Token | ! |
Token ID | 0 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
iring | +0.015 |
eddy | +0.014 |
from | +0.013 |
ucks | +0.013 |
accidents | +0.013 |
Neg logit contributions | |
sel | -0.025 |
ued | -0.024 |
chie | -0.024 |
None | -0.023 |
| -0.022 |
Token | He |
Token ID | 679 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
iring | +0.003 |
eddy | +0.003 |
ucks | +0.003 |
Doctor | +0.003 |
accidents | +0.003 |
Neg logit contributions | |
sel | -0.005 |
chie | -0.004 |
ued | -0.004 |
pe | -0.004 |
none | -0.004 |
Token | put |
Token ID | 1234 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
sel | +0.002 |
chie | +0.002 |
ued | +0.002 |
None | +0.002 |
top | +0.002 |
Neg logit contributions | |
iring | -0.002 |
eddy | -0.002 |
ucks | -0.002 |
fort | -0.002 |
imi | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
eddy | +0.023 |
honey | +0.022 |
from | +0.022 |
iring | +0.021 |
ucks | +0.021 |
Neg logit contributions | |
chie | -0.065 |
ued | -0.063 |
sel | -0.061 |
ical | -0.061 |
None | -0.061 |
Token | l |
Token ID | 300 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
iring | +0.022 |
honey | +0.020 |
eddy | +0.020 |
imi | +0.019 |
ucks | +0.019 |
Neg logit contributions | |
sel | -0.050 |
ued | -0.049 |
None | -0.048 |
chie | -0.048 |
top | -0.047 |
Token | oll |
Token ID | 692 |
Feature activation | +5.82e+00 |
Pos logit contributions | |
iring | +0.060 |
fort | +0.058 |
eddy | +0.056 |
ucks | +0.056 |
accidents | +0.055 |
Neg logit contributions | |
sel | -0.115 |
ued | -0.107 |
chie | -0.106 |
| -0.103 |
top | -0.101 |
Token | ipop |
Token ID | 42800 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
iring | +0.149 |
eddy | +0.145 |
ucks | +0.141 |
imi | +0.138 |
fort | +0.137 |
Neg logit contributions | |
sel | -0.111 |
ued | -0.105 |
chie | -0.104 |
None | -0.103 |
| -0.100 |
Token | on |
Token ID | 319 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
iring | +0.042 |
eddy | +0.038 |
ucks | +0.037 |
fort | +0.037 |
accidents | +0.035 |
Neg logit contributions | |
sel | -0.091 |
chie | -0.087 |
ued | -0.087 |
None | -0.085 |
| -0.084 |
Token | his |
Token ID | 465 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
chie | +0.020 |
ued | +0.019 |
sel | +0.019 |
None | +0.018 |
ounded | +0.017 |
Neg logit contributions | |
from | -0.007 |
iring | -0.007 |
cartoons | -0.007 |
eddy | -0.007 |
accidents | -0.006 |
Token | head |
Token ID | 1182 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
sel | +0.034 |
ued | +0.032 |
chie | +0.032 |
None | +0.031 |
top | +0.031 |
Neg logit contributions | |
iring | -0.018 |
eddy | -0.017 |
fort | -0.017 |
imi | -0.016 |
ucks | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
chie | +0.048 |
ued | +0.047 |
sel | +0.045 |
None | +0.045 |
Fer | +0.042 |
Neg logit contributions | |
from | -0.011 |
eddy | -0.008 |
iring | -0.008 |
about | -0.006 |
itch | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
iring | +0.096 |
ucks | +0.092 |
eddy | +0.090 |
check | +0.088 |
accidents | +0.088 |
Neg logit contributions | |
sel | -0.089 |
ued | -0.082 |
| -0.080 |
top | -0.080 |
chie | -0.078 |
Token | They |
Token ID | 1119 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
iring | +0.016 |
ucks | +0.016 |
fort | +0.016 |
eddy | +0.016 |
imi | +0.015 |
Neg logit contributions | |
sel | -0.010 |
ued | -0.009 |
chie | -0.009 |
None | -0.008 |
| -0.008 |
Token | made |
Token ID | 925 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
fort | +0.042 |
dust | +0.041 |
snow | +0.040 |
eddy | +0.039 |
mosquitoes | +0.039 |
Neg logit contributions | |
ued | -0.047 |
chie | -0.046 |
sel | -0.045 |
None | -0.044 |
top | -0.041 |
Token | a |
Token ID | 257 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
arter | +0.039 |
iring | +0.039 |
eddy | +0.039 |
imi | +0.037 |
ucks | +0.036 |
Neg logit contributions | |
| -0.035 |
sel | -0.034 |
top | -0.032 |
one | -0.031 |
none | -0.030 |
Token | big |
Token ID | 1263 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
ucks | +0.057 |
check | +0.055 |
iring | +0.053 |
adoes | +0.052 |
accidents | +0.051 |
Neg logit contributions | |
| -0.035 |
top | -0.028 |
sel | -0.028 |
One | -0.026 |
second | -0.026 |
Token | snow |
Token ID | 6729 |
Feature activation | +5.57e+00 |
Pos logit contributions | |
iring | +0.056 |
ucks | +0.050 |
check | +0.049 |
eddy | +0.044 |
mosquitoes | +0.041 |
Neg logit contributions | |
| -0.102 |
sel | -0.099 |
top | -0.095 |
One | -0.092 |
chie | -0.091 |
Token | man |
Token ID | 805 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
iring | +0.137 |
ucks | +0.134 |
accidents | +0.131 |
check | +0.129 |
mosquitoes | +0.127 |
Neg logit contributions | |
sel | -0.111 |
pe | -0.110 |
top | -0.101 |
| -0.098 |
none | -0.096 |
Token | in |
Token ID | 287 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
iring | +0.023 |
ucks | +0.021 |
eddy | +0.020 |
mosquitoes | +0.020 |
imi | +0.020 |
Neg logit contributions | |
sel | -0.046 |
ued | -0.043 |
| -0.042 |
chie | -0.042 |
top | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
ued | +0.051 |
sel | +0.049 |
chie | +0.048 |
ical | +0.046 |
None | +0.045 |
Neg logit contributions | |
snow | -0.019 |
dust | -0.019 |
fort | -0.019 |
eddy | -0.019 |
ucks | -0.018 |
Token | yard |
Token ID | 12699 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
sel | +0.042 |
| +0.040 |
ued | +0.039 |
chie | +0.039 |
top | +0.039 |
Neg logit contributions | |
iring | -0.017 |
ucks | -0.015 |
eddy | -0.015 |
imi | -0.014 |
accidents | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
chie | +0.012 |
sel | +0.012 |
ued | +0.011 |
None | +0.010 |
ience | +0.010 |
Neg logit contributions | |
iring | -0.007 |
fort | -0.007 |
from | -0.006 |
ucks | -0.006 |
eddy | -0.006 |
Token | mud |
Token ID | 17492 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
iring | +0.004 |
eddy | +0.004 |
ucks | +0.004 |
fort | +0.004 |
imi | +0.004 |
Neg logit contributions | |
sel | -0.008 |
ued | -0.008 |
chie | -0.008 |
| -0.008 |
None | -0.008 |
Token | fight |
Token ID | 1907 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
iring | +0.075 |
eddy | +0.069 |
ucks | +0.068 |
imi | +0.066 |
mosquitoes | +0.063 |
Neg logit contributions | |
sel | -0.118 |
chie | -0.110 |
ued | -0.110 |
| -0.109 |
top | -0.108 |
Token | . |
Token ID | 13 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
sel | +0.044 |
chie | +0.041 |
ued | +0.041 |
| +0.039 |
None | +0.039 |
Neg logit contributions | |
iring | -0.030 |
eddy | -0.028 |
ucks | -0.027 |
fort | -0.027 |
mosquitoes | -0.027 |
Token | They |
Token ID | 1119 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
iring | +0.011 |
ucks | +0.010 |
eddy | +0.010 |
fort | +0.010 |
imi | +0.010 |
Neg logit contributions | |
sel | -0.012 |
chie | -0.012 |
ued | -0.012 |
top | -0.011 |
| -0.011 |
Token | threw |
Token ID | 9617 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
dust | +0.015 |
itch | +0.014 |
mess | +0.013 |
check | +0.013 |
from | +0.013 |
Neg logit contributions | |
chie | -0.026 |
sel | -0.026 |
ued | -0.026 |
None | -0.025 |
ical | -0.024 |
Token | mud |
Token ID | 17492 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
mosquitoes | +0.009 |
fort | +0.008 |
accidents | +0.008 |
snow | +0.008 |
dust | +0.008 |
Neg logit contributions | |
sel | -0.016 |
ued | -0.016 |
chie | -0.016 |
None | -0.015 |
ical | -0.014 |
Token | at |
Token ID | 379 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
iring | +0.091 |
eddy | +0.084 |
ucks | +0.081 |
imi | +0.080 |
fort | +0.076 |
Neg logit contributions | |
sel | -0.154 |
ued | -0.145 |
chie | -0.143 |
| -0.142 |
top | -0.140 |
Token | each |
Token ID | 1123 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
iring | +0.027 |
mosquitoes | +0.027 |
eddy | +0.025 |
ucks | +0.025 |
imi | +0.024 |
Neg logit contributions | |
sel | -0.059 |
ued | -0.059 |
chie | -0.058 |
ical | -0.055 |
None | -0.054 |
Token | other |
Token ID | 584 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
sel | +0.012 |
ued | +0.011 |
chie | +0.011 |
None | +0.011 |
| +0.011 |
Neg logit contributions | |
iring | -0.011 |
ucks | -0.010 |
eddy | -0.010 |
fort | -0.010 |
mosquitoes | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
sel | +0.028 |
ued | +0.027 |
chie | +0.027 |
None | +0.026 |
| +0.025 |
Neg logit contributions | |
iring | -0.012 |
fort | -0.012 |
mosquitoes | -0.011 |
eddy | -0.011 |
from | -0.011 |
Token | got |
Token ID | 1392 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
chie | +0.003 |
sel | +0.003 |
ued | +0.003 |
None | +0.003 |
top | +0.003 |
Neg logit contributions | |
mosquitoes | -0.002 |
accidents | -0.002 |
fort | -0.002 |
iring | -0.002 |
itch | -0.002 |
Token | with |
Token ID | 351 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
iring | +0.013 |
ucks | +0.011 |
eddy | +0.011 |
imi | +0.011 |
accidents | +0.011 |
Neg logit contributions | |
sel | -0.025 |
ued | -0.024 |
| -0.024 |
chie | -0.023 |
None | -0.023 |
Token | snow |
Token ID | 6729 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
sel | +0.002 |
| +0.002 |
ued | +0.002 |
chie | +0.002 |
None | +0.002 |
Neg logit contributions | |
iring | -0.001 |
ucks | -0.001 |
eddy | -0.001 |
fort | -0.001 |
check | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +5.41e-03 |
Pos logit contributions | |
iring | +0.089 |
ucks | +0.085 |
eddy | +0.083 |
check | +0.081 |
accidents | +0.081 |
Neg logit contributions | |
sel | -0.089 |
ued | -0.080 |
| -0.080 |
top | -0.079 |
chie | -0.079 |
Token | She |
Token ID | 1375 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
iring | +0.000 |
eddy | +0.000 |
ucks | +0.000 |
cartoons | +0.000 |
fort | +0.000 |
Neg logit contributions | |
ued | -0.000 |
sel | -0.000 |
chie | -0.000 |
ience | -0.000 |
pe | -0.000 |
Token | made |
Token ID | 925 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
fort | +0.023 |
eddy | +0.023 |
iring | +0.023 |
imi | +0.022 |
ucks | +0.022 |
Neg logit contributions | |
sel | -0.021 |
ued | -0.021 |
chie | -0.021 |
None | -0.020 |
top | -0.019 |
Token | snow |
Token ID | 6729 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
iring | +0.036 |
eddy | +0.036 |
arter | +0.036 |
imi | +0.034 |
ucks | +0.034 |
Neg logit contributions | |
sel | -0.025 |
| -0.025 |
top | -0.022 |
chie | -0.021 |
ued | -0.021 |
Token | balls |
Token ID | 21591 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
check | +0.113 |
iring | +0.112 |
mosquitoes | +0.111 |
accidents | +0.107 |
ucks | +0.105 |
Neg logit contributions | |
sel | -0.117 |
pe | -0.109 |
| -0.108 |
top | -0.105 |
none | -0.100 |
Token | and |
Token ID | 290 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
iring | +0.056 |
eddy | +0.053 |
ucks | +0.053 |
imi | +0.052 |
accidents | +0.050 |
Neg logit contributions | |
sel | -0.091 |
| -0.084 |
ued | -0.084 |
top | -0.082 |
none | -0.081 |
Token | snow |
Token ID | 6729 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
iring | +0.025 |
eddy | +0.022 |
ucks | +0.021 |
imi | +0.020 |
accidents | +0.019 |
Neg logit contributions | |
sel | -0.043 |
| -0.041 |
chie | -0.039 |
ued | -0.039 |
top | -0.038 |
Token | men |
Token ID | 3653 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
iring | +0.096 |
ucks | +0.090 |
mosquitoes | +0.089 |
accidents | +0.089 |
check | +0.087 |
Neg logit contributions | |
sel | -0.101 |
| -0.091 |
top | -0.088 |
pe | -0.087 |
none | -0.086 |
Token | with |
Token ID | 351 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
iring | +0.003 |
ucks | +0.003 |
eddy | +0.003 |
