |
Neg logit contributions | |
ind | -0.020 |
cha | -0.019 |
appearance | -0.018 |
yacht | -0.018 |
bicycles | -0.018 |
Token | off |
Token ID | 2364 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
opener | +0.142 |
aver | +0.125 |
inda | +0.124 |
Linda | +0.124 |
izzy | +0.117 |
Neg logit contributions | |
ind | -0.116 |
cha | -0.114 |
bicycles | -0.105 |
helicopter | -0.101 |
yacht | -0.099 |
Token | , |
Token ID | 11 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
opener | +0.052 |
aver | +0.048 |
inda | +0.046 |
Linda | +0.043 |
eh | +0.043 |
Neg logit contributions | |
ind | -0.037 |
cha | -0.036 |
bicycles | -0.034 |
yacht | -0.033 |
appearance | -0.033 |
Token | Mia |
Token ID | 32189 |
Feature activation | +1.66e-03 |
Pos logit contributions | |
opener | +0.054 |
aver | +0.050 |
inda | +0.047 |
Linda | +0.044 |
eh | +0.044 |
Neg logit contributions | |
ind | -0.053 |
cha | -0.052 |
bicycles | -0.048 |
appearance | -0.048 |
yacht | -0.048 |
Token | ?" |
Token ID | 1701 |
Feature activation | +5.35e-03 |
Pos logit contributions | |
opener | +0.003 |
aver | +0.003 |
inda | +0.003 |
eh | +0.003 |
Linda | +0.003 |
Neg logit contributions | |
ind | -0.003 |
cha | -0.003 |
bicycles | -0.002 |
appearance | -0.002 |
yacht | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +4.55e-03 |
Pos logit contributions | |
opener | +0.007 |
aver | +0.006 |
eh | +0.006 |
inda | +0.006 |
avers | +0.005 |
Neg logit contributions | |
cha | -0.010 |
mall | -0.010 |
bicycles | -0.010 |
village | -0.010 |
festival | -0.010 |
Token | they |
Token ID | 484 |
Feature activation | -8.73e-04 |
Pos logit contributions | |
ind | +0.015 |
cha | +0.014 |
bicycles | +0.013 |
appearance | +0.013 |
ranch | +0.013 |
Neg logit contributions | |
opener | -0.020 |
aver | -0.017 |
inda | -0.017 |
Linda | -0.016 |
Jill | -0.016 |
Token | didn |
Token ID | 1422 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
ind | +0.001 |
cha | +0.001 |
bicycles | +0.001 |
appearance | +0.001 |
helicopter | +0.001 |
Neg logit contributions | |
opener | -0.002 |
aver | -0.001 |
inda | -0.001 |
izzy | -0.001 |
avers | -0.001 |
Token | 't |
Token ID | 470 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
opener | +0.039 |
aver | +0.039 |
inda | +0.037 |
eh | +0.035 |
Linda | +0.034 |
Neg logit contributions | |
ind | -0.036 |
cha | -0.035 |
yacht | -0.033 |
helicopter | -0.033 |
bicycles | -0.032 |
Token | cost |
Token ID | 1575 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
opener | +0.019 |
aver | +0.017 |
inda | +0.017 |
eh | +0.016 |
Linda | +0.016 |
Neg logit contributions | |
ind | -0.015 |
cha | -0.015 |
yacht | -0.014 |
appearance | -0.014 |
bicycles | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
opener | +0.039 |
aver | +0.034 |
inda | +0.033 |
Linda | +0.031 |
eh | +0.031 |
Neg logit contributions | |
ind | -0.038 |
cha | -0.037 |
yacht | -0.035 |
appearance | -0.035 |
bicycles | -0.035 |
Token | lot |
Token ID | 1256 |
Feature activation | +7.38e-02 |
Pos logit contributions | |
opener | +0.036 |
aver | +0.032 |
inda | +0.030 |
eh | +0.030 |
Linda | +0.029 |
Neg logit contributions | |
ind | -0.028 |
cha | -0.028 |
bicycles | -0.025 |
appearance | -0.025 |
yacht | -0.025 |
Token | of |
Token ID | 286 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
aver | +0.111 |
opener | +0.107 |
inda | +0.107 |
eh | +0.102 |
Linda | +0.099 |
Neg logit contributions | |
ind | -0.128 |
cha | -0.122 |
yacht | -0.120 |
festival | -0.119 |
bicycles | -0.117 |
Token | money |
Token ID | 1637 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
opener | +0.038 |
aver | +0.031 |
Jill | +0.029 |
Jen | +0.029 |
Linda | +0.029 |
Neg logit contributions | |
ind | -0.042 |
cha | -0.042 |
yacht | -0.037 |
helicopter | -0.037 |
appearance | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +1.84e-03 |
Pos logit contributions | |
opener | +0.056 |
aver | +0.045 |
inda | +0.040 |
Jill | +0.039 |
Linda | +0.039 |
Neg logit contributions | |
ind | -0.067 |
cha | -0.065 |
appearance | -0.061 |
bicycles | -0.060 |
helicopter | -0.060 |
Token | Sometimes |
Token ID | 8975 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
opener | +0.003 |
aver | +0.003 |
inda | +0.003 |
eh | +0.003 |
Linda | +0.003 |
Neg logit contributions | |
ind | -0.003 |
cha | -0.003 |
yacht | -0.003 |
bicycles | -0.003 |
appearance | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
ind | +0.022 |
cha | +0.020 |
appearance | +0.018 |
uted | +0.018 |
ishly | +0.018 |
Neg logit contributions | |
opener | -0.019 |
aver | -0.016 |
Mia | -0.015 |
Jen | -0.015 |
Liz | -0.015 |
Token | no |
Token ID | 645 |
Feature activation | -6.98e-03 |
Pos logit contributions | |
opener | +0.013 |
aver | +0.012 |
inda | +0.011 |
eh | +0.011 |
Linda | +0.011 |
Neg logit contributions | |
ind | -0.010 |
cha | -0.010 |
yacht | -0.009 |
bicycles | -0.009 |
appearance | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
ind | +0.008 |
cha | +0.008 |
appearance | +0.008 |
re | +0.007 |
yacht | +0.007 |
Neg logit contributions | |
opener | -0.016 |
aver | -0.015 |
inda | -0.014 |
eh | -0.013 |
izzy | -0.013 |
Token | I |
Token ID | 314 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
opener | +0.052 |
aver | +0.046 |
Linda | +0.046 |
Liz | +0.045 |
Jill | +0.045 |
Neg logit contributions | |
ind | -0.056 |
cha | -0.049 |
ranch | -0.048 |
bicycles | -0.047 |
appearance | -0.046 |
Token | must |
Token ID | 1276 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
opener | +0.042 |
aver | +0.039 |
inda | +0.037 |
eh | +0.035 |
Linda | +0.035 |
Neg logit contributions | |
ind | -0.030 |
cha | -0.029 |
yacht | -0.026 |
appearance | -0.026 |
re | -0.026 |
Token | have |
Token ID | 423 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
opener | +0.028 |
aver | +0.026 |
inda | +0.024 |
eh | +0.023 |
Linda | +0.023 |
Neg logit contributions | |
ind | -0.025 |
cha | -0.025 |
bicycles | -0.023 |
yacht | -0.023 |
appearance | -0.023 |
Token | accidentally |
Token ID | 14716 |
Feature activation | +7.37e-02 |
Pos logit contributions | |
opener | +0.062 |
aver | +0.057 |
inda | +0.055 |
izzy | +0.052 |
Linda | +0.050 |
Neg logit contributions | |
cha | -0.047 |
ind | -0.046 |
yacht | -0.043 |
re | -0.043 |
appearance | -0.043 |
Token | spilled |
Token ID | 31896 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
opener | +0.132 |
aver | +0.120 |
inda | +0.116 |
izzy | +0.106 |
inn | +0.106 |
Neg logit contributions | |
cha | -0.118 |
ind | -0.116 |
yacht | -0.109 |
appearance | -0.108 |
bicycles | -0.108 |
Token | some |
Token ID | 617 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
opener | +0.051 |
aver | +0.044 |
inda | +0.043 |
Linda | +0.042 |
eh | +0.041 |
Neg logit contributions | |
ind | -0.047 |
cha | -0.044 |
bicycles | -0.041 |
appearance | -0.041 |
ranch | -0.041 |
Token | water |
Token ID | 1660 |
Feature activation | +5.61e-03 |
Pos logit contributions | |
opener | +0.018 |
aver | +0.016 |
inda | +0.016 |
Linda | +0.015 |
eh | +0.014 |
Neg logit contributions | |
ind | -0.019 |
cha | -0.018 |
yacht | -0.017 |
bicycles | -0.017 |
helicopter | -0.017 |
Token | on |
Token ID | 319 |
Feature activation | +1.80e-03 |
Pos logit contributions | |
opener | +0.009 |
aver | +0.008 |
inda | +0.007 |
eh | +0.007 |
izzy | +0.007 |
Neg logit contributions | |
ind | -0.010 |
cha | -0.010 |
bicycles | -0.009 |
appearance | -0.009 |
helicopter | -0.009 |
Token | it |
Token ID | 340 |
Feature activation | +6.00e-04 |
Pos logit contributions | |
opener | +0.003 |
aver | +0.003 |
inda | +0.003 |
Linda | +0.003 |
Jill | +0.003 |
Neg logit contributions | |
ind | -0.003 |
cha | -0.003 |
bicycles | -0.003 |
appearance | -0.003 |
yacht | -0.003 |
Token | said |
Token ID | 531 |
Feature activation | -2.97e-03 |
Pos logit contributions | |
ind | +0.025 |
cha | +0.024 |
appearance | +0.023 |
bicycles | +0.023 |
yacht | +0.023 |
Neg logit contributions | |
opener | -0.024 |
aver | -0.022 |
inda | -0.021 |
eh | -0.020 |
Linda | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -3.62e-04 |
Pos logit contributions | |
cha | +0.003 |
yacht | +0.002 |
helicopter | +0.002 |
re | +0.002 |
ind | +0.002 |
Neg logit contributions | |
opener | -0.007 |
inda | -0.007 |
aver | -0.007 |
izzy | -0.006 |
eh | -0.006 |
Token | " |
Token ID | 366 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
cha | +0.000 |
yacht | +0.000 |
re | +0.000 |
helicopter | +0.000 |
puppy | +0.000 |
Neg logit contributions | |
opener | -0.001 |
aver | -0.001 |
inda | -0.001 |
eh | -0.001 |
izzy | -0.001 |
Token | I |
Token ID | 40 |
Feature activation | -1.42e-03 |
Pos logit contributions | |
ind | +0.039 |
cha | +0.038 |
yacht | +0.035 |
bicycles | +0.035 |
appearance | +0.035 |
Neg logit contributions | |
opener | -0.048 |
aver | -0.044 |
inda | -0.042 |
eh | -0.040 |
Linda | -0.039 |
Token | have |
Token ID | 423 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
ind | +0.002 |
cha | +0.002 |
bicycles | +0.002 |
yacht | +0.002 |
appearance | +0.002 |
Neg logit contributions | |
opener | -0.003 |
aver | -0.003 |
inda | -0.003 |
eh | -0.002 |
Linda | -0.002 |
Token | lot |
Token ID | 1256 |
Feature activation | +7.35e-02 |
Pos logit contributions | |
opener | +0.047 |
aver | +0.041 |
inda | +0.039 |
izzy | +0.036 |
inn | +0.035 |
Neg logit contributions | |
ind | -0.067 |
cha | -0.066 |
bicycles | -0.063 |
yacht | -0.063 |
appearance | -0.062 |
Token | ion |
Token ID | 295 |
Feature activation | +4.06e-03 |
Pos logit contributions | |
inda | +0.127 |
aver | +0.121 |
opener | +0.120 |
Linda | +0.110 |
izzy | +0.109 |
Neg logit contributions | |
puppies | -0.108 |
re | -0.104 |
ponies | -0.103 |
ind | -0.100 |
bicycles | -0.100 |
Token | to |
Token ID | 284 |
Feature activation | -5.87e-03 |
Pos logit contributions | |
opener | +0.007 |
aver | +0.006 |
izzy | +0.005 |
inda | +0.005 |
Linda | +0.005 |
Neg logit contributions | |
ind | -0.007 |
appearance | -0.007 |
cha | -0.007 |
bicycles | -0.007 |
helicopter | -0.007 |
Token | make |
Token ID | 787 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
ind | +0.010 |
cha | +0.010 |
bicycles | +0.009 |
yacht | +0.009 |
appearance | +0.009 |
Neg logit contributions | |
opener | -0.010 |
aver | -0.009 |
inda | -0.008 |
Linda | -0.008 |
eh | -0.008 |
Token | your |
Token ID | 534 |
Feature activation | +2.69e-03 |
Pos logit contributions | |
opener | +0.031 |
aver | +0.028 |
inda | +0.027 |
eh | +0.026 |
Linda | +0.026 |
Neg logit contributions | |
ind | -0.020 |
cha | -0.019 |
yacht | -0.018 |
bicycles | -0.018 |
appearance | -0.018 |
Token | wings |
Token ID | 12098 |
Feature activation | -8.91e-03 |
Pos logit contributions | |
opener | +0.005 |
aver | +0.004 |
inda | +0.004 |
eh | +0.004 |
Linda | +0.004 |
Neg logit contributions | |
cha | -0.005 |
ind | -0.004 |
yacht | -0.004 |
bicycles | -0.004 |
festival | -0.004 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.75e-03 |
Pos logit contributions | |
opener | +0.067 |
aver | +0.060 |
inda | +0.057 |
Linda | +0.055 |
Jill | +0.052 |
Neg logit contributions | |
ind | -0.080 |
cha | -0.075 |
bicycles | -0.073 |
yacht | -0.072 |
helicopter | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
opener | +0.005 |
aver | +0.005 |
inda | +0.005 |
eh | +0.005 |
Linda | +0.005 |
Neg logit contributions | |
ind | -0.004 |
cha | -0.004 |
bicycles | -0.004 |
yacht | -0.004 |
appearance | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
opener | +0.025 |
aver | +0.023 |
inda | +0.023 |
Linda | +0.022 |
Jill | +0.022 |
Neg logit contributions | |
ind | -0.024 |
ranch | -0.021 |
bicycles | -0.020 |
cha | -0.020 |
yacht | -0.020 |
Token | 's |
Token ID | 338 |
Feature activation | -2.78e-03 |
Pos logit contributions | |
ind | +0.015 |
cha | +0.014 |
bicycles | +0.013 |
yacht | +0.013 |
appearance | +0.013 |
Neg logit contributions | |
opener | -0.025 |
aver | -0.024 |
inda | -0.023 |
eh | -0.022 |
izzy | -0.022 |
Token | not |
Token ID | 407 |
Feature activation | +4.41e-03 |
Pos logit contributions | |
ind | +0.004 |
cha | +0.004 |
appearance | +0.004 |
yacht | +0.004 |
bicycles | +0.004 |
Neg logit contributions | |
opener | -0.005 |
aver | -0.005 |
inda | -0.004 |
Linda | -0.004 |
izzy | -0.004 |
Token | |
Token ID | 220 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
opener | +0.008 |
aver | +0.008 |
inda | +0.007 |
eh | +0.007 |
Linda | +0.007 |
Neg logit contributions | |
ind | -0.007 |
cha | -0.007 |
bicycles | -0.006 |
yacht | -0.006 |
appearance | -0.006 |
Token | icky |
Token ID | 17479 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
aver | +0.103 |
opener | +0.101 |
Linda | +0.090 |
inda | +0.089 |
avers | +0.084 |
Neg logit contributions | |
ind | -0.131 |
cha | -0.123 |
aud | -0.112 |
aren | -0.110 |
aults | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | +3.22e-03 |
Pos logit contributions | |
opener | +0.022 |
aver | +0.020 |
inda | +0.019 |
eh | +0.018 |
izzy | +0.018 |
Neg logit contributions | |
ind | -0.023 |
cha | -0.022 |
yacht | -0.021 |
bicycles | -0.021 |
helicopter | -0.021 |
Token | It |
Token ID | 632 |
Feature activation | +6.27e-03 |
Pos logit contributions | |
opener | +0.006 |
aver | +0.006 |
inda | +0.006 |
eh | +0.005 |
avers | +0.005 |
Neg logit contributions | |
cha | -0.005 |
ind | -0.005 |
appearance | -0.004 |
yacht | -0.004 |
bicycles | -0.004 |
Token | 's |
Token ID | 338 |
Feature activation | +1.73e-03 |
Pos logit contributions | |
opener | +0.013 |
aver | +0.012 |
inda | +0.011 |
izzy | +0.011 |
eh | +0.011 |
Neg logit contributions | |
ind | -0.009 |
cha | -0.008 |
yacht | -0.008 |
bicycles | -0.008 |
appearance | -0.008 |
Token | soft |
Token ID | 2705 |
Feature activation | -8.33e-03 |
Pos logit contributions | |
opener | +0.003 |
aver | +0.003 |
inda | +0.003 |
eh | +0.003 |
Linda | +0.002 |
Neg logit contributions | |
cha | -0.003 |
ind | -0.003 |
bicycles | -0.003 |
yacht | -0.003 |
helicopter | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +9.60e-03 |
Pos logit contributions | |
opener | +0.066 |
aver | +0.057 |
inda | +0.053 |
one | +0.050 |
Jen | +0.050 |
Neg logit contributions | |
ind | -0.104 |
cha | -0.103 |
bicycles | -0.100 |
helicopter | -0.099 |
yacht | -0.098 |
Token | It |
Token ID | 632 |
Feature activation | +8.73e-03 |
Pos logit contributions | |
opener | +0.021 |
aver | +0.019 |
inda | +0.019 |
eh | +0.018 |
Linda | +0.017 |
Neg logit contributions | |
ind | -0.012 |
cha | -0.012 |
appearance | -0.010 |
yacht | -0.010 |
bicycles | -0.010 |
Token | is |
Token ID | 318 |
Feature activation | +7.89e-03 |
Pos logit contributions | |
opener | +0.019 |
aver | +0.018 |
inda | +0.017 |
izzy | +0.017 |
eh | +0.016 |
Neg logit contributions | |
ind | -0.011 |
cha | -0.010 |
bicycles | -0.010 |
appearance | -0.010 |
yacht | -0.010 |
Token | for |
Token ID | 329 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
opener | +0.013 |
aver | +0.012 |
inda | +0.011 |
eh | +0.010 |
Linda | +0.010 |
Neg logit contributions | |
ind | -0.014 |
cha | -0.014 |
bicycles | -0.013 |
yacht | -0.013 |
appearance | -0.013 |
Token | grown |
Token ID | 7334 |
Feature activation | +5.84e-02 |
Pos logit contributions | |
opener | +0.027 |
aver | +0.024 |
inda | +0.023 |
Linda | +0.023 |
Jill | +0.022 |
Neg logit contributions | |
cha | -0.021 |
ind | -0.021 |
bicycles | -0.020 |
helicopter | -0.020 |
yacht | -0.019 |
Token | - |
Token ID | 12 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
opener | +0.132 |
aver | +0.121 |
inda | +0.114 |
Linda | +0.111 |
izzy | +0.110 |
Neg logit contributions | |
ind | -0.079 |
cha | -0.065 |
appearance | -0.061 |
re | -0.059 |
bicycles | -0.057 |
Token | ups |
Token ID | 4739 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
opener | +0.114 |
aver | +0.103 |
inda | +0.094 |
Linda | +0.092 |
inn | +0.091 |
Neg logit contributions | |
ind | -0.144 |
cha | -0.136 |
ize | -0.120 |
pige | -0.120 |
bicycles | -0.120 |
Token | . |
Token ID | 13 |
Feature activation | +6.63e-03 |
Pos logit contributions | |
opener | +0.020 |
aver | +0.016 |
inda | +0.015 |
izzy | +0.015 |
one | +0.015 |
Neg logit contributions | |
cha | -0.034 |
helicopter | -0.034 |
yacht | -0.033 |
bicycles | -0.032 |
ind | -0.032 |
Token | You |
Token ID | 921 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
opener | +0.014 |
aver | +0.014 |
inda | +0.013 |
eh | +0.013 |
Linda | +0.012 |
Neg logit contributions | |
ind | -0.008 |
cha | -0.008 |
appearance | -0.007 |
yacht | -0.007 |
bicycles | -0.007 |
Token | could |
Token ID | 714 |
Feature activation | -3.30e-03 |
Pos logit contributions | |
opener | +0.050 |
aver | +0.046 |
inda | +0.044 |
izzy | +0.043 |
Linda | +0.041 |
Neg logit contributions | |
ind | -0.035 |
cha | -0.034 |
appearance | -0.032 |
bicycles | -0.031 |
yacht | -0.031 |
Token | get |
Token ID | 651 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
ind | +0.006 |
cha | +0.005 |
yacht | +0.005 |
bicycles | +0.005 |
appearance | +0.005 |
Neg logit contributions | |
opener | -0.006 |
aver | -0.005 |
inda | -0.005 |
eh | -0.005 |
Linda | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
opener | +0.029 |
aver | +0.027 |
inda | +0.026 |
eh | +0.024 |
izzy | +0.024 |
Neg logit contributions | |
cha | -0.023 |
ind | -0.023 |
yacht | -0.023 |
re | -0.022 |
helicopter | -0.022 |
Token | Let |
Token ID | 5756 |
Feature activation | -6.44e-03 |
Pos logit contributions | |
ind | +0.027 |
cha | +0.027 |
bicycles | +0.025 |
yacht | +0.024 |
festival | +0.024 |
Neg logit contributions | |
opener | -0.040 |
aver | -0.038 |
inda | -0.036 |
eh | -0.035 |
Linda | -0.034 |
Token | 's |
Token ID | 338 |
Feature activation | +7.15e-03 |
Pos logit contributions | |
ind | +0.011 |
bicycles | +0.011 |
yacht | +0.010 |
cha | +0.010 |
appearance | +0.010 |
Neg logit contributions | |
inda | -0.009 |
aver | -0.009 |
Linda | -0.009 |
opener | -0.009 |
eh | -0.008 |
Token | play |
Token ID | 711 |
Feature activation | -8.58e-04 |
Pos logit contributions | |
opener | +0.012 |
aver | +0.010 |
inda | +0.010 |
Linda | +0.010 |
Liz | +0.010 |
Neg logit contributions | |
ind | -0.013 |
cha | -0.012 |
appearance | -0.011 |
ponies | -0.011 |
bicycles | -0.011 |
Token | hide |
Token ID | 7808 |
Feature activation | -3.83e-03 |
Pos logit contributions | |
ind | +0.002 |
cha | +0.002 |
appearance | +0.001 |
bicycles | +0.001 |
yacht | +0.001 |
Neg logit contributions | |
opener | -0.001 |
aver | -0.001 |
inda | -0.001 |
Linda | -0.001 |
eh | -0.001 |
Token | - |
Token ID | 12 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
appearance | +0.005 |
ind | +0.005 |
cha | +0.005 |
bicycles | +0.005 |
yacht | +0.005 |
Neg logit contributions | |
opener | -0.007 |
inda | -0.007 |
aver | -0.007 |
Linda | -0.006 |
eh | -0.006 |
Token | and |
Token ID | 392 |
Feature activation | +8.89e-03 |
Pos logit contributions | |
opener | +0.134 |
aver | +0.123 |
Linda | +0.115 |
inda | +0.114 |
inn | +0.110 |
Neg logit contributions | |
ind | -0.112 |
cha | -0.107 |
bicycles | -0.099 |
festival | -0.094 |
yacht | -0.094 |
Token | - |
Token ID | 12 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
opener | +0.016 |
aver | +0.015 |
inda | +0.015 |
eh | +0.014 |
Linda | +0.014 |
Neg logit contributions | |
ind | -0.014 |
cha | -0.013 |
appearance | -0.013 |
yacht | -0.013 |
bicycles | -0.013 |
Token | seek |
Token ID | 36163 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
opener | +0.089 |
aver | +0.081 |
inda | +0.073 |
Linda | +0.072 |
izzy | +0.067 |
Neg logit contributions | |
cha | -0.125 |
ind | -0.124 |
bicycles | -0.116 |
festival | -0.111 |
yacht | -0.110 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
opener | +0.033 |
aver | +0.029 |
inda | +0.028 |
Jill | +0.027 |
Linda | +0.027 |
Neg logit contributions | |
ind | -0.031 |
cha | -0.029 |
appearance | -0.028 |
yacht | -0.028 |
helicopter | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
opener | +0.022 |
aver | +0.021 |
inda | +0.020 |
eh | +0.019 |
izzy | +0.018 |
Neg logit contributions | |
cha | -0.019 |
yacht | -0.018 |
ind | -0.018 |
helicopter | -0.018 |
re | -0.018 |
Token | pile |
Token ID | 14540 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
ind | +0.014 |
cha | +0.014 |
bicycles | +0.013 |
appearance | +0.013 |
re | +0.012 |
Neg logit contributions | |
opener | -0.017 |
aver | -0.015 |
inda | -0.015 |
Linda | -0.014 |
eh | -0.014 |
Token | of |
Token ID | 286 |
Feature activation | +1.39e-04 |
Pos logit contributions | |
opener | +0.033 |
aver | +0.030 |
inda | +0.028 |
eh | +0.026 |
Linda | +0.025 |
Neg logit contributions | |
ind | -0.048 |
cha | -0.048 |
yacht | -0.045 |
bicycles | -0.045 |
appearance | -0.045 |
Token | paw |
Token ID | 41827 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
opener | +0.000 |
aver | +0.000 |
Linda | +0.000 |
inda | +0.000 |
Jill | +0.000 |
Neg logit contributions | |
cha | -0.000 |
ind | -0.000 |
appearance | -0.000 |
bicycles | -0.000 |
uted | -0.000 |
Token | prints |
Token ID | 20842 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
opener | +0.037 |
aver | +0.033 |
inda | +0.032 |
eh | +0.030 |
Linda | +0.030 |
Neg logit contributions | |
ind | -0.034 |
cha | -0.032 |
appearance | -0.030 |
bicycles | -0.030 |
yacht | -0.030 |
Token | " |
Token ID | 1 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
opener | +0.049 |
aver | +0.044 |
inda | +0.042 |
Linda | +0.039 |
eh | +0.039 |
Neg logit contributions | |
ind | -0.044 |
cha | -0.042 |
appearance | -0.040 |
bicycles | -0.039 |
yacht | -0.038 |
Token | |
Token ID | 220 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
opener | +0.090 |
aver | +0.082 |
inda | +0.078 |
eh | +0.074 |
Linda | +0.073 |
Neg logit contributions | |
ind | -0.081 |
cha | -0.080 |
bicycles | -0.075 |
yacht | -0.074 |
appearance | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | +8.87e-03 |
Pos logit contributions | |
opener | +0.106 |
aver | +0.102 |
inda | +0.095 |
Linda | +0.094 |