imi | +0.003 |
fort | +0.003 |
Neg logit contributions | |
sel | -0.004 |
ued | -0.004 |
chie | -0.004 |
| -0.004 |
None | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
iring | +0.010 |
eddy | +0.010 |
imi | +0.009 |
ucks | +0.009 |
accidents | +0.009 |
Neg logit contributions | |
| -0.013 |
sel | -0.013 |
ued | -0.013 |
top | -0.012 |
None | -0.012 |
Token | snow |
Token ID | 6729 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
iring | +0.001 |
ucks | +0.001 |
eddy | +0.001 |
check | +0.001 |
accidents | +0.001 |
Neg logit contributions | |
sel | -0.001 |
| -0.001 |
none | -0.001 |
top | -0.001 |
None | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
iring | +0.095 |
ucks | +0.090 |
check | +0.088 |
accidents | +0.088 |
eddy | +0.088 |
Neg logit contributions | |
sel | -0.077 |
pe | -0.070 |
| -0.069 |
top | -0.069 |
ued | -0.068 |
Token | They |
Token ID | 1119 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
iring | +0.030 |
eddy | +0.028 |
ucks | +0.028 |
fort | +0.027 |
imi | +0.027 |
Neg logit contributions | |
sel | -0.025 |
ued | -0.023 |
| -0.023 |
chie | -0.022 |
None | -0.022 |
Token | made |
Token ID | 925 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
fort | +0.031 |
dust | +0.031 |
snow | +0.030 |
itch | +0.029 |
imi | +0.028 |
Neg logit contributions | |
ued | -0.037 |
chie | -0.036 |
sel | -0.035 |
None | -0.034 |
ical | -0.032 |
Token | snow |
Token ID | 6729 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
arter | +0.036 |
iring | +0.035 |
eddy | +0.034 |
imi | +0.034 |
ivering | +0.033 |
Neg logit contributions | |
| -0.032 |
sel | -0.031 |
one | -0.029 |
top | -0.028 |
none | -0.028 |
Token | balls |
Token ID | 21591 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
mosquitoes | +0.110 |
iring | +0.109 |
check | +0.109 |
accidents | +0.104 |
wolves | +0.104 |
Neg logit contributions | |
sel | -0.114 |
pe | -0.112 |
| -0.110 |
top | -0.102 |
none | -0.099 |
Token | and |
Token ID | 290 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
iring | +0.049 |
imi | +0.047 |
eddy | +0.046 |
ucks | +0.046 |
accidents | +0.043 |
Neg logit contributions | |
sel | -0.077 |
| -0.070 |
ued | -0.069 |
none | -0.068 |
top | -0.068 |
Token | snow |
Token ID | 6729 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
iring | +0.021 |
eddy | +0.017 |
ucks | +0.017 |
imi | +0.015 |
check | +0.015 |
Neg logit contributions | |
sel | -0.038 |
| -0.037 |
top | -0.034 |
none | -0.034 |
chie | -0.034 |
Token | men |
Token ID | 3653 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
iring | +0.097 |
mosquitoes | +0.092 |
accidents | +0.091 |
check | +0.090 |
imi | +0.088 |
Neg logit contributions | |
sel | -0.091 |
pe | -0.085 |
| -0.085 |
top | -0.080 |
none | -0.079 |
Token | and |
Token ID | 290 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
sel | +0.009 |
| +0.009 |
ued | +0.008 |
top | +0.008 |
chie | +0.008 |
Neg logit contributions | |
iring | -0.009 |
ucks | -0.008 |
imi | -0.008 |
eddy | -0.008 |
mosquitoes | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
iring | +0.068 |
eddy | +0.064 |
fort | +0.062 |
ucks | +0.062 |
imi | +0.061 |
Neg logit contributions | |
sel | -0.072 |
chie | -0.068 |
ued | -0.068 |
None | -0.065 |
| -0.064 |
Token | They |
Token ID | 1119 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
iring | +0.010 |
fort | +0.010 |
ucks | +0.010 |
eddy | +0.010 |
cartoons | +0.009 |
Neg logit contributions | |
chie | -0.017 |
sel | -0.017 |
ued | -0.016 |
top | -0.014 |
None | -0.014 |
Token | made |
Token ID | 925 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
dust | +0.026 |
fort | +0.025 |
snow | +0.025 |
iring | +0.025 |
eddy | +0.025 |
Neg logit contributions | |
ued | -0.039 |
chie | -0.039 |
sel | -0.038 |
None | -0.036 |
ical | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
iring | +0.047 |
arter | +0.047 |
eddy | +0.047 |
imi | +0.047 |
ucks | +0.046 |
Neg logit contributions | |
sel | -0.027 |
| -0.027 |
top | -0.024 |
none | -0.023 |
one | -0.022 |
Token | big |
Token ID | 1263 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
ucks | +0.046 |
iring | +0.044 |
check | +0.042 |
mosquitoes | +0.041 |
eddy | +0.040 |
Neg logit contributions | |
| -0.037 |
sel | -0.032 |
top | -0.031 |
chie | -0.030 |
One | -0.030 |
Token | snow |
Token ID | 6729 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
iring | +0.045 |
ucks | +0.040 |
check | +0.039 |
eddy | +0.035 |
mosquitoes | +0.034 |
Neg logit contributions | |
| -0.099 |
sel | -0.096 |
top | -0.092 |
None | -0.090 |
chie | -0.089 |
Token | man |
Token ID | 805 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ucks | +0.125 |
iring | +0.124 |
mosquitoes | +0.118 |
check | +0.117 |
accidents | +0.115 |
Neg logit contributions | |
sel | -0.112 |
pe | -0.107 |
top | -0.102 |
| -0.101 |
bar | -0.098 |
Token | with |
Token ID | 351 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
iring | +0.014 |
eddy | +0.014 |
fort | +0.013 |
ucks | +0.013 |
imi | +0.012 |
Neg logit contributions | |
sel | -0.036 |
chie | -0.035 |
ued | -0.035 |
None | -0.034 |
| -0.033 |
Token | a |
Token ID | 257 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
ued | +0.016 |
chie | +0.016 |
sel | +0.016 |
None | +0.015 |
top | +0.014 |
Neg logit contributions | |
iring | -0.012 |
eddy | -0.011 |
mosquitoes | -0.011 |
ucks | -0.011 |
snow | -0.011 |
Token | hat |
Token ID | 6877 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
sel | +0.017 |
ued | +0.016 |
chie | +0.016 |
None | +0.016 |
top | +0.015 |
Neg logit contributions | |
iring | -0.008 |
fort | -0.008 |
eddy | -0.008 |
ucks | -0.008 |
imi | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
iring | +0.029 |
ucks | +0.027 |
mosquitoes | +0.026 |
eddy | +0.026 |
imi | +0.026 |
Neg logit contributions | |
sel | -0.053 |
| -0.049 |
ued | -0.049 |
top | -0.048 |
chie | -0.048 |
Token | play |
Token ID | 711 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
iring | +0.024 |
eddy | +0.021 |
ucks | +0.020 |
accidents | +0.019 |
imi | +0.018 |
Neg logit contributions | |
| -0.026 |
One | -0.022 |
top | -0.021 |
sel | -0.021 |
ued | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
iring | +0.014 |
eddy | +0.013 |
ucks | +0.013 |
imi | +0.013 |
check | +0.012 |
Neg logit contributions | |
| -0.008 |
sel | -0.008 |
ued | -0.008 |
None | -0.008 |
top | -0.007 |
Token | She |
Token ID | 1375 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
iring | +0.007 |
eddy | +0.007 |
ucks | +0.007 |
mosquitoes | +0.006 |
imi | +0.006 |
Neg logit contributions | |
| -0.007 |
sel | -0.007 |
None | -0.006 |
ued | -0.006 |
top | -0.006 |
Token | made |
Token ID | 925 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
iring | +0.015 |
eddy | +0.015 |
ucks | +0.015 |
fort | +0.014 |
imi | +0.014 |
Neg logit contributions | |
sel | -0.013 |
ued | -0.012 |
| -0.012 |
chie | -0.012 |
top | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
arter | +0.037 |
iring | +0.035 |
eddy | +0.034 |
imi | +0.033 |
ucks | +0.033 |
Neg logit contributions | |
| -0.017 |
one | -0.014 |
sel | -0.013 |
none | -0.011 |
ued | -0.011 |
Token | snow |
Token ID | 6729 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
ucks | +0.039 |
iring | +0.037 |
asc | +0.035 |
adoes | +0.035 |
eddy | +0.034 |
Neg logit contributions | |
| -0.029 |
bank | -0.024 |
second | -0.023 |
chie | -0.023 |
sel | -0.023 |
Token | man |
Token ID | 805 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
ucks | +0.132 |
iring | +0.132 |
mosquitoes | +0.129 |
wolves | +0.123 |
pets | +0.120 |
Neg logit contributions | |
pe | -0.098 |
bar | -0.097 |
sel | -0.095 |
top | -0.086 |
| -0.086 |
Token | and |
Token ID | 290 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
iring | +0.013 |
ucks | +0.012 |
mosquitoes | +0.011 |
imi | +0.011 |
accidents | +0.011 |
Neg logit contributions | |
sel | -0.019 |
| -0.018 |
top | -0.018 |
ued | -0.017 |
chie | -0.017 |
Token | had |
Token ID | 550 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
iring | +0.012 |
ucks | +0.011 |
eddy | +0.011 |
imi | +0.011 |
fort | +0.010 |
Neg logit contributions | |
sel | -0.011 |
| -0.010 |
ued | -0.010 |
chie | -0.009 |
None | -0.009 |
Token | so |
Token ID | 523 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
sel | +0.008 |
ued | +0.008 |
chie | +0.008 |
None | +0.008 |
top | +0.007 |
Neg logit contributions | |
fort | -0.007 |
honey | -0.007 |
iring | -0.007 |
eddy | -0.006 |
snow | -0.006 |
Token | much |
Token ID | 881 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
iring | +0.028 |
ucks | +0.027 |
eddy | +0.027 |
fort | +0.026 |
imi | +0.026 |
Neg logit contributions | |
sel | -0.014 |
ued | -0.013 |
chie | -0.012 |
| -0.012 |
None | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
iring | +0.013 |
eddy | +0.013 |
ucks | +0.013 |
imi | +0.012 |
fort | +0.012 |
Neg logit contributions | |
sel | -0.016 |
ued | -0.015 |
chie | -0.015 |
None | -0.014 |
| -0.013 |
Token | We |
Token ID | 775 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
iring | +0.028 |
fort | +0.026 |
ucks | +0.026 |
eddy | +0.025 |
accidents | +0.025 |
Neg logit contributions | |
| -0.023 |
sel | -0.023 |
None | -0.022 |
ued | -0.021 |
chie | -0.021 |
Token | made |
Token ID | 925 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
iring | +0.024 |
eddy | +0.022 |
ucks | +0.022 |
fort | +0.022 |
imi | +0.021 |
Neg logit contributions | |
sel | -0.035 |
ued | -0.033 |
chie | -0.033 |
None | -0.032 |
| -0.032 |
Token | a |
Token ID | 257 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
iring | +0.038 |
ucks | +0.034 |
fort | +0.034 |
eddy | +0.033 |
arter | +0.033 |
Neg logit contributions | |
| -0.035 |
sel | -0.033 |
ued | -0.031 |
top | -0.031 |
chie | -0.029 |
Token | nice |
Token ID | 3621 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
iring | +0.021 |
adoes | +0.019 |
ucks | +0.019 |
check | +0.019 |
mosquitoes | +0.018 |
Neg logit contributions | |
| -0.017 |
One | -0.014 |
second | -0.014 |
top | -0.013 |
one | -0.012 |
Token | snow |
Token ID | 6729 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
iring | +0.027 |
check | +0.025 |
mosquitoes | +0.023 |
spies | +0.023 |
adoes | +0.023 |
Neg logit contributions | |
| -0.037 |
one | -0.032 |
One | -0.032 |
top | -0.030 |
None | -0.028 |
Token | man |
Token ID | 805 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
iring | +0.129 |
mosquitoes | +0.117 |
accidents | +0.114 |
check | +0.112 |
ucks | +0.111 |
Neg logit contributions | |
sel | -0.105 |
pe | -0.101 |
top | -0.092 |
| -0.092 |
bar | -0.089 |
Token | outside |
Token ID | 2354 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
iring | +0.013 |
ucks | +0.012 |
eddy | +0.012 |
imi | +0.011 |
mosquitoes | +0.011 |
Neg logit contributions | |
sel | -0.012 |
ued | -0.011 |
chie | -0.011 |
| -0.010 |
top | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
eddy | +0.023 |
iring | +0.023 |
fort | +0.022 |
from | +0.022 |
ucks | +0.022 |
Neg logit contributions | |
sel | -0.029 |
ued | -0.028 |
chie | -0.027 |
None | -0.026 |
| -0.025 |
Token | He |
Token ID | 679 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
iring | +0.046 |
mosquitoes | +0.042 |
fort | +0.041 |
imi | +0.041 |
ucks | +0.041 |
Neg logit contributions | |
| -0.031 |
sel | -0.029 |
None | -0.028 |
One | -0.028 |
ued | -0.025 |
Token | is |
Token ID | 318 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
iring | +0.003 |
eddy | +0.002 |
ucks | +0.002 |
fort | +0.002 |
imi | +0.002 |
Neg logit contributions | |