Liz | +0.093 |
Neg logit contributions | |
ind | -0.120 |
cha | -0.107 |
aults | -0.102 |
uted | -0.098 |
ize | -0.097 |
Token |
|
Token ID | 198 |
Feature activation | -3.61e-04 |
Pos logit contributions | |
opener | +0.016 |
aver | +0.015 |
inda | +0.014 |
eh | +0.014 |
Linda | +0.013 |
Neg logit contributions | |
ind | -0.014 |
cha | -0.013 |
bicycles | -0.012 |
re | -0.012 |
helicopter | -0.012 |
Token | L |
Token ID | 43 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
ind | +0.001 |
cha | +0.001 |
yacht | +0.001 |
bicycles | +0.001 |
helicopter | +0.001 |
Neg logit contributions | |
opener | -0.001 |
aver | -0.001 |
inda | -0.001 |
eh | -0.001 |
Linda | -0.001 |
Token | ucky |
Token ID | 5309 |
Feature activation | +2.69e-03 |
Pos logit contributions | |
opener | +0.051 |
Liz | +0.042 |
aver | +0.041 |
Jen | +0.039 |
Linda | +0.037 |
Neg logit contributions | |
cha | -0.068 |
ind | -0.066 |
iling | -0.063 |
puppies | -0.062 |
aren | -0.059 |
Token | smiled |
Token ID | 13541 |
Feature activation | +6.09e-03 |
Pos logit contributions | |
opener | +0.005 |
aver | +0.005 |
inda | +0.005 |
Linda | +0.004 |
eh | +0.004 |
Neg logit contributions | |
ind | -0.004 |
cha | -0.004 |
bicycles | -0.004 |
yacht | -0.004 |
appearance | -0.004 |
Token | heard |
Token ID | 2982 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
cha | +0.029 |
ind | +0.029 |
re | +0.027 |
yacht | +0.027 |
bicycles | +0.027 |
Neg logit contributions | |
opener | -0.035 |
aver | -0.032 |
inda | -0.031 |
Linda | -0.029 |
eh | -0.029 |
Token | them |
Token ID | 606 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
opener | +0.079 |
aver | +0.074 |
inda | +0.071 |
Linda | +0.068 |
Liz | +0.066 |
Neg logit contributions | |
cha | -0.052 |
ind | -0.052 |
yacht | -0.048 |
bicycles | -0.047 |
festival | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | +4.72e-03 |
Pos logit contributions | |
opener | +0.028 |
Liz | +0.017 |
inda | +0.017 |
izzy | +0.016 |
Mia | +0.016 |
Neg logit contributions | |
cha | -0.059 |
ind | -0.058 |
festival | -0.055 |
yacht | -0.054 |
culture | -0.053 |
Token | No |
Token ID | 1400 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
opener | +0.009 |
aver | +0.009 |
inda | +0.008 |
eh | +0.008 |
avers | +0.007 |
Neg logit contributions | |
ind | -0.007 |
cha | -0.007 |
bicycles | -0.006 |
appearance | -0.006 |
yacht | -0.006 |
Token | one |
Token ID | 530 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
re | +0.017 |
appearance | +0.017 |
cha | +0.017 |
puppies | +0.016 |
ind | +0.016 |
Neg logit contributions | |
opener | -0.020 |
aver | -0.018 |
inda | -0.018 |
eh | -0.017 |
izzy | -0.016 |
Token | came |
Token ID | 1625 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
ind | +0.029 |
cha | +0.028 |
yacht | +0.026 |
bicycles | +0.026 |
appearance | +0.026 |
Neg logit contributions | |
opener | -0.028 |
aver | -0.026 |
inda | -0.024 |
eh | -0.023 |
Linda | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
opener | +0.110 |
aver | +0.099 |
inda | +0.094 |
Linda | +0.087 |
eh | +0.087 |
Neg logit contributions | |
cha | -0.129 |
ind | -0.129 |
yacht | -0.121 |
bicycles | -0.120 |
festival | -0.119 |
Token | help |
Token ID | 1037 |
Feature activation | +8.69e-03 |
Pos logit contributions | |
opener | +0.022 |
aver | +0.020 |
inda | +0.019 |
eh | +0.018 |
izzy | +0.018 |
Neg logit contributions | |
ind | -0.028 |
cha | -0.027 |
yacht | -0.026 |
appearance | -0.026 |
bicycles | -0.026 |
Token | them |
Token ID | 606 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
opener | +0.016 |
aver | +0.014 |
inda | +0.014 |
Linda | +0.013 |
Liz | +0.013 |
Neg logit contributions | |
ind | -0.014 |
cha | -0.014 |
bicycles | -0.013 |
yacht | -0.013 |
festival | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +2.39e-03 |
Pos logit contributions | |
opener | +0.019 |
aver | +0.014 |
inda | +0.013 |
izzy | +0.013 |
Liz | +0.013 |
Neg logit contributions | |
ind | -0.031 |
cha | -0.030 |
bicycles | -0.028 |
festival | -0.028 |
helicopter | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +4.19e-03 |
Pos logit contributions | |
opener | +0.005 |
aver | +0.004 |
inda | +0.004 |
eh | +0.004 |
Linda | +0.004 |
Neg logit contributions | |
ind | -0.004 |
cha | -0.003 |
bicycles | -0.003 |
appearance | -0.003 |
yacht | -0.003 |
Token | their |
Token ID | 511 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
opener | +0.072 |
aver | +0.064 |
inda | +0.060 |
eh | +0.060 |
inn | +0.057 |
Neg logit contributions | |
ind | -0.050 |
cha | -0.049 |
bicycles | -0.045 |
helicopter | -0.045 |
appearance | -0.044 |
Token | cries |
Token ID | 24691 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
opener | +0.021 |
aver | +0.018 |
inda | +0.018 |
Liz | +0.017 |
Linda | +0.017 |
Neg logit contributions | |
cha | -0.021 |
ind | -0.020 |
festival | -0.019 |
yacht | -0.019 |
ranch | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +9.37e-03 |
Pos logit contributions | |
opener | +0.034 |
aver | +0.031 |
inda | +0.030 |
Linda | +0.028 |
izzy | +0.028 |
Neg logit contributions | |
ind | -0.026 |
cha | -0.026 |
yacht | -0.024 |
bicycles | -0.024 |
festival | -0.024 |
Token | No |
Token ID | 1400 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
opener | +0.018 |
aver | +0.016 |
inda | +0.016 |
eh | +0.015 |
avers | +0.014 |
Neg logit contributions | |
ind | -0.014 |
cha | -0.014 |
appearance | -0.013 |
bicycles | -0.013 |
yacht | -0.013 |
Token | one |
Token ID | 530 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
appearance | +0.021 |
cha | +0.020 |
bell | +0.020 |
re | +0.020 |
aren | +0.020 |
Neg logit contributions | |
opener | -0.024 |
aver | -0.022 |
eh | -0.021 |
avers | -0.020 |
inn | -0.020 |
Token | came |
Token ID | 1625 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
cha | +0.023 |
ind | +0.023 |
bicycles | +0.021 |
appearance | +0.021 |
yacht | +0.021 |
Neg logit contributions | |
opener | -0.025 |
aver | -0.023 |
inda | -0.022 |
eh | -0.021 |
Linda | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
opener | +0.119 |
aver | +0.107 |
inda | +0.100 |
eh | +0.095 |
Linda | +0.093 |
Neg logit contributions | |
ind | -0.125 |
cha | -0.119 |
appearance | -0.113 |
bicycles | -0.113 |
yacht | -0.111 |
Token | help |
Token ID | 1037 |
Feature activation | +8.88e-03 |
Pos logit contributions | |
opener | +0.020 |
aver | +0.019 |
inda | +0.018 |
eh | +0.017 |
izzy | +0.017 |
Neg logit contributions | |
ind | -0.019 |
cha | -0.019 |
appearance | -0.018 |
yacht | -0.018 |
re | -0.018 |
Token | them |
Token ID | 606 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
opener | +0.018 |
aver | +0.017 |
inda | +0.016 |
eh | +0.016 |
avers | +0.015 |
Neg logit contributions | |
ind | -0.012 |
cha | -0.012 |
bicycles | -0.011 |
appearance | -0.011 |
yacht | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +5.79e-03 |
Pos logit contributions | |
opener | +0.020 |
aver | +0.015 |
inda | +0.015 |
Liz | +0.014 |
izzy | +0.014 |
Neg logit contributions | |
ind | -0.030 |
cha | -0.029 |
festival | -0.027 |
bicycles | -0.027 |
yacht | -0.026 |
Token | They |
Token ID | 1119 |
Feature activation | +8.19e-03 |
Pos logit contributions | |
opener | +0.011 |
aver | +0.010 |
inda | +0.010 |
eh | +0.009 |
avers | +0.009 |
Neg logit contributions | |
ind | -0.009 |
cha | -0.009 |
appearance | -0.008 |
bicycles | -0.008 |
yacht | -0.008 |
Token | he |
Token ID | 339 |
Feature activation | -5.81e-03 |
Pos logit contributions | |
opener | +0.008 |
aver | +0.007 |
inda | +0.007 |
Linda | +0.007 |
Jill | +0.007 |
Neg logit contributions | |
ind | -0.009 |
cha | -0.009 |
bicycles | -0.008 |
helicopter | -0.008 |
appearance | -0.008 |
Token | didn |
Token ID | 1422 |
Feature activation | +6.83e-03 |
Pos logit contributions | |
ind | +0.009 |
cha | +0.009 |
appearance | +0.009 |
bicycles | +0.008 |
yacht | +0.008 |
Neg logit contributions | |
opener | -0.011 |
aver | -0.010 |
inda | -0.009 |
Linda | -0.008 |
izzy | -0.008 |
Token | 't |
Token ID | 470 |
Feature activation | +7.47e-03 |
Pos logit contributions | |
aver | +0.013 |
opener | +0.012 |
inda | +0.012 |
eh | +0.012 |
Linda | +0.011 |
Neg logit contributions | |
ind | -0.010 |
cha | -0.010 |
helicopter | -0.009 |
yacht | -0.009 |
bicycles | -0.009 |
Token | want |
Token ID | 765 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
opener | +0.014 |
aver | +0.013 |
inda | +0.012 |
eh | +0.012 |
Linda | +0.012 |
Neg logit contributions | |
ind | -0.011 |
cha | -0.011 |
yacht | -0.010 |
appearance | -0.010 |
re | -0.010 |
Token | L |
Token ID | 406 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
opener | +0.020 |
aver | +0.019 |
inda | +0.017 |
eh | +0.017 |
avers | +0.016 |
Neg logit contributions | |
ind | -0.024 |
cha | -0.024 |
appearance | -0.023 |
bicycles | -0.023 |
yacht | -0.022 |
Token | yl |
Token ID | 2645 |
Feature activation | +7.02e-02 |
Pos logit contributions | |
opener | +0.071 |
aver | +0.063 |
eh | +0.056 |
inda | +0.054 |
avers | +0.053 |
Neg logit contributions | |
ind | -0.086 |
cha | -0.085 |
mall | -0.076 |
ize | -0.074 |
appearance | -0.074 |
Token | a |
Token ID | 64 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
opener | +0.108 |
aver | +0.088 |
inn | +0.078 |
Linda | +0.078 |
inda | +0.076 |
Neg logit contributions | |
ind | -0.140 |
cha | -0.134 |
bicycles | -0.124 |
appearance | -0.124 |
helicopter | -0.123 |
Token | to |
Token ID | 284 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
opener | +0.061 |
aver | +0.054 |
inda | +0.054 |
Linda | +0.050 |
Jill | +0.048 |
Neg logit contributions | |
ind | -0.084 |
cha | -0.080 |
bicycles | -0.076 |
helicopter | -0.075 |
yacht | -0.074 |
Token | be |
Token ID | 307 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
opener | +0.026 |
aver | +0.023 |
Jen | +0.022 |
Jill | +0.021 |
inda | +0.021 |
Neg logit contributions | |
cha | -0.026 |
ind | -0.026 |
bicycles | -0.024 |
helicopter | -0.023 |
festival | -0.022 |
Token | unhappy |
Token ID | 19283 |
Feature activation | +6.64e-03 |
Pos logit contributions | |
opener | +0.073 |
aver | +0.068 |
inda | +0.065 |
eh | +0.062 |
Linda | +0.061 |
Neg logit contributions | |
ind | -0.052 |
cha | -0.051 |
bicycles | -0.047 |
yacht | -0.047 |
appearance | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +2.82e-03 |
Pos logit contributions | |
opener | +0.009 |
Jill | +0.007 |
aver | +0.007 |
inda | +0.007 |
Linda | +0.006 |
Neg logit contributions | |
ind | -0.015 |
cha | -0.014 |
yacht | -0.013 |
helicopter | -0.013 |
bicycles | -0.013 |
Token | " |
Token ID | 1 |
Feature activation | -8.65e-03 |
Pos logit contributions | |
opener | +0.002 |
aver | +0.002 |
inda | +0.002 |
Linda | +0.002 |
izzy | +0.002 |
Neg logit contributions | |
ind | -0.002 |
cha | -0.002 |
re | -0.001 |
helicopter | -0.001 |
festival | -0.001 |
Token | Let |
Token ID | 5756 |
Feature activation | -2.30e-03 |
Pos logit contributions | |
cha | +0.010 |
ind | +0.010 |
bicycles | +0.009 |
festival | +0.009 |
yacht | +0.009 |
Neg logit contributions | |
opener | -0.018 |
aver | -0.018 |
inda | -0.018 |
Linda | -0.017 |
eh | -0.017 |
Token | 's |
Token ID | 338 |
Feature activation | +5.04e-03 |
Pos logit contributions | |
ind | +0.004 |
cha | +0.004 |
appearance | +0.004 |
bicycles | +0.004 |
mall | +0.004 |
Neg logit contributions | |
inda | -0.003 |
opener | -0.003 |
aver | -0.003 |
eh | -0.003 |
Linda | -0.003 |
Token | play |
Token ID | 711 |
Feature activation | -3.67e-03 |
Pos logit contributions | |
opener | +0.009 |
aver | +0.008 |
inda | +0.008 |
Linda | +0.008 |
eh | +0.007 |
Neg logit contributions | |
ind | -0.008 |
cha | -0.008 |
bicycles | -0.007 |
appearance | -0.007 |
helicopter | -0.007 |
Token | tug |
Token ID | 27762 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
ind | +0.007 |
cha | +0.006 |
appearance | +0.006 |
bicycles | +0.006 |
yacht | +0.006 |
Neg logit contributions | |
opener | -0.006 |
aver | -0.006 |
inda | -0.005 |
Linda | -0.005 |
eh | -0.005 |
Token | - |
Token ID | 12 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
opener | +0.027 |
inda | +0.026 |
aver | +0.025 |
inn | +0.025 |
Linda | +0.023 |
Neg logit contributions | |
appearance | -0.027 |
ranch | -0.026 |
ind | -0.026 |
mall | -0.026 |
difference | -0.025 |
Token | of |
Token ID | 1659 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
opener | +0.117 |
aver | +0.113 |
inda | +0.098 |
Linda | +0.098 |
avers | +0.095 |
Neg logit contributions | |
ind | -0.117 |
cha | -0.115 |
ize | -0.102 |
bicycles | -0.101 |
festival | -0.099 |
Token | - |
Token ID | 12 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
opener | +0.047 |
aver | +0.042 |
inda | +0.042 |
eh | +0.040 |
izzy | +0.040 |
Neg logit contributions | |
ind | -0.046 |
appearance | -0.045 |
cha | -0.044 |
ranch | -0.044 |
mall | -0.043 |
Token | war |
Token ID | 5767 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
opener | +0.116 |
aver | +0.111 |
Linda | +0.098 |
inda | +0.098 |
avers | +0.094 |
Neg logit contributions | |
ind | -0.111 |
cha | -0.109 |
bicycles | -0.096 |
ize | -0.096 |
festival | -0.093 |
Token | ," |
Token ID | 553 |
Feature activation | -4.97e-04 |
Pos logit contributions | |
opener | +0.045 |
aver | +0.040 |
inda | +0.038 |
Linda | +0.035 |
eh | +0.035 |
Neg logit contributions | |
ind | -0.037 |
cha | -0.036 |
appearance | -0.035 |
yacht | -0.034 |
bicycles | -0.033 |
Token | said |
Token ID | 531 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
ind | +0.001 |
cha | +0.001 |
appearance | +0.001 |
bicycles | +0.001 |
yacht | +0.001 |
Neg logit contributions | |
opener | -0.001 |
aver | -0.001 |
inda | -0.001 |
Linda | -0.001 |
eh | -0.001 |
Token | It |
Token ID | 632 |
Feature activation | +4.94e-03 |
Pos logit contributions | |
opener | +0.005 |
aver | +0.005 |
inda | +0.005 |
eh | +0.005 |
avers | +0.005 |
Neg logit contributions | |
cha | -0.003 |
ind | -0.003 |
appearance | -0.003 |
aren | -0.003 |
bicycles | -0.003 |
Token | is |
Token ID | 318 |
Feature activation | +6.03e-04 |
Pos logit contributions | |
opener | +0.010 |
aver | +0.009 |
inda | +0.009 |
izzy | +0.008 |
eh | +0.008 |
Neg logit contributions | |
ind | -0.007 |
cha | -0.006 |
bicycles | -0.006 |
yacht | -0.006 |
appearance | -0.006 |
Token | only |
Token ID | 691 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
opener | +0.001 |
aver | +0.001 |
inda | +0.001 |
eh | +0.001 |
Linda | +0.001 |
Neg logit contributions | |
ind | -0.001 |
cha | -0.001 |
bicycles | -0.001 |
yacht | -0.001 |
appearance | -0.001 |
Token | for |
Token ID | 329 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
opener | +0.016 |
aver | +0.015 |
inda | +0.014 |
eh | +0.013 |
Linda | +0.013 |
Neg logit contributions | |
ind | -0.020 |
cha | -0.019 |
bicycles | -0.018 |
yacht | -0.018 |
appearance | -0.018 |
Token | grown |
Token ID | 7334 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
opener | +0.022 |
aver | +0.019 |
inda | +0.019 |
Linda | +0.018 |
Jill | +0.018 |
Neg logit contributions | |
cha | -0.016 |
ind | -0.016 |
ranch | -0.015 |
helicopter | -0.015 |
yacht | -0.015 |
Token | - |
Token ID | 12 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
opener | +0.119 |
aver | +0.109 |
inda | +0.104 |
Linda | +0.101 |
izzy | +0.101 |
Neg logit contributions | |
ind | -0.071 |
cha | -0.058 |
appearance | -0.056 |
re | -0.053 |
bicycles | -0.052 |
Token | ups |
Token ID | 4739 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
opener | +0.105 |
aver | +0.095 |
inda | +0.089 |
Linda | +0.087 |
inn | +0.082 |
Neg logit contributions | |
ind | -0.143 |
cha | -0.135 |
bicycles | -0.121 |
appearance | -0.120 |
ize | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | +3.34e-03 |
Pos logit contributions | |
opener | +0.020 |
aver | +0.015 |
one | +0.015 |
inda | +0.015 |
izzy | +0.015 |
Neg logit contributions | |
cha | -0.033 |
helicopter | -0.033 |
yacht | -0.033 |
ind | -0.032 |
bicycles | -0.032 |
Token | You |
Token ID | 921 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
opener | +0.007 |
aver | +0.007 |
inda | +0.007 |
eh | +0.006 |
avers | +0.006 |
Neg logit contributions | |
ind | -0.004 |
cha | -0.004 |
appearance | -0.004 |
bicycles | -0.003 |
yacht | -0.003 |
Token | are |
Token ID | 389 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
opener | +0.043 |
aver | +0.037 |
inda | +0.035 |
izzy | +0.035 |
Linda | +0.033 |
Neg logit contributions | |
ind | -0.037 |
cha | -0.035 |
appearance | -0.033 |
bicycles | -0.032 |
ranch | -0.032 |
Token | still |
Token ID | 991 |
Feature activation | +2.78e-03 |
Pos logit contributions | |
ind | +0.016 |
cha | +0.016 |
bicycles | +0.015 |
appearance | +0.015 |
yacht | +0.015 |
Neg logit contributions | |
opener | -0.019 |
aver | -0.018 |
inda | -0.017 |
eh | -0.016 |
Linda | -0.016 |
Token | " |
Token ID | 366 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
opener | +0.006 |
aver | +0.005 |
inda | +0.005 |
Linda | +0.005 |
eh | +0.004 |
Neg logit contributions | |
ind | -0.010 |
cha | -0.009 |
bicycles | -0.009 |
appearance | -0.009 |
festival | -0.009 |
Token | I |
Token ID | 40 |
Feature activation | +5.67e-03 |
Pos logit contributions | |
ind | +0.032 |
cha | +0.032 |
bicycles | +0.029 |
appearance | +0.027 |
yacht | +0.027 |
Neg logit contributions | |
opener | -0.052 |
aver | -0.047 |
inda | -0.045 |
eh | -0.044 |
Linda | -0.042 |
Token | 'm |
Token ID | 1101 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
opener | +0.009 |
aver | +0.009 |
inda | +0.008 |
eh | +0.008 |
Linda | +0.008 |
Neg logit contributions | |
ind | -0.010 |
cha | -0.010 |
yacht | -0.009 |
appearance | -0.009 |
bicycles | -0.009 |
Token | playing |
Token ID | 2712 |
Feature activation | +3.71e-03 |
Pos logit contributions | |
opener | +0.028 |
aver | +0.026 |
inda | +0.025 |
eh | +0.024 |
Linda | +0.024 |
Neg logit contributions | |
ind | -0.016 |
cha | -0.016 |
yacht | -0.014 |
bicycles | -0.014 |
appearance | -0.014 |
Token | hide |
Token ID | 7808 |
Feature activation | -1.90e-03 |
Pos logit contributions | |
opener | +0.006 |
aver | +0.005 |
inda | +0.005 |
Linda | +0.005 |
eh | +0.005 |
Neg logit contributions | |
ind | -0.007 |
appearance | -0.006 |
cha | -0.006 |
bicycles | -0.006 |
yacht | -0.006 |
Token | - |
Token ID | 12 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
ind | +0.003 |
appearance | +0.003 |
yacht | +0.003 |
bicycles | +0.003 |
cha | +0.003 |
Neg logit contributions | |
opener | -0.003 |
inda | -0.003 |
aver | -0.003 |
Linda | -0.003 |
eh | -0.003 |
Token | and |
Token ID | 392 |
Feature activation | +8.98e-03 |
Pos logit contributions | |
opener | +0.128 |
aver | +0.117 |
Linda | +0.108 |
inda | +0.108 |
inn | +0.104 |
Neg logit contributions | |
ind | -0.110 |
cha | -0.105 |
bicycles | -0.096 |
festival | -0.092 |
helicopter | -0.091 |
Token | - |
Token ID | 12 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
opener | +0.017 |
aver | +0.016 |
inda | +0.015 |
Linda | +0.014 |
eh | +0.014 |
Neg logit contributions | |
ind | -0.013 |
cha | -0.013 |
yacht | -0.012 |
appearance | -0.012 |
bicycles | -0.012 |
Token | seek |
Token ID | 36163 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
opener | +0.074 |
aver | +0.067 |
inda | +0.061 |
Linda | +0.057 |
izzy | +0.054 |
Neg logit contributions | |
cha | -0.115 |
ind | -0.113 |
bicycles | -0.106 |
festival | -0.102 |
helicopter | -0.100 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
opener | +0.040 |
aver | +0.035 |
inda | +0.035 |
Linda | +0.033 |
Jill | +0.033 |
Neg logit contributions | |
ind | -0.039 |
cha | -0.037 |
yacht | -0.037 |
helicopter | -0.036 |
appearance | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | +6.29e-03 |
Pos logit contributions | |
opener | +0.019 |
aver | +0.018 |
inda | +0.017 |
eh | +0.016 |
avers | +0.015 |
Neg logit contributions | |
cha | -0.016 |
ind | -0.016 |
bicycles | -0.015 |
yacht | -0.015 |
appearance | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -8.88e-04 |
Pos logit contributions | |
opener | +0.046 |
aver | +0.038 |
inda | +0.037 |
eh | +0.034 |
Linda | +0.034 |
Neg logit contributions | |
ind | -0.059 |
cha | -0.057 |
helicopter | -0.054 |
yacht | -0.054 |
festival | -0.054 |
Token | It |
Token ID | 632 |
Feature activation | +6.04e-03 |
Pos logit contributions | |
cha | +0.001 |
ind | +0.001 |
appearance | +0.001 |
yacht | +0.001 |
bicycles | +0.001 |
Neg logit contributions | |
opener | -0.002 |
aver | -0.002 |
inda | -0.002 |
eh | -0.002 |
avers | -0.001 |
Token | is |
Token ID | 318 |
Feature activation | +2.51e-03 |
Pos logit contributions | |
opener | +0.012 |
aver | +0.011 |
inda | +0.010 |
izzy | +0.010 |
eh | +0.010 |
Neg logit contributions | |
ind | -0.009 |
cha | -0.008 |
appearance | -0.008 |
bicycles | -0.008 |
yacht | -0.008 |
Token | for |
Token ID | 329 |
Feature activation | +8.92e-03 |
Pos logit contributions | |
opener | +0.004 |
aver | +0.004 |
inda | +0.004 |
eh | +0.004 |
Linda | +0.003 |
Neg logit contributions | |
cha | -0.004 |
ind | -0.004 |
bicycles | -0.004 |
yacht | -0.004 |
appearance | -0.004 |
Token | grown |
Token ID | 7334 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
opener | +0.017 |
aver | +0.015 |
inda | +0.014 |
eh | +0.014 |
Jill | +0.014 |
Neg logit contributions | |
ind | -0.013 |
cha | -0.013 |
bicycles | -0.012 |
helicopter | -0.012 |
ranch | -0.012 |
Token | - |
Token ID | 12 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
opener | +0.122 |
aver | +0.113 |
inda | +0.107 |
Linda | +0.105 |
izzy | +0.104 |
Neg logit contributions | |
ind | -0.071 |
cha | -0.057 |
re | -0.053 |
appearance | -0.052 |
forever | -0.049 |
Token | ups |
Token ID | 4739 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
opener | +0.103 |
aver | +0.093 |
inda | +0.089 |
Linda | +0.089 |
Liz | +0.080 |
Neg logit contributions | |
ind | -0.139 |
cha | -0.132 |
ize | -0.118 |
bicycles | -0.116 |
yacht | -0.116 |
Token | . |
Token ID | 13 |
Feature activation | +1.77e-04 |
Pos logit contributions | |
opener | +0.016 |
aver | +0.012 |
inda | +0.011 |
izzy | +0.011 |
one | +0.011 |
Neg logit contributions | |
cha | -0.021 |
yacht | -0.021 |
helicopter | -0.021 |
ind | -0.021 |
bicycles | -0.021 |
Token | It |
Token ID | 632 |
Feature activation | +4.18e-03 |
Pos logit contributions | |
opener | +0.000 |
aver | +0.000 |
inda | +0.000 |
eh | +0.000 |
izzy | +0.000 |
Neg logit contributions | |
ind | -0.000 |
cha | -0.000 |
appearance | -0.000 |
yacht | -0.000 |
bicycles | -0.000 |
Token | has |
Token ID | 468 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
opener | +0.008 |
aver | +0.007 |
inda | +0.007 |
izzy | +0.007 |
eh | +0.007 |
Neg logit contributions | |
ind | -0.006 |
cha | -0.006 |
bicycles | -0.006 |
appearance | -0.006 |
yacht | -0.005 |
Token | nuts |
Token ID | 14380 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
opener | +0.053 |
aver | +0.047 |
inda | +0.045 |
eh | +0.042 |
Linda | +0.042 |
Neg logit contributions | |
ind | -0.057 |
cha | -0.056 |
yacht | -0.052 |
bicycles | -0.052 |
appearance | -0.051 |
Token | " |
Token ID | 366 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
ind | +0.010 |
cha | +0.009 |
appearance | +0.009 |
bicycles | +0.009 |
helicopter | +0.009 |
Neg logit contributions | |
opener | -0.006 |
aver | -0.005 |
inda | -0.005 |
Linda | -0.005 |
eh | -0.005 |
Token | Let |
Token ID | 5756 |
Feature activation | -4.35e-03 |
Pos logit contributions | |
cha | +0.029 |
ind | +0.028 |
bicycles | +0.025 |
festival | +0.025 |
helicopter | +0.024 |
Neg logit contributions | |
opener | -0.047 |
aver | -0.045 |
inda | -0.042 |
eh | -0.040 |
Linda | -0.040 |
Token | 's |
Token ID | 338 |
Feature activation | +5.03e-03 |
Pos logit contributions | |
ind | +0.007 |
bicycles | +0.006 |
yacht | +0.006 |
cha | +0.006 |
festival | +0.006 |
Neg logit contributions | |
opener | -0.007 |
inda | -0.007 |
aver | -0.007 |
Linda | -0.007 |
eh | -0.007 |
Token | play |
Token ID | 711 |
Feature activation | -5.74e-04 |
Pos logit contributions | |
opener | +0.009 |
aver | +0.008 |
inda | +0.008 |
Linda | +0.007 |
Jill | +0.007 |
Neg logit contributions | |
ind | -0.008 |
cha | -0.008 |
bicycles | -0.008 |
helicopter | -0.007 |
appearance | -0.007 |
Token | hide |
Token ID | 7808 |
Feature activation | -1.71e-03 |
Pos logit contributions | |
ind | +0.001 |
cha | +0.001 |
bicycles | +0.001 |
yacht | +0.001 |
appearance | +0.001 |
Neg logit contributions | |
opener | -0.001 |
aver | -0.001 |
inda | -0.001 |
eh | -0.001 |
Linda | -0.001 |
Token | - |
Token ID | 12 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
ind | +0.002 |
cha | +0.002 |
appearance | +0.002 |
yacht | +0.002 |
bicycles | +0.002 |
Neg logit contributions | |
opener | -0.003 |
aver | -0.003 |
inda | -0.003 |
eh | -0.003 |
Linda | -0.003 |
Token | and |
Token ID | 392 |
Feature activation | +9.90e-03 |
Pos logit contributions | |
opener | +0.136 |
aver | +0.127 |
Linda | +0.120 |
inda | +0.117 |
inn | +0.112 |
Neg logit contributions | |
ind | -0.100 |
cha | -0.092 |
bicycles | -0.085 |
festival | -0.083 |
pige | -0.083 |
Token | - |
Token ID | 12 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
opener | +0.019 |
aver | +0.017 |
inda | +0.017 |
eh | +0.016 |
Linda | +0.016 |
Neg logit contributions | |
ind | -0.015 |
cha | -0.014 |
yacht | -0.013 |
bicycles | -0.013 |
appearance | -0.013 |
Token | seek |
Token ID | 36163 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
opener | +0.086 |
aver | +0.082 |
inda | +0.074 |
Linda | +0.071 |
avers | +0.065 |
Neg logit contributions | |
cha | -0.110 |
ind | -0.107 |
bicycles | -0.100 |
festival | -0.098 |
ize | -0.097 |
Token | !" |
Token ID | 2474 |
Feature activation | -9.13e-04 |
Pos logit contributions | |
opener | +0.027 |
aver | +0.023 |
inda | +0.023 |
Linda | +0.022 |
Jill | +0.022 |
Neg logit contributions | |
ind | -0.025 |
cha | -0.024 |
yacht | -0.024 |
helicopter | -0.023 |
appearance | -0.023 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
cha | +0.001 |
ind | +0.001 |
bicycles | +0.001 |
yacht | +0.001 |
appearance | +0.001 |
Neg logit contributions | |
opener | -0.002 |
aver | -0.002 |
inda | -0.002 |
eh | -0.001 |
avers | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +6.33e-03 |
Pos logit contributions | |
opener | +0.057 |
aver | +0.046 |
one | +0.042 |
inda | +0.041 |
Mia | +0.040 |
Neg logit contributions | |
ind | -0.093 |
cha | -0.093 |
yacht | -0.089 |
helicopter | -0.088 |
bicycles | -0.087 |
Token | Coffee |
Token ID | 19443 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
opener | +0.012 |
aver | +0.011 |
inda | +0.011 |
eh | +0.010 |
Linda | +0.010 |
Neg logit contributions | |
ind | -0.009 |
cha | -0.009 |
bicycles | -0.008 |
yacht | -0.008 |
appearance | -0.008 |
Token | is |
Token ID | 318 |
Feature activation | +4.94e-03 |
Pos logit contributions | |
ind | +0.015 |
cha | +0.014 |
bicycles | +0.014 |
yacht | +0.013 |
appearance | +0.013 |
Neg logit contributions | |
opener | -0.023 |
inda | -0.020 |
aver | -0.020 |
izzy | -0.020 |
Linda | -0.019 |
Token | for |
Token ID | 329 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
opener | +0.009 |
aver | +0.008 |
inda | +0.008 |
Linda | +0.007 |
eh | +0.007 |
Neg logit contributions | |
cha | -0.008 |
ind | -0.008 |
bicycles | -0.008 |
yacht | -0.007 |
helicopter | -0.007 |
Token | grown |
Token ID | 7334 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
opener | +0.021 |
aver | +0.019 |
inda | +0.018 |
Linda | +0.017 |
eh | +0.017 |
Neg logit contributions | |
cha | -0.017 |
ind | -0.016 |
helicopter | -0.016 |
bicycles | -0.015 |
yacht | -0.015 |
Token | - |
Token ID | 12 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
opener | +0.121 |
aver | +0.114 |
inda | +0.106 |
Linda | +0.104 |
izzy | +0.102 |
Neg logit contributions | |
ind | -0.071 |
appearance | -0.054 |
cha | -0.053 |
re | -0.051 |
forever | -0.048 |
Token | ups |
Token ID | 4739 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
opener | +0.107 |
aver | +0.098 |
inda | +0.090 |
Linda | +0.088 |
Jill | +0.085 |
Neg logit contributions | |
ind | -0.140 |
cha | -0.126 |
ize | -0.113 |
bicycles | -0.111 |
appearance | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | +5.55e-03 |
Pos logit contributions | |
opener | +0.016 |
aver | +0.012 |
inda | +0.011 |
izzy | +0.011 |
one | +0.011 |
Neg logit contributions | |
cha | -0.026 |
helicopter | -0.024 |
yacht | -0.024 |
bicycles | -0.024 |
ind | -0.024 |
Token | Now |
Token ID | 2735 |
Feature activation | +8.71e-03 |
Pos logit contributions | |
opener | +0.011 |
aver | +0.010 |
inda | +0.010 |
eh | +0.009 |
Linda | +0.009 |
Neg logit contributions | |
ind | -0.008 |
cha | -0.008 |
appearance | -0.007 |
bicycles | -0.007 |
yacht | -0.007 |
Token | help |
Token ID | 1037 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
opener | +0.010 |
Mia | +0.010 |
Jen | +0.009 |
Liz | +0.008 |
aster | +0.007 |
Neg logit contributions | |
ind | -0.020 |
uted | -0.017 |
ized | -0.017 |
cha | -0.017 |
bicycles | -0.016 |
Token | me |
Token ID | 502 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
cha | +0.017 |
ind | +0.016 |
yacht | +0.016 |
bicycles | +0.015 |
helicopter | +0.015 |
Neg logit contributions | |
opener | -0.026 |
aver | -0.023 |
inda | -0.022 |
izzy | -0.021 |
Linda | -0.021 |
Token | door |
Token ID | 3420 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
opener | +0.012 |
aver | +0.011 |
inda | +0.010 |
eh | +0.010 |
Linda | +0.009 |
Neg logit contributions | |
ind | -0.010 |
cha | -0.010 |
bicycles | -0.010 |
appearance | -0.010 |
yacht | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +5.01e-03 |
Pos logit contributions | |
opener | +0.033 |
aver | +0.031 |
inda | +0.030 |
eh | +0.028 |
Linda | +0.028 |
Neg logit contributions | |
ind | -0.018 |
cha | -0.018 |
yacht | -0.016 |
bicycles | -0.016 |
appearance | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +5.37e-03 |
Pos logit contributions | |
opener | +0.011 |
aver | +0.010 |
inda | +0.010 |
eh | +0.009 |
izzy | +0.009 |
Neg logit contributions | |
ind | -0.006 |
cha | -0.006 |
yacht | -0.005 |
bicycles | -0.005 |
appearance | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +1.39e-03 |
Pos logit contributions | |
opener | +0.010 |
aver | +0.009 |
inda | +0.008 |
eh | +0.008 |
izzy | +0.008 |
Neg logit contributions | |
cha | -0.009 |
ind | -0.009 |
bicycles | -0.008 |
yacht | -0.008 |
helicopter | -0.008 |
Token | her |
Token ID | 607 |
Feature activation | +2.10e-03 |
Pos logit contributions | |
opener | +0.002 |
aver | +0.002 |
inda | +0.002 |
Linda | +0.002 |
eh | +0.002 |
Neg logit contributions | |
ind | -0.002 |
cha | -0.002 |
yacht | -0.002 |
bicycles | -0.002 |
appearance | -0.002 |
Token | amaz |
Token ID | 40642 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
opener | +0.004 |
inda | +0.004 |
aver | +0.004 |
Linda | +0.004 |
Liz | +0.004 |
Neg logit contributions | |
ind | -0.003 |
cha | -0.003 |
yacht | -0.003 |
aren | -0.003 |
pige | -0.003 |
Token | ement |
Token ID | 972 |
Feature activation | -8.66e-03 |
Pos logit contributions | |
ind | +0.070 |
cha | +0.067 |
ranch | +0.062 |
appearance | +0.061 |
yacht | +0.061 |
Neg logit contributions | |
opener | -0.191 |
aver | -0.183 |
inda | -0.176 |
inn | -0.169 |
Linda | -0.168 |
Token | , |
Token ID | 11 |
Feature activation | +3.19e-03 |
Pos logit contributions | |
ind | +0.015 |
cha | +0.014 |
bicycles | +0.013 |
festival | +0.013 |
appearance | +0.013 |
Neg logit contributions | |
opener | -0.015 |
aver | -0.014 |
inda | -0.013 |
Linda | -0.012 |
Jill | -0.012 |
Token | she |
Token ID | 673 |
Feature activation | +1.32e-04 |
Pos logit contributions | |
opener | +0.005 |
inda | +0.004 |
Linda | +0.004 |
aver | +0.004 |
Jill | +0.004 |
Neg logit contributions | |
ind | -0.006 |
cha | -0.006 |
appearance | -0.006 |
yacht | -0.006 |
bicycles | -0.006 |
Token | could |
Token ID | 714 |
Feature activation | +7.80e-03 |
Pos logit contributions | |
opener | +0.000 |
aver | +0.000 |
inda | +0.000 |
Linda | +0.000 |
eh | +0.000 |
Neg logit contributions | |
ind | -0.000 |
cha | -0.000 |
yacht | -0.000 |
appearance | -0.000 |
bicycles | -0.000 |
Token | see |
Token ID | 766 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
opener | +0.014 |
aver | +0.013 |
inda | +0.012 |
eh | +0.012 |
Linda | +0.011 |
Neg logit contributions | |
ind | -0.012 |
cha | -0.012 |
yacht | -0.011 |
bicycles | -0.011 |
appearance | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -9.75e-03 |
Pos logit contributions | |
ind | +0.031 |
cha | +0.031 |
yacht | +0.029 |
bicycles | +0.029 |
appearance | +0.028 |
Neg logit contributions | |
opener | -0.034 |
aver | -0.031 |
inda | -0.030 |
eh | -0.028 |
Linda | -0.027 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
ind | +0.016 |
cha | +0.015 |
appearance | +0.014 |
iling | +0.013 |
ize | +0.013 |
Neg logit contributions | |
opener | -0.019 |
aver | -0.017 |
inda | -0.015 |
Linda | -0.015 |
eh | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -6.08e-03 |
Pos logit contributions | |
opener | +0.035 |
aver | +0.031 |
inda | +0.031 |
Linda | +0.029 |
izzy | +0.028 |
Neg logit contributions | |
ind | -0.035 |
cha | -0.035 |
appearance | -0.032 |
bicycles | -0.032 |
yacht | -0.031 |
Token | â |
Token ID | 22940 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
ind | +0.010 |
cha | +0.010 |
appearance | +0.009 |
bicycles | +0.009 |
yacht | +0.009 |
Neg logit contributions | |
opener | -0.011 |
aver | -0.010 |
inda | -0.009 |
Linda | -0.009 |
eh | -0.009 |
Token | € |
Token ID | 26391 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
ind | +0.031 |
cha | +0.030 |
appearance | +0.027 |
yacht | +0.027 |
bicycles | +0.027 |
Neg logit contributions | |
opener | -0.038 |
aver | -0.034 |
inda | -0.033 |
eh | -0.031 |
Linda | -0.031 |
Token | � |
Token ID | 447 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
opener | +0.021 |
aver | +0.019 |
inda | +0.017 |
Linda | +0.017 |
eh | +0.016 |
Neg logit contributions | |
ind | -0.027 |
cha | -0.026 |
appearance | -0.025 |
yacht | -0.025 |
festival | -0.025 |
Token | � |
Token ID | 251 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
appearance | +0.152 |
ind | +0.152 |
strangers | +0.143 |
ponies | +0.139 |
cha | +0.138 |
Neg logit contributions | |
opener | -0.111 |
aver | -0.097 |
eh | -0.088 |
Linda | -0.084 |
inn | -0.083 |
Token | with |
Token ID | 4480 |
Feature activation | -5.06e-03 |
Pos logit contributions | |
ind | +0.028 |
cha | +0.027 |
appearance | +0.026 |
bicycles | +0.025 |
yacht | +0.025 |
Neg logit contributions | |
opener | -0.024 |
aver | -0.022 |
inda | -0.021 |
Linda | -0.020 |
eh | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
ind | +0.009 |
cha | +0.008 |
bicycles | +0.008 |
yacht | +0.008 |
re | +0.008 |
Neg logit contributions | |
opener | -0.009 |
aver | -0.008 |
inda | -0.007 |
eh | -0.007 |
izzy | -0.007 |
Token | smile |
Token ID | 8212 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
opener | +0.024 |
aver | +0.023 |
inda | +0.022 |
eh | +0.021 |
Linda | +0.020 |
Neg logit contributions | |
ind | -0.016 |
cha | -0.015 |
yacht | -0.014 |
bicycles | -0.014 |
appearance | -0.014 |
Token | on |
Token ID | 319 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
opener | +0.041 |
aver | +0.038 |
inda | +0.036 |
Linda | +0.034 |
izzy | +0.033 |
Neg logit contributions | |
ind | -0.037 |
cha | -0.037 |
bicycles | -0.034 |
appearance | -0.034 |
festival | -0.033 |
Token | magical |
Token ID | 10883 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
opener | +0.016 |
aver | +0.015 |
Linda | +0.014 |
Jill | +0.014 |
eh | +0.013 |
Neg logit contributions | |
ind | -0.016 |
cha | -0.015 |
appearance | -0.014 |
bicycles | -0.014 |
iling | -0.014 |
Token | noise |
Token ID | 7838 |
Feature activation | -1.23e-05 |
Pos logit contributions | |
ind | +0.028 |
cha | +0.028 |
bicycles | +0.027 |
appearance | +0.025 |
ponies | +0.025 |
Neg logit contributions | |
opener | -0.035 |
aver | -0.033 |
inda | -0.031 |
Linda | -0.030 |
Jill | -0.029 |
Token | ! |
Token ID | 0 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
ind | +0.000 |
cha | +0.000 |
appearance | +0.000 |
bicycles | +0.000 |
ponies | +0.000 |
Neg logit contributions | |
opener | -0.000 |
aver | -0.000 |
inda | -0.000 |
Linda | -0.000 |
Jill | -0.000 |
Token | To |
Token ID | 1675 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
opener | +0.031 |
aver | +0.030 |
inda | +0.029 |
eh | +0.028 |
avers | +0.026 |
Neg logit contributions | |
cha | -0.026 |
bicycles | -0.024 |
yacht | -0.023 |
ind | -0.022 |
helicopter | -0.022 |
Token | his |
Token ID | 465 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
ind | +0.029 |
cha | +0.028 |
bicycles | +0.026 |
yacht | +0.026 |
appearance | +0.026 |
Neg logit contributions | |
opener | -0.024 |
aver | -0.022 |
inda | -0.021 |
Linda | -0.019 |
eh | -0.019 |
Token | amaz |
Token ID | 40642 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
ind | +0.016 |
cha | +0.015 |
bicycles | +0.014 |
aren | +0.013 |
yacht | +0.013 |
Neg logit contributions | |
opener | -0.022 |
aver | -0.020 |
inda | -0.020 |
Linda | -0.019 |
Liz | -0.018 |
Token | ement |
Token ID | 972 |
Feature activation | -2.68e-03 |
Pos logit contributions | |
ind | +0.072 |
ranch | +0.068 |
cha | +0.066 |
aults | +0.064 |
puppies | +0.064 |
Neg logit contributions | |
opener | -0.154 |
aver | -0.148 |
inda | -0.140 |
Jill | -0.138 |
inn | -0.137 |
Token | he |
Token ID | 339 |
Feature activation | -9.89e-04 |
Pos logit contributions | |
ind | +0.004 |
cha | +0.004 |
bicycles | +0.004 |
festival | +0.004 |
appearance | +0.004 |
Neg logit contributions | |
opener | -0.005 |
aver | -0.005 |
inda | -0.004 |
Linda | -0.004 |
Jill | -0.004 |
Token | had |
Token ID | 550 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
ind | +0.002 |
cha | +0.002 |
bicycles | +0.002 |
yacht | +0.002 |
helicopter | +0.002 |
Neg logit contributions | |
opener | -0.002 |
aver | -0.001 |
inda | -0.001 |
Linda | -0.001 |
eh | -0.001 |
Token | revealed |
Token ID | 4602 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
opener | +0.029 |
aver | +0.025 |
inda | +0.024 |
izzy | +0.023 |
eh | +0.023 |
Neg logit contributions | |
ind | -0.030 |
cha | -0.030 |
yacht | -0.028 |
bicycles | -0.028 |
re | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | +3.54e-03 |
Pos logit contributions | |
opener | +0.031 |
aver | +0.028 |
inda | +0.027 |
Linda | +0.025 |
Jill | +0.024 |
Neg logit contributions | |
ind | -0.044 |
cha | -0.043 |
festival | -0.041 |
appearance | -0.040 |
ranch | -0.040 |
Token | her |
Token ID | 607 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
opener | +0.021 |
aver | +0.019 |
inda | +0.018 |
Linda | +0.016 |
eh | +0.016 |
Neg logit contributions | |
ind | -0.026 |
cha | -0.026 |
bicycles | -0.024 |
appearance | -0.024 |
yacht | -0.024 |
Token | journey |
Token ID | 7002 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
opener | +0.022 |
aver | +0.019 |
inda | +0.018 |
Linda | +0.018 |
Liz | +0.017 |
Neg logit contributions | |
ind | -0.022 |
cha | -0.021 |
ize | -0.020 |
iling | -0.019 |
uted | -0.019 |
Token | home |
Token ID | 1363 |
Feature activation | -5.35e-03 |
Pos logit contributions | |
ind | +0.032 |
cha | +0.032 |
appearance | +0.029 |
bicycles | +0.029 |
yacht | +0.029 |
Neg logit contributions | |
opener | -0.036 |
aver | -0.032 |
inda | -0.031 |
Linda | -0.029 |
eh | -0.028 |
Token | â |
Token ID | 22940 |
Feature activation | -3.34e-03 |
Pos logit contributions | |
ind | +0.009 |
cha | +0.009 |
bicycles | +0.008 |
yacht | +0.008 |
appearance | +0.008 |
Neg logit contributions | |
opener | -0.009 |
aver | -0.008 |
inda | -0.008 |
Linda | -0.008 |
eh | -0.007 |
Token | € |
Token ID | 26391 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
ind | +0.005 |
cha | +0.005 |
appearance | +0.005 |
festival | +0.005 |
ranch | +0.005 |
Neg logit contributions | |
opener | -0.006 |
aver | -0.005 |
inda | -0.005 |
Linda | -0.005 |
izzy | -0.005 |
Token | � |
Token ID | 447 |
Feature activation | -7.01e-02 |
Pos logit contributions | |
opener | +0.041 |
aver | +0.037 |
inda | +0.035 |
eh | +0.033 |
Linda | +0.033 |
Neg logit contributions | |
ind | -0.045 |
cha | -0.044 |
yacht | -0.042 |
appearance | -0.042 |
re | -0.041 |
Token | � |
Token ID | 251 |
Feature activation | -8.17e-03 |
Pos logit contributions | |
ind | +0.126 |
appearance | +0.124 |
bicycles | +0.116 |
cha | +0.116 |
re | +0.114 |
Neg logit contributions | |
opener | -0.114 |
aver | -0.096 |
eh | -0.091 |
inda | -0.090 |
Linda | -0.089 |
Token | content |
Token ID | 2695 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
ind | +0.016 |
cha | +0.016 |
appearance | +0.016 |
bicycles | +0.015 |
yacht | +0.015 |
Neg logit contributions | |
opener | -0.011 |
aver | -0.010 |
inda | -0.009 |
Linda | -0.009 |
eh | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +2.16e-03 |
Pos logit contributions | |
ind | +0.038 |
cha | +0.036 |
bicycles | +0.035 |
appearance | +0.035 |
yacht | +0.033 |
Neg logit contributions | |
opener | -0.041 |
aver | -0.038 |
inda | -0.036 |
Linda | -0.034 |
eh | -0.033 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
opener | +0.004 |
aver | +0.004 |
inda | +0.003 |
Linda | +0.003 |
Jill | +0.003 |
Neg logit contributions | |
ind | -0.004 |
cha | -0.003 |
bicycles | -0.003 |
appearance | -0.003 |
yacht | -0.003 |
Token | with |
Token ID | 351 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
ind | +0.027 |
cha | +0.024 |
bicycles | +0.024 |
appearance | +0.023 |
yacht | +0.023 |
Neg logit contributions | |
opener | -0.017 |
Jill | -0.014 |
Linda | -0.014 |
inda | -0.014 |
aver | -0.014 |
Token | bird |
Token ID | 6512 |
Feature activation | -8.04e-03 |
Pos logit contributions | |
aver | +0.001 |
opener | +0.001 |
eh | +0.001 |
inda | +0.001 |
Mia | +0.001 |
Neg logit contributions | |
ind | -0.001 |
cha | -0.001 |
appearance | -0.000 |
aren | -0.000 |
aults | -0.000 |
Token | looked |
Token ID | 3114 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
ind | +0.015 |
cha | +0.015 |
mall | +0.014 |
festival | +0.014 |
bicycles | +0.014 |
Neg logit contributions | |
aver | -0.012 |
opener | -0.012 |
inda | -0.011 |
eh | -0.010 |
Linda | -0.010 |
Token | at |
Token ID | 379 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
ind | +0.061 |
bicycles | +0.060 |
cha | +0.058 |
billboard | +0.057 |
pige | +0.057 |
Neg logit contributions | |
Linda | -0.047 |
inda | -0.046 |
Jill | -0.046 |
opener | -0.042 |
aver | -0.041 |
Token | her |
Token ID | 607 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
ind | +0.029 |
cha | +0.029 |
yacht | +0.028 |
ranch | +0.026 |
festival | +0.026 |
Neg logit contributions | |
opener | -0.020 |
Linda | -0.019 |
Jill | -0.019 |
inda | -0.019 |
Mia | -0.019 |
Token | in |
Token ID | 287 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
opener | +0.020 |
Linda | +0.017 |
inda | +0.016 |
Mia | +0.016 |
Jill | +0.015 |
Neg logit contributions | |
cha | -0.025 |
ind | -0.025 |
iling | -0.022 |
bicycles | -0.021 |
mall | -0.021 |
Token | amaz |
Token ID | 40642 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
cha | +0.024 |
ind | +0.023 |
yacht | +0.021 |
bicycles | +0.020 |
ranch | +0.020 |
Neg logit contributions | |
opener | -0.024 |
Jill | -0.021 |
Linda | -0.021 |
inda | -0.020 |
Mia | -0.019 |
Token | ement |
Token ID | 972 |
Feature activation | +3.79e-04 |
Pos logit contributions | |
ind | +0.068 |
ranch | +0.066 |
cha | +0.066 |
yacht | +0.064 |
puppies | +0.061 |
Neg logit contributions | |
opener | -0.151 |
aver | -0.146 |
inda | -0.143 |
Jill | -0.137 |
inn | -0.137 |
Token | , |
Token ID | 11 |
Feature activation | +4.72e-03 |
Pos logit contributions | |
opener | +0.001 |
inda | +0.001 |
aver | +0.001 |
Linda | +0.000 |
Jill | +0.000 |
Neg logit contributions | |
ind | -0.001 |