sel | -0.003 |
ued | -0.003 |
| -0.003 |
chie | -0.003 |
top | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
iring | +0.069 |
eddy | +0.065 |
ucks | +0.064 |
fort | +0.064 |
imi | +0.062 |
Neg logit contributions | |
sel | -0.070 |
ued | -0.066 |
chie | -0.066 |
| -0.063 |
None | -0.063 |
Token | They |
Token ID | 1119 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
iring | +0.010 |
ucks | +0.010 |
eddy | +0.009 |
fort | +0.009 |
imi | +0.009 |
Neg logit contributions | |
chie | -0.014 |
sel | -0.014 |
ued | -0.013 |
top | -0.012 |
None | -0.012 |
Token | made |
Token ID | 925 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
dust | +0.024 |
iring | +0.024 |
fort | +0.024 |
snow | +0.023 |
eddy | +0.023 |
Neg logit contributions | |
ued | -0.037 |
chie | -0.037 |
sel | -0.036 |
None | -0.035 |
ical | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
eddy | +0.053 |
iring | +0.053 |
imi | +0.053 |
arter | +0.053 |
ucks | +0.051 |
Neg logit contributions | |
sel | -0.026 |
| -0.025 |
top | -0.023 |
none | -0.022 |
one | -0.021 |
Token | big |
Token ID | 1263 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
ucks | +0.045 |
iring | +0.043 |
check | +0.042 |
mosquitoes | +0.040 |
eddy | +0.040 |
Neg logit contributions | |
| -0.035 |
sel | -0.030 |
top | -0.028 |
chie | -0.027 |
One | -0.027 |
Token | snow |
Token ID | 6729 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
iring | +0.044 |
check | +0.038 |
ucks | +0.038 |
eddy | +0.034 |
mosquitoes | +0.033 |
Neg logit contributions | |
| -0.096 |
sel | -0.093 |
top | -0.089 |
None | -0.086 |
chie | -0.086 |
Token | man |
Token ID | 805 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
iring | +0.126 |
ucks | +0.125 |
mosquitoes | +0.120 |
check | +0.118 |
accidents | +0.117 |
Neg logit contributions | |
sel | -0.107 |
pe | -0.104 |
top | -0.098 |
| -0.096 |
bar | -0.094 |
Token | with |
Token ID | 351 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
iring | +0.013 |
eddy | +0.012 |
ucks | +0.012 |
fort | +0.012 |
imi | +0.011 |
Neg logit contributions | |
sel | -0.031 |
ued | -0.030 |
chie | -0.030 |
None | -0.029 |
| -0.029 |
Token | a |
Token ID | 257 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
ued | +0.014 |
chie | +0.014 |
sel | +0.014 |
None | +0.013 |
top | +0.012 |
Neg logit contributions | |
iring | -0.010 |
eddy | -0.010 |
ucks | -0.009 |
mosquitoes | -0.009 |
fort | -0.009 |
Token | hat |
Token ID | 6877 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
sel | +0.015 |
ued | +0.014 |
chie | +0.014 |
None | +0.014 |
top | +0.014 |
Neg logit contributions | |
iring | -0.008 |
fort | -0.007 |
eddy | -0.007 |
ucks | -0.007 |
imi | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
iring | +0.029 |
ucks | +0.027 |
mosquitoes | +0.027 |
imi | +0.026 |
eddy | +0.025 |
Neg logit contributions | |
sel | -0.051 |
| -0.047 |
ued | -0.046 |
top | -0.046 |
None | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
iring | +0.074 |
eddy | +0.070 |
ucks | +0.070 |
fort | +0.069 |
imi | +0.068 |
Neg logit contributions | |
sel | -0.064 |
ued | -0.060 |
chie | -0.059 |
| -0.057 |
None | -0.056 |
Token | They |
Token ID | 1119 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
iring | +0.021 |
ucks | +0.019 |
eddy | +0.019 |
imi | +0.018 |
mosquitoes | +0.018 |
Neg logit contributions | |
sel | -0.021 |
ued | -0.020 |
| -0.020 |
chie | -0.019 |
None | -0.019 |
Token | made |
Token ID | 925 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
dust | +0.029 |
fort | +0.028 |
iring | +0.028 |
snow | +0.027 |
itch | +0.027 |
Neg logit contributions | |
ued | -0.042 |
chie | -0.042 |
sel | -0.041 |
None | -0.039 |
ical | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
imi | +0.047 |
arter | +0.047 |
iring | +0.046 |
eddy | +0.046 |
ucks | +0.044 |
Neg logit contributions | |
sel | -0.024 |
| -0.023 |
top | -0.020 |
none | -0.020 |
one | -0.019 |
Token | big |
Token ID | 1263 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
ucks | +0.046 |
iring | +0.044 |
check | +0.043 |
mosquitoes | +0.041 |
adoes | +0.041 |
Neg logit contributions | |
| -0.035 |
sel | -0.030 |
top | -0.029 |
chie | -0.027 |
bank | -0.027 |
Token | snow |
Token ID | 6729 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
iring | +0.048 |
ucks | +0.042 |
check | +0.042 |
eddy | +0.037 |
mosquitoes | +0.036 |
Neg logit contributions | |
| -0.094 |
sel | -0.092 |
top | -0.088 |
None | -0.084 |
ued | -0.084 |
Token | man |
Token ID | 805 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
iring | +0.123 |
ucks | +0.122 |
mosquitoes | +0.116 |
accidents | +0.115 |
check | +0.115 |
Neg logit contributions | |
sel | -0.110 |
pe | -0.107 |
top | -0.100 |
| -0.096 |
bar | -0.095 |
Token | with |
Token ID | 351 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
iring | +0.014 |
eddy | +0.013 |
ucks | +0.013 |
fort | +0.012 |
imi | +0.012 |
Neg logit contributions | |
sel | -0.033 |
ued | -0.031 |
chie | -0.031 |
| -0.030 |
None | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
ued | +0.019 |
chie | +0.018 |
sel | +0.018 |
None | +0.017 |
top | +0.016 |
Neg logit contributions | |
eddy | -0.013 |
iring | -0.013 |
mosquitoes | -0.012 |
snow | -0.012 |
ucks | -0.012 |
Token | hat |
Token ID | 6877 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
sel | +0.017 |
ued | +0.017 |
chie | +0.017 |
None | +0.016 |
top | +0.016 |
Neg logit contributions | |
iring | -0.008 |
fort | -0.008 |
eddy | -0.008 |
ucks | -0.008 |
imi | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
iring | +0.032 |
ucks | +0.031 |
mosquitoes | +0.030 |
imi | +0.029 |
accidents | +0.029 |
Neg logit contributions | |
sel | -0.051 |
| -0.047 |
ued | -0.045 |
top | -0.045 |
None | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
iring | +0.078 |
eddy | +0.074 |
ucks | +0.074 |
fort | +0.072 |
imi | +0.072 |
Neg logit contributions | |
sel | -0.068 |
ued | -0.063 |
chie | -0.063 |
| -0.060 |
None | -0.060 |
Token | They |
Token ID | 1119 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
iring | +0.018 |
ucks | +0.018 |
eddy | +0.018 |
fort | +0.017 |
imi | +0.017 |
Neg logit contributions | |
sel | -0.021 |
chie | -0.020 |
ued | -0.019 |
| -0.018 |
None | -0.018 |
Token | make |
Token ID | 787 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
iring | +0.020 |
fort | +0.019 |
mosquitoes | +0.019 |
ucks | +0.019 |
eddy | +0.019 |
Neg logit contributions | |
sel | -0.047 |
ued | -0.046 |
chie | -0.046 |
None | -0.045 |
top | -0.043 |
Token | a |
Token ID | 257 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
iring | +0.031 |
eddy | +0.031 |
arter | +0.031 |
ucks | +0.030 |
imi | +0.030 |
Neg logit contributions | |
| -0.023 |
sel | -0.023 |
top | -0.021 |
none | -0.020 |
one | -0.020 |
Token | big |
Token ID | 1263 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
ucks | +0.048 |
iring | +0.046 |
check | +0.046 |
adoes | +0.044 |
accidents | +0.043 |
Neg logit contributions | |
| -0.035 |
sel | -0.028 |
seas | -0.028 |
top | -0.028 |
second | -0.028 |
Token | snow |
Token ID | 6729 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
iring | +0.051 |
check | +0.043 |
ucks | +0.043 |
eddy | +0.038 |
mosquitoes | +0.036 |
Neg logit contributions | |
| -0.102 |
sel | -0.096 |
top | -0.093 |
One | -0.091 |
None | -0.089 |
Token | man |
Token ID | 805 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
iring | +0.123 |
ucks | +0.121 |
accidents | +0.115 |
check | +0.115 |
mosquitoes | +0.114 |
Neg logit contributions | |
sel | -0.109 |
pe | -0.108 |
| -0.101 |
top | -0.100 |
bar | -0.096 |
Token | with |
Token ID | 351 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
iring | +0.013 |
eddy | +0.012 |
ucks | +0.011 |
fort | +0.011 |
imi | +0.011 |
Neg logit contributions | |
sel | -0.031 |
chie | -0.030 |
ued | -0.030 |
None | -0.029 |
| -0.029 |
Token | a |
Token ID | 257 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
ued | +0.007 |
chie | +0.007 |
sel | +0.007 |
None | +0.006 |
| +0.006 |
Neg logit contributions | |
iring | -0.005 |
eddy | -0.005 |
mosquitoes | -0.005 |
fort | -0.005 |
ucks | -0.005 |
Token | hat |
Token ID | 6877 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
sel | +0.014 |
ued | +0.014 |
chie | +0.014 |
None | +0.013 |
top | +0.013 |
Neg logit contributions | |
iring | -0.006 |
fort | -0.006 |
eddy | -0.006 |
ucks | -0.005 |
imi | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
iring | +0.033 |
ucks | +0.031 |
mosquitoes | +0.030 |
eddy | +0.030 |
imi | +0.029 |
Neg logit contributions | |
sel | -0.058 |
| -0.054 |
ued | -0.053 |
top | -0.052 |
None | -0.052 |
Token | with |
Token ID | 351 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
iring | +0.034 |
eddy | +0.033 |
imi | +0.033 |
ucks | +0.031 |
accidents | +0.030 |
Neg logit contributions | |
| -0.036 |
ued | -0.035 |
sel | -0.035 |
None | -0.033 |
top | -0.032 |
Token | snow |
Token ID | 6729 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
iring | +0.016 |
eddy | +0.014 |
ucks | +0.014 |
fort | +0.014 |
mosquitoes | +0.014 |
Neg logit contributions | |
sel | -0.025 |
ued | -0.024 |
chie | -0.023 |
None | -0.022 |
| -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
iring | +0.088 |
ucks | +0.083 |
eddy | +0.082 |
imi | +0.079 |
mosquitoes | +0.078 |
Neg logit contributions | |
sel | -0.101 |
ued | -0.093 |
chie | -0.092 |
| -0.091 |
top | -0.089 |
Token | They |
Token ID | 1119 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
iring | +0.032 |
ucks | +0.030 |
eddy | +0.030 |
fort | +0.029 |
imi | +0.029 |
Neg logit contributions | |
sel | -0.039 |
chie | -0.037 |
ued | -0.037 |
top | -0.034 |
None | -0.033 |
Token | made |
Token ID | 925 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
fort | +0.020 |
dust | +0.020 |
itch | +0.020 |
mosquitoes | +0.020 |
from | +0.019 |
Neg logit contributions | |
chie | -0.027 |
ued | -0.027 |
sel | -0.025 |
None | -0.025 |
top | -0.024 |
Token | snow |
Token ID | 6729 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
iring | +0.033 |
eddy | +0.031 |
arter | +0.031 |
ucks | +0.030 |
check | +0.029 |
Neg logit contributions | |
| -0.027 |
sel | -0.027 |
top | -0.024 |
ued | -0.023 |
none | -0.023 |
Token | balls |
Token ID | 21591 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
iring | +0.105 |
mosquitoes | +0.100 |
check | +0.096 |
imi | +0.096 |
ucks | +0.095 |
Neg logit contributions | |
sel | -0.127 |
| -0.115 |
top | -0.113 |
pe | -0.113 |
ued | -0.107 |
Token | and |
Token ID | 290 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
iring | +0.054 |
eddy | +0.050 |
ucks | +0.050 |
imi | +0.049 |
mosquitoes | +0.046 |
Neg logit contributions | |
sel | -0.089 |
ued | -0.082 |
| -0.082 |
top | -0.080 |
None | -0.079 |
Token | snow |
Token ID | 6729 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
iring | +0.028 |
eddy | +0.024 |
ucks | +0.024 |
imi | +0.023 |
accidents | +0.021 |
Neg logit contributions | |
sel | -0.040 |
| -0.038 |
ued | -0.037 |
top | -0.036 |
chie | -0.036 |
Token | men |
Token ID | 3653 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
iring | +0.091 |
ucks | +0.085 |
imi | +0.083 |
eddy | +0.083 |
mosquitoes | +0.082 |
Neg logit contributions | |
sel | -0.106 |
| -0.096 |
ued | -0.095 |
top | -0.094 |
chie | -0.092 |
Token | and |
Token ID | 290 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
iring | +0.004 |
eddy | +0.004 |
ucks | +0.004 |
fort | +0.004 |
imi | +0.003 |
Neg logit contributions | |
sel | -0.006 |
ued | -0.006 |
chie | -0.006 |
None | -0.006 |