cha | -0.001 |
festival | -0.001 |
bicycles | -0.001 |
mall | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +1.54e-03 |
Pos logit contributions | |
opener | +0.008 |
aver | +0.007 |
Linda | +0.007 |
inda | +0.007 |
Jill | +0.007 |
Neg logit contributions | |
ind | -0.008 |
cha | -0.008 |
bicycles | -0.007 |
festival | -0.007 |
appearance | -0.007 |
Token | said |
Token ID | 531 |
Feature activation | +1.35e-03 |
Pos logit contributions | |
opener | +0.002 |
aver | +0.002 |
inda | +0.002 |
Linda | +0.002 |
Jill | +0.002 |
Neg logit contributions | |
ind | -0.003 |
cha | -0.003 |
appearance | -0.003 |
bicycles | -0.003 |
yacht | -0.003 |
Token | : |
Token ID | 25 |
Feature activation | +2.99e-03 |
Pos logit contributions | |
opener | +0.003 |
aver | +0.002 |
inda | +0.002 |
Linda | +0.002 |
Jill | +0.002 |
Neg logit contributions | |
ind | -0.002 |
cha | -0.002 |
bicycles | -0.002 |
appearance | -0.002 |
yacht | -0.002 |
Token | The |
Token ID | 383 |
Feature activation | +2.27e-03 |
Pos logit contributions | |
opener | +0.016 |
aver | +0.015 |
inda | +0.014 |
eh | +0.013 |
izzy | +0.013 |
Neg logit contributions | |
cha | -0.014 |
ind | -0.014 |
bicycles | -0.013 |
ranch | -0.013 |
festival | -0.013 |
Token | boy |
Token ID | 2933 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
opener | +0.004 |
aver | +0.004 |
inda | +0.004 |
eh | +0.004 |
Linda | +0.004 |
Neg logit contributions | |
ind | -0.003 |
cha | -0.003 |
bicycles | -0.003 |
appearance | -0.003 |
yacht | -0.003 |
Token | watched |
Token ID | 7342 |
Feature activation | -9.68e-03 |
Pos logit contributions | |
opener | +0.020 |
aver | +0.020 |
inda | +0.017 |
eh | +0.017 |
avers | +0.016 |
Neg logit contributions | |
ind | -0.024 |
cha | -0.023 |
appearance | -0.023 |
festival | -0.022 |
bicycles | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
ind | +0.019 |
cha | +0.018 |
bicycles | +0.017 |
appearance | +0.017 |
mall | +0.017 |
Neg logit contributions | |
opener | -0.015 |
inda | -0.013 |
aver | -0.013 |
Linda | -0.012 |
Jill | -0.012 |
Token | in |
Token ID | 287 |
Feature activation | -7.99e-03 |
Pos logit contributions | |
opener | +0.020 |
Mia | +0.016 |
Linda | +0.016 |
inda | +0.016 |
Jen | +0.015 |
Neg logit contributions | |
ind | -0.024 |
cha | -0.023 |
bicycles | -0.021 |
mall | -0.020 |
iling | -0.020 |
Token | amaz |
Token ID | 40642 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
cha | +0.013 |
ind | +0.013 |
yacht | +0.011 |
ize | +0.011 |
bicycles | +0.011 |
Neg logit contributions | |
opener | -0.015 |
aver | -0.013 |
Linda | -0.013 |
inda | -0.013 |
Jill | -0.012 |
Token | ement |
Token ID | 972 |
Feature activation | -3.50e-04 |
Pos logit contributions | |
ind | +0.057 |
cha | +0.055 |
ranch | +0.050 |
yacht | +0.049 |
appearance | +0.049 |
Neg logit contributions | |
opener | -0.169 |
aver | -0.163 |
inda | -0.156 |
inn | -0.150 |
eh | -0.149 |
Token | . |
Token ID | 13 |
Feature activation | +6.07e-03 |
Pos logit contributions | |
cha | +0.001 |
ind | +0.001 |
bicycles | +0.001 |
festival | +0.001 |
helicopter | +0.001 |
Neg logit contributions | |
opener | -0.001 |
aver | -0.000 |
inda | -0.000 |
Linda | -0.000 |
Jill | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +6.15e-03 |
Pos logit contributions | |
aver | +0.012 |
opener | +0.012 |
inda | +0.012 |
eh | +0.011 |
avers | +0.011 |
Neg logit contributions | |
cha | -0.007 |
bicycles | -0.007 |
ind | -0.007 |
ranch | -0.007 |
ponies | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +4.62e-03 |
Pos logit contributions | |
opener | +0.012 |
aver | +0.011 |
inda | +0.011 |
eh | +0.010 |
Linda | +0.010 |
Neg logit contributions | |
ind | -0.008 |
cha | -0.008 |
bicycles | -0.007 |
re | -0.007 |
festival | -0.007 |
Token | The |
Token ID | 464 |
Feature activation | -5.42e-03 |
Pos logit contributions | |
opener | +0.008 |
aver | +0.007 |
inda | +0.007 |
Linda | +0.007 |
izzy | +0.007 |
Neg logit contributions | |
ind | -0.008 |
cha | -0.007 |
bicycles | -0.007 |
festival | -0.007 |
helicopter | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
ind | +0.002 |
cha | +0.002 |
appearance | +0.002 |
festival | +0.002 |
yacht | +0.002 |
Neg logit contributions | |
aver | -0.002 |
opener | -0.002 |
inda | -0.002 |
eh | -0.001 |
Linda | -0.001 |
Token | his |
Token ID | 465 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
ind | +0.021 |
cha | +0.021 |
yacht | +0.020 |
bicycles | +0.020 |
helicopter | +0.020 |
Neg logit contributions | |
opener | -0.021 |
aver | -0.019 |
inda | -0.018 |
eh | -0.017 |
izzy | -0.017 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
cha | +0.026 |
ind | +0.026 |
iling | +0.024 |
aren | +0.024 |
ize | +0.024 |
Neg logit contributions | |
opener | -0.020 |
aver | -0.019 |
inda | -0.016 |
Linda | -0.016 |
Liz | -0.016 |
Token | watched |
Token ID | 7342 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
cha | +0.032 |
ind | +0.031 |
appearance | +0.030 |
festival | +0.028 |
yacht | +0.028 |
Neg logit contributions | |
aver | -0.032 |
opener | -0.031 |
inda | -0.029 |
avers | -0.027 |
Liz | -0.026 |
Token | in |
Token ID | 287 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
ind | +0.050 |
actus | +0.047 |
mall | +0.046 |
appearance | +0.045 |
cha | +0.045 |
Neg logit contributions | |
opener | -0.025 |
Jill | -0.019 |
Linda | -0.018 |
Mia | -0.018 |
Liz | -0.018 |
Token | amaz |
Token ID | 40642 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
ind | +0.025 |
cha | +0.024 |
ize | +0.021 |
yacht | +0.019 |
lder | +0.019 |
Neg logit contributions | |
opener | -0.030 |
Linda | -0.026 |
aver | -0.025 |
Jill | -0.025 |
inda | -0.025 |
Token | ement |
Token ID | 972 |
Feature activation | +8.31e-03 |
Pos logit contributions | |
ind | +0.075 |
ranch | +0.074 |
appearance | +0.071 |
pige | +0.071 |
puppies | +0.070 |
Neg logit contributions | |
opener | -0.133 |
aver | -0.130 |
inda | -0.127 |
Jill | -0.125 |
inn | -0.124 |
Token | , |
Token ID | 11 |
Feature activation | +6.94e-03 |
Pos logit contributions | |
opener | +0.011 |
aver | +0.009 |
inda | +0.009 |
Linda | +0.008 |
Jill | +0.008 |
Neg logit contributions | |
cha | -0.017 |
ind | -0.017 |
mall | -0.016 |
bicycles | -0.016 |
festival | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -3.00e-04 |
Pos logit contributions | |
opener | +0.011 |
aver | +0.010 |
Jill | +0.010 |
Linda | +0.010 |
Jen | +0.010 |
Neg logit contributions | |
ind | -0.013 |
cha | -0.012 |
appearance | -0.011 |
bicycles | -0.011 |
festival | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -9.51e-03 |
Pos logit contributions | |
ind | +0.001 |
cha | +0.001 |
appearance | +0.001 |
bicycles | +0.001 |
mall | +0.001 |
Neg logit contributions | |
Jill | -0.000 |
opener | -0.000 |
Linda | -0.000 |
inda | -0.000 |
aver | -0.000 |
Token | knight |
Token ID | 22062 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
ind | +0.017 |
cha | +0.016 |
appearance | +0.015 |
bicycles | +0.015 |
aren | +0.015 |
Neg logit contributions | |
opener | -0.016 |
aver | -0.015 |
inda | -0.014 |
eh | -0.013 |
Linda | -0.012 |
Token | interesting |
Token ID | 3499 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
ind | +0.007 |
cha | +0.007 |
festival | +0.006 |
yacht | +0.006 |
bicycles | +0.006 |
Neg logit contributions | |
opener | -0.007 |
aver | -0.006 |
inda | -0.006 |
Linda | -0.006 |
eh | -0.005 |
Token | things |
Token ID | 1243 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
opener | +0.023 |
inda | +0.020 |
aver | +0.020 |
Linda | +0.019 |
eh | +0.018 |
Neg logit contributions | |
ind | -0.017 |
cha | -0.016 |
festival | -0.016 |
yacht | -0.015 |
ranch | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -4.04e-03 |
Pos logit contributions | |
ind | +0.036 |
cha | +0.035 |
appearance | +0.033 |
bicycles | +0.033 |
yacht | +0.033 |
Neg logit contributions | |
opener | -0.025 |
aver | -0.019 |
inda | -0.019 |
Linda | -0.018 |
izzy | -0.017 |
Token | To |
Token ID | 1675 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
cha | +0.006 |
bicycles | +0.006 |
ind | +0.006 |
mall | +0.005 |
helicopter | +0.005 |
Neg logit contributions | |
opener | -0.008 |
aver | -0.007 |
inda | -0.007 |
eh | -0.006 |
avers | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | -5.19e-03 |
Pos logit contributions | |
ind | +0.028 |
cha | +0.027 |
appearance | +0.026 |
yacht | +0.026 |
bicycles | +0.026 |
Neg logit contributions | |
opener | -0.037 |
aver | -0.035 |
inda | -0.032 |
eh | -0.032 |
izzy | -0.031 |
Token | amaz |
Token ID | 40642 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
ind | +0.007 |
cha | +0.007 |
bicycles | +0.006 |
yacht | +0.006 |
aren | +0.006 |
Neg logit contributions | |
opener | -0.011 |
aver | -0.009 |
inda | -0.009 |
Linda | -0.009 |
Liz | -0.008 |
Token | ement |
Token ID | 972 |
Feature activation | -4.19e-03 |
Pos logit contributions | |
ind | +0.067 |
cha | +0.064 |
aults | +0.060 |
ranch | +0.060 |
puppies | +0.058 |
Neg logit contributions | |
opener | -0.150 |
aver | -0.145 |
inda | -0.136 |
Jill | -0.135 |
inn | -0.134 |
Token | , |
Token ID | 11 |
Feature activation | -3.93e-03 |
Pos logit contributions | |
ind | +0.007 |
cha | +0.006 |
bicycles | +0.006 |
festival | +0.006 |
appearance | +0.006 |
Neg logit contributions | |
opener | -0.008 |
aver | -0.007 |
inda | -0.007 |
Linda | -0.007 |
Jill | -0.007 |
Token | she |
Token ID | 673 |
Feature activation | +3.80e-04 |
Pos logit contributions | |
ind | +0.009 |
appearance | +0.008 |
cha | +0.008 |
yacht | +0.007 |
iling | +0.007 |
Neg logit contributions | |
opener | -0.005 |
Linda | -0.004 |
Jill | -0.004 |
inda | -0.004 |
aver | -0.004 |
Token | unearthed |
Token ID | 41562 |
Feature activation | +6.56e-03 |
Pos logit contributions | |
opener | +0.001 |
aver | +0.001 |
inda | +0.001 |
Linda | +0.000 |
eh | +0.000 |
Neg logit contributions | |
ind | -0.001 |
cha | -0.001 |
bicycles | -0.001 |
appearance | -0.001 |
yacht | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -5.60e-03 |
Pos logit contributions | |
opener | +0.011 |
aver | +0.010 |
inda | +0.009 |
inn | +0.009 |
eh | +0.009 |
Neg logit contributions | |
cha | -0.011 |
bicycles | -0.011 |
ind | -0.011 |
re | -0.011 |
helicopter | -0.010 |
Token | onto |
Token ID | 4291 |
Feature activation | +1.60e-03 |
Pos logit contributions | |
opener | +0.002 |
aver | +0.002 |
inda | +0.002 |
eh | +0.002 |
izzy | +0.002 |
Neg logit contributions | |
cha | -0.002 |
ind | -0.002 |
bicycles | -0.002 |
yacht | -0.002 |
re | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | -6.10e-03 |
Pos logit contributions | |
aver | +0.004 |
opener | +0.004 |
inda | +0.004 |
avers | +0.003 |
eh | +0.003 |
Neg logit contributions | |
re | -0.002 |
yacht | -0.001 |
helicopter | -0.001 |
cha | -0.001 |
ind | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +2.60e-03 |
Pos logit contributions | |
ind | +0.009 |
cha | +0.009 |
bicycles | +0.009 |
yacht | +0.009 |
appearance | +0.008 |
Neg logit contributions | |
opener | -0.011 |
aver | -0.010 |
inda | -0.010 |
eh | -0.009 |
Linda | -0.009 |
Token | To |
Token ID | 1675 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
inda | +0.005 |
aver | +0.005 |
opener | +0.004 |
eh | +0.004 |
avers | +0.004 |
Neg logit contributions | |
cha | -0.004 |
re | -0.004 |
bicycles | -0.004 |
helicopter | -0.004 |
ind | -0.004 |
Token | his |
Token ID | 465 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
ind | +0.023 |
cha | +0.023 |
re | +0.022 |
appearance | +0.022 |
yacht | +0.022 |
Neg logit contributions | |
opener | -0.026 |
aver | -0.024 |
inda | -0.023 |
eh | -0.023 |
avers | -0.022 |
Token | amaz |
Token ID | 40642 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
ind | +0.016 |
cha | +0.015 |
yacht | +0.013 |
bicycles | +0.013 |
aren | +0.013 |
Neg logit contributions | |
opener | -0.023 |
aver | -0.020 |
inda | -0.020 |
Linda | -0.019 |
inn | -0.018 |
Token | ement |
Token ID | 972 |
Feature activation | -3.74e-03 |
Pos logit contributions | |
ind | +0.058 |
cha | +0.053 |
ranch | +0.050 |
yacht | +0.048 |
appearance | +0.047 |
Neg logit contributions | |
opener | -0.166 |
aver | -0.159 |
inda | -0.152 |
Linda | -0.148 |
inn | -0.147 |
Token | , |
Token ID | 11 |
Feature activation | -1.78e-03 |
Pos logit contributions | |
ind | +0.005 |
cha | +0.005 |
bicycles | +0.005 |
appearance | +0.005 |
yacht | +0.004 |
Neg logit contributions | |
opener | -0.008 |
aver | -0.007 |
inda | -0.007 |
Linda | -0.006 |
eh | -0.006 |
Token | he |
Token ID | 339 |
Feature activation | -3.70e-03 |
Pos logit contributions | |
ind | +0.004 |
appearance | +0.004 |
cha | +0.004 |
ranch | +0.004 |
iling | +0.004 |
Neg logit contributions | |
opener | -0.002 |
aver | -0.002 |
Linda | -0.002 |
inda | -0.002 |
eh | -0.002 |
Token | could |
Token ID | 714 |
Feature activation | +4.08e-03 |
Pos logit contributions | |
ind | +0.006 |
cha | +0.006 |
bicycles | +0.006 |
yacht | +0.006 |
appearance | +0.006 |
Neg logit contributions | |
opener | -0.006 |
aver | -0.006 |
inda | -0.006 |
eh | -0.005 |
Linda | -0.005 |
Token | fit |
Token ID | 4197 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
opener | +0.007 |
aver | +0.007 |
inda | +0.006 |
eh | +0.006 |
Linda | +0.006 |
Neg logit contributions | |
ind | -0.007 |
cha | -0.007 |
yacht | -0.006 |
bicycles | -0.006 |
appearance | -0.006 |
Token | watched |
Token ID | 7342 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
ind | +0.029 |
cha | +0.027 |
appearance | +0.027 |
ranch | +0.026 |
bicycles | +0.026 |
Neg logit contributions | |
aver | -0.026 |
inda | -0.025 |
opener | -0.025 |
Linda | -0.022 |
izzy | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -8.68e-03 |
Pos logit contributions | |
ind | +0.040 |
appearance | +0.037 |
cha | +0.037 |
actus | +0.036 |
mall | +0.036 |
Neg logit contributions | |
opener | -0.013 |
Jill | -0.013 |
Linda | -0.012 |
Mia | -0.012 |
Liz | -0.011 |
Token | k |
Token ID | 479 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
cha | +0.013 |
appearance | +0.012 |
ind | +0.012 |
aren | +0.011 |
iling | +0.011 |
Neg logit contributions | |
opener | -0.014 |
aver | -0.014 |
avers | -0.012 |
one | -0.012 |
inda | -0.012 |
Token | ite |
Token ID | 578 |
Feature activation | +9.94e-04 |
Pos logit contributions | |
ind | +0.019 |
cha | +0.018 |
appearance | +0.018 |
yacht | +0.017 |
bicycles | +0.017 |
Neg logit contributions | |
opener | -0.021 |
aver | -0.019 |
inda | -0.018 |
eh | -0.017 |
izzy | -0.017 |
Token | in |
Token ID | 287 |
Feature activation | -8.40e-03 |
Pos logit contributions | |
opener | +0.002 |
inda | +0.001 |
aver | +0.001 |
Linda | +0.001 |
Liz | +0.001 |
Neg logit contributions | |
ind | -0.002 |
cha | -0.002 |
appearance | -0.002 |
bicycles | -0.002 |
mall | -0.002 |
Token | amaz |
Token ID | 40642 |
Feature activation | -6.77e-02 |
Pos logit contributions | |
cha | +0.015 |
ind | +0.014 |
ize | +0.012 |
yacht | +0.012 |
helicopter | +0.012 |
Neg logit contributions | |
opener | -0.015 |
Jill | -0.013 |
Linda | -0.013 |
inda | -0.013 |
Jen | -0.013 |
Token | ement |
Token ID | 972 |
Feature activation | +8.95e-03 |
Pos logit contributions | |
ranch | +0.075 |
ind | +0.073 |
appearance | +0.072 |
cha | +0.069 |
puppies | +0.069 |
Neg logit contributions | |
opener | -0.130 |
aver | -0.128 |
inda | -0.125 |
inn | -0.124 |
Jill | -0.124 |
Token | , |
Token ID | 11 |
Feature activation | +2.22e-03 |
Pos logit contributions | |
opener | +0.012 |
inda | +0.010 |
aver | +0.010 |
Linda | +0.009 |
Jill | +0.009 |
Neg logit contributions | |
cha | -0.018 |
ind | -0.018 |
bicycles | -0.016 |
mall | -0.016 |
festival | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -4.02e-05 |
Pos logit contributions | |
Jill | +0.003 |
opener | +0.003 |
Linda | +0.003 |
Jen | +0.003 |
Mia | +0.003 |
Neg logit contributions | |
ind | -0.004 |
cha | -0.004 |
bicycles | -0.003 |
appearance | -0.003 |
iling | -0.003 |
Token | Little |
Token ID | 7703 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
ind | +0.000 |
cha | +0.000 |
appearance | +0.000 |
ranch | +0.000 |
bicycles | +0.000 |
Neg logit contributions | |
Linda | -0.000 |
Jill | -0.000 |
inda | -0.000 |
opener | -0.000 |
Liz | -0.000 |
Token | Joe |
Token ID | 5689 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
ind | +0.038 |
appearance | +0.033 |
yacht | +0.033 |
helicopter | +0.033 |
ranch | +0.033 |
Neg logit contributions | |
opener | -0.026 |
inda | -0.025 |
Linda | -0.024 |
Jill | -0.024 |
aver | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -2.13e-03 |
Pos logit contributions | |
opener | +0.002 |
aver | +0.002 |
inda | +0.002 |
Linda | +0.002 |
eh | +0.002 |
Neg logit contributions | |
ind | -0.001 |
cha | -0.001 |
yacht | -0.001 |
bicycles | -0.001 |
helicopter | -0.001 |
Token | Tim |
Token ID | 5045 |
Feature activation | +5.09e-03 |
Pos logit contributions | |
cha | +0.003 |
ind | +0.003 |
bicycles | +0.003 |
yacht | +0.003 |
helicopter | +0.003 |
Neg logit contributions | |
opener | -0.004 |
aver | -0.004 |
inda | -0.004 |
eh | -0.003 |
izzy | -0.003 |
Token | my |
Token ID | 1820 |
Feature activation | +8.53e-04 |
Pos logit contributions | |
opener | +0.008 |
aver | +0.008 |
inda | +0.007 |
eh | +0.007 |
Linda | +0.007 |
Neg logit contributions | |
ind | -0.009 |
cha | -0.009 |
bicycles | -0.008 |
appearance | -0.008 |
yacht | -0.008 |
Token | watched |
Token ID | 7342 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
opener | +0.002 |
aver | +0.002 |
inda | +0.002 |
eh | +0.001 |
Linda | +0.001 |
Neg logit contributions | |
ind | -0.001 |
cha | -0.001 |
bicycles | -0.001 |
yacht | -0.001 |
appearance | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | -9.63e-03 |
Pos logit contributions | |
ind | +0.023 |
cha | +0.023 |
bicycles | +0.022 |
appearance | +0.021 |
festival | +0.021 |
Neg logit contributions | |
opener | -0.020 |
aver | -0.017 |
inda | -0.017 |
Linda | -0.017 |
Jill | -0.016 |
Token | amaz |
Token ID | 40642 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
ind | +0.017 |
cha | +0.016 |
yacht | +0.014 |
bicycles | +0.014 |
ranch | +0.014 |
Neg logit contributions | |
opener | -0.018 |
Linda | -0.015 |
aver | -0.015 |
inda | -0.015 |
Jill | -0.014 |
Token | ement |
Token ID | 972 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ranch | +0.070 |
ind | +0.068 |
appearance | +0.064 |
re | +0.064 |
country | +0.063 |
Neg logit contributions | |
opener | -0.142 |
inda | -0.137 |
aver | -0.136 |
Jill | -0.136 |
inn | -0.135 |
Token | as |
Token ID | 355 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
opener | +0.014 |
inda | +0.012 |
aver | +0.012 |
Linda | +0.012 |
Jill | +0.011 |
Neg logit contributions | |
ind | -0.020 |
cha | -0.020 |
festival | -0.020 |
mall | -0.019 |
bicycles | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -7.57e-03 |
Pos logit contributions | |
opener | +0.030 |
aver | +0.026 |
inda | +0.025 |
Linda | +0.024 |
izzy | +0.023 |
Neg logit contributions | |
ind | -0.035 |
cha | -0.034 |
appearance | -0.033 |
yacht | -0.032 |
bicycles | -0.032 |
Token | black |
Token ID | 2042 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
bell | +0.009 |
appearance | +0.009 |
cha | +0.008 |
bicycles | +0.008 |
mall | +0.008 |
Neg logit contributions | |
opener | -0.016 |
aver | -0.015 |
inn | -0.014 |
inda | -0.014 |
avers | -0.014 |
Token | board |
Token ID | 3526 |
Feature activation | -2.47e-03 |
Pos logit contributions | |
opener | +0.027 |
aver | +0.026 |
inda | +0.024 |
avers | +0.024 |
eh | +0.023 |
Neg logit contributions | |
bell | -0.021 |
cha | -0.021 |
yacht | -0.020 |
appearance | -0.020 |
bicycles | -0.019 |
Token | on |
Token ID | 319 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
opener | +0.041 |
aver | +0.038 |
inda | +0.036 |
Linda | +0.034 |
izzy | +0.033 |
Neg logit contributions | |
ind | -0.037 |
cha | -0.037 |
bicycles | -0.034 |
appearance | -0.034 |
festival | -0.033 |
Token | his |
Token ID | 465 |
Feature activation | +6.92e-03 |
Pos logit contributions | |
ind | +0.031 |
cha | +0.031 |
appearance | +0.029 |
bicycles | +0.029 |
festival | +0.028 |
Neg logit contributions | |
opener | -0.022 |
aver | -0.019 |
inda | -0.018 |
Linda | -0.018 |
Jill | -0.017 |
Token | face |
Token ID | 1986 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
opener | +0.013 |
aver | +0.012 |
inda | +0.011 |
eh | +0.011 |
Linda | +0.011 |
Neg logit contributions | |
ind | -0.011 |
cha | -0.010 |
festival | -0.009 |
aren | -0.009 |
mall | -0.009 |
Token | â |
Token ID | 22940 |
Feature activation | -6.11e-03 |
Pos logit contributions | |
opener | +0.020 |
aver | +0.018 |
inda | +0.017 |
Linda | +0.017 |
Jill | +0.016 |
Neg logit contributions | |
ind | -0.022 |
cha | -0.021 |
bicycles | -0.020 |
appearance | -0.019 |
festival | -0.019 |
Token | € |
Token ID | 26391 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
ind | +0.010 |
cha | +0.010 |
appearance | +0.009 |
yacht | +0.009 |
bicycles | +0.009 |
Neg logit contributions | |
opener | -0.011 |
aver | -0.009 |
inda | -0.009 |
Linda | -0.008 |
eh | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
opener | +0.042 |
aver | +0.037 |
inda | +0.034 |
Linda | +0.033 |
eh | +0.032 |
Neg logit contributions | |
ind | -0.053 |
cha | -0.052 |
appearance | -0.050 |
yacht | -0.050 |
bicycles | -0.049 |
Token | � |
Token ID | 251 |
Feature activation | -8.20e-03 |
Pos logit contributions | |
ind | +0.126 |
appearance | +0.123 |
bicycles | +0.117 |
cha | +0.115 |
ponies | +0.115 |
Neg logit contributions | |
opener | -0.106 |
aver | -0.089 |
eh | -0.082 |
Linda | -0.081 |
inn | -0.080 |
Token | he |
Token ID | 258 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
ind | +0.015 |
cha | +0.014 |
bicycles | +0.014 |
appearance | +0.014 |
yacht | +0.014 |
Neg logit contributions | |
opener | -0.013 |
aver | -0.012 |
inda | -0.011 |
Linda | -0.011 |
eh | -0.011 |
Token | went |
Token ID | 1816 |
Feature activation | -3.55e-03 |
Pos logit contributions | |
ind | +0.016 |
appearance | +0.015 |
cha | +0.015 |
bicycles | +0.015 |
ranch | +0.014 |
Neg logit contributions | |
opener | -0.018 |
aver | -0.017 |
inda | -0.016 |
Linda | -0.016 |
eh | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | -9.43e-03 |
Pos logit contributions | |
ind | +0.004 |
cha | +0.004 |
yacht | +0.004 |
re | +0.003 |
ranch | +0.003 |
Neg logit contributions | |
opener | -0.008 |
aver | -0.007 |
inda | -0.007 |
one | -0.007 |
eh | -0.007 |
Token | play |
Token ID | 711 |
Feature activation | -5.30e-03 |
Pos logit contributions | |
ind | +0.015 |
cha | +0.015 |
yacht | +0.014 |
bicycles | +0.014 |
appearance | +0.014 |
Neg logit contributions | |
opener | -0.017 |
aver | -0.015 |
inda | -0.015 |
eh | -0.014 |
Linda | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +8.04e-03 |
Pos logit contributions | |
cha | +0.021 |
ind | +0.021 |
bicycles | +0.019 |
festival | +0.019 |
helicopter | +0.019 |
Neg logit contributions | |
opener | -0.011 |
aver | -0.008 |
inda | -0.008 |
Linda | -0.008 |
eh | -0.007 |
Token | He |
Token ID | 679 |
Feature activation | +2.39e-03 |
Pos logit contributions | |
opener | +0.014 |
aver | +0.013 |
inda | +0.012 |
eh | +0.012 |
izzy | +0.011 |
Neg logit contributions | |
cha | -0.013 |
ind | -0.013 |
bicycles | -0.012 |
yacht | -0.012 |
helicopter | -0.012 |
Token | watched |
Token ID | 7342 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
opener | +0.004 |
aver | +0.004 |
inda | +0.003 |
Linda | +0.003 |
eh | +0.003 |
Neg logit contributions | |
ind | -0.004 |
cha | -0.004 |
appearance | -0.004 |
bicycles | -0.004 |
helicopter | -0.004 |
Token | them |
Token ID | 606 |
Feature activation | +3.92e-03 |
Pos logit contributions | |
ind | +0.019 |
cha | +0.017 |
appearance | +0.017 |
bicycles | +0.017 |
mall | +0.017 |
Neg logit contributions | |
opener | -0.021 |
aver | -0.019 |
inda | -0.018 |
Linda | -0.018 |
Jill | -0.018 |
Token | in |
Token ID | 287 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
opener | +0.006 |
inda | +0.004 |
Linda | +0.004 |
aver | +0.004 |
Mia | +0.004 |
Neg logit contributions | |
cha | -0.008 |
ind | -0.008 |
bicycles | -0.007 |
mall | -0.007 |
appearance | -0.007 |
Token | amaz |
Token ID | 40642 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
cha | +0.021 |
ind | +0.020 |
ize | +0.018 |
yacht | +0.018 |
helicopter | +0.018 |
Neg logit contributions | |
opener | -0.019 |
Jill | -0.016 |
Linda | -0.015 |
inda | -0.015 |
aver | -0.015 |
Token | ement |
Token ID | 972 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
ranch | +0.077 |
miss | +0.073 |
re | +0.071 |
appearance | +0.071 |
ind | +0.071 |
Neg logit contributions | |
aver | -0.127 |
opener | -0.127 |
inda | -0.125 |
Jill | -0.124 |
inn | -0.123 |
Token | and |
Token ID | 290 |
Feature activation | +1.24e-03 |
Pos logit contributions | |
opener | +0.015 |
aver | +0.013 |
inda | +0.013 |
Linda | +0.012 |
Jill | +0.012 |
Neg logit contributions | |
cha | -0.020 |
ind | -0.019 |
festival | -0.019 |
mall | -0.019 |
bicycles | -0.019 |
Token | even |
Token ID | 772 |
Feature activation | -4.94e-03 |
Pos logit contributions | |
opener | +0.002 |
Linda | +0.002 |
Jill | +0.002 |
inda | +0.002 |
aver | +0.002 |
Neg logit contributions | |
ind | -0.003 |
cha | -0.002 |
bicycles | -0.002 |
helicopter | -0.002 |
mall | -0.002 |
Token | laughed |
Token ID | 13818 |
Feature activation | -8.37e-03 |
Pos logit contributions | |
ind | +0.008 |
cha | +0.008 |
yacht | +0.007 |
re | +0.007 |
appearance | +0.007 |
Neg logit contributions | |
opener | -0.009 |
aver | -0.008 |
inda | -0.007 |
izzy | -0.007 |
eh | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -1.18e-03 |
Pos logit contributions | |
ind | +0.017 |
cha | +0.016 |
mall | +0.016 |
appearance | +0.015 |
bicycles | +0.015 |
Neg logit contributions | |
opener | -0.012 |
aver | -0.010 |
inda | -0.010 |
Linda | -0.010 |
Jill | -0.010 |
Token | his |
Token ID | 465 |
Feature activation | +4.09e-03 |
Pos logit contributions | |
opener | +0.027 |
aver | +0.024 |
inda | +0.024 |
Linda | +0.022 |
eh | +0.022 |
Neg logit contributions | |
ind | -0.026 |
cha | -0.026 |
yacht | -0.024 |
appearance | -0.024 |
bicycles | -0.023 |
Token | favorite |
Token ID | 4004 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
opener | +0.007 |
aver | +0.007 |
inda | +0.006 |
eh | +0.006 |
Linda | +0.006 |
Neg logit contributions | |
ind | -0.007 |
cha | -0.007 |
yacht | -0.006 |
bicycles | -0.006 |
appearance | -0.006 |
Token | animal |
Token ID | 5044 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
ind | +0.026 |
cha | +0.026 |
yacht | +0.024 |
bicycles | +0.023 |
appearance | +0.023 |
Neg logit contributions | |
opener | -0.029 |
aver | -0.026 |
inda | -0.025 |
eh | -0.024 |
Linda | -0.024 |
Token | â |
Token ID | 22940 |
Feature activation | -3.82e-03 |
Pos logit contributions | |
ind | +0.058 |
cha | +0.055 |
festival | +0.051 |
appearance | +0.051 |
yacht | +0.051 |
Neg logit contributions | |
opener | -0.051 |
aver | -0.044 |
inda | -0.044 |
Linda | -0.042 |
Liz | -0.040 |
Token | € |
Token ID | 26391 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
ind | +0.006 |
cha | +0.006 |
appearance | +0.006 |
festival | +0.006 |
ranch | +0.005 |
Neg logit contributions | |
opener | -0.007 |
aver | -0.006 |
inda | -0.006 |
Linda | -0.005 |
izzy | -0.005 |
Token | � |
Token ID | 447 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
opener | +0.039 |
aver | +0.036 |
inda | +0.034 |
eh | +0.032 |
Linda | +0.032 |
Neg logit contributions | |
ind | -0.034 |
cha | -0.033 |
yacht | -0.031 |
appearance | -0.031 |
bicycles | -0.030 |
Token | � |
Token ID | 251 |
Feature activation | -6.76e-03 |
Pos logit contributions | |
ind | +0.118 |
appearance | +0.114 |
cha | +0.111 |
bicycles | +0.109 |
re | +0.107 |
Neg logit contributions | |
opener | -0.113 |
aver | -0.094 |
inda | -0.090 |
eh | -0.090 |
izzy | -0.088 |
Token | a |
Token ID | 64 |
Feature activation | +6.18e-03 |
Pos logit contributions | |
ind | +0.012 |
cha | +0.012 |
bicycles | +0.011 |
yacht | +0.011 |
appearance | +0.011 |
Neg logit contributions | |
opener | -0.011 |
aver | -0.010 |
inda | -0.010 |
eh | -0.009 |
Linda | -0.009 |
Token | hipp |
Token ID | 18568 |
Feature activation | -7.39e-03 |
Pos logit contributions | |
opener | +0.013 |
aver | +0.012 |
inda | +0.012 |
eh | +0.011 |
izzy | +0.011 |
Neg logit contributions | |
cha | -0.007 |
ind | -0.007 |
re | -0.007 |
yacht | -0.007 |
bicycles | -0.007 |
Token | opot |
Token ID | 43372 |
Feature activation | +6.76e-03 |
Pos logit contributions | |
ind | +0.017 |
cha | +0.017 |
bicycles | +0.016 |
yacht | +0.016 |
appearance | +0.016 |
Neg logit contributions | |
opener | -0.008 |
aver | -0.007 |
inda | -0.006 |
eh | -0.006 |
Linda | -0.006 |
Token | amus |
Token ID | 25509 |
Feature activation | +5.20e-04 |
Pos logit contributions | |
opener | +0.014 |
aver | +0.013 |
inda | +0.012 |
eh | +0.012 |
Linda | +0.012 |
Neg logit contributions | |
ind | -0.009 |
cha | -0.009 |
bicycles | -0.008 |
yacht | -0.008 |
appearance | -0.008 |
Token | watch |
Token ID | 2342 |
Feature activation | -2.46e-03 |
Pos logit contributions | |
opener | +0.005 |
Mia | +0.004 |
inda | +0.004 |
Linda | +0.003 |
Jill | +0.003 |
Neg logit contributions | |
ind | -0.006 |
cha | -0.005 |
bicycles | -0.005 |
mall | -0.005 |
uted | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -3.24e-03 |
Pos logit contributions | |
cha | +0.005 |
ind | +0.005 |
mall | +0.004 |
iling | +0.004 |
actus | +0.004 |
Neg logit contributions | |
opener | -0.003 |
Mia | -0.003 |
Jill | -0.003 |
Liz | -0.003 |
Jen | -0.003 |
Token | big |
Token ID | 1263 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
cha | +0.006 |
ind | +0.005 |
ize | +0.005 |
uted | +0.005 |
ishly | +0.005 |
Neg logit contributions | |
opener | -0.004 |
aver | -0.004 |
eh | -0.004 |
avers | -0.003 |
Mia | -0.003 |
Token | elephant |
Token ID | 20950 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
cha | +0.020 |
ind | +0.020 |
uted | +0.019 |
aults | +0.019 |
ized | +0.018 |
Neg logit contributions | |
opener | -0.013 |
Mia | -0.012 |
Jen | -0.012 |
Jill | -0.012 |
Linda | -0.011 |
Token | in |
Token ID | 287 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
opener | +0.022 |
inda | +0.019 |
aver | +0.018 |
eh | +0.018 |
Mia | +0.017 |
Neg logit contributions | |
ind | -0.025 |
cha | -0.024 |
bicycles | -0.022 |
yacht | -0.021 |
mall | -0.021 |
Token | amaz |
Token ID | 40642 |
Feature activation | -6.65e-02 |
Pos logit contributions | |
cha | +0.036 |
ind | +0.034 |
yacht | +0.031 |
ize | +0.030 |
bicycles | +0.030 |
Neg logit contributions | |
opener | -0.020 |
Jill | -0.016 |
Linda | -0.016 |
Mia | -0.016 |
aver | -0.015 |
Token | ement |
Token ID | 972 |
Feature activation | +9.41e-03 |
Pos logit contributions | |
ind | +0.060 |
cha | +0.059 |
ranch | +0.058 |
yacht | +0.058 |
appearance | +0.058 |
Neg logit contributions | |
opener | -0.144 |
aver | -0.141 |
inda | -0.137 |
inn | -0.133 |
eh | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | +2.35e-03 |
Pos logit contributions | |
opener | +0.013 |
aver | +0.012 |
inda | +0.012 |
Linda | +0.010 |
Jill | +0.010 |
Neg logit contributions | |
cha | -0.018 |
ind | -0.018 |
bicycles | -0.017 |
festival | -0.016 |
yacht | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +2.23e-03 |
Pos logit contributions | |
opener | +0.004 |
aver | +0.004 |
inda | +0.004 |
eh | +0.004 |
izzy | +0.003 |
Neg logit contributions | |
cha | -0.004 |
ind | -0.004 |
bicycles | -0.004 |
helicopter | -0.003 |
yacht | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -9.33e-05 |
Pos logit contributions | |
opener | +0.004 |
aver | +0.004 |
inda | +0.004 |
eh | +0.004 |
Linda | +0.004 |
Neg logit contributions | |
ind | -0.003 |
cha | -0.003 |
bicycles | -0.003 |
re | -0.003 |
helicopter | -0.002 |
Token | The |
Token ID | 464 |
Feature activation | -7.81e-03 |
Pos logit contributions | |
ind | +0.000 |
cha | +0.000 |
bicycles | +0.000 |
festival | +0.000 |
helicopter | +0.000 |
Neg logit contributions | |
opener | -0.000 |
aver | -0.000 |
inda | -0.000 |
Linda | -0.000 |
izzy | -0.000 |
Token | Ben |
Token ID | 11696 |
Feature activation | -4.73e-03 |
Pos logit contributions | |
opener | +0.013 |
inda | +0.011 |
aver | +0.011 |
Linda | +0.011 |
Liz | +0.011 |
Neg logit contributions | |
ind | -0.009 |
cha | -0.008 |
bicycles | -0.007 |
festival | -0.007 |
re | -0.007 |
Token | smiled |
Token ID | 13541 |
Feature activation | +2.31e-03 |
Pos logit contributions | |
ind | +0.008 |
cha | +0.008 |
bicycles | +0.008 |
appearance | +0.008 |
yacht | +0.008 |
Neg logit contributions | |
aver | -0.007 |
opener | -0.007 |
inda | -0.007 |
Linda | -0.006 |
eh | -0.006 |
Token | � |
Token ID | 6184 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
opener | +0.004 |
aver | +0.004 |
inda | +0.004 |
Linda | +0.004 |
Jill | +0.003 |
Neg logit contributions | |
cha | -0.004 |
ind | -0.004 |
bicycles | -0.003 |
festival | -0.003 |
billboard | -0.003 |
Token | � |
Token ID | 95 |
Feature activation | +3.45e-03 |
Pos logit contributions | |
ind | +0.036 |
cha | +0.036 |
yacht | +0.033 |
appearance | +0.033 |
bicycles | +0.032 |
Neg logit contributions | |
opener | -0.036 |
aver | -0.033 |
inda | -0.031 |
eh | -0.030 |
Linda | -0.029 |
Token | € |
Token ID | 26391 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
opener | +0.006 |
aver | +0.006 |
inda | +0.005 |
Linda | +0.005 |
izzy | +0.005 |
Neg logit contributions | |
cha | -0.005 |
ind | -0.005 |
appearance | -0.005 |
festival | -0.005 |
billboard | -0.005 |
Token | � |
Token ID | 447 |
Feature activation | -6.64e-02 |
Pos logit contributions | |
opener | +0.043 |
aver | +0.039 |
inda | +0.037 |
eh | +0.036 |
Linda | +0.036 |
Neg logit contributions | |
ind | -0.036 |
cha | -0.034 |
appearance | -0.033 |
yacht | -0.033 |
bicycles | -0.032 |
Token | � |
Token ID | 250 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
ind | +0.106 |
appearance | +0.104 |
strangers | +0.098 |
bicycles | +0.098 |
ponies | +0.097 |
Neg logit contributions | |
opener | -0.120 |
aver | -0.105 |
eh | -0.100 |
inda | -0.098 |
Linda | -0.098 |
Token | it |
Token ID | 340 |
Feature activation | -6.08e-03 |
Pos logit contributions | |
ind | +0.020 |
cha | +0.019 |
bicycles | +0.017 |
re | +0.017 |
festival | +0.017 |
Neg logit contributions | |
opener | -0.033 |
aver | -0.030 |
inda | -0.029 |
eh | -0.028 |
Linda | -0.028 |
Token | had |
Token ID | 550 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
ind | +0.008 |
cha | +0.008 |
bicycles | +0.008 |
yacht | +0.007 |
appearance | +0.007 |
Neg logit contributions | |
opener | -0.012 |
aver | -0.012 |
inda | -0.011 |
eh | -0.010 |
Linda | -0.010 |
Token | been |
Token ID | 587 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
opener | +0.042 |
aver | +0.038 |
inda | +0.036 |
eh | +0.034 |
Linda | +0.034 |
Neg logit contributions | |
ind | -0.047 |
cha | -0.047 |
bicycles | -0.044 |
yacht | -0.044 |
appearance | -0.043 |
Token | a |
Token ID | 257 |
Feature activation | -6.37e-03 |
Pos logit contributions | |
opener | +0.048 |
aver | +0.042 |
inda | +0.041 |
izzy | +0.039 |
Linda | +0.038 |
Neg logit contributions | |
ind | -0.038 |
cha | -0.037 |
re | -0.034 |
appearance | -0.034 |
yacht | -0.033 |
Token | She |
Token ID | 1375 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
opener | +0.009 |
aver | +0.008 |
inda | +0.008 |
eh | +0.007 |
Linda | +0.007 |
Neg logit contributions | |
ind | -0.008 |
cha | -0.008 |
bicycles | -0.007 |
appearance | -0.007 |
yacht | -0.007 |
Token | opened |
Token ID | 4721 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
opener | +0.032 |
aver | +0.031 |
inda | +0.030 |
Linda | +0.027 |
izzy | +0.025 |
Neg logit contributions | |
ind | -0.035 |
cha | -0.035 |
appearance | -0.033 |
yacht | -0.033 |
bicycles | -0.032 |
Token | her |
Token ID | 607 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
opener | +0.031 |
inda | +0.028 |
Linda | +0.027 |
aver | +0.027 |
Jill | +0.026 |
Neg logit contributions | |
ind | -0.035 |
cha | -0.035 |
appearance | -0.032 |
yacht | -0.032 |
festival | -0.031 |
Token | mouth |
Token ID | 5422 |
Feature activation | -6.55e-03 |
Pos logit contributions | |
opener | +0.031 |
inda | +0.028 |
Linda | +0.028 |
aver | +0.027 |
Liz | +0.026 |
Neg logit contributions | |
cha | -0.028 |
ind | -0.027 |
iling | -0.025 |
ize | -0.025 |
uted | -0.025 |
Token | in |
Token ID | 287 |
Feature activation | -1.04e-03 |
Pos logit contributions | |
ind | +0.009 |
cha | +0.009 |
yacht | +0.008 |
bicycles | +0.008 |
appearance | +0.008 |
Neg logit contributions | |
opener | -0.014 |
aver | -0.013 |
inda | -0.012 |
Linda | -0.011 |
eh | -0.011 |
Token | amaz |
Token ID | 40642 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
cha | +0.002 |
ind | +0.002 |
yacht | +0.002 |
helicopter | +0.002 |
ranch | +0.002 |
Neg logit contributions | |
opener | -0.001 |
Jill | -0.001 |
Linda | -0.001 |
inda | -0.001 |
Jen | -0.001 |
Token | ement |
Token ID | 972 |
Feature activation | -2.60e-04 |
Pos logit contributions | |
ind | +0.068 |
ranch | +0.067 |
yacht | +0.065 |
cha | +0.064 |
puppies | +0.062 |
Neg logit contributions | |
opener | -0.140 |
inda | -0.134 |
aver | -0.132 |
Jill | -0.129 |
Linda | -0.128 |
Token | . |
Token ID | 13 |
Feature activation | +5.84e-03 |
Pos logit contributions | |
cha | +0.000 |
ind | +0.000 |
festival | +0.000 |
helicopter | +0.000 |
bicycles | +0.000 |
Neg logit contributions | |
opener | -0.000 |
inda | -0.000 |
Linda | -0.000 |
Jill | -0.000 |
aver | -0.000 |
Token | She |
Token ID | 1375 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
opener | +0.010 |
aver | +0.009 |
inda | +0.009 |
eh | +0.008 |
izzy | +0.008 |
Neg logit contributions | |
cha | -0.010 |
ind | -0.009 |
bicycles | -0.009 |
helicopter | -0.009 |
yacht | -0.009 |
Token | had |
Token ID | 550 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
opener | +0.027 |
aver | +0.026 |
inda | +0.025 |
Linda | +0.023 |
eh | +0.022 |
Neg logit contributions | |
ind | -0.033 |
cha | -0.032 |
yacht | -0.031 |
appearance | -0.031 |
festival | -0.031 |
Token | never |
Token ID | 1239 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
opener | +0.030 |
aver | +0.027 |
inda | +0.026 |
eh | +0.024 |
Linda | +0.024 |
Neg logit contributions | |
ind | -0.029 |
cha | -0.029 |
yacht | -0.027 |
bicycles | -0.027 |
appearance | -0.027 |
Token | special |
Token ID | 2041 |
Feature activation | -8.64e-03 |
Pos logit contributions | |
opener | +0.002 |
aver | +0.002 |
inda | +0.002 |
avers | +0.001 |
Linda | +0.001 |
Neg logit contributions | |
festival | -0.001 |
yacht | -0.001 |
helicopter | -0.001 |
cha | -0.001 |
re | -0.001 |
Token | cookie |
Token ID | 19751 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
cha | +0.011 |
ind | +0.011 |
festival | +0.011 |
helicopter | +0.011 |
yacht | +0.011 |
Neg logit contributions | |
opener | -0.017 |
aver | -0.016 |
inda | -0.016 |
izzy | -0.015 |
Linda | -0.015 |
Token | � |
Token ID | 6184 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
ind | +0.019 |
cha | +0.019 |
yacht | +0.017 |
bicycles | +0.017 |
appearance | +0.017 |
Neg logit contributions | |
opener | -0.025 |
aver | -0.023 |
inda | -0.022 |
eh | -0.021 |
Linda | -0.021 |
Token | � |
Token ID | 95 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
cha | +0.015 |
ind | +0.014 |
festival | +0.013 |
yacht | +0.013 |
appearance | +0.013 |
Neg logit contributions | |
opener | -0.021 |
aver | -0.021 |
inda | -0.020 |
Linda | -0.018 |
eh | -0.018 |
Token | € |
Token ID | 26391 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
opener | +0.024 |
aver | +0.022 |
inda | +0.021 |
izzy | +0.020 |
Linda | +0.020 |
Neg logit contributions | |
cha | -0.019 |
ind | -0.018 |
festival | -0.017 |
billboard | -0.017 |
mall | -0.016 |
Token | � |
Token ID | 447 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
opener | +0.049 |
aver | +0.045 |
inda | +0.043 |
eh | +0.041 |
Linda | +0.041 |
Neg logit contributions | |
ind | -0.037 |
cha | -0.035 |
yacht | -0.033 |
appearance | -0.033 |
bicycles | -0.033 |
Token | � |
Token ID | 251 |
Feature activation | -9.98e-04 |
Pos logit contributions | |
ind | +0.109 |
appearance | +0.106 |
bicycles | +0.102 |
cha | +0.100 |
yacht | +0.098 |
Neg logit contributions | |
opener | -0.119 |
aver | -0.104 |
eh | -0.100 |
inda | -0.097 |
Linda | -0.095 |
Token | it |
Token ID | 340 |
Feature activation | -4.79e-03 |
Pos logit contributions | |
cha | +0.002 |
ind | +0.001 |
yacht | +0.001 |
re | +0.001 |
festival | +0.001 |
Neg logit contributions | |
opener | -0.002 |
aver | -0.002 |
inda | -0.002 |
eh | -0.002 |
avers | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +2.10e-03 |
Pos logit contributions | |
ind | +0.008 |
cha | +0.007 |
bicycles | +0.007 |
yacht | +0.007 |
appearance | +0.007 |
Neg logit contributions | |
opener | -0.009 |
aver | -0.008 |
inda | -0.008 |
eh | -0.007 |
Linda | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +3.04e-04 |
Pos logit contributions | |
opener | +0.004 |
aver | +0.003 |
inda | +0.003 |
eh | +0.003 |
Linda | +0.003 |
Neg logit contributions | |
ind | -0.004 |
cha | -0.004 |
bicycles | -0.003 |
yacht | -0.003 |
appearance | -0.003 |
Token | most |
Token ID | 749 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
opener | +0.001 |
aver | +0.000 |
inda | +0.000 |
eh | +0.000 |
Linda | +0.000 |
Neg logit contributions | |
ind | -0.000 |
cha | -0.000 |
bicycles | -0.000 |
ize | -0.000 |
appearance | -0.000 |
Token | her |
Token ID | 607 |
Feature activation | +1.98e-03 |
Pos logit contributions | |
ind | +0.018 |
cha | +0.017 |
aults | +0.015 |
iling | +0.015 |
yacht | +0.015 |
Neg logit contributions | |
opener | -0.009 |
Linda | -0.009 |
Liz | -0.009 |
Jill | -0.009 |
inda | -0.008 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
opener | +0.003 |
aver | +0.003 |
inda | +0.003 |
Linda | +0.003 |
izzy | +0.003 |
Neg logit contributions | |
cha | -0.003 |
ind | -0.003 |
appearance | -0.003 |
yacht | -0.003 |
bicycles | -0.003 |
Token | my |
Token ID | 1820 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
cha | +0.035 |
ind | +0.034 |
yacht | +0.032 |
appearance | +0.032 |
festival | +0.032 |
Neg logit contributions | |
opener | -0.025 |
aver | -0.023 |
inda | -0.021 |
Linda | -0.020 |
izzy | -0.019 |
Token | watched |
Token ID | 7342 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
cha | +0.029 |
ind | +0.029 |
appearance | +0.027 |
festival | +0.026 |
yacht | +0.025 |
Neg logit contributions | |
aver | -0.028 |
opener | -0.028 |
inda | -0.026 |
Linda | -0.024 |
avers | -0.024 |
Token | in |
Token ID | 287 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
ind | +0.040 |
appearance | +0.036 |
mall | +0.036 |
actus | +0.035 |
bicycles | +0.035 |
Neg logit contributions | |
opener | -0.020 |
Linda | -0.017 |
Liz | -0.016 |
Mia | -0.015 |
Jill | -0.015 |
Token | amaz |
Token ID | 40642 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
ind | +0.021 |
cha | +0.020 |
ize | +0.017 |
yacht | +0.017 |
bicycles | +0.017 |
Neg logit contributions | |
opener | -0.026 |
Linda | -0.022 |
Jill | -0.022 |
inda | -0.021 |
Jen | -0.021 |
Token | ement |
Token ID | 972 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
ind | +0.068 |
ranch | +0.067 |
appearance | +0.065 |
yacht | +0.063 |
aults | +0.063 |
Neg logit contributions | |
opener | -0.133 |
inda | -0.129 |
aver | -0.129 |
Jill | -0.126 |
inn | -0.125 |
Token | as |
Token ID | 355 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
opener | +0.014 |
inda | +0.012 |
aver | +0.011 |
Linda | +0.011 |
Liz | +0.011 |
Neg logit contributions | |
cha | -0.022 |
ind | -0.022 |
mall | -0.021 |
bicycles | -0.021 |
festival | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -2.24e-03 |
Pos logit contributions | |
opener | +0.025 |