| -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
iring | +0.087 |
ucks | +0.083 |
eddy | +0.082 |
imi | +0.080 |
accidents | +0.080 |
Neg logit contributions | |
sel | -0.061 |
ued | -0.055 |
| -0.055 |
top | -0.054 |
chie | -0.053 |
Token | They |
Token ID | 1119 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
iring | +0.007 |
ucks | +0.007 |
eddy | +0.007 |
fort | +0.007 |
cartoons | +0.006 |
Neg logit contributions | |
sel | -0.006 |
chie | -0.006 |
ued | -0.006 |
top | -0.005 |
None | -0.005 |
Token | make |
Token ID | 787 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
fort | +0.020 |
iring | +0.020 |
mosquitoes | +0.019 |
eddy | +0.019 |
ucks | +0.019 |
Neg logit contributions | |
sel | -0.044 |
ued | -0.043 |
chie | -0.042 |
None | -0.042 |
| -0.040 |
Token | a |
Token ID | 257 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
eddy | +0.027 |
iring | +0.025 |
arter | +0.025 |
imi | +0.025 |
ucks | +0.025 |
Neg logit contributions | |
sel | -0.027 |
| -0.026 |
none | -0.024 |
top | -0.024 |
one | -0.024 |
Token | big |
Token ID | 1263 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
ucks | +0.049 |
check | +0.047 |
iring | +0.046 |
adoes | +0.045 |
accidents | +0.044 |
Neg logit contributions | |
| -0.026 |
sel | -0.021 |
seas | -0.020 |
second | -0.020 |
top | -0.019 |
Token | snow |
Token ID | 6729 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
iring | +0.055 |
check | +0.050 |
ucks | +0.048 |
eddy | +0.043 |
mosquitoes | +0.040 |
Neg logit contributions | |
| -0.093 |
sel | -0.089 |
top | -0.085 |
One | -0.082 |
chie | -0.080 |
Token | man |
Token ID | 805 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
iring | +0.131 |
ucks | +0.125 |
accidents | +0.122 |
check | +0.120 |
mosquitoes | +0.119 |
Neg logit contributions | |
pe | -0.104 |
sel | -0.103 |
top | -0.090 |
bar | -0.088 |
| -0.087 |
Token | with |
Token ID | 351 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
iring | +0.016 |
ucks | +0.015 |
imi | +0.014 |
eddy | +0.014 |
mosquitoes | +0.014 |
Neg logit contributions | |
sel | -0.029 |
ued | -0.027 |
| -0.027 |
top | -0.026 |
chie | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
sel | +0.008 |
ued | +0.008 |
chie | +0.008 |
None | +0.007 |
| +0.007 |
Neg logit contributions | |
iring | -0.006 |
eddy | -0.006 |
ucks | -0.006 |
fort | -0.006 |
mosquitoes | -0.005 |
Token | hat |
Token ID | 6877 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
sel | +0.016 |
ued | +0.015 |
chie | +0.015 |
| +0.014 |
None | +0.014 |
Neg logit contributions | |
iring | -0.008 |
eddy | -0.008 |
ucks | -0.008 |
fort | -0.007 |
imi | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
iring | +0.037 |
ucks | +0.035 |
mosquitoes | +0.035 |
accidents | +0.034 |
imi | +0.034 |
Neg logit contributions | |
sel | -0.051 |
| -0.047 |
top | -0.045 |
ued | -0.045 |
None | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
iring | +0.069 |
eddy | +0.065 |
ucks | +0.065 |
fort | +0.065 |
imi | +0.063 |
Neg logit contributions | |
sel | -0.063 |
chie | -0.059 |
ued | -0.059 |
None | -0.056 |
| -0.055 |
Token | They |
Token ID | 1119 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ucks | +0.024 |
iring | +0.024 |
fort | +0.024 |
eddy | +0.024 |
imi | +0.024 |
Neg logit contributions | |
sel | -0.009 |
chie | -0.008 |
ued | -0.007 |
top | -0.006 |
None | -0.005 |
Token | make |
Token ID | 787 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
iring | +0.018 |
fort | +0.018 |
mosquitoes | +0.017 |
eddy | +0.017 |
ucks | +0.017 |
Neg logit contributions | |
sel | -0.038 |
ued | -0.037 |
chie | -0.037 |
None | -0.036 |
| -0.035 |
Token | a |
Token ID | 257 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
eddy | +0.025 |
iring | +0.025 |
imi | +0.023 |
ucks | +0.023 |
arter | +0.023 |
Neg logit contributions | |
| -0.040 |
sel | -0.039 |
top | -0.037 |
none | -0.037 |
ued | -0.036 |
Token | big |
Token ID | 1263 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
ucks | +0.041 |
iring | +0.040 |
check | +0.038 |
eddy | +0.037 |
accidents | +0.037 |
Neg logit contributions | |
| -0.039 |
sel | -0.033 |
chie | -0.033 |
top | -0.033 |
bank | -0.033 |
Token | snow |
Token ID | 6729 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
iring | +0.041 |
ucks | +0.034 |
eddy | +0.032 |
check | +0.032 |
mosquitoes | +0.028 |
Neg logit contributions | |
| -0.113 |
sel | -0.111 |
top | -0.107 |
chie | -0.106 |
ued | -0.106 |
Token | man |
Token ID | 805 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
iring | +0.121 |
ucks | +0.113 |
accidents | +0.111 |
mosquitoes | +0.111 |
check | +0.109 |
Neg logit contributions | |
pe | -0.108 |
sel | -0.107 |
| -0.103 |
top | -0.101 |
bar | -0.097 |
Token | with |
Token ID | 351 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
iring | +0.017 |
eddy | +0.016 |
ucks | +0.016 |
fort | +0.015 |
imi | +0.015 |
Neg logit contributions | |
sel | -0.029 |
ued | -0.027 |
chie | -0.027 |
| -0.026 |
None | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
ued | +0.008 |
sel | +0.008 |
chie | +0.008 |
None | +0.008 |
top | +0.008 |
Neg logit contributions | |
eddy | -0.005 |
iring | -0.005 |
mosquitoes | -0.005 |
fort | -0.005 |
snow | -0.005 |
Token | hat |
Token ID | 6877 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
sel | +0.019 |
ued | +0.019 |
chie | +0.019 |
None | +0.018 |
top | +0.018 |
Neg logit contributions | |
fort | -0.008 |
iring | -0.008 |
eddy | -0.008 |
ucks | -0.007 |
imi | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
iring | +0.032 |
ucks | +0.029 |
eddy | +0.029 |
mosquitoes | +0.028 |
imi | +0.028 |
Neg logit contributions | |
sel | -0.051 |
ued | -0.048 |
| -0.047 |
chie | -0.047 |
top | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
iring | +0.012 |
ucks | +0.012 |
eddy | +0.010 |
fort | +0.010 |
imi | +0.010 |
Neg logit contributions | |
sel | -0.015 |
chie | -0.014 |
ued | -0.014 |
top | -0.012 |
none | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
iring | +0.016 |
ucks | +0.016 |
eddy | +0.015 |
imi | +0.015 |
fort | +0.014 |
Neg logit contributions | |
sel | -0.019 |
chie | -0.018 |
ued | -0.017 |
none | -0.016 |
top | -0.016 |
Token | Jen |
Token ID | 44875 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
sel | +0.010 |
ued | +0.009 |
chie | +0.009 |
None | +0.009 |
| +0.009 |
Neg logit contributions | |
iring | -0.005 |
ucks | -0.004 |
eddy | -0.004 |
mosquitoes | -0.004 |
check | -0.004 |
Token | put |
Token ID | 1234 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
iring | +0.022 |
fort | +0.022 |
ucks | +0.021 |
eddy | +0.021 |
pets | +0.020 |
Neg logit contributions | |
chie | -0.037 |
sel | -0.036 |
ued | -0.035 |
None | -0.034 |
| -0.032 |
Token | the |
Token ID | 262 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
honey | +0.016 |
ucks | +0.016 |
from | +0.016 |
iring | +0.015 |
mosquitoes | +0.015 |
Neg logit contributions | |
chie | -0.044 |
ued | -0.044 |
sel | -0.042 |
None | -0.042 |
ical | -0.042 |
Token | cel |
Token ID | 18725 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
iring | +0.023 |
fort | +0.022 |
eddy | +0.022 |
ucks | +0.021 |
accidents | +0.021 |
Neg logit contributions | |
sel | -0.039 |
ued | -0.038 |
chie | -0.037 |
None | -0.036 |
top | -0.036 |
Token | ery |
Token ID | 1924 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
iring | +0.103 |
ucks | +0.099 |
eddy | +0.098 |
imi | +0.094 |
cartoons | +0.093 |
Neg logit contributions | |
sel | -0.134 |
chie | -0.121 |
ued | -0.120 |
| -0.116 |
top | -0.112 |
Token | in |
Token ID | 287 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
iring | +0.035 |
fort | +0.033 |
from | +0.031 |
eddy | +0.030 |
mosquitoes | +0.029 |
Neg logit contributions | |
sel | -0.100 |
chie | -0.098 |
ued | -0.096 |
None | -0.095 |
| -0.093 |
Token | her |
Token ID | 607 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
ued | +0.045 |
chie | +0.043 |
sel | +0.042 |
ical | +0.041 |
ience | +0.041 |
Neg logit contributions | |
from | -0.016 |
honey | -0.015 |
dust | -0.014 |
snow | -0.014 |
fort | -0.012 |
Token | mouth |
Token ID | 5422 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
sel | +0.006 |
ued | +0.006 |
chie | +0.005 |
None | +0.005 |
top | +0.005 |
Neg logit contributions | |
fort | -0.004 |
honey | -0.003 |
pets | -0.003 |
itch | -0.003 |
eddy | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +6.33e-02 |
Pos logit contributions | |
chie | +0.020 |
ued | +0.019 |
sel | +0.019 |
None | +0.018 |
Fer | +0.017 |
Neg logit contributions | |
from | -0.005 |
iring | -0.004 |
eddy | -0.003 |
fort | -0.003 |
about | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
iring | +0.013 |
eddy | +0.012 |
ucks | +0.012 |
fort | +0.011 |
mosquitoes | +0.011 |
Neg logit contributions | |
sel | -0.018 |
ued | -0.018 |
chie | -0.017 |
| -0.017 |
None | -0.017 |
Token | dog |
Token ID | 3290 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
iring | +0.002 |
ucks | +0.002 |
check | +0.002 |
eddy | +0.002 |
rap | +0.002 |
Neg logit contributions | |
sel | -0.003 |
| -0.003 |
none | -0.003 |
one | -0.003 |
pe | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
sel | +0.005 |
chie | +0.005 |
ued | +0.005 |
None | +0.004 |
top | +0.004 |
Neg logit contributions | |
iring | -0.003 |
fort | -0.003 |
eddy | -0.003 |
from | -0.003 |
mosquitoes | -0.003 |
Token | They |
Token ID | 1119 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
iring | +0.031 |
eddy | +0.029 |
ucks | +0.029 |
fort | +0.029 |
imi | +0.028 |
Neg logit contributions | |
sel | -0.031 |
ued | -0.029 |
chie | -0.029 |
| -0.028 |
None | -0.027 |
Token | threw |
Token ID | 9617 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
pets | +0.015 |
mosquitoes | +0.014 |
fort | +0.014 |
itch | +0.014 |
dust | +0.014 |
Neg logit contributions | |
chie | -0.025 |
ued | -0.025 |
sel | -0.025 |
top | -0.023 |
None | -0.023 |
Token | snow |
Token ID | 6729 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
iring | +0.008 |
eddy | +0.008 |
imi | +0.008 |
ucks | +0.008 |
fort | +0.007 |
Neg logit contributions | |
sel | -0.009 |
| -0.008 |
ued | -0.008 |
chie | -0.008 |
None | -0.008 |
Token | balls |
Token ID | 21591 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
iring | +0.119 |
imi | +0.113 |
ucks | +0.111 |
check | +0.107 |
eddy | +0.106 |
Neg logit contributions | |
sel | -0.115 |
pe | -0.104 |
none | -0.096 |
| -0.095 |
ued | -0.093 |
Token | at |
Token ID | 379 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
iring | +0.043 |
eddy | +0.039 |
ucks | +0.039 |
fort | +0.037 |
imi | +0.036 |
Neg logit contributions | |
sel | -0.110 |
ued | -0.105 |
chie | -0.104 |
| -0.103 |
None | -0.102 |
Token | him |
Token ID | 683 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
iring | +0.023 |
mosquitoes | +0.022 |
ucks | +0.021 |
eddy | +0.021 |
fort | +0.021 |
Neg logit contributions | |
sel | -0.048 |
ued | -0.047 |
chie | -0.047 |
ical | -0.044 |
None | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
sel | +0.016 |
chie | +0.015 |
ued | +0.015 |
None | +0.014 |
| +0.014 |
Neg logit contributions | |
iring | -0.009 |
eddy | -0.008 |
fort | -0.008 |
ucks | -0.008 |
mosquitoes | -0.008 |
Token | he |
Token ID | 339 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
sel | +0.008 |
ued | +0.007 |
| +0.007 |
chie | +0.007 |
None | +0.007 |
Neg logit contributions | |
iring | -0.008 |
eddy | -0.008 |
ucks | -0.008 |
imi | -0.008 |
fort | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
iring | +0.004 |
eddy | +0.004 |
from | +0.003 |
fort | +0.003 |