Linda | +0.022 |
inda | +0.021 |
aver | +0.021 |
Liz | +0.021 |
Neg logit contributions | |
ind | -0.027 |
cha | -0.026 |
appearance | -0.025 |
yacht | -0.024 |
bicycles | -0.024 |
Token | machine |
Token ID | 4572 |
Feature activation | +8.90e-03 |
Pos logit contributions | |
helicopter | +0.003 |
ind | +0.003 |
yacht | +0.003 |
cha | +0.003 |
re | +0.003 |
Neg logit contributions | |
opener | -0.004 |
inda | -0.004 |
aver | -0.004 |
eh | -0.004 |
inn | -0.004 |
Token | flew |
Token ID | 13112 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
opener | +0.014 |
aver | +0.012 |
inda | +0.012 |
Linda | +0.011 |
avers | +0.010 |
Neg logit contributions | |
ind | -0.018 |
cha | -0.016 |
appearance | -0.016 |
bicycles | -0.015 |
yacht | -0.015 |
Token | with |
Token ID | 351 |
Feature activation | +4.85e-04 |
Pos logit contributions | |
cha | +0.046 |
ind | +0.045 |
bicycles | +0.043 |
yacht | +0.042 |
appearance | +0.041 |
Neg logit contributions | |
opener | -0.043 |
inda | -0.038 |
Jill | -0.037 |
Linda | -0.037 |
aver | -0.035 |
Token | joy |
Token ID | 8716 |
Feature activation | +1.76e-03 |
Pos logit contributions | |
opener | +0.001 |
inda | +0.001 |
Linda | +0.001 |
Jill | +0.001 |
aver | +0.001 |
Neg logit contributions | |
ind | -0.001 |
cha | -0.001 |
ranch | -0.001 |
yacht | -0.001 |
appearance | -0.001 |
Token | � |
Token ID | 6184 |
Feature activation | -9.02e-03 |
Pos logit contributions | |
opener | +0.003 |
inda | +0.002 |
Linda | +0.002 |
Jill | +0.002 |
aver | +0.002 |
Neg logit contributions | |
cha | -0.003 |
ind | -0.003 |
bicycles | -0.003 |
helicopter | -0.003 |
festival | -0.003 |
Token | � |
Token ID | 95 |
Feature activation | +5.12e-03 |
Pos logit contributions | |
ind | +0.014 |
cha | +0.014 |
yacht | +0.013 |
appearance | +0.013 |
festival | +0.013 |
Neg logit contributions | |
opener | -0.016 |
aver | -0.015 |
inda | -0.014 |
eh | -0.014 |
Linda | -0.013 |
Token | € |
Token ID | 26391 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
opener | +0.009 |
aver | +0.009 |
eh | +0.008 |
inda | +0.008 |
avers | +0.008 |
Neg logit contributions | |
ind | -0.008 |
cha | -0.008 |
appearance | -0.007 |
festival | -0.007 |
billboard | -0.007 |
Token | � |
Token ID | 447 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
opener | +0.050 |
aver | +0.046 |
inda | +0.044 |
eh | +0.042 |
Linda | +0.041 |
Neg logit contributions | |
ind | -0.037 |
cha | -0.036 |
yacht | -0.033 |
bicycles | -0.033 |
appearance | -0.033 |
Token | � |
Token ID | 250 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
ind | +0.106 |
appearance | +0.102 |
bicycles | +0.098 |
cha | +0.095 |
strangers | +0.094 |
Neg logit contributions | |
opener | -0.124 |
aver | -0.105 |
inda | -0.103 |
eh | -0.101 |
Linda | -0.100 |
Token | now |
Token ID | 783 |
Feature activation | -5.50e-03 |
Pos logit contributions | |
ind | +0.019 |
cha | +0.018 |
bicycles | +0.016 |
re | +0.016 |
festival | +0.016 |
Neg logit contributions | |
opener | -0.028 |
aver | -0.026 |
inda | -0.025 |
eh | -0.024 |
Linda | -0.023 |
Token | she |
Token ID | 673 |
Feature activation | +2.60e-03 |
Pos logit contributions | |
ind | +0.009 |
cha | +0.008 |
bicycles | +0.008 |
yacht | +0.008 |
ranch | +0.008 |
Neg logit contributions | |
opener | -0.010 |
inda | -0.009 |
aver | -0.009 |
Linda | -0.009 |
Jill | -0.008 |
Token | could |
Token ID | 714 |
Feature activation | -2.45e-03 |
Pos logit contributions | |
opener | +0.005 |
aver | +0.005 |
inda | +0.005 |
Linda | +0.005 |
izzy | +0.004 |
Neg logit contributions | |
ind | -0.004 |
cha | -0.003 |
bicycles | -0.003 |
yacht | -0.003 |
appearance | -0.003 |
Token | write |
Token ID | 3551 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
ind | +0.004 |
cha | +0.004 |
bicycles | +0.004 |
yacht | +0.004 |
appearance | +0.004 |
Neg logit contributions | |
opener | -0.004 |
aver | -0.004 |
inda | -0.004 |
Linda | -0.003 |
eh | -0.003 |
Token | A |
Token ID | 32 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
opener | +0.001 |
inda | +0.001 |
aver | +0.001 |
izzy | +0.001 |
iddle | +0.001 |
Neg logit contributions | |
ind | -0.001 |
cha | -0.001 |
yacht | -0.001 |
re | -0.001 |
helicopter | -0.001 |
Token | man |
Token ID | 582 |
Feature activation | +3.16e-03 |
Pos logit contributions | |
helicopter | +0.012 |
re | +0.011 |
bell | +0.011 |
yacht | +0.011 |
festival | +0.010 |
Neg logit contributions | |
opener | -0.026 |
inda | -0.025 |
izzy | -0.024 |
inn | -0.023 |
iddle | -0.023 |
Token | heard |
Token ID | 2982 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
opener | +0.004 |
aver | +0.004 |
inda | +0.004 |
eh | +0.003 |
avers | +0.003 |
Neg logit contributions | |
ind | -0.006 |
appearance | -0.006 |
cha | -0.006 |
yacht | -0.006 |
ranch | -0.006 |
Token | them |
Token ID | 606 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
opener | +0.047 |
aver | +0.043 |
inda | +0.042 |
Linda | +0.040 |
eh | +0.039 |
Neg logit contributions | |
ind | -0.031 |
cha | -0.031 |
appearance | -0.028 |
bicycles | -0.028 |
yacht | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
opener | +0.023 |
aver | +0.019 |
Liz | +0.018 |
Jen | +0.017 |
inda | +0.017 |
Neg logit contributions | |
cha | -0.024 |
ind | -0.024 |
festival | -0.023 |
appearance | -0.022 |
culture | -0.022 |
Token | came |
Token ID | 1625 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
opener | +0.029 |
aver | +0.027 |
inda | +0.026 |
eh | +0.024 |
inn | +0.024 |
Neg logit contributions | |
cha | -0.025 |
ind | -0.024 |
re | -0.023 |
yacht | -0.023 |
bicycles | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | -4.68e-03 |
Pos logit contributions | |
opener | +0.075 |
aver | +0.070 |
inda | +0.065 |
eh | +0.063 |
izzy | +0.060 |
Neg logit contributions | |
ind | -0.070 |
cha | -0.066 |
bicycles | -0.063 |
re | -0.063 |
appearance | -0.060 |
Token | see |
Token ID | 766 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
ind | +0.008 |
cha | +0.007 |
yacht | +0.007 |
bicycles | +0.007 |
appearance | +0.007 |
Neg logit contributions | |
opener | -0.008 |
aver | -0.008 |
inda | -0.007 |
eh | -0.007 |
izzy | -0.007 |
Token | what |
Token ID | 644 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
opener | +0.021 |
aver | +0.019 |
inda | +0.019 |
Linda | +0.018 |
eh | +0.017 |
Neg logit contributions | |
ind | -0.015 |
cha | -0.015 |
yacht | -0.014 |
bicycles | -0.014 |
appearance | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | -4.64e-03 |
Pos logit contributions | |
ind | +0.034 |
cha | +0.034 |
bicycles | +0.031 |
yacht | +0.031 |
appearance | +0.031 |
Neg logit contributions | |
opener | -0.051 |
aver | -0.047 |
inda | -0.045 |
eh | -0.043 |
Linda | -0.042 |
Token | wrong |
Token ID | 2642 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
ind | +0.007 |
cha | +0.007 |
appearance | +0.007 |
bicycles | +0.007 |
yacht | +0.007 |
Neg logit contributions | |
aver | -0.008 |
opener | -0.008 |
eh | -0.007 |
inda | -0.007 |
avers | -0.007 |
Token | for |
Token ID | 329 |
Feature activation | -7.20e-03 |
Pos logit contributions | |
opener | +0.027 |
Liz | +0.026 |
Linda | +0.026 |
Jill | +0.025 |
Mia | +0.024 |
Neg logit contributions | |
ind | -0.039 |
cha | -0.035 |
uted | -0.034 |
bicycles | -0.033 |
aults | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | -8.14e-04 |
Pos logit contributions | |
ind | +0.014 |
cha | +0.014 |
bicycles | +0.013 |
re | +0.013 |
festival | +0.013 |
Neg logit contributions | |
opener | -0.010 |
aver | -0.009 |
inda | -0.009 |
eh | -0.008 |
izzy | -0.008 |
Token | while |
Token ID | 981 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
ind | +0.001 |
cha | +0.001 |
yacht | +0.001 |
festival | +0.001 |
ranch | +0.001 |
Neg logit contributions | |
opener | -0.001 |
aver | -0.001 |
inda | -0.001 |
izzy | -0.001 |
Linda | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
opener | +0.025 |
aver | +0.023 |
inda | +0.022 |
Linda | +0.022 |
eh | +0.021 |
Neg logit contributions | |
ind | -0.018 |
cha | -0.017 |
bicycles | -0.016 |
yacht | -0.015 |
appearance | -0.015 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
opener | +0.017 |
aver | +0.015 |
inda | +0.014 |
Linda | +0.013 |
eh | +0.013 |
Neg logit contributions | |
ind | -0.028 |
cha | -0.028 |
bicycles | -0.026 |
yacht | -0.026 |
appearance | -0.026 |
Token | came |
Token ID | 1625 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
opener | +0.025 |
aver | +0.024 |
inda | +0.023 |
eh | +0.022 |
Linda | +0.022 |
Neg logit contributions | |
ind | -0.017 |
cha | -0.017 |
bicycles | -0.016 |
yacht | -0.016 |
appearance | -0.016 |
Token | back |
Token ID | 736 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
opener | +0.102 |
aver | +0.095 |
inda | +0.090 |
eh | +0.086 |
izzy | +0.086 |
Neg logit contributions | |
ind | -0.052 |
cha | -0.042 |
bicycles | -0.041 |
re | -0.040 |
forever | -0.040 |
Token | inside |
Token ID | 2641 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
cha | +0.041 |
ind | +0.040 |
yacht | +0.038 |
bicycles | +0.038 |
appearance | +0.037 |
Neg logit contributions | |
opener | -0.035 |
aver | -0.029 |
inda | -0.028 |
Linda | -0.028 |
eh | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
ind | +0.015 |
cha | +0.014 |
yacht | +0.013 |
bicycles | +0.013 |
appearance | +0.013 |
Neg logit contributions | |
opener | -0.020 |
aver | -0.018 |
inda | -0.017 |
eh | -0.016 |
Linda | -0.016 |
Token | asked |
Token ID | 1965 |
Feature activation | -8.84e-03 |
Pos logit contributions | |
ind | +0.022 |
cha | +0.022 |
bicycles | +0.020 |
appearance | +0.020 |
yacht | +0.020 |
Neg logit contributions | |
opener | -0.021 |
aver | -0.019 |
inda | -0.018 |
Linda | -0.017 |
eh | -0.017 |
Token | for |
Token ID | 329 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
ind | +0.016 |
cha | +0.016 |
yacht | +0.015 |
appearance | +0.014 |
bicycles | +0.014 |
Neg logit contributions | |
opener | -0.014 |
inda | -0.012 |
Linda | -0.012 |
aver | -0.012 |
Liz | -0.011 |
Token | there |
Token ID | 612 |
Feature activation | +7.23e-03 |
Pos logit contributions | |
opener | +0.012 |
aver | +0.011 |
inda | +0.010 |
Linda | +0.010 |
eh | +0.010 |
Neg logit contributions | |
ind | -0.008 |
cha | -0.008 |
yacht | -0.007 |
helicopter | -0.007 |
bicycles | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
opener | +0.012 |
aver | +0.012 |
inda | +0.011 |
izzy | +0.010 |
Linda | +0.010 |
Neg logit contributions | |
ind | -0.012 |
cha | -0.012 |
yacht | -0.011 |
appearance | -0.011 |
bicycles | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -9.04e-03 |
Pos logit contributions | |
opener | +0.024 |
aver | +0.020 |
inda | +0.019 |
Linda | +0.017 |
izzy | +0.017 |
Neg logit contributions | |
ind | -0.036 |
cha | -0.036 |
bicycles | -0.034 |
yacht | -0.034 |
helicopter | -0.034 |
Token | little |
Token ID | 1310 |
Feature activation | -5.52e-03 |
Pos logit contributions | |
cha | +0.017 |
bicycles | +0.016 |
appearance | +0.016 |
aren | +0.015 |
ishly | +0.015 |
Neg logit contributions | |
aver | -0.014 |
opener | -0.014 |
eh | -0.012 |
inda | -0.011 |
avers | -0.011 |
Token | boy |
Token ID | 2933 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
cha | +0.010 |
appearance | +0.010 |
bicycles | +0.009 |
ind | +0.009 |
uted | +0.009 |
Neg logit contributions | |
opener | -0.008 |
aver | -0.008 |
izzy | -0.007 |
Linda | -0.007 |
eh | -0.007 |
Token | named |
Token ID | 3706 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
opener | +0.031 |
inda | +0.027 |
aver | +0.026 |
Linda | +0.025 |
izzy | +0.024 |
Neg logit contributions | |
ind | -0.029 |
cha | -0.026 |
re | -0.026 |
yacht | -0.025 |
helicopter | -0.025 |
Token | Alex |
Token ID | 4422 |
Feature activation | -3.28e-03 |
Pos logit contributions | |
opener | +0.100 |
aver | +0.093 |
inda | +0.089 |
eh | +0.084 |
Linda | +0.081 |
Neg logit contributions | |
ind | -0.073 |
cha | -0.073 |
yacht | -0.068 |
bicycles | -0.068 |
helicopter | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | -7.40e-03 |
Pos logit contributions | |
cha | +0.006 |
ind | +0.006 |
bicycles | +0.005 |
appearance | +0.005 |
yacht | +0.005 |
Neg logit contributions | |
opener | -0.005 |
aver | -0.005 |
inda | -0.005 |
eh | -0.004 |
izzy | -0.004 |
Token | He |
Token ID | 679 |
Feature activation | -1.26e-03 |
Pos logit contributions | |
ind | +0.013 |
cha | +0.013 |
bicycles | +0.013 |
yacht | +0.012 |
appearance | +0.012 |
Neg logit contributions | |
opener | -0.011 |
aver | -0.011 |
inda | -0.010 |
eh | -0.010 |
avers | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -4.56e-03 |
Pos logit contributions | |
cha | +0.001 |
ind | +0.001 |
appearance | +0.001 |
yacht | +0.001 |
bicycles | +0.001 |
Neg logit contributions | |
opener | -0.003 |
aver | -0.003 |
inda | -0.003 |
eh | -0.003 |
izzy | -0.002 |
Token | always |
Token ID | 1464 |
Feature activation | -4.34e-03 |
Pos logit contributions | |
ind | +0.007 |
cha | +0.007 |
yacht | +0.006 |
re | +0.006 |
bicycles | +0.006 |
Neg logit contributions | |
opener | -0.009 |
aver | -0.008 |
inda | -0.008 |
eh | -0.007 |
Linda | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +2.48e-03 |
Pos logit contributions | |
opener | +0.035 |
aver | +0.031 |
inda | +0.029 |
Linda | +0.028 |
eh | +0.028 |
Neg logit contributions | |
ind | -0.037 |
cha | -0.036 |
yacht | -0.034 |
bicycles | -0.034 |
helicopter | -0.034 |
Token | I |
Token ID | 314 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
opener | +0.005 |
aver | +0.005 |
inda | +0.005 |
eh | +0.005 |
avers | +0.004 |
Neg logit contributions | |
cha | -0.003 |
ind | -0.003 |
bicycles | -0.003 |
appearance | -0.003 |
helicopter | -0.003 |
Token | should |
Token ID | 815 |
Feature activation | -3.14e-03 |
Pos logit contributions | |
opener | +0.027 |
aver | +0.025 |
inda | +0.024 |
eh | +0.023 |
Linda | +0.023 |
Neg logit contributions | |
ind | -0.015 |
cha | -0.015 |
yacht | -0.014 |
bicycles | -0.014 |
appearance | -0.014 |
Token | not |
Token ID | 407 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
ind | +0.006 |
cha | +0.006 |
bicycles | +0.006 |
appearance | +0.005 |
yacht | +0.005 |
Neg logit contributions | |
opener | -0.005 |
aver | -0.004 |
inda | -0.004 |
Linda | -0.004 |
Jill | -0.004 |
Token | have |
Token ID | 423 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
opener | +0.023 |
aver | +0.021 |
inda | +0.021 |
eh | +0.019 |
Linda | +0.019 |
Neg logit contributions | |
ind | -0.015 |
cha | -0.015 |
appearance | -0.014 |
bicycles | -0.014 |
yacht | -0.014 |
Token | taken |
Token ID | 2077 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
opener | +0.059 |
aver | +0.053 |
inda | +0.052 |
izzy | +0.049 |
Linda | +0.048 |
Neg logit contributions | |
ind | -0.054 |
cha | -0.053 |
bicycles | -0.051 |
appearance | -0.050 |
yacht | -0.050 |
Token | your |
Token ID | 534 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
opener | +0.096 |
aver | +0.090 |
inda | +0.085 |
eh | +0.082 |
izzy | +0.080 |
Neg logit contributions | |
ind | -0.060 |
cha | -0.059 |
bicycles | -0.055 |
appearance | -0.054 |
yacht | -0.053 |
Token | sack |
Token ID | 23704 |
Feature activation | +5.50e-03 |
Pos logit contributions | |
opener | +0.042 |
aver | +0.036 |
inda | +0.035 |
Linda | +0.034 |
eh | +0.033 |
Neg logit contributions | |
ind | -0.027 |
cha | -0.026 |
re | -0.022 |
festival | -0.022 |
bicycles | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -5.42e-04 |
Pos logit contributions | |
opener | +0.010 |
aver | +0.009 |
inda | +0.008 |
eh | +0.008 |
Linda | +0.008 |
Neg logit contributions | |
ind | -0.009 |
cha | -0.009 |
bicycles | -0.009 |
yacht | -0.008 |
appearance | -0.008 |
Token | I |
Token ID | 314 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
cha | +0.001 |
ind | +0.001 |
appearance | +0.001 |
bicycles | +0.001 |
helicopter | +0.001 |
Neg logit contributions | |
opener | -0.001 |
aver | -0.001 |
inda | -0.001 |
eh | -0.001 |
avers | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +4.48e-03 |
Pos logit contributions | |
opener | +0.030 |
aver | +0.027 |
inda | +0.026 |
Linda | +0.025 |
eh | +0.025 |
Neg logit contributions | |
ind | -0.018 |
cha | -0.017 |
bicycles | -0.016 |
yacht | -0.016 |
appearance | -0.016 |
Token | jail |
Token ID | 7356 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
opener | +0.033 |
aver | +0.029 |
inda | +0.028 |
Linda | +0.028 |
Jill | +0.027 |
Neg logit contributions | |
ind | -0.032 |
cha | -0.029 |
bicycles | -0.028 |
yacht | -0.027 |
ranch | -0.027 |
Token | is |
Token ID | 318 |
Feature activation | +9.72e-04 |
Pos logit contributions | |
opener | +0.030 |
aver | +0.028 |
inda | +0.027 |
Linda | +0.026 |
Liz | +0.025 |
Neg logit contributions | |
ind | -0.021 |
cha | -0.020 |
bicycles | -0.019 |
yacht | -0.019 |
appearance | -0.018 |
Token | like |
Token ID | 588 |
Feature activation | -1.32e-03 |
Pos logit contributions | |
opener | +0.002 |
aver | +0.002 |
inda | +0.002 |
eh | +0.001 |
Linda | +0.001 |
Neg logit contributions | |
ind | -0.002 |
cha | -0.001 |
bicycles | -0.001 |
yacht | -0.001 |
appearance | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -2.36e-03 |
Pos logit contributions | |
ind | +0.003 |
cha | +0.002 |
appearance | +0.002 |
yacht | +0.002 |
bicycles | +0.002 |
Neg logit contributions | |
opener | -0.002 |
aver | -0.002 |
inda | -0.002 |
Linda | -0.002 |
Jill | -0.002 |
Token | time |
Token ID | 640 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
cha | +0.004 |
ind | +0.004 |
uted | +0.004 |
bicycles | +0.004 |
iling | +0.004 |
Neg logit contributions | |
opener | -0.004 |
aver | -0.004 |
eh | -0.003 |
Linda | -0.003 |
Jill | -0.003 |
Token | - |
Token ID | 12 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
opener | +0.077 |
aver | +0.069 |
inda | +0.065 |
Linda | +0.062 |
Jill | +0.060 |
Neg logit contributions | |
ind | -0.080 |
cha | -0.078 |
bicycles | -0.073 |
yacht | -0.072 |
appearance | -0.070 |
Token | out |
Token ID | 448 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
opener | +0.068 |
aver | +0.061 |
inda | +0.058 |
Linda | +0.054 |
eh | +0.054 |
Neg logit contributions | |
ind | -0.073 |
cha | -0.072 |
yacht | -0.067 |
bicycles | -0.067 |
helicopter | -0.066 |
Token | for |
Token ID | 329 |
Feature activation | +2.14e-03 |
Pos logit contributions | |
opener | +0.020 |
aver | +0.019 |
inda | +0.017 |
eh | +0.017 |
Jill | +0.016 |
Neg logit contributions | |
ind | -0.021 |
cha | -0.020 |
bicycles | -0.019 |
appearance | -0.018 |
yacht | -0.017 |
Token | grown |
Token ID | 7334 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
opener | +0.004 |
aver | +0.003 |
Jill | +0.003 |
Linda | +0.003 |
inda | +0.003 |
Neg logit contributions | |
cha | -0.003 |
ind | -0.003 |
yacht | -0.003 |
bicycles | -0.003 |
helicopter | -0.003 |
Token | - |
Token ID | 12 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
opener | +0.087 |
aver | +0.080 |
inda | +0.077 |
izzy | +0.074 |
Linda | +0.073 |
Neg logit contributions | |
ind | -0.062 |
cha | -0.057 |
bicycles | -0.053 |
appearance | -0.053 |
yacht | -0.053 |
Token | ups |
Token ID | 4739 |
Feature activation | +9.87e-03 |
Pos logit contributions | |
opener | +0.075 |
aver | +0.066 |
inda | +0.062 |
Linda | +0.057 |
izzy | +0.055 |
Neg logit contributions | |
ind | -0.130 |
cha | -0.127 |
bicycles | -0.120 |
yacht | -0.120 |
helicopter | -0.118 |
Token | were |
Token ID | 547 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
ind | +0.008 |
cha | +0.007 |
appearance | +0.007 |
ranch | +0.007 |
aults | +0.007 |
Neg logit contributions | |
opener | -0.006 |
Jill | -0.005 |
aver | -0.005 |
Liz | -0.005 |
Linda | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
opener | +0.026 |
aver | +0.024 |
inda | +0.022 |
Linda | +0.021 |
Jill | +0.021 |
Neg logit contributions | |
ind | -0.027 |
cha | -0.027 |
appearance | -0.024 |
yacht | -0.024 |
ize | -0.024 |
Token | few |
Token ID | 1178 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
cha | +0.025 |
ind | +0.024 |
iling | +0.023 |
uted | +0.023 |
bicycles | +0.022 |
Neg logit contributions | |
opener | -0.024 |
aver | -0.022 |
Linda | -0.020 |
eh | -0.019 |
inda | -0.019 |
Token | pictures |
Token ID | 5986 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
opener | +0.038 |
aver | +0.036 |
inda | +0.034 |
eh | +0.033 |
Linda | +0.032 |
Neg logit contributions | |
ind | -0.030 |
cha | -0.029 |
yacht | -0.027 |
appearance | -0.027 |
bicycles | -0.026 |
Token | on |
Token ID | 319 |
Feature activation | -2.14e-03 |
Pos logit contributions | |
opener | +0.022 |
aver | +0.017 |
inda | +0.016 |
Linda | +0.014 |
Jill | +0.014 |
Neg logit contributions | |
ind | -0.040 |
cha | -0.037 |
appearance | -0.036 |
yacht | -0.034 |
bicycles | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | +7.88e-03 |
Pos logit contributions | |
cha | +0.004 |
ind | +0.004 |
appearance | +0.004 |
ishly | +0.004 |
aren | +0.004 |
Neg logit contributions | |
opener | -0.003 |
Jill | -0.003 |
Linda | -0.002 |
inda | -0.002 |
aver | -0.002 |
Token | walls |
Token ID | 7714 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
opener | +0.012 |
inda | +0.010 |
aver | +0.010 |
Liz | +0.010 |
Linda | +0.010 |
Neg logit contributions | |
cha | -0.014 |
ind | -0.013 |
iling | -0.013 |
ize | -0.013 |
uted | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +5.57e-03 |
Pos logit contributions | |
opener | +0.026 |
aver | +0.022 |
inda | +0.021 |
Jill | +0.020 |
Linda | +0.020 |
Neg logit contributions | |
ind | -0.029 |
cha | -0.029 |
helicopter | -0.026 |
appearance | -0.026 |
bicycles | -0.026 |
Token | |
Token ID | 220 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
opener | +0.009 |
aver | +0.008 |
inda | +0.008 |
eh | +0.007 |
Linda | +0.007 |
Neg logit contributions | |
ind | -0.010 |
cha | -0.010 |
bicycles | -0.009 |
yacht | -0.009 |
appearance | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +6.48e-03 |
Pos logit contributions | |
opener | +0.033 |
aver | +0.033 |
inda | +0.031 |
eh | +0.030 |
Linda | +0.028 |
Neg logit contributions | |
cha | -0.027 |
ind | -0.027 |
bicycles | -0.026 |
aren | -0.025 |
yacht | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +3.50e-03 |
Pos logit contributions | |
opener | +0.011 |
aver | +0.011 |
inda | +0.010 |
eh | +0.010 |
Linda | +0.010 |
Neg logit contributions | |
ind | -0.010 |
cha | -0.010 |
bicycles | -0.010 |
yacht | -0.009 |
helicopter | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +9.32e-04 |
Pos logit contributions | |
opener | +0.010 |
inda | +0.010 |
aver | +0.010 |
eh | +0.009 |
wn | +0.009 |
Neg logit contributions | |
ind | -0.004 |
cha | -0.004 |
us | -0.003 |
re | -0.003 |
wishes | -0.003 |
Token | " |
Token ID | 1 |
Feature activation | -7.07e-03 |
Pos logit contributions | |
opener | +0.002 |
inda | +0.002 |
iddle | +0.002 |
Liz | +0.002 |
izzy | +0.002 |
Neg logit contributions | |
ind | -0.001 |
cha | -0.001 |
village | -0.001 |
aults | -0.001 |
country | -0.001 |
Token | Let |
Token ID | 5756 |
Feature activation | -1.88e-03 |
Pos logit contributions | |
ind | +0.009 |
cha | +0.009 |
yacht | +0.009 |
bicycles | +0.009 |
festival | +0.008 |
Neg logit contributions | |
opener | -0.014 |
aver | -0.013 |
inda | -0.013 |
eh | -0.012 |
Linda | -0.012 |
Token | 's |
Token ID | 338 |
Feature activation | +4.14e-03 |
Pos logit contributions | |
ind | +0.003 |
bicycles | +0.003 |
cha | +0.003 |
appearance | +0.003 |
festival | +0.003 |
Neg logit contributions | |
opener | -0.003 |
inda | -0.003 |
aver | -0.003 |
Linda | -0.003 |
Jill | -0.003 |
Token | go |
Token ID | 467 |
Feature activation | -4.12e-03 |
Pos logit contributions | |
opener | +0.007 |
aver | +0.006 |
inda | +0.006 |
Linda | +0.006 |
Jill | +0.005 |
Neg logit contributions | |
ind | -0.007 |
cha | -0.007 |
bicycles | -0.007 |
appearance | -0.007 |
ponies | -0.007 |
Token | see |
Token ID | 766 |
Feature activation | +7.67e-03 |
Pos logit contributions | |
ind | +0.005 |
cha | +0.005 |
yacht | +0.005 |
re | +0.004 |
helicopter | +0.004 |
Neg logit contributions | |
opener | -0.009 |
aver | -0.008 |
inda | -0.008 |
eh | -0.008 |
Linda | -0.007 |
Token | it |
Token ID | 340 |
Feature activation | -6.64e-03 |
Pos logit contributions | |
opener | +0.010 |
Jill | +0.010 |
Jen | +0.010 |
Mia | +0.010 |
aver | +0.009 |
Neg logit contributions | |
ind | -0.014 |
cha | -0.013 |
appearance | -0.013 |
ranch | -0.013 |
ishly | -0.013 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
ind | +0.012 |
cha | +0.012 |
bicycles | +0.011 |
yacht | +0.011 |
appearance | +0.011 |
Neg logit contributions | |
opener | -0.010 |
inda | -0.009 |
aver | -0.009 |
Linda | -0.008 |
Mia | -0.008 |
Token | Jen |
Token ID | 13364 |
Feature activation | +6.81e-03 |
Pos logit contributions | |
aver | +0.025 |
eh | +0.024 |
opener | +0.024 |
inda | +0.023 |
iddle | +0.023 |
Neg logit contributions | |
cha | -0.019 |
yacht | -0.018 |
re | -0.018 |
puppy | -0.017 |
helicopter | -0.017 |
Token | said |
Token ID | 531 |
Feature activation | +6.82e-03 |
Pos logit contributions | |
opener | +0.012 |
aver | +0.011 |
inda | +0.010 |
eh | +0.010 |
Linda | +0.010 |
Neg logit contributions | |
ind | -0.011 |
cha | -0.011 |
bicycles | -0.010 |
yacht | -0.010 |
re | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +4.95e-03 |
Pos logit contributions | |
opener | +0.013 |
aver | +0.013 |
inda | +0.012 |
eh | +0.012 |
izzy | +0.011 |
Neg logit contributions | |
cha | -0.010 |
ind | -0.009 |
yacht | -0.009 |
bicycles | -0.009 |
re | -0.009 |
Token | She |
Token ID | 1375 |
Feature activation | +5.84e-03 |
Pos logit contributions | |
ind | +0.004 |
cha | +0.004 |
bicycles | +0.004 |
appearance | +0.004 |
helicopter | +0.004 |
Neg logit contributions | |
opener | -0.008 |
aver | -0.008 |
inda | -0.007 |
eh | -0.007 |
avers | -0.007 |
Token | learned |
Token ID | 4499 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
opener | +0.011 |
aver | +0.010 |
inda | +0.009 |
eh | +0.009 |
Linda | +0.009 |
Neg logit contributions | |
ind | -0.009 |
cha | -0.009 |
yacht | -0.008 |
bicycles | -0.008 |
appearance | -0.008 |
Token | her |
Token ID | 607 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
aver | +0.046 |
opener | +0.046 |
inda | +0.043 |
eh | +0.041 |
izzy | +0.041 |
Neg logit contributions | |
ind | -0.032 |
cha | -0.030 |
bicycles | -0.030 |
helicopter | -0.029 |
ponies | -0.029 |
Token | lesson |
Token ID | 11483 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
opener | +0.022 |
aver | +0.020 |
inda | +0.019 |
eh | +0.018 |
Linda | +0.018 |
Neg logit contributions | |
ind | -0.020 |
cha | -0.020 |
yacht | -0.019 |
bicycles | -0.019 |
helicopter | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -9.87e-03 |
Pos logit contributions | |
ind | +0.023 |
cha | +0.022 |
yacht | +0.022 |
helicopter | +0.021 |
ranch | +0.021 |
Neg logit contributions | |
opener | -0.025 |
inda | -0.022 |
aver | -0.022 |
Linda | -0.020 |
izzy | -0.020 |
Token | She |
Token ID | 1375 |
Feature activation | +8.58e-03 |
Pos logit contributions | |
ind | +0.013 |
cha | +0.012 |
bicycles | +0.012 |
appearance | +0.012 |
helicopter | +0.011 |
Neg logit contributions | |
opener | -0.020 |
aver | -0.020 |
inda | -0.018 |
eh | -0.018 |
avers | -0.017 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
opener | +0.016 |
aver | +0.015 |
inda | +0.014 |
eh | +0.013 |
Linda | +0.013 |
Neg logit contributions | |
ind | -0.013 |
cha | -0.013 |
yacht | -0.012 |
bicycles | -0.012 |
appearance | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | -1.43e-03 |
Pos logit contributions | |
cha | +0.047 |
ind | +0.046 |
yacht | +0.044 |
helicopter | +0.043 |
appearance | +0.042 |
Neg logit contributions | |
opener | -0.039 |
Jen | -0.032 |
aver | -0.031 |
Linda | -0.031 |
Jill | -0.031 |
Token | bake |
Token ID | 28450 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
ind | +0.002 |
cha | +0.002 |
bicycles | +0.002 |
yacht | +0.002 |
appearance | +0.002 |
Neg logit contributions | |
opener | -0.002 |
aver | -0.002 |
inda | -0.002 |
eh | -0.002 |
Linda | -0.002 |
Token | with |
Token ID | 351 |
Feature activation | +2.85e-03 |
Pos logit contributions | |
opener | +0.020 |
Mia | +0.016 |
Jen | +0.016 |
Jill | +0.016 |
Liz | +0.015 |
Neg logit contributions | |
ind | -0.032 |
cha | -0.030 |
yacht | -0.029 |
appearance | -0.029 |
bicycles | -0.028 |
Token | her |
Token ID | 607 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
opener | +0.005 |
aver | +0.004 |
inda | +0.004 |
Linda | +0.004 |
eh | +0.004 |
Neg logit contributions | |
cha | -0.005 |
ind | -0.005 |
yacht | -0.004 |
bicycles | -0.004 |
appearance | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +2.52e-03 |
Pos logit contributions | |
opener | +0.015 |
aver | +0.012 |
inda | +0.012 |
Linda | +0.012 |
Liz | +0.011 |
Neg logit contributions | |
ind | -0.025 |
cha | -0.024 |
festival | -0.024 |
yacht | -0.024 |
bicycles | -0.024 |
Token | Lily |
Token ID | 20037 |
Feature activation | +8.64e-03 |
Pos logit contributions | |
opener | +0.004 |
aver | +0.004 |
inda | +0.004 |
eh | +0.004 |
avers | +0.004 |
Neg logit contributions | |
cha | -0.004 |
ind | -0.004 |
bicycles | -0.004 |
appearance | -0.004 |
yacht | -0.004 |
Token | got |
Token ID | 1392 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
opener | +0.014 |
aver | +0.014 |
inda | +0.013 |
Linda | +0.012 |
eh | +0.012 |
Neg logit contributions | |
ind | -0.015 |
cha | -0.014 |
bicycles | -0.014 |
yacht | -0.014 |
festival | -0.014 |
Token | upset |
Token ID | 9247 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
opener | +0.043 |
aver | +0.040 |
inda | +0.038 |
eh | +0.037 |
izzy | +0.035 |
Neg logit contributions | |
cha | -0.024 |
ind | -0.024 |
helicopter | -0.022 |
yacht | -0.022 |
re | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +1.33e-03 |
Pos logit contributions | |
opener | +0.025 |
Linda | +0.022 |
inda | +0.021 |
Liz | +0.021 |
Jill | +0.020 |
Neg logit contributions | |
ind | -0.027 |
cha | -0.025 |
yacht | -0.025 |
festival | -0.024 |
bicycles | -0.024 |
Token | pulled |
Token ID | 5954 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
opener | +0.002 |
aver | +0.002 |
inda | +0.002 |
eh | +0.002 |
Linda | +0.002 |
Neg logit contributions | |
ind | -0.002 |
cha | -0.002 |
yacht | -0.002 |
bicycles | -0.002 |
appearance | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
opener | +0.038 |
aver | +0.035 |
inda | +0.034 |
Linda | +0.032 |
izzy | +0.031 |
Neg logit contributions | |
ind | -0.030 |
cha | -0.029 |
yacht | -0.028 |
bicycles | -0.027 |
appearance | -0.027 |
Token | monster |
Token ID | 9234 |
Feature activation | -2.29e-03 |
Pos logit contributions | |
opener | +0.026 |
aver | +0.024 |
inda | +0.023 |
eh | +0.022 |
Linda | +0.022 |
Neg logit contributions | |
ind | -0.014 |
cha | -0.013 |
appearance | -0.012 |
bicycles | -0.012 |
yacht | -0.012 |
Token | toy |
Token ID | 13373 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
ind | +0.003 |
cha | +0.003 |
yacht | +0.002 |
bicycles | +0.002 |
appearance | +0.002 |
Neg logit contributions | |
opener | -0.005 |
aver | -0.005 |
inda | -0.004 |
eh | -0.004 |
Linda | -0.004 |
Token | away |
Token ID | 1497 |
Feature activation | +7.30e-03 |
Pos logit contributions | |
opener | +0.024 |
aver | +0.020 |
inda | +0.019 |
Linda | +0.019 |
izzy | +0.018 |
Neg logit contributions | |
ind | -0.021 |
cha | -0.020 |
appearance | -0.019 |
bicycles | -0.019 |
festival | -0.018 |
Token | from |
Token ID | 422 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
opener | +0.013 |
aver | +0.012 |
inda | +0.011 |
Linda | +0.011 |
eh | +0.010 |
Neg logit contributions | |
ind | -0.012 |
cha | -0.012 |
bicycles | -0.011 |
yacht | -0.011 |
appearance | -0.011 |
Token | asks |
Token ID | 7893 |
Feature activation | +7.35e-03 |
Pos logit contributions | |
opener | +0.030 |
aver | +0.027 |
inda | +0.026 |
eh | +0.025 |
Linda | +0.025 |
Neg logit contributions | |
ind | -0.021 |
cha | -0.020 |
bicycles | -0.019 |
yacht | -0.019 |
appearance | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
opener | +0.016 |
aver | +0.016 |
eh | +0.016 |
inda | +0.015 |
ction | +0.014 |
Neg logit contributions | |
cha | -0.007 |
ind | -0.007 |
bicycles | -0.007 |
re | -0.007 |
strangers | -0.007 |
Token | He |
Token ID | 679 |
Feature activation | +2.29e-03 |
Pos logit contributions | |
inda | +0.029 |
aver | +0.028 |
eh | +0.027 |
opener | +0.027 |
izzy | +0.026 |
Neg logit contributions | |
re | -0.017 |
helicopter | -0.016 |
yacht | -0.016 |
bell | -0.016 |
cha | -0.016 |
Token | is |
Token ID | 318 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
opener | +0.005 |
aver | +0.004 |
inda | +0.004 |
Linda | +0.004 |
eh | +0.004 |
Neg logit contributions | |
ind | -0.003 |
cha | -0.003 |
yacht | -0.003 |
bicycles | -0.003 |
appearance | -0.003 |
Token | not |
Token ID | 407 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
ind | +0.017 |
cha | +0.015 |
re | +0.015 |
yacht | +0.014 |
bicycles | +0.014 |
Neg logit contributions | |
opener | -0.031 |
inda | -0.028 |
aver | -0.027 |
izzy | -0.026 |
Linda | -0.026 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
opener | +0.026 |
aver | +0.024 |
inda | +0.023 |
eh | +0.022 |
Linda | +0.022 |
Neg logit contributions | |
ind | -0.014 |
cha | -0.013 |
yacht | -0.012 |
bicycles | -0.012 |
appearance | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +8.61e-03 |
Pos logit contributions | |
opener | +0.032 |
Jill | +0.025 |
aver | +0.025 |
inda | +0.025 |
Jen | +0.024 |
Neg logit contributions | |
ind | -0.046 |
cha | -0.045 |
helicopter | -0.043 |
ranch | -0.042 |
yacht | -0.042 |
Token |
|
Token ID | 198 |
Feature activation | +4.43e-03 |
Pos logit contributions | |
opener | +0.015 |
aver | +0.015 |
inda | +0.014 |
eh | +0.014 |
izzy | +0.013 |
Neg logit contributions | |
cha | -0.012 |
ind | -0.012 |
bicycles | -0.012 |
re | -0.012 |
yacht | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +1.23e-03 |
Pos logit contributions | |
opener | +0.009 |
aver | +0.009 |
inda | +0.009 |
eh | +0.008 |
iddle | +0.008 |
Neg logit contributions | |
ind | -0.006 |
cha | -0.005 |
bicycles | -0.005 |
helicopter | -0.005 |
re | -0.005 |
Token | Tom |
Token ID | 13787 |
Feature activation | +7.42e-03 |
Pos logit contributions | |
opener | +0.003 |
inda | +0.002 |
iddle | +0.002 |
eh | +0.002 |
wn | +0.002 |
Neg logit contributions | |
ind | -0.002 |
cha | -0.001 |
bicycles | -0.001 |
us | -0.001 |
village | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -3.97e-03 |
Pos logit contributions | |
opener | +0.014 |
aver | +0.012 |
inda | +0.012 |
Linda | +0.011 |
izzy | +0.011 |
Neg logit contributions | |
ind | -0.012 |
cha | -0.011 |
yacht | -0.011 |
helicopter | -0.011 |
festival | -0.011 |
Token | Paul |
Token ID | 3362 |
Feature activation | -5.90e-03 |
Pos logit contributions | |
opener | +0.014 |
aver | +0.013 |
inda | +0.012 |
eh | +0.012 |
Linda | +0.011 |
Neg logit contributions | |
ind | -0.013 |
cha | -0.013 |
bicycles | -0.012 |
yacht | -0.012 |
appearance | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -4.71e-03 |
Pos logit contributions | |
ind | +0.010 |
cha | +0.010 |
appearance | +0.009 |
yacht | +0.009 |
festival | +0.009 |
Neg logit contributions | |
opener | -0.010 |
aver | -0.009 |
inda | -0.009 |
Linda | -0.008 |
eh | -0.008 |
Token | his |
Token ID | 465 |
Feature activation | -9.96e-03 |
Pos logit contributions | |
ind | +0.008 |
cha | +0.008 |
yacht | +0.008 |
bicycles | +0.007 |
re | +0.007 |
Neg logit contributions | |
opener | -0.008 |
aver | -0.007 |
inda | -0.007 |
eh | -0.007 |
izzy | -0.006 |
Token | mum |
Token ID | 25682 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
ind | +0.019 |
cha | +0.019 |
aren | +0.018 |
helicopter | +0.018 |
bicycles | +0.018 |
Neg logit contributions | |
opener | -0.013 |
aver | -0.013 |
inda | -0.012 |
Linda | -0.011 |
Jill | -0.011 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
ind | +0.044 |
cha | +0.043 |
appearance | +0.041 |
festival | +0.040 |
yacht | +0.039 |
Neg logit contributions | |
opener | -0.037 |
aver | -0.035 |
inda | -0.034 |
Linda | -0.031 |
izzy | -0.030 |
Token | it |
Token ID | 340 |
Feature activation | -5.58e-03 |
Pos logit contributions | |
ind | +0.026 |
cha | +0.024 |
appearance | +0.023 |
bicycles | +0.023 |
ranch | +0.022 |
Neg logit contributions | |
opener | -0.028 |
aver | -0.024 |
inda | -0.024 |
Linda | -0.023 |
Liz | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | +8.88e-04 |
Pos logit contributions | |
ind | +0.011 |
cha | +0.010 |
yacht | +0.009 |
pige | +0.009 |
appearance | +0.009 |
Neg logit contributions | |
opener | -0.009 |
inda | -0.008 |
aver | -0.008 |
Linda | -0.007 |
Liz | -0.007 |
Token | funny |
Token ID | 8258 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
opener | +0.002 |
aver | +0.001 |
inda | +0.001 |
Linda | +0.001 |
Jill | +0.001 |
Neg logit contributions | |
ind | -0.002 |
cha | -0.001 |
bicycles | -0.001 |
yacht | -0.001 |
appearance | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +3.07e-04 |
Pos logit contributions | |
opener | +0.018 |
inda | +0.016 |
Linda | +0.015 |
Jill | +0.015 |
aver | +0.015 |
Neg logit contributions | |
ind | -0.019 |
cha | -0.018 |
yacht | -0.017 |
helicopter | -0.016 |
bicycles | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +3.14e-03 |
Pos logit contributions | |
opener | +0.000 |
aver | +0.000 |
inda | +0.000 |
Linda | +0.000 |
eh | +0.000 |
Neg logit contributions | |
ind | -0.001 |
cha | -0.001 |
appearance | -0.001 |
yacht | -0.001 |
bicycles | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +1.31e-03 |
Pos logit contributions | |
opener | +0.006 |
aver | +0.005 |
inda | +0.005 |
eh | +0.005 |
Linda | +0.005 |
Neg logit contributions | |
ind | -0.005 |
cha | -0.005 |
bicycles | -0.004 |
re | -0.004 |
helicopter | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
ind | +0.014 |
cha | +0.013 |
appearance | +0.012 |
bicycles | +0.012 |
yacht | +0.012 |
Neg logit contributions | |
opener | -0.019 |
aver | -0.018 |
inda | -0.017 |
eh | -0.016 |
Linda | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
opener | +0.018 |
aver | +0.016 |
inda | +0.016 |
Linda | +0.015 |
eh | +0.014 |
Neg logit contributions | |
ind | -0.023 |
cha | -0.022 |
appearance | -0.021 |
yacht | -0.021 |
bicycles | -0.020 |
Token | strange |
Token ID | 6283 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
ind | +0.016 |
cha | +0.016 |
bicycles | +0.015 |
appearance | +0.015 |
yacht | +0.014 |
Neg logit contributions | |
opener | -0.022 |
aver | -0.020 |
inda | -0.018 |
Linda | -0.018 |
eh | -0.018 |
Token | man |
Token ID | 582 |
Feature activation | +9.61e-03 |
Pos logit contributions | |
ind | +0.022 |
cha | +0.022 |
bicycles | +0.021 |
appearance | +0.020 |
aren | +0.019 |
Neg logit contributions | |
opener | -0.029 |
aver | -0.028 |
inda | -0.025 |
eh | -0.025 |
Linda | -0.025 |
Token | came |
Token ID | 1625 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
opener | +0.014 |
aver | +0.013 |
inda | +0.011 |
eh | +0.011 |
Linda | +0.010 |
Neg logit contributions | |
ind | -0.019 |
cha | -0.018 |
appearance | -0.018 |
bicycles | -0.018 |
festival | -0.018 |
Token | over |
Token ID | 625 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
opener | +0.086 |
aver | +0.078 |
inda | +0.076 |
eh | +0.072 |
Linda | +0.071 |
Neg logit contributions | |
cha | -0.067 |
ind | -0.065 |
appearance | -0.062 |
yacht | -0.062 |
festival | -0.062 |
Token | to |
Token ID | 284 |
Feature activation | -8.80e-03 |
Pos logit contributions | |
ind | +0.022 |
cha | +0.021 |
yacht | +0.020 |
appearance | +0.020 |
bicycles | +0.020 |
Neg logit contributions | |
opener | -0.029 |
inda | -0.025 |
aver | -0.025 |
Linda | -0.025 |
eh | -0.024 |
Token | her |
Token ID | 607 |
Feature activation | +6.42e-03 |
Pos logit contributions | |
ind | +0.016 |
cha | +0.015 |
bicycles | +0.015 |
yacht | +0.014 |
appearance | +0.014 |
Neg logit contributions | |
opener | -0.014 |
Linda | -0.012 |
Jill | -0.012 |
inda | -0.011 |
aver | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +2.02e-03 |
Pos logit contributions | |
opener | +0.010 |
aver | +0.008 |
inda | +0.008 |
eh | +0.007 |
Linda | +0.007 |
Neg logit contributions | |
cha | -0.013 |
ind | -0.012 |
aren | -0.011 |
ize | -0.011 |
appearance | -0.011 |
Token | He |
Token ID | 679 |
Feature activation | +2.35e-03 |
Pos logit contributions | |
opener | +0.003 |
aver | +0.003 |
inda | +0.002 |
Linda | +0.002 |
eh | +0.002 |
Neg logit contributions | |
ind | -0.004 |
cha | -0.004 |
bicycles | -0.004 |
yacht | -0.004 |
appearance | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -4.66e-03 |
Pos logit contributions | |
opener | +0.004 |
aver | +0.003 |
inda | +0.003 |
Linda | +0.003 |
eh | +0.003 |
Neg logit contributions | |
ind | -0.004 |
cha | -0.004 |
appearance | -0.004 |
bicycles | -0.004 |
yacht | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
opener | +0.026 |
aver | +0.024 |
inda | +0.023 |
Linda | +0.022 |
eh | +0.021 |
Neg logit contributions | |
ind | -0.020 |
cha | -0.019 |
bicycles | -0.018 |
yacht | -0.018 |
appearance | -0.017 |
Token | Anna |
Token ID | 11735 |
Feature activation | -1.08e-03 |
Pos logit contributions | |
opener | +0.036 |
aver | +0.032 |
inda | +0.031 |
eh | +0.029 |
Linda | +0.029 |
Neg logit contributions | |
ind | -0.035 |
cha | -0.034 |
yacht | -0.032 |
bicycles | -0.032 |
appearance | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
ind | +0.002 |
cha | +0.002 |
bicycles | +0.002 |
yacht | +0.002 |
appearance | +0.002 |
Neg logit contributions | |
opener | -0.002 |
aver | -0.002 |
inda | -0.002 |
Linda | -0.001 |
eh | -0.001 |
Token | You |
Token ID | 921 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
cha | +0.021 |
ind | +0.021 |
bicycles | +0.019 |
yacht | +0.019 |
appearance | +0.019 |
Neg logit contributions | |
opener | -0.035 |
aver | -0.032 |
inda | -0.031 |
eh | -0.030 |
Linda | -0.029 |
Token | are |
Token ID | 389 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
opener | +0.024 |
aver | +0.022 |
inda | +0.021 |
izzy | +0.020 |
Linda | +0.020 |
Neg logit contributions | |
ind | -0.013 |
cha | -0.011 |
appearance | -0.010 |
bicycles | -0.010 |
yacht | -0.010 |
Token | very |
Token ID | 845 |
Feature activation | -9.81e-03 |
Pos logit contributions | |
cha | +0.029 |
ind | +0.029 |
appearance | +0.028 |
bicycles | +0.027 |
yacht | +0.027 |
Neg logit contributions | |
opener | -0.026 |
aver | -0.025 |
inda | -0.023 |
Linda | -0.022 |
eh | -0.021 |
Token | kind |
Token ID | 1611 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
ind | +0.015 |
cha | +0.015 |
bicycles | +0.015 |
appearance | +0.015 |
yacht | +0.014 |
Neg logit contributions | |
opener | -0.017 |
aver | -0.017 |
inda | -0.015 |
Linda | -0.014 |
izzy | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +9.10e-03 |
Pos logit contributions | |
opener | +0.033 |
aver | +0.030 |
inda | +0.028 |
Linda | +0.027 |
izzy | +0.026 |
Neg logit contributions | |
ind | -0.028 |
cha | -0.028 |
yacht | -0.026 |
bicycles | -0.025 |
helicopter | -0.025 |
Token | brave |
Token ID | 14802 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
opener | +0.017 |
aver | +0.015 |
inda | +0.015 |
Linda | +0.014 |
eh | +0.013 |
Neg logit contributions | |
ind | -0.015 |
cha | -0.014 |
bicycles | -0.013 |
appearance | -0.013 |
yacht | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -7.11e-03 |
Pos logit contributions | |
ind | +0.022 |
cha | +0.022 |
yacht | +0.021 |
bicycles | +0.020 |
helicopter | +0.020 |
Neg logit contributions | |
opener | -0.016 |
aver | -0.014 |
inda | -0.013 |
Linda | -0.012 |
izzy | -0.012 |
Token | You |
Token ID | 921 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
cha | +0.008 |
ind | +0.008 |
re | +0.007 |
bicycles | +0.007 |
appearance | +0.007 |
Neg logit contributions | |
opener | -0.016 |