honey | +0.003 |
Neg logit contributions | |
chie | -0.006 |
ued | -0.006 |
sel | -0.006 |
None | -0.005 |
| -0.005 |
Token | It |
Token ID | 632 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
sel | +0.002 |
chie | +0.002 |
ued | +0.002 |
top | +0.002 |
pe | +0.002 |
Neg logit contributions | |
iring | -0.002 |
eddy | -0.002 |
ucks | -0.002 |
fort | -0.002 |
imi | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
iring | +0.015 |
eddy | +0.014 |
ucks | +0.014 |
fort | +0.013 |
imi | +0.013 |
Neg logit contributions | |
sel | -0.016 |
ued | -0.015 |
chie | -0.015 |
| -0.014 |
None | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
sel | +0.014 |
| +0.013 |
ued | +0.013 |
chie | +0.013 |
top | +0.012 |
Neg logit contributions | |
iring | -0.018 |
ucks | -0.018 |
eddy | -0.017 |
imi | -0.016 |
fort | -0.016 |
Token | best |
Token ID | 1266 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
sel | +0.004 |
| +0.003 |
chie | +0.003 |
ued | +0.003 |
top | +0.003 |
Neg logit contributions | |
iring | -0.004 |
ucks | -0.004 |
eddy | -0.004 |
imi | -0.003 |
mosquitoes | -0.003 |
Token | snow |
Token ID | 6729 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
iring | +0.026 |
ucks | +0.024 |
mosquitoes | +0.023 |
check | +0.023 |
asc | +0.021 |
Neg logit contributions | |
| -0.044 |
one | -0.044 |
top | -0.041 |
bar | -0.041 |
One | -0.041 |
Token | man |
Token ID | 805 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ucks | +0.116 |
iring | +0.113 |
imi | +0.104 |
mosquitoes | +0.101 |
cartoons | +0.098 |
Neg logit contributions | |
sel | -0.125 |
top | -0.110 |
| -0.107 |
chie | -0.107 |
pe | -0.106 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
eddy | +0.035 |
iring | +0.035 |
fort | +0.033 |
from | +0.032 |
mosquitoes | +0.032 |
Neg logit contributions | |
sel | -0.048 |
ued | -0.048 |
chie | -0.046 |
None | -0.045 |
| -0.045 |
Token | had |
Token ID | 550 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
iring | +0.036 |
eddy | +0.035 |
fort | +0.034 |
imi | +0.034 |
ucks | +0.033 |
Neg logit contributions | |
sel | -0.034 |
ued | -0.033 |
chie | -0.032 |
None | -0.031 |
| -0.030 |
Token | ever |
Token ID | 1683 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
sel | +0.030 |
ued | +0.029 |
chie | +0.029 |
None | +0.029 |
| +0.027 |
Neg logit contributions | |
iring | -0.019 |
eddy | -0.017 |
from | -0.017 |
check | -0.017 |
ucks | -0.016 |
Token | seen |
Token ID | 1775 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
ued | +0.003 |
sel | +0.003 |
chie | +0.003 |
None | +0.003 |
| +0.003 |
Neg logit contributions | |
iring | -0.002 |
accidents | -0.002 |
fort | -0.002 |
honey | -0.002 |
mosquitoes | -0.002 |
Token | man |
Token ID | 805 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
iring | +0.105 |
ucks | +0.098 |
mosquitoes | +0.096 |
accidents | +0.091 |
check | +0.091 |
Neg logit contributions | |
sel | -0.086 |
pe | -0.084 |
bar | -0.083 |
top | -0.077 |
| -0.075 |
Token | . |
Token ID | 13 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
sel | +0.005 |
| +0.005 |
chie | +0.005 |
ued | +0.005 |
top | +0.005 |
Neg logit contributions | |
iring | -0.004 |
ucks | -0.003 |
imi | -0.003 |
eddy | -0.003 |
mosquitoes | -0.003 |
Token | She |
Token ID | 1375 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
iring | +0.005 |
eddy | +0.005 |
ucks | +0.005 |
fort | +0.005 |
imi | +0.005 |
Neg logit contributions | |
sel | -0.003 |
| -0.003 |
ued | -0.003 |
chie | -0.003 |
None | -0.003 |
Token | rolled |
Token ID | 11686 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
iring | +0.011 |
ucks | +0.010 |
eddy | +0.010 |
fort | +0.010 |
imi | +0.010 |
Neg logit contributions | |
sel | -0.010 |
ued | -0.010 |
chie | -0.009 |
| -0.009 |
top | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
iring | +0.022 |
imi | +0.020 |
ucks | +0.020 |
arter | +0.020 |
eddy | +0.020 |
Neg logit contributions | |
| -0.017 |
sel | -0.017 |
ued | -0.015 |
chie | -0.015 |
top | -0.015 |
Token | snow |
Token ID | 6729 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
iring | +0.019 |
ucks | +0.017 |
check | +0.016 |
arter | +0.015 |
cartoons | +0.015 |
Neg logit contributions | |
sel | -0.039 |
| -0.038 |
bar | -0.036 |
ued | -0.036 |
chie | -0.036 |
Token | into |
Token ID | 656 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
iring | +0.113 |
ucks | +0.112 |
imi | +0.102 |
accidents | +0.101 |
mosquitoes | +0.100 |
Neg logit contributions | |
sel | -0.125 |
pe | -0.112 |
| -0.112 |
top | -0.112 |
bar | -0.108 |
Token | three |
Token ID | 1115 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
iring | +0.000 |
eddy | +0.000 |
ucks | +0.000 |
imi | +0.000 |
fort | +0.000 |
Neg logit contributions | |
sel | -0.000 |
| -0.000 |
chie | -0.000 |
ued | -0.000 |
None | -0.000 |
Token | big |
Token ID | 1263 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
sel | +0.027 |
ued | +0.026 |
chie | +0.025 |
| +0.025 |
top | +0.024 |
Neg logit contributions | |
iring | -0.019 |
eddy | -0.018 |
ucks | -0.018 |
imi | -0.017 |
fort | -0.016 |
Token | balls |
Token ID | 11333 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
iring | +0.011 |
eddy | +0.010 |
ucks | +0.010 |
fort | +0.010 |
imi | +0.010 |
Neg logit contributions | |
sel | -0.013 |
ued | -0.013 |
chie | -0.013 |
| -0.012 |
None | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
iring | +0.013 |
from | +0.013 |
fort | +0.012 |
eddy | +0.011 |
ucks | +0.010 |
Neg logit contributions | |
chie | -0.048 |
sel | -0.048 |
ued | -0.046 |
None | -0.045 |
| -0.044 |
Token | snow |
Token ID | 6729 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
iring | +0.004 |
ucks | +0.004 |
eddy | +0.003 |
check | +0.003 |
accidents | +0.003 |
Neg logit contributions | |
sel | -0.007 |
| -0.007 |
chie | -0.007 |
ued | -0.007 |
top | -0.006 |
Token | fort |
Token ID | 6285 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
iring | +0.088 |
ucks | +0.080 |
accidents | +0.079 |
mosquitoes | +0.078 |
check | +0.075 |
Neg logit contributions | |
sel | -0.104 |
| -0.097 |
top | -0.094 |
pe | -0.093 |
ued | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
iring | +0.036 |
eddy | +0.034 |
ucks | +0.034 |
fort | +0.033 |
imi | +0.033 |
Neg logit contributions | |
sel | -0.032 |
ued | -0.030 |
chie | -0.030 |
| -0.029 |
None | -0.028 |
Token | They |
Token ID | 1119 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ucks | +0.019 |
eddy | +0.019 |
iring | +0.018 |
cartoons | +0.018 |
fort | +0.018 |
Neg logit contributions | |
chie | -0.028 |
sel | -0.027 |
ued | -0.026 |
top | -0.023 |
pe | -0.023 |
Token | throw |
Token ID | 3714 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
iring | +0.018 |
eddy | +0.017 |
ucks | +0.017 |
fort | +0.017 |
imi | +0.017 |
Neg logit contributions | |
sel | -0.033 |
ued | -0.031 |
chie | -0.031 |
None | -0.030 |
| -0.030 |
Token | snow |
Token ID | 6729 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
iring | +0.009 |
eddy | +0.008 |
ucks | +0.008 |
imi | +0.008 |
fort | +0.008 |
Neg logit contributions | |
sel | -0.015 |
ued | -0.014 |
chie | -0.014 |
| -0.014 |
None | -0.014 |
Token | balls |
Token ID | 21591 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
iring | +0.122 |
ucks | +0.112 |
accidents | +0.110 |
imi | +0.110 |
check | +0.109 |
Neg logit contributions | |
sel | -0.114 |
pe | -0.099 |
| -0.099 |
top | -0.094 |
ued | -0.094 |
Token | at |
Token ID | 379 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
iring | +0.033 |
eddy | +0.030 |
ucks | +0.029 |
fort | +0.028 |
mosquitoes | +0.027 |
Neg logit contributions | |
sel | -0.106 |
chie | -0.104 |
ued | -0.101 |
None | -0.098 |
| -0.098 |
Token | each |
Token ID | 1123 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
iring | +0.020 |
eddy | +0.020 |
fort | +0.020 |
mosquitoes | +0.019 |
ucks | +0.019 |
Neg logit contributions | |
ued | -0.041 |
sel | -0.040 |
chie | -0.040 |
None | -0.037 |
ical | -0.037 |
Token | other |
Token ID | 584 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
sel | +0.022 |
| +0.020 |
ued | +0.020 |
chie | +0.020 |
top | +0.019 |
Neg logit contributions | |
iring | -0.027 |
eddy | -0.025 |
ucks | -0.025 |
imi | -0.024 |
accidents | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
sel | +0.031 |
chie | +0.030 |
ued | +0.030 |
None | +0.029 |
top | +0.027 |
Neg logit contributions | |
fort | -0.023 |
iring | -0.022 |
eddy | -0.022 |
from | -0.021 |
mosquitoes | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
iring | +0.013 |
eddy | +0.012 |
ucks | +0.012 |
imi | +0.011 |
fort | +0.011 |
Neg logit contributions | |
sel | -0.012 |
ued | -0.011 |
chie | -0.011 |
| -0.011 |
None | -0.010 |
Token | scarf |
Token ID | 36953 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
sel | +0.020 |
ued | +0.019 |
chie | +0.019 |
None | +0.018 |
top | +0.018 |
Neg logit contributions | |
iring | -0.008 |
fort | -0.008 |
eddy | -0.008 |
ucks | -0.007 |
imi | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
iring | +0.053 |
ucks | +0.050 |
imi | +0.049 |
eddy | +0.049 |
mosquitoes | +0.049 |
Neg logit contributions | |
sel | -0.042 |
| -0.037 |
ued | -0.037 |
top | -0.036 |
chie | -0.036 |
Token | They |
Token ID | 1119 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
iring | +0.025 |
eddy | +0.024 |
ucks | +0.024 |
fort | +0.023 |
imi | +0.022 |
Neg logit contributions | |
sel | -0.030 |
chie | -0.029 |
ued | -0.029 |
top | -0.026 |
None | -0.026 |
Token | threw |
Token ID | 9617 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
iring | +0.009 |
eddy | +0.008 |
ucks | +0.008 |
fort | +0.008 |
mosquitoes | +0.008 |
Neg logit contributions | |
chie | -0.011 |
ued | -0.011 |
sel | -0.011 |
None | -0.010 |
top | -0.010 |
Token | snow |
Token ID | 6729 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
iring | +0.009 |
eddy | +0.008 |
ucks | +0.008 |
fort | +0.008 |
mosquitoes | +0.008 |
Neg logit contributions | |
sel | -0.012 |
ued | -0.011 |
chie | -0.011 |
| -0.011 |
None | -0.011 |
Token | balls |
Token ID | 21591 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
iring | +0.117 |
imi | +0.110 |
check | +0.106 |
ucks | +0.106 |
mosquitoes | +0.106 |
Neg logit contributions | |
sel | -0.120 |
pe | -0.104 |
| -0.097 |
top | -0.096 |
ued | -0.094 |
Token | at |
Token ID | 379 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
iring | +0.039 |
eddy | +0.035 |
ucks | +0.035 |
fort | +0.033 |
mosquitoes | +0.032 |
Neg logit contributions | |
sel | -0.108 |
chie | -0.104 |
ued | -0.103 |
| -0.100 |
None | -0.100 |
Token | each |
Token ID | 1123 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
eddy | +0.018 |
mosquitoes | +0.018 |
iring | +0.017 |
fort | +0.017 |
snow | +0.017 |
Neg logit contributions | |
ued | -0.044 |
sel | -0.043 |
chie | -0.043 |
ical | -0.041 |
None | -0.040 |
Token | other |
Token ID | 584 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
sel | +0.024 |
ued | +0.023 |
chie | +0.023 |
None | +0.022 |
| +0.022 |
Neg logit contributions | |
iring | -0.024 |
eddy | -0.023 |
ucks | -0.023 |
fort | -0.022 |
imi | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
sel | +0.037 |
ued | +0.036 |
chie | +0.035 |
None | +0.034 |
| +0.033 |
Neg logit contributions | |
iring | -0.030 |
eddy | -0.029 |
fort | -0.029 |
ucks | -0.028 |
mosquitoes | -0.027 |
Token | he |
Token ID | 339 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
sel | +0.011 |
chie | +0.011 |
ued | +0.011 |
None | +0.010 |
| +0.010 |
Neg logit contributions | |
from | -0.005 |
iring | -0.005 |
eddy | -0.005 |
accidents | -0.004 |
fort | -0.004 |
Token | had |
Token ID | 550 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
sel | +0.037 |
ued | +0.037 |
None | +0.037 |
chie | +0.035 |
| +0.034 |
Neg logit contributions | |
iring | -0.032 |
check | -0.030 |
from | -0.030 |
eddy | -0.030 |
dust | -0.029 |
Token | seen |
Token ID | 1775 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
sel | +0.043 |
None | +0.042 |
ued | +0.042 |
chie | +0.042 |
| +0.040 |
Neg logit contributions | |
from | -0.024 |
check | -0.023 |
iring | -0.021 |
about | -0.020 |
friends | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
sel | +0.009 |
chie | +0.009 |
ued | +0.008 |
None | +0.008 |
| +0.008 |
Neg logit contributions | |
iring | -0.005 |
from | -0.005 |
eddy | -0.005 |
accidents | -0.004 |
mosquitoes | -0.004 |
Token | year |
Token ID | 614 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
sel | +0.014 |
ued | +0.013 |
chie | +0.013 |
None | +0.012 |
| +0.012 |
Neg logit contributions | |
fort | -0.006 |
iring | -0.006 |
cartoons | -0.006 |
eddy | -0.006 |
mosquitoes | -0.006 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
None | +0.130 |
sel | +0.124 |
chie | +0.123 |
ued | +0.123 |
none | +0.121 |
Neg logit contributions | |
from | -0.078 |
iring | -0.072 |
about | -0.060 |
eddy | -0.059 |
mess | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
chie | +0.199 |
ued | +0.194 |
sel | +0.193 |
None | +0.188 |
ience | +0.177 |
Neg logit contributions | |
from | -0.101 |
iring | -0.089 |
eddy | -0.086 |
ies | -0.084 |
fort | -0.083 |
Token | He |
Token ID | 679 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
sel | +0.020 |
chie | +0.019 |
ued | +0.018 |
top | +0.016 |
pe | +0.016 |
Neg logit contributions | |
Doctor | -0.012 |
iring | -0.012 |
eddy | -0.011 |
ucks | -0.011 |
Luna | -0.011 |
Token | went |
Token ID | 1816 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
sel | +0.026 |
chie | +0.025 |
ued | +0.024 |
None | +0.024 |
top | +0.023 |
Neg logit contributions | |
iring | -0.017 |
from | -0.016 |
dust | -0.016 |
doctors | -0.016 |
check | -0.016 |
Token | home |
Token ID | 1363 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
iring | +0.002 |
eddy | +0.002 |
ucks | +0.002 |
fort | +0.002 |
imi | +0.001 |
Neg logit contributions | |
sel | -0.003 |
ued | -0.003 |
chie | -0.003 |
| -0.003 |
None | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
iring | +0.013 |
from | +0.012 |
eddy | +0.011 |
fort | +0.010 |
ucks | +0.010 |
Neg logit contributions | |
sel | -0.042 |
ued | -0.040 |
chie | -0.040 |
None | -0.038 |
top | -0.038 |
Token | our |
Token ID | 674 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
mosquitoes | +0.020 |
wolves | +0.019 |
animals | +0.019 |
cartoons | +0.018 |
iring | +0.018 |
Neg logit contributions | |
sel | -0.047 |
ued | -0.044 |
ical | -0.042 |
None | -0.042 |
top | -0.041 |
Token | country |
Token ID | 1499 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
sel | +0.025 |
ued | +0.023 |
chie | +0.022 |
None | +0.022 |
| +0.022 |
Neg logit contributions | |
iring | -0.013 |
fort | -0.012 |
eddy | -0.011 |
ucks | -0.011 |
mosquitoes | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
sel | +0.085 |
chie | +0.080 |
ued | +0.078 |
None | +0.075 |
top | +0.070 |
Neg logit contributions | |
from | -0.041 |
fort | -0.038 |
iring | -0.037 |
about | -0.034 |
friends | -0.034 |
Token | long |
Token ID | 890 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
sel | +0.014 |
ued | +0.014 |
None | +0.013 |
chie | +0.013 |
top | +0.013 |
Neg logit contributions | |
fort | -0.006 |
friends | -0.005 |
mess | -0.005 |
dog | -0.005 |
wolves | -0.005 |
Token | time |
Token ID | 640 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
sel | +0.046 |
chie | +0.044 |
None | +0.043 |
ued | +0.042 |
top | +0.042 |
Neg logit contributions | |
fort | -0.024 |
wolves | -0.021 |
animals | -0.021 |
pets | -0.020 |
mosquitoes | -0.020 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.58e+00 |
Pos logit contributions | |
sel | +0.075 |
chie | +0.072 |
ued | +0.070 |
None | +0.068 |
| +0.062 |
Neg logit contributions | |
from | -0.041 |
iring | -0.038 |
about | -0.036 |
friends | -0.035 |
animals | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
chie | +0.199 |
sel | +0.196 |
ued | +0.189 |
None | +0.187 |
top | +0.172 |
Neg logit contributions | |
from | -0.099 |
iring | -0.087 |
fort | -0.084 |
ies | -0.080 |
friends | -0.080 |
Token | He |
Token ID | 679 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
sel | +0.023 |
chie | +0.022 |
ued | +0.021 |
ience | +0.018 |
top | +0.018 |
Neg logit contributions | |
Doctor | -0.013 |
Luna | -0.012 |
eddy | -0.012 |
ucks | -0.012 |
cartoons | -0.012 |
Token | helped |
Token ID | 4193 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
sel | +0.029 |
chie | +0.028 |
ued | +0.026 |
None | +0.026 |
top | +0.025 |
Neg logit contributions | |
from | -0.015 |
iring | -0.013 |
animals | -0.013 |
pets | -0.013 |
doctors | -0.013 |
Token | many |
Token ID | 867 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
sel | +0.014 |
ued | +0.013 |
chie | +0.013 |
None | +0.013 |
| +0.013 |
Neg logit contributions | |
iring | -0.008 |
eddy | -0.007 |
ucks | -0.007 |
mosquitoes | -0.007 |
fort | -0.007 |
Token | people |
Token ID | 661 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
sel | +0.009 |
chie | +0.008 |
ued | +0.008 |
None | +0.008 |
top | +0.008 |
Neg logit contributions | |
iring | -0.003 |
wolves | -0.003 |
mosquitoes | -0.003 |
animals | -0.003 |
cartoons | -0.002 |
Token | filled |
Token ID | 5901 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
sel | +0.034 |
chie | +0.033 |
ued | +0.032 |
| +0.031 |
None | +0.031 |
Neg logit contributions | |
iring | -0.016 |
eddy | -0.014 |
fort | -0.014 |
ucks | -0.014 |
accidents | -0.013 |
Token | with |
Token ID | 351 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
sel | +0.033 |
| +0.031 |
ued | +0.031 |
top | +0.031 |
chie | +0.030 |
Neg logit contributions | |
iring | -0.017 |
imi | -0.016 |
ucks | -0.016 |
eddy | -0.015 |
fort | -0.015 |
Token | treasures |
Token ID | 29561 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
sel | +0.022 |
ued | +0.021 |
chie | +0.020 |
| +0.020 |
None | +0.020 |
Neg logit contributions | |
iring | -0.015 |
eddy | -0.014 |
ucks | -0.014 |
fort | -0.014 |
mosquitoes | -0.014 |
Token | from |
Token ID | 422 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
iring | +0.007 |
fort | +0.007 |
eddy | +0.006 |
from | +0.006 |
accidents | +0.006 |
Neg logit contributions | |
sel | -0.012 |
chie | -0.012 |
ued | -0.012 |
None | -0.012 |
| -0.012 |
Token | long |
Token ID | 890 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
iring | +0.010 |
fort | +0.009 |
from | +0.009 |
mosquitoes | +0.009 |
eddy | +0.009 |
Neg logit contributions | |
sel | -0.019 |
chie | -0.018 |
ued | -0.017 |
None | -0.017 |
| -0.016 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.49e+00 |
Pos logit contributions | |
sel | +0.046 |
chie | +0.046 |
ued | +0.044 |
None | +0.042 |
top | +0.042 |
Neg logit contributions | |
fort | -0.037 |
iring | -0.037 |
eddy | -0.035 |
mosquitoes | -0.035 |
dust | -0.034 |
Token | ! |
Token ID | 0 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
chie | +0.186 |
ued | +0.181 |
sel | +0.178 |
None | +0.172 |
top | +0.160 |
Neg logit contributions | |
from | -0.104 |
iring | -0.102 |
fort | -0.100 |
eddy | -0.091 |
ies | -0.090 |
Token |
|
Token ID | 198 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
sel | +0.032 |
chie | +0.031 |
ued | +0.028 |
pe | +0.026 |
top | +0.026 |
Neg logit contributions | |
iring | -0.020 |
ucks | -0.020 |
fort | -0.019 |
eddy | -0.019 |
Luna | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
sel | +0.016 |
chie | +0.015 |
ued | +0.015 |
none | +0.014 |
top | +0.014 |
Neg logit contributions | |
iring | -0.014 |
eddy | -0.013 |
ucks | -0.013 |
imi | -0.012 |
fort | -0.012 |
Token | The |
Token ID | 464 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
sel | +0.035 |
chie | +0.032 |
ued | +0.032 |
None | +0.031 |
| +0.030 |
Neg logit contributions | |
iring | -0.029 |
eddy | -0.027 |
ucks | -0.027 |
fort | -0.026 |
mosquitoes | -0.026 |
Token | adventurers |
Token ID | 36843 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
sel | +0.028 |
ued | +0.027 |
chie | +0.026 |
| +0.026 |
None | +0.025 |
Neg logit contributions | |
iring | -0.023 |
eddy | -0.023 |
ucks | -0.022 |
imi | -0.021 |
check | -0.020 |
Token | big |
Token ID | 1263 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
sel | +0.017 |
ued | +0.016 |
chie | +0.016 |
None | +0.015 |
top | +0.015 |
Neg logit contributions | |
fort | -0.010 |
iring | -0.009 |
eddy | -0.009 |
mosquitoes | -0.009 |
accidents | -0.009 |
Token | farm |
Token ID | 5318 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
fort | +0.024 |
iring | +0.021 |
eddy | +0.021 |
mosquitoes | +0.021 |
accidents | +0.020 |
Neg logit contributions | |
sel | -0.043 |
ued | -0.042 |
chie | -0.041 |
None | -0.039 |
| -0.039 |
Token | a |
Token ID | 257 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
sel | +0.048 |
chie | +0.047 |
ued | +0.047 |
None | +0.045 |
| +0.043 |
Neg logit contributions | |
fort | -0.021 |
iring | -0.021 |
from | -0.020 |
eddy | -0.020 |
doctors | -0.018 |
Token | long |
Token ID | 890 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
sel | +0.024 |
ued | +0.022 |
chie | +0.022 |
None | +0.021 |
top | +0.021 |
Neg logit contributions | |
fort | -0.013 |
iring | -0.013 |
eddy | -0.012 |
mosquitoes | -0.012 |
honey | -0.012 |
Token | time |
Token ID | 640 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
sel | +0.052 |
chie | +0.051 |
ued | +0.048 |
None | +0.047 |
top | +0.045 |
Neg logit contributions | |
fort | -0.029 |
mosquitoes | -0.024 |
snow | -0.024 |
wolves | -0.024 |
cartoons | -0.024 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.32e+00 |
Pos logit contributions | |
sel | +0.076 |
ued | +0.074 |
chie | +0.073 |
None | +0.068 |
Fer | +0.063 |
Neg logit contributions | |
from | -0.061 |
iring | -0.059 |
fort | -0.056 |
about | -0.055 |
pets | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
chie | +0.185 |
sel | +0.182 |
ued | +0.181 |
None | +0.174 |
top | +0.162 |
Neg logit contributions | |
from | -0.097 |
fort | -0.089 |
iring | -0.087 |
eddy | -0.085 |
ies | -0.083 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
sel | +0.007 |
chie | +0.007 |
ued | +0.007 |
top | +0.006 |
pe | +0.006 |
Neg logit contributions | |
eddy | -0.002 |
iring | -0.002 |
ucks | -0.002 |
fort | -0.002 |
cartoons | -0.002 |
Token | listened |
Token ID | 16399 |
Feature activation | +6.63e-03 |
Pos logit contributions | |
iring | +0.026 |
eddy | +0.024 |
ucks | +0.024 |
fort | +0.024 |
imi | +0.023 |
Neg logit contributions | |
sel | -0.029 |
chie | -0.027 |
ued | -0.027 |
None | -0.026 |
| -0.026 |
Token | as |
Token ID | 355 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
from | +0.000 |
about | +0.000 |
iring | +0.000 |
and | +0.000 |
up | +0.000 |
Neg logit contributions | |
chie | -0.000 |
sel | -0.000 |
Fer | -0.000 |
ignition | -0.000 |
ued | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
iring | +0.069 |
ucks | +0.066 |
eddy | +0.065 |
fort | +0.062 |
imi | +0.062 |
Neg logit contributions | |
sel | -0.071 |
ued | -0.065 |
| -0.064 |
chie | -0.064 |
None | -0.063 |
Token | a |
Token ID | 257 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
iring | +0.003 |
eddy | +0.003 |
doctors | +0.003 |
mosquitoes | +0.003 |