aver | -0.015 |
inda | -0.014 |
eh | -0.014 |
izzy | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -7.43e-03 |
Pos logit contributions | |
opener | +0.033 |
aver | +0.030 |
inda | +0.029 |
Linda | +0.027 |
eh | +0.026 |
Neg logit contributions | |
ind | -0.039 |
cha | -0.038 |
appearance | -0.036 |
yacht | -0.035 |
bicycles | -0.035 |
Token | big |
Token ID | 1263 |
Feature activation | -8.50e-03 |
Pos logit contributions | |
cha | +0.012 |
ind | +0.012 |
bicycles | +0.011 |
appearance | +0.011 |
iling | +0.011 |
Neg logit contributions | |
opener | -0.013 |
aver | -0.012 |
inda | -0.011 |
eh | -0.011 |
Linda | -0.011 |
Token | circle |
Token ID | 9197 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
ind | +0.015 |
cha | +0.015 |
bicycles | +0.014 |
uted | +0.014 |
ponies | +0.014 |
Neg logit contributions | |
opener | -0.013 |
aver | -0.012 |
Linda | -0.011 |
Jill | -0.011 |
inda | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +1.74e-04 |
Pos logit contributions | |
opener | +0.023 |
aver | +0.022 |
inda | +0.021 |
izzy | +0.020 |
Linda | +0.020 |
Neg logit contributions | |
ind | -0.017 |
cha | -0.017 |
yacht | -0.016 |
helicopter | -0.016 |
bicycles | -0.015 |
Token | They |
Token ID | 1119 |
Feature activation | +1.40e-03 |
Pos logit contributions | |
opener | +0.000 |
aver | +0.000 |
eh | +0.000 |
inda | +0.000 |
avers | +0.000 |
Neg logit contributions | |
cha | -0.000 |
bicycles | -0.000 |
ind | -0.000 |
yacht | -0.000 |
puppies | -0.000 |
Token | stayed |
Token ID | 9658 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
opener | +0.002 |
aver | +0.002 |
inda | +0.002 |
Linda | +0.002 |
eh | +0.002 |
Neg logit contributions | |
ind | -0.002 |
cha | -0.002 |
appearance | -0.002 |
bicycles | -0.002 |
yacht | -0.002 |
Token | close |
Token ID | 1969 |
Feature activation | +5.17e-03 |
Pos logit contributions | |
cha | +0.030 |
ind | +0.029 |
appearance | +0.028 |
bicycles | +0.027 |
aren | +0.026 |
Neg logit contributions | |
aver | -0.033 |
opener | -0.033 |
inda | -0.031 |
Linda | -0.030 |
avers | -0.029 |
Token | together |
Token ID | 1978 |
Feature activation | +8.66e-03 |
Pos logit contributions | |
opener | +0.006 |
aver | +0.005 |
inda | +0.005 |
Linda | +0.005 |
Jill | +0.005 |
Neg logit contributions | |
cha | -0.011 |
ind | -0.011 |
helicopter | -0.011 |
festival | -0.010 |
yacht | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -9.69e-04 |
Pos logit contributions | |
opener | +0.014 |
inda | +0.012 |
aver | +0.011 |
Jill | +0.011 |
Linda | +0.011 |
Neg logit contributions | |
cha | -0.017 |
ind | -0.017 |
bicycles | -0.015 |
mall | -0.015 |
helicopter | -0.015 |
Token | sang |
Token ID | 25889 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
ind | +0.002 |
cha | +0.002 |
ponies | +0.002 |
bicycles | +0.002 |
ranch | +0.002 |
Neg logit contributions | |
opener | -0.002 |
Jill | -0.001 |
inda | -0.001 |
Linda | -0.001 |
aver | -0.001 |
Token | songs |
Token ID | 7259 |
Feature activation | -7.76e-03 |
Pos logit contributions | |
opener | +0.020 |
inda | +0.018 |
aver | +0.017 |
Linda | +0.017 |
Jill | +0.016 |
Neg logit contributions | |
ind | -0.021 |
cha | -0.021 |
appearance | -0.019 |
mall | -0.019 |
yacht | -0.019 |
Token | looks |
Token ID | 3073 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
ind | +0.011 |
cha | +0.011 |
yacht | +0.010 |
festival | +0.010 |
ranch | +0.010 |
Neg logit contributions | |
opener | -0.011 |
inda | -0.009 |
Linda | -0.009 |
aver | -0.009 |
Liz | -0.009 |
Token | for |
Token ID | 329 |
Feature activation | +2.01e-05 |
Pos logit contributions | |
ind | +0.049 |
cha | +0.047 |
bicycles | +0.045 |
festival | +0.043 |
yacht | +0.043 |
Neg logit contributions | |
opener | -0.075 |
aver | -0.074 |
inda | -0.072 |
Linda | -0.069 |
eh | -0.069 |
Token | another |
Token ID | 1194 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
opener | +0.000 |
aver | +0.000 |
inda | +0.000 |
Linda | +0.000 |
eh | +0.000 |
Neg logit contributions | |
ind | -0.000 |
cha | -0.000 |
yacht | -0.000 |
bicycles | -0.000 |
appearance | -0.000 |
Token | toy |
Token ID | 13373 |
Feature activation | +4.68e-03 |
Pos logit contributions | |
ind | +0.020 |
cha | +0.019 |
bicycles | +0.018 |
yacht | +0.018 |
appearance | +0.018 |
Neg logit contributions | |
opener | -0.024 |
aver | -0.022 |
inda | -0.021 |
eh | -0.020 |
Linda | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e-03 |
Pos logit contributions | |
opener | +0.007 |
aver | +0.006 |
inda | +0.006 |
Linda | +0.006 |
izzy | +0.006 |
Neg logit contributions | |
ind | -0.009 |
cha | -0.009 |
yacht | -0.008 |
bicycles | -0.008 |
appearance | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -9.13e-04 |
Pos logit contributions | |
opener | +0.002 |
aver | +0.002 |
inda | +0.002 |
eh | +0.002 |
avers | +0.002 |
Neg logit contributions | |
cha | -0.002 |
ind | -0.002 |
bicycles | -0.002 |
appearance | -0.002 |
festival | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -2.47e-03 |
Pos logit contributions | |
ind | +0.001 |
cha | +0.001 |
bicycles | +0.001 |
re | +0.001 |
helicopter | +0.001 |
Neg logit contributions | |
opener | -0.002 |
aver | -0.002 |
inda | -0.002 |
eh | -0.001 |
Linda | -0.001 |
Token | But |
Token ID | 1537 |
Feature activation | -8.66e-04 |
Pos logit contributions | |
ind | +0.004 |
cha | +0.004 |
bicycles | +0.003 |
festival | +0.003 |
helicopter | +0.003 |
Neg logit contributions | |
opener | -0.004 |
aver | -0.004 |
inda | -0.004 |
Linda | -0.004 |
izzy | -0.004 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
ind | +0.001 |
cha | +0.001 |
yacht | +0.001 |
bicycles | +0.001 |
appearance | +0.001 |
Neg logit contributions | |
opener | -0.001 |
aver | -0.001 |
inda | -0.001 |
Linda | -0.001 |
eh | -0.001 |
Token | says |
Token ID | 1139 |
Feature activation | -5.27e-03 |
Pos logit contributions | |
ind | +0.026 |
yacht | +0.024 |
helicopter | +0.023 |
bicycles | +0.023 |
ranch | +0.022 |
Neg logit contributions | |
opener | -0.026 |
aver | -0.022 |
inda | -0.021 |
Mia | -0.021 |
eh | -0.020 |
Token | no |
Token ID | 645 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
cha | +0.007 |
ind | +0.007 |
yacht | +0.006 |
appearance | +0.006 |
bicycles | +0.006 |
Neg logit contributions | |
opener | -0.011 |
aver | -0.010 |
inda | -0.010 |
eh | -0.009 |
izzy | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +6.03e-03 |
Pos logit contributions | |
opener | +0.011 |
aver | +0.011 |
inda | +0.011 |
eh | +0.010 |
izzy | +0.010 |
Neg logit contributions | |
ind | -0.005 |
cha | -0.005 |
bicycles | -0.004 |
yacht | -0.004 |
appearance | -0.004 |
Token | Inside |
Token ID | 14384 |
Feature activation | +9.16e-03 |
Pos logit contributions | |
inda | +0.008 |
aver | +0.008 |
opener | +0.008 |
eh | +0.007 |
izzy | +0.007 |
Neg logit contributions | |
bicycles | -0.012 |
cha | -0.012 |
billboard | -0.011 |
yacht | -0.011 |
helicopter | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +4.92e-03 |
Pos logit contributions | |
opener | +0.017 |
aver | +0.016 |
inda | +0.015 |
Linda | +0.014 |
izzy | +0.014 |
Neg logit contributions | |
ind | -0.014 |
cha | -0.014 |
appearance | -0.013 |
yacht | -0.012 |
bicycles | -0.012 |
Token | he |
Token ID | 339 |
Feature activation | +1.48e-03 |
Pos logit contributions | |
opener | +0.006 |
aver | +0.005 |
Jill | +0.005 |
Jen | +0.005 |
Liz | +0.005 |
Neg logit contributions | |
ind | -0.011 |
appearance | -0.010 |
cha | -0.010 |
ranch | -0.010 |
wedding | -0.009 |
Token | found |
Token ID | 1043 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
opener | +0.002 |
aver | +0.002 |
inda | +0.002 |
eh | +0.002 |
Linda | +0.002 |
Neg logit contributions | |
ind | -0.003 |
cha | -0.003 |
yacht | -0.002 |
bicycles | -0.002 |
appearance | -0.002 |
Token | something |
Token ID | 1223 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
opener | +0.026 |
aver | +0.024 |
inda | +0.023 |
eh | +0.023 |
izzy | +0.022 |
Neg logit contributions | |
cha | -0.028 |
bicycles | -0.028 |
re | -0.027 |
yacht | -0.026 |
helicopter | -0.026 |
Token | that |
Token ID | 326 |
Feature activation | +6.60e-03 |
Pos logit contributions | |
ind | +0.083 |
cha | +0.077 |
appearance | +0.074 |
bicycles | +0.071 |
ranch | +0.071 |
Neg logit contributions | |
opener | -0.098 |
aver | -0.086 |
inda | -0.081 |
Linda | -0.079 |
eh | -0.077 |
Token | belonged |
Token ID | 19611 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
opener | +0.011 |
aver | +0.010 |
inda | +0.009 |
Linda | +0.009 |
Jill | +0.009 |
Neg logit contributions | |
ind | -0.012 |
cha | -0.011 |
appearance | -0.011 |
helicopter | -0.010 |
ranch | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -2.39e-03 |
Pos logit contributions | |
opener | +0.020 |
aver | +0.019 |
inda | +0.018 |
aster | +0.017 |
inn | +0.017 |
Neg logit contributions | |
ind | -0.016 |
cha | -0.015 |
forever | -0.015 |
bicycles | -0.015 |
mall | -0.014 |
Token | him |
Token ID | 683 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
ind | +0.005 |
cha | +0.004 |
helicopter | +0.004 |
appearance | +0.004 |
yacht | +0.004 |
Neg logit contributions | |
opener | -0.004 |
Jill | -0.003 |
Jen | -0.003 |
aver | -0.003 |
Mia | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +8.06e-03 |
Pos logit contributions | |
ind | +0.024 |
cha | +0.023 |
bicycles | +0.022 |
festival | +0.022 |
yacht | +0.022 |
Neg logit contributions | |
opener | -0.019 |
aver | -0.016 |
inda | -0.016 |
Linda | -0.015 |
izzy | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +1.98e-04 |
Pos logit contributions | |
opener | +0.005 |
aver | +0.004 |
inda | +0.004 |
eh | +0.004 |
Linda | +0.004 |
Neg logit contributions | |
ind | -0.004 |
cha | -0.004 |
bicycles | -0.003 |
mall | -0.003 |
re | -0.003 |
Token | But |
Token ID | 1537 |
Feature activation | +9.66e-03 |
Pos logit contributions | |
opener | +0.000 |
aver | +0.000 |
inda | +0.000 |
Linda | +0.000 |
izzy | +0.000 |
Neg logit contributions | |
ind | -0.000 |
cha | -0.000 |
bicycles | -0.000 |
festival | -0.000 |
helicopter | -0.000 |
Token | then |
Token ID | 788 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
opener | +0.017 |
aver | +0.016 |
inda | +0.015 |
Linda | +0.015 |
eh | +0.014 |
Neg logit contributions | |
ind | -0.016 |
cha | -0.015 |
yacht | -0.015 |
bicycles | -0.015 |
appearance | -0.014 |
Token | she |
Token ID | 673 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
opener | +0.023 |
aver | +0.021 |
inda | +0.020 |
Linda | +0.019 |
eh | +0.019 |
Neg logit contributions | |
ind | -0.020 |
cha | -0.019 |
yacht | -0.018 |
bicycles | -0.018 |
appearance | -0.018 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
opener | +0.022 |
aver | +0.020 |
inda | +0.019 |
eh | +0.018 |
Linda | +0.018 |
Neg logit contributions | |
ind | -0.022 |
cha | -0.021 |
bicycles | -0.020 |
yacht | -0.020 |
appearance | -0.020 |
Token | something |
Token ID | 1223 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
opener | +0.017 |
aver | +0.015 |
inda | +0.014 |
eh | +0.013 |
izzy | +0.013 |
Neg logit contributions | |
ind | -0.026 |
cha | -0.025 |
bicycles | -0.024 |
yacht | -0.024 |
helicopter | -0.024 |
Token | else |
Token ID | 2073 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
ind | +0.067 |
cha | +0.063 |
appearance | +0.060 |
bicycles | +0.059 |
yacht | +0.058 |
Neg logit contributions | |
opener | -0.093 |
aver | -0.085 |
inda | -0.082 |
Linda | -0.078 |
eh | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
ind | +0.023 |
cha | +0.021 |
yacht | +0.021 |
bicycles | +0.021 |
helicopter | +0.020 |
Neg logit contributions | |
opener | -0.020 |
inda | -0.018 |
aver | -0.017 |
Linda | -0.017 |
Jill | -0.016 |
Token | Something |
Token ID | 13742 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
opener | +0.015 |
aver | +0.015 |
inda | +0.014 |
eh | +0.013 |
avers | +0.013 |
Neg logit contributions | |
cha | -0.011 |
bicycles | -0.010 |
ind | -0.010 |
helicopter | -0.010 |
yacht | -0.010 |
Token | even |
Token ID | 772 |
Feature activation | +7.15e-03 |
Pos logit contributions | |
ind | +0.067 |
cha | +0.059 |
appearance | +0.058 |
bicycles | +0.056 |
ranch | +0.056 |
Neg logit contributions | |
opener | -0.073 |
aver | -0.065 |
Linda | -0.062 |
inda | -0.062 |
Jill | -0.058 |
Token | better |
Token ID | 1365 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
opener | +0.013 |
izzy | +0.011 |
inda | +0.011 |
inn | +0.011 |
aver | +0.011 |
Neg logit contributions | |
cha | -0.010 |
re | -0.010 |
ind | -0.010 |
bicycles | -0.009 |
helicopter | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
ind | +0.026 |
cha | +0.025 |
appearance | +0.024 |
bicycles | +0.023 |
yacht | +0.023 |
Neg logit contributions | |
opener | -0.031 |
aver | -0.028 |
inda | -0.027 |
eh | -0.026 |
Linda | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +1.22e-03 |
Pos logit contributions | |
opener | +0.027 |
Linda | +0.024 |
aver | +0.024 |
Jill | +0.024 |
inda | +0.024 |
Neg logit contributions | |
ind | -0.027 |
cha | -0.026 |
yacht | -0.022 |
appearance | -0.022 |
helicopter | -0.022 |
Token | thanked |
Token ID | 26280 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
opener | +0.002 |
inda | +0.002 |
Linda | +0.002 |
aver | +0.002 |
Jill | +0.002 |
Neg logit contributions | |
ind | -0.002 |
cha | -0.002 |
appearance | -0.002 |
yacht | -0.002 |
bicycles | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
cha | +0.025 |
ind | +0.024 |
yacht | +0.022 |
bicycles | +0.022 |
appearance | +0.022 |
Neg logit contributions | |
opener | -0.019 |
Linda | -0.017 |
inda | -0.017 |
Jill | -0.016 |
Liz | -0.016 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.49e-04 |
Pos logit contributions | |
opener | +0.019 |
aver | +0.017 |
inda | +0.016 |
Linda | +0.016 |
Liz | +0.015 |
Neg logit contributions | |
cha | -0.021 |
ind | -0.021 |
bicycles | -0.019 |
yacht | -0.019 |
appearance | -0.019 |
Token | again |
Token ID | 757 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
cha | +0.001 |
ind | +0.001 |
yacht | +0.001 |
bicycles | +0.001 |
appearance | +0.001 |
Neg logit contributions | |
opener | -0.001 |
inda | -0.001 |
aver | -0.000 |
Linda | -0.000 |
Jill | -0.000 |
Token | for |
Token ID | 329 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
cha | +0.080 |
bicycles | +0.077 |
ind | +0.076 |
helicopter | +0.074 |
yacht | +0.074 |
Neg logit contributions | |
opener | -0.064 |
aver | -0.055 |
inda | -0.055 |
Linda | -0.052 |
Jill | -0.049 |
Token | carrying |
Token ID | 6872 |
Feature activation | +1.49e-04 |
Pos logit contributions | |
ind | +0.054 |
cha | +0.053 |
appearance | +0.049 |
bicycles | +0.049 |
yacht | +0.047 |
Neg logit contributions | |
opener | -0.056 |
aver | -0.050 |
inda | -0.048 |
Linda | -0.047 |
Jill | -0.045 |
Token | it |
Token ID | 340 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
opener | +0.000 |
inda | +0.000 |
aver | +0.000 |
Linda | +0.000 |
eh | +0.000 |
Neg logit contributions | |
ind | -0.000 |
cha | -0.000 |
bicycles | -0.000 |
yacht | -0.000 |
appearance | -0.000 |
Token | for |
Token ID | 329 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
ind | +0.018 |
cha | +0.018 |
appearance | +0.017 |
yacht | +0.017 |
bicycles | +0.017 |
Neg logit contributions | |
opener | -0.016 |
aver | -0.014 |
inda | -0.014 |
Linda | -0.013 |
eh | -0.013 |
Token | her |
Token ID | 607 |
Feature activation | +6.53e-03 |
Pos logit contributions | |
ind | +0.036 |
cha | +0.036 |
yacht | +0.035 |
bicycles | +0.034 |
helicopter | +0.034 |
Neg logit contributions | |
opener | -0.029 |
inda | -0.026 |
Linda | -0.026 |
aver | -0.025 |
Jill | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -8.11e-04 |
Pos logit contributions | |
ind | +0.014 |
cha | +0.014 |
bicycles | +0.013 |
helicopter | +0.013 |
yacht | +0.013 |
Neg logit contributions | |
opener | -0.015 |
aver | -0.015 |
inda | -0.014 |
eh | -0.013 |
izzy | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -6.83e-04 |
Pos logit contributions | |
ind | +0.001 |
cha | +0.001 |
bicycles | +0.001 |
helicopter | +0.001 |
festival | +0.001 |
Neg logit contributions | |
opener | -0.002 |
aver | -0.001 |
inda | -0.001 |
eh | -0.001 |
Linda | -0.001 |
Token | One |
Token ID | 3198 |
Feature activation | -2.40e-03 |
Pos logit contributions | |
ind | +0.001 |
cha | +0.001 |
festival | +0.001 |
bicycles | +0.001 |
helicopter | +0.001 |
Neg logit contributions | |
opener | -0.001 |
aver | -0.001 |
inda | -0.001 |
Linda | -0.001 |
izzy | -0.001 |
Token | day |
Token ID | 1110 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
ind | +0.003 |
re | +0.003 |
festival | +0.002 |
yacht | +0.002 |
helicopter | +0.002 |
Neg logit contributions | |
opener | -0.005 |
inda | -0.005 |
aver | -0.005 |
Linda | -0.005 |
izzy | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +5.66e-04 |
Pos logit contributions | |
opener | +0.028 |
aver | +0.026 |
inda | +0.025 |
eh | +0.024 |
Linda | +0.024 |
Neg logit contributions | |
ind | -0.017 |
cha | -0.017 |
bicycles | -0.015 |
yacht | -0.015 |
appearance | -0.015 |
Token | something |
Token ID | 1223 |
Feature activation | -4.89e-02 |
Pos logit contributions | |
opener | +0.001 |
aver | +0.001 |
inda | +0.001 |
Linda | +0.001 |
eh | +0.001 |
Neg logit contributions | |
ind | -0.001 |
cha | -0.001 |
appearance | -0.001 |
bicycles | -0.001 |
yacht | -0.001 |
Token | special |
Token ID | 2041 |
Feature activation | -8.52e-03 |
Pos logit contributions | |
cha | +0.046 |
yacht | +0.041 |
ind | +0.041 |
helicopter | +0.041 |
festival | +0.040 |
Neg logit contributions | |
opener | -0.122 |
aver | -0.110 |
inda | -0.108 |
izzy | -0.105 |
Linda | -0.103 |
Token | happened |
Token ID | 3022 |
Feature activation | +4.51e-03 |
Pos logit contributions | |
ind | +0.013 |
cha | +0.013 |
appearance | +0.012 |
bicycles | +0.012 |
yacht | +0.012 |
Neg logit contributions | |
opener | -0.016 |
aver | -0.015 |
inda | -0.014 |
eh | -0.013 |
Linda | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +6.68e-03 |
Pos logit contributions | |
opener | +0.007 |
aver | +0.007 |
inda | +0.006 |
eh | +0.006 |
Linda | +0.006 |
Neg logit contributions | |
ind | -0.008 |
cha | -0.008 |
bicycles | -0.007 |
yacht | -0.007 |
helicopter | -0.007 |
Token | The |
Token ID | 383 |
Feature activation | +1.02e-03 |
Pos logit contributions | |
aver | +0.012 |
opener | +0.011 |
inda | +0.011 |
eh | +0.010 |
izzy | +0.010 |
Neg logit contributions | |
cha | -0.010 |
ind | -0.010 |
helicopter | -0.010 |
festival | -0.010 |
yacht | -0.010 |
Token | farmer |
Token ID | 18739 |
Feature activation | -5.64e-03 |
Pos logit contributions | |
aver | +0.002 |
opener | +0.002 |
eh | +0.002 |
avers | +0.002 |
inda | +0.001 |
Neg logit contributions | |
cha | -0.002 |
bicycles | -0.002 |
ind | -0.002 |
appearance | -0.002 |
ize | -0.001 |
Token | always |
Token ID | 1464 |
Feature activation | -4.02e-04 |
Pos logit contributions | |
ind | +0.003 |
cha | +0.003 |
bicycles | +0.003 |
yacht | +0.003 |
appearance | +0.003 |
Neg logit contributions | |
opener | -0.004 |
aver | -0.004 |
inda | -0.004 |
eh | -0.004 |
Linda | -0.004 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.92e-03 |
Pos logit contributions | |
ind | +0.001 |
cha | +0.001 |
bicycles | +0.001 |
yacht | +0.001 |
appearance | +0.001 |
Neg logit contributions | |
opener | -0.001 |
aver | -0.001 |
inda | -0.001 |
Linda | -0.001 |
eh | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -4.76e-03 |
Pos logit contributions | |
opener | +0.002 |
inda | +0.002 |
Linda | +0.002 |
aver | +0.002 |
Jill | +0.002 |
Neg logit contributions | |
ind | -0.004 |
cha | -0.004 |
yacht | -0.004 |
bicycles | -0.004 |
helicopter | -0.004 |
Token | help |
Token ID | 1037 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
ind | +0.008 |
cha | +0.008 |
yacht | +0.007 |
bicycles | +0.007 |
appearance | +0.007 |
Neg logit contributions | |
opener | -0.008 |
aver | -0.008 |
inda | -0.007 |
eh | -0.007 |
Linda | -0.007 |
Token | out |
Token ID | 503 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
cha | +0.020 |
ind | +0.019 |
yacht | +0.018 |
bicycles | +0.018 |
festival | +0.018 |
Neg logit contributions | |
opener | -0.020 |
inda | -0.018 |
aver | -0.017 |
Linda | -0.017 |
Jill | -0.016 |
Token | wherever |
Token ID | 14530 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
opener | +0.029 |
aver | +0.026 |
inda | +0.026 |
Linda | +0.025 |
eh | +0.024 |
Neg logit contributions | |
ind | -0.030 |
cha | -0.030 |
yacht | -0.028 |
bicycles | -0.028 |
appearance | -0.027 |
Token | she |
Token ID | 673 |
Feature activation | -9.98e-03 |
Pos logit contributions | |
ind | +0.106 |
cha | +0.096 |
appearance | +0.096 |
yacht | +0.094 |
bicycles | +0.092 |
Neg logit contributions | |
opener | -0.072 |
inda | -0.061 |
Linda | -0.060 |
aver | -0.060 |
Jill | -0.058 |
Token | could |
Token ID | 714 |
Feature activation | -9.05e-03 |
Pos logit contributions | |
ind | +0.019 |
yacht | +0.017 |
bicycles | +0.017 |
cha | +0.017 |
appearance | +0.016 |
Neg logit contributions | |
opener | -0.016 |
aver | -0.014 |
inda | -0.014 |
izzy | -0.013 |
eh | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -3.58e-03 |
Pos logit contributions | |
ind | +0.016 |
cha | +0.015 |
bicycles | +0.014 |
yacht | +0.014 |
appearance | +0.014 |
Neg logit contributions | |
opener | -0.016 |
aver | -0.014 |
inda | -0.013 |
Linda | -0.012 |
eh | -0.012 |
Token | |
Token ID | 220 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
ind | +0.006 |
cha | +0.006 |
bicycles | +0.006 |
helicopter | +0.005 |
yacht | +0.005 |
Neg logit contributions | |
opener | -0.006 |
aver | -0.006 |
inda | -0.005 |
eh | -0.005 |
izzy | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +5.35e-03 |
Pos logit contributions | |
opener | +0.034 |
aver | +0.032 |
inda | +0.030 |
eh | +0.029 |
Linda | +0.027 |
Neg logit contributions | |
ind | -0.025 |
cha | -0.025 |
bicycles | -0.024 |
helicopter | -0.023 |
aren | -0.022 |