cartoons | +0.003 |
Neg logit contributions | |
chie | -0.005 |
ued | -0.005 |
sel | -0.005 |
ical | -0.004 |
None | -0.004 |
Token | new |
Token ID | 649 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
iring | +0.005 |
ucks | +0.005 |
eddy | +0.004 |
imi | +0.004 |
check | +0.004 |
Neg logit contributions | |
sel | -0.006 |
chie | -0.006 |
| -0.006 |
ued | -0.006 |
None | -0.005 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
sel | +0.005 |
chie | +0.005 |
| +0.005 |
ued | +0.005 |
None | +0.005 |
Neg logit contributions | |
iring | -0.003 |
ucks | -0.003 |
eddy | -0.003 |
imi | -0.003 |
accidents | -0.003 |
Token | in |
Token ID | 287 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
sel | +0.041 |
ued | +0.039 |
| +0.039 |
chie | +0.038 |
top | +0.038 |
Neg logit contributions | |
iring | -0.028 |
ucks | -0.026 |
eddy | -0.026 |
imi | -0.025 |
fort | -0.025 |
Token | his |
Token ID | 465 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
sel | +0.055 |
ued | +0.052 |
chie | +0.052 |
| +0.052 |
None | +0.050 |
Neg logit contributions | |
iring | -0.037 |
ucks | -0.034 |
eddy | -0.034 |
fort | -0.033 |
imi | -0.032 |
Token | class |
Token ID | 1398 |
Feature activation | -6.31e+00 |
Pos logit contributions | |
| +0.060 |
sel | +0.060 |
chie | +0.057 |
ued | +0.057 |
None | +0.057 |
Neg logit contributions | |
iring | -0.033 |
ucks | -0.030 |
eddy | -0.029 |
mosquitoes | -0.028 |
accidents | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
sel | +0.200 |
chie | +0.195 |
ued | +0.181 |
None | +0.168 |
ical | +0.162 |
Neg logit contributions | |
room | -0.094 |
fort | -0.089 |
from | -0.089 |
friends | -0.086 |
house | -0.085 |
Token | Her |
Token ID | 2332 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
sel | +0.012 |
chie | +0.011 |
ued | +0.011 |
none | +0.010 |
top | +0.010 |
Neg logit contributions | |
eddy | -0.005 |
iring | -0.005 |
ucks | -0.005 |
cartoons | -0.005 |
from | -0.005 |
Token | name |
Token ID | 1438 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
iring | +0.013 |
ucks | +0.012 |
eddy | +0.012 |
rim | +0.012 |
accidents | +0.011 |
Neg logit contributions | |
sel | -0.018 |
| -0.018 |
None | -0.017 |
none | -0.016 |
second | -0.016 |
Token | is |
Token ID | 318 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
iring | +0.008 |
ucks | +0.008 |
eddy | +0.007 |
fort | +0.007 |
imi | +0.007 |
Neg logit contributions | |
sel | -0.010 |
| -0.010 |
ued | -0.010 |
None | -0.009 |
top | -0.009 |
Token | Lisa |
Token ID | 15378 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
sel | +0.081 |
ued | +0.079 |
chie | +0.078 |
top | +0.073 |
None | +0.072 |
Neg logit contributions | |
iring | -0.026 |
imi | -0.025 |
eddy | -0.025 |
cartoons | -0.023 |
mosquitoes | -0.023 |
Token | is |
Token ID | 318 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
sel | +0.055 |
ued | +0.052 |
None | +0.051 |
| +0.051 |
chie | +0.051 |
Neg logit contributions | |
iring | -0.022 |
fort | -0.020 |
accidents | -0.020 |
mosquitoes | -0.019 |
eddy | -0.019 |
Token | from |
Token ID | 422 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
sel | +0.063 |
ued | +0.059 |
chie | +0.058 |
None | +0.058 |
top | +0.056 |
Neg logit contributions | |
iring | -0.036 |
accidents | -0.034 |
from | -0.034 |
fort | -0.033 |
mosquitoes | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
iring | +0.001 |
accidents | +0.001 |
from | +0.001 |
mosquitoes | +0.001 |
eddy | +0.001 |
Neg logit contributions | |
sel | -0.001 |
ued | -0.001 |
None | -0.001 |
chie | -0.001 |
| -0.001 |
Token | long |
Token ID | 890 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
sel | +0.042 |
ued | +0.039 |
None | +0.037 |
chie | +0.036 |
top | +0.036 |
Neg logit contributions | |
fort | -0.023 |
mess | -0.021 |
snow | -0.020 |
eddy | -0.020 |
mosquitoes | -0.020 |
Token | time |
Token ID | 640 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
sel | +0.061 |
ued | +0.057 |
chie | +0.057 |
None | +0.056 |
top | +0.055 |
Neg logit contributions | |
fort | -0.028 |
mess | -0.027 |
snow | -0.025 |
dust | -0.024 |
dog | -0.023 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.30e+00 |
Pos logit contributions | |
sel | +0.076 |
ued | +0.071 |
chie | +0.070 |
None | +0.069 |
| +0.066 |
Neg logit contributions | |
from | -0.048 |
iring | -0.047 |
fort | -0.045 |
here | -0.044 |
about | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
sel | +0.177 |
chie | +0.172 |
ued | +0.171 |
None | +0.167 |
top | +0.156 |
Neg logit contributions | |
from | -0.101 |
fort | -0.098 |
iring | -0.097 |
eddy | -0.093 |
mosquitoes | -0.088 |
Token | from |
Token ID | 422 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
sel | +0.026 |
ued | +0.025 |
chie | +0.025 |
| +0.024 |
None | +0.024 |
Neg logit contributions | |
iring | -0.017 |
eddy | -0.016 |
ucks | -0.016 |
fort | -0.015 |
imi | -0.015 |
Token | when |
Token ID | 618 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
iring | +0.009 |
eddy | +0.008 |
mosquitoes | +0.008 |
ucks | +0.008 |
fort | +0.008 |
Neg logit contributions | |
sel | -0.017 |
ued | -0.016 |
chie | -0.016 |
None | -0.015 |
| -0.015 |
Token | dinosaurs |
Token ID | 27199 |
Feature activation | +6.31e-02 |
Pos logit contributions | |
iring | +0.021 |
accidents | +0.020 |
fort | +0.019 |
mosquitoes | +0.019 |
honey | +0.019 |
Neg logit contributions | |
sel | -0.042 |
chie | -0.039 |
ued | -0.039 |
None | -0.037 |
top | -0.037 |
Token | lived |
Token ID | 5615 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
iring | +0.001 |
fort | +0.001 |
from | +0.001 |
mosquitoes | +0.001 |
check | +0.001 |
Neg logit contributions | |
sel | -0.002 |
chie | -0.002 |
None | -0.002 |
ued | -0.002 |
top | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -9.78e-01 |
Pos logit contributions | |
sel | +0.025 |
ued | +0.023 |
chie | +0.023 |
| +0.022 |
None | +0.022 |
Neg logit contributions | |
iring | -0.025 |
eddy | -0.024 |
ucks | -0.023 |
fort | -0.023 |
mosquitoes | -0.023 |
Token | ship |
Token ID | 4074 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
ued | +0.029 |
sel | +0.028 |
chie | +0.027 |
None | +0.027 |
top | +0.026 |
Neg logit contributions | |
fort | -0.015 |
mess | -0.014 |
dust | -0.014 |
snow | -0.013 |
eddy | -0.013 |
Token | had |
Token ID | 550 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
sel | +0.028 |
chie | +0.027 |
ued | +0.026 |
None | +0.026 |
| +0.026 |
Neg logit contributions | |
iring | -0.016 |
from | -0.016 |
fort | -0.016 |
accidents | -0.015 |
eddy | -0.015 |
Token | wrecked |
Token ID | 44770 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
ued | +0.043 |
sel | +0.042 |
| +0.041 |
chie | +0.041 |
None | +0.041 |
Neg logit contributions | |
from | -0.029 |
dust | -0.029 |
iring | -0.028 |
doctors | -0.027 |
animals | -0.026 |
Token | long |
Token ID | 890 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
ued | +0.022 |
sel | +0.021 |
None | +0.021 |
chie | +0.021 |
| +0.020 |
Neg logit contributions | |
iring | -0.011 |
eddy | -0.011 |
fort | -0.011 |
accidents | -0.010 |
from | -0.010 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.28e+00 |
Pos logit contributions | |
chie | +0.023 |
ued | +0.022 |
sel | +0.022 |
None | +0.021 |
| +0.021 |
Neg logit contributions | |
fort | -0.019 |
dust | -0.018 |
mess | -0.018 |
snow | -0.017 |
from | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
chie | +0.194 |
ued | +0.189 |
sel | +0.188 |
None | +0.182 |
ience | +0.169 |
Neg logit contributions | |
from | -0.093 |
iring | -0.079 |
fort | -0.079 |
eddy | -0.075 |
about | -0.074 |
Token | and |
Token ID | 290 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
sel | +0.021 |
ued | +0.020 |
chie | +0.019 |
| +0.019 |
None | +0.019 |
Neg logit contributions | |
iring | -0.013 |
eddy | -0.012 |
ucks | -0.012 |
fort | -0.012 |
accidents | -0.012 |
Token | now |
Token ID | 783 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
sel | +0.040 |
chie | +0.037 |
ued | +0.037 |
None | +0.035 |
top | +0.035 |
Neg logit contributions | |
iring | -0.034 |
accidents | -0.031 |
eddy | -0.031 |
fort | -0.031 |
mosquitoes | -0.031 |
Token | it |
Token ID | 340 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
iring | +0.006 |
accidents | +0.006 |
fort | +0.006 |
eddy | +0.006 |
mosquitoes | +0.006 |
Neg logit contributions | |
sel | -0.007 |
chie | -0.007 |
ued | -0.007 |
top | -0.006 |
None | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
sel | +0.006 |
chie | +0.006 |
ued | +0.006 |
None | +0.006 |
| +0.006 |
Neg logit contributions | |
iring | -0.005 |
fort | -0.005 |
eddy | -0.005 |
accidents | -0.005 |
from | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
iring | +0.002 |
accidents | +0.002 |
honey | +0.002 |
eddy | +0.002 |
fort | +0.002 |
Neg logit contributions | |
ued | -0.004 |
sel | -0.004 |
chie | -0.004 |
None | -0.004 |
ical | -0.004 |
Token | scale |
Token ID | 5046 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
iring | +0.006 |
fort | +0.006 |
mosquitoes | +0.005 |
eddy | +0.005 |
honey | +0.005 |
Neg logit contributions | |
sel | -0.008 |
chie | -0.007 |
ued | -0.007 |
None | -0.007 |
| -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
chie | +0.037 |
ued | +0.037 |
sel | +0.037 |
None | +0.036 |
| +0.035 |
Neg logit contributions | |
from | -0.021 |
fort | -0.019 |
iring | -0.019 |
eddy | -0.018 |
accidents | -0.016 |
Token | long |
Token ID | 890 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
sel | +0.022 |
ued | +0.021 |
chie | +0.020 |
None | +0.019 |
top | +0.019 |
Neg logit contributions | |
fort | -0.013 |
eddy | -0.012 |
iring | -0.012 |
honey | -0.012 |
accidents | -0.011 |
Token | time |
Token ID | 640 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
sel | +0.062 |
chie | +0.061 |
ued | +0.058 |
None | +0.056 |
top | +0.055 |
Neg logit contributions | |
fort | -0.030 |
mess | -0.026 |
dust | -0.026 |
snow | -0.025 |
itch | -0.025 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.28e+00 |
Pos logit contributions | |
chie | +0.072 |
ued | +0.071 |
sel | +0.071 |
None | +0.066 |
| +0.062 |
Neg logit contributions | |
from | -0.048 |
iring | -0.046 |
fort | -0.046 |
about | -0.044 |
eddy | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
chie | +0.179 |
sel | +0.175 |
ued | +0.174 |
None | +0.165 |
top | +0.153 |
Neg logit contributions | |
from | -0.102 |
fort | -0.097 |
iring | -0.095 |
eddy | -0.094 |
ies | -0.086 |
Token |
|
Token ID | 198 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
iring | +0.004 |
eddy | +0.004 |
ucks | +0.004 |
imi | +0.004 |
fort | +0.004 |
Neg logit contributions | |
sel | -0.006 |
chie | -0.005 |
ued | -0.005 |
top | -0.005 |
ical | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
iring | +0.009 |
eddy | +0.009 |
ucks | +0.009 |
imi | +0.008 |
fort | +0.008 |
Neg logit contributions | |
sel | -0.010 |
chie | -0.010 |
ued | -0.009 |
None | -0.009 |
top | -0.009 |
Token | As |
Token ID | 1722 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
sel | +0.014 |
ued | +0.013 |
chie | +0.013 |
| +0.013 |
None | +0.013 |
Neg logit contributions | |
iring | -0.013 |
ucks | -0.013 |
eddy | -0.012 |
fort | -0.012 |
imi | -0.012 |
Token | he |
Token ID | 339 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
iring | +0.043 |
eddy | +0.040 |
accidents | +0.040 |
fort | +0.039 |
mosquitoes | +0.039 |
Neg logit contributions | |
sel | -0.067 |
chie | -0.063 |
ued | -0.063 |
None | -0.059 |
top | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
iring | +0.009 |
eddy | +0.009 |
ucks | +0.009 |
imi | +0.009 |
mosquitoes | +0.009 |
Neg logit contributions | |
sel | -0.010 |
chie | -0.009 |
ued | -0.009 |
| -0.009 |
None | -0.009 |
Token | new |
Token ID | 649 |
Feature activation | -9.89e-02 |
Pos logit contributions | |
iring | +0.009 |
ucks | +0.009 |
eddy | +0.008 |
check | +0.008 |
imi | +0.008 |
Neg logit contributions | |
sel | -0.010 |
| -0.010 |
chie | -0.010 |
None | -0.009 |
ued | -0.009 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
sel | +0.003 |
ued | +0.003 |
chie | +0.003 |
| +0.003 |
None | +0.003 |
Neg logit contributions | |
iring | -0.002 |
eddy | -0.002 |
ucks | -0.002 |
fort | -0.001 |
imi | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
sel | +0.035 |
| +0.033 |
ued | +0.033 |
chie | +0.032 |
top | +0.032 |
Neg logit contributions | |
iring | -0.025 |
ucks | -0.023 |
eddy | -0.023 |
imi | -0.022 |
fort | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
sel | +0.043 |
| +0.041 |
ued | +0.040 |
chie | +0.040 |
None | +0.040 |
Neg logit contributions | |
iring | -0.031 |
ucks | -0.029 |
eddy | -0.029 |
fort | -0.027 |
imi | -0.027 |
Token | class |
Token ID | 1398 |
Feature activation | -6.23e+00 |
Pos logit contributions | |
sel | +0.041 |
ued | +0.039 |
chie | +0.038 |
| +0.038 |
None | +0.037 |
Neg logit contributions | |
iring | -0.015 |
eddy | -0.014 |
ucks | -0.014 |
fort | -0.013 |
imi | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
sel | +0.199 |
chie | +0.195 |
ued | +0.181 |
None | +0.167 |
ical | +0.162 |
Neg logit contributions | |
room | -0.092 |
from | -0.090 |
iring | -0.087 |
fort | -0.086 |
friends | -0.086 |
Token | Her |
Token ID | 2332 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
iring | +0.016 |
ucks | +0.015 |
eddy | +0.015 |
imi | +0.014 |
fort | +0.014 |
Neg logit contributions | |
sel | -0.027 |
ued | -0.025 |
chie | -0.025 |
top | -0.023 |
None | -0.023 |
Token | name |
Token ID | 1438 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
iring | +0.017 |
ucks | +0.016 |
eddy | +0.016 |
check | +0.015 |
mosquitoes | +0.014 |
Neg logit contributions | |
sel | -0.030 |
| -0.029 |
None | -0.028 |
ued | -0.028 |
chie | -0.028 |
Token | is |
Token ID | 318 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
iring | +0.013 |
ucks | +0.012 |
eddy | +0.011 |
fort | +0.011 |
check | +0.011 |
Neg logit contributions | |
sel | -0.013 |
| -0.012 |
ued | -0.012 |
None | -0.011 |
top | -0.011 |
Token | Mia |
Token ID | 32189 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
sel | +0.067 |
ued | +0.065 |
chie | +0.064 |
top | +0.061 |
None | +0.060 |
Neg logit contributions | |
iring | -0.027 |
eddy | -0.025 |
imi | -0.025 |
mosquitoes | -0.023 |
ucks | -0.023 |
Token | found |
Token ID | 1043 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
sel | +0.022 |
ued | +0.022 |
chie | +0.021 |
None | +0.020 |
top | +0.020 |
Neg logit contributions | |
iring | -0.014 |
pets | -0.014 |
accidents | -0.014 |
doctors | -0.014 |
from | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
sel | +0.007 |
chie | +0.007 |
ued | +0.007 |
None | +0.006 |
top | +0.006 |
Neg logit contributions | |
iring | -0.005 |
honey | -0.004 |
from | -0.004 |
eddy | -0.004 |
mosquitoes | -0.004 |
Token | truck |
Token ID | 7779 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
sel | +0.001 |
ued | +0.001 |
chie | +0.001 |
None | +0.001 |
| +0.001 |
Neg logit contributions | |
iring | -0.001 |
fort | -0.001 |
eddy | -0.001 |
mosquitoes | -0.001 |
honey | -0.001 |
Token | many |
Token ID | 867 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
sel | +0.009 |
chie | +0.009 |
ued | +0.009 |
None | +0.009 |
| +0.008 |
Neg logit contributions | |
from | -0.004 |
iring | -0.004 |
eddy | -0.003 |
fort | -0.003 |
accidents | -0.003 |
Token | years |
Token ID | 812 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
sel | +0.027 |
chie | +0.026 |
None | +0.025 |
ued | +0.025 |
| +0.025 |
Neg logit contributions | |
iring | -0.013 |
mosquitoes | -0.012 |
fort | -0.012 |
accidents | -0.012 |
honey | -0.012 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.21e+00 |
Pos logit contributions | |
chie | +0.020 |
None | +0.020 |
sel | +0.020 |
| +0.019 |
ued | +0.019 |
Neg logit contributions | |
iring | -0.009 |
eddy | -0.009 |
from | -0.008 |
fort | -0.007 |
doctors | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
chie | +0.189 |
ued | +0.182 |
sel | +0.182 |
None | +0.177 |
ounded | +0.163 |
Neg logit contributions | |
from | -0.092 |
iring | -0.082 |
ies | -0.078 |
fort | -0.078 |
eddy | -0.077 |
Token | worked |
Token ID | 3111 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
sel | +0.045 |
chie | +0.044 |
ued | +0.042 |
None | +0.040 |
top | +0.039 |
Neg logit contributions | |
iring | -0.038 |
accidents | -0.034 |
honey | -0.034 |
fort | -0.034 |
from | -0.033 |
Token | hard |
Token ID | 1327 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
None | +0.068 |
sel | +0.068 |
chie | +0.068 |
ued | +0.065 |
These | +0.064 |
Neg logit contributions | |
from | -0.034 |
iring | -0.028 |
about | -0.027 |
accidents | -0.027 |
by | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
sel | +0.014 |
chie | +0.014 |
None | +0.013 |
ued | +0.013 |
| +0.013 |
Neg logit contributions | |
iring | -0.005 |
from | -0.005 |
accidents | -0.005 |
fort | -0.004 |
about | -0.004 |
Token | fix |
Token ID | 4259 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
iring | +0.002 |
from | +0.002 |
dust | +0.002 |
check | +0.002 |
fort | +0.002 |
Neg logit contributions | |
sel | -0.007 |
ued | -0.007 |
chie | -0.007 |
None | -0.007 |
ical | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
iring | +0.026 |
mosquitoes | +0.024 |
eddy | +0.024 |
imi | +0.024 |
ucks | +0.024 |
Neg logit contributions | |
sel | -0.034 |
chie | -0.034 |
ued | -0.033 |
None | -0.030 |
| -0.030 |
Token | new |
Token ID | 649 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
iring | +0.012 |
ucks | +0.011 |
eddy | +0.011 |
imi | +0.010 |
check | +0.010 |
Neg logit contributions | |
sel | -0.015 |
chie | -0.014 |
| -0.014 |
ued | -0.014 |
None | -0.014 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
sel | +0.003 |
ued | +0.003 |
chie | +0.003 |
| +0.003 |
None | +0.003 |
Neg logit contributions | |
iring | -0.002 |
ucks | -0.002 |
eddy | -0.002 |
imi | -0.002 |
fort | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
sel | +0.041 |
| +0.038 |
ued | +0.038 |
chie | +0.037 |
top | +0.037 |
Neg logit contributions | |
iring | -0.026 |
ucks | -0.025 |
eddy | -0.024 |
imi | -0.023 |
fort | -0.023 |
Token | her |
Token ID | 607 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
sel | +0.042 |
ued | +0.039 |
| +0.039 |
chie | +0.039 |
None | +0.038 |
Neg logit contributions | |
iring | -0.032 |
ucks | -0.030 |
eddy | -0.030 |
fort | -0.029 |
imi | -0.028 |
Token | class |
Token ID | 1398 |
Feature activation | -6.16e+00 |
Pos logit contributions | |
sel | +0.037 |
ued | +0.035 |
chie | +0.035 |
| +0.035 |
None | +0.034 |
Neg logit contributions | |
iring | -0.014 |
ucks | -0.012 |
eddy | -0.012 |
mosquitoes | -0.011 |
imi | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
chie | +0.192 |
sel | +0.190 |
ued | +0.175 |
None | +0.165 |
ical | +0.156 |
Neg logit contributions | |
from | -0.093 |
iring | -0.090 |
room | -0.088 |
about | -0.086 |
fort | -0.085 |
Token | Her |
Token ID | 2332 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
sel | +0.004 |
ued | +0.004 |
chie | +0.004 |
top | +0.004 |
none | +0.004 |
Neg logit contributions | |
eddy | -0.002 |
ucks | -0.002 |
iring | -0.002 |
cartoons | -0.002 |
from | -0.002 |
Token | name |
Token ID | 1438 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
iring | +0.014 |
ucks | +0.013 |
eddy | +0.013 |
mosquitoes | +0.012 |
accidents | +0.012 |
Neg logit contributions | |
sel | -0.029 |
| -0.028 |
ued | -0.027 |
None | -0.027 |
chie | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
iring | +0.006 |
eddy | +0.006 |
ucks | +0.006 |
fort | +0.006 |
imi | +0.006 |
Neg logit contributions | |
sel | -0.008 |
chie | -0.008 |
ued | -0.008 |
None | -0.007 |
top | -0.007 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
sel | +0.074 |
ued | +0.073 |
chie | +0.072 |
top | +0.067 |
None | +0.067 |
Neg logit contributions | |
iring | -0.028 |
imi | -0.027 |
eddy | -0.026 |
mosquitoes | -0.025 |
cartoons | -0.024 |
Token | my |
Token ID | 1820 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
sel | +0.006 |
chie | +0.006 |
ued | +0.006 |
None | +0.006 |
top | +0.005 |
Neg logit contributions | |
iring | -0.006 |
eddy | -0.006 |
from | -0.006 |
accidents | -0.006 |
imi | -0.006 |
Token | had |
Token ID | 550 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
chie | +0.021 |
sel | +0.021 |
ued | +0.020 |
None | +0.020 |
top | +0.018 |
Neg logit contributions | |
iring | -0.017 |
from | -0.016 |
eddy | -0.016 |
accidents | -0.016 |
dust | -0.016 |
Token | told |
Token ID | 1297 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
None | +0.039 |
ued | +0.039 |
sel | +0.039 |
chie | +0.038 |
pool | +0.036 |
Neg logit contributions | |
from | -0.022 |
dust | -0.022 |
check | -0.020 |
mess | -0.020 |
accidents | -0.020 |
Token | him |
Token ID | 683 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
sel | +0.045 |
ued | +0.043 |
chie | +0.042 |
None | +0.041 |
| +0.041 |
Neg logit contributions | |
iring | -0.019 |
eddy | -0.017 |
ucks | -0.016 |
fort | -0.016 |
imi | -0.016 |
Token | long |
Token ID | 890 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
sel | +0.048 |
chie | +0.046 |
ued | +0.045 |
None | +0.042 |
top | +0.042 |
Neg logit contributions | |
from | -0.019 |
iring | -0.018 |
about | -0.018 |
accidents | -0.018 |
doctors | -0.017 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.13e+00 |
Pos logit contributions | |
sel | +0.045 |
chie | +0.042 |
ued | +0.041 |
None | +0.040 |
top | +0.039 |
Neg logit contributions | |
fort | -0.023 |
dust | -0.023 |
honey | -0.022 |
itch | -0.022 |
mosquitoes | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
chie | +0.187 |
sel | +0.186 |
ued | +0.180 |
None | +0.173 |
ience | +0.161 |
Neg logit contributions | |
from | -0.091 |
about | -0.078 |
fort | -0.077 |
iring | -0.075 |
friends | -0.073 |
Token | The |
Token ID | 383 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
sel | +0.026 |
chie | +0.025 |
ued | +0.024 |
top | +0.021 |
arest | +0.021 |
Neg logit contributions | |
Doctor | -0.014 |
Luna | -0.013 |
iring | -0.013 |
imi | -0.013 |
eddy | -0.013 |
Token | bird |
Token ID | 6512 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
sel | +0.021 |
ued | +0.020 |
chie | +0.020 |
None | +0.020 |
| +0.019 |
Neg logit contributions | |
fort | -0.010 |
iring | -0.010 |
mosquitoes | -0.009 |
doctors | -0.009 |
cartoons | -0.009 |
Token | spread |
Token ID | 4104 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
iring | +0.024 |
fort | +0.023 |
eddy | +0.022 |
imi | +0.022 |
accidents | +0.022 |
Neg logit contributions | |
sel | -0.030 |
chie | -0.028 |
ued | -0.027 |
None | -0.027 |
top | -0.026 |
Token | out |
Token ID | 503 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
sel | +0.012 |
ued | +0.011 |
chie | +0.011 |
None | +0.011 |
| +0.011 |
Neg logit contributions | |
iring | -0.007 |
eddy | -0.007 |
ucks | -0.007 |
fort | -0.007 |
mosquitoes | -0.007 |
Token | grandma |
Token ID | 49890 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
sel | +0.061 |
ued | +0.058 |
chie | +0.057 |
None | +0.056 |
| +0.055 |
Neg logit contributions | |
iring | -0.017 |
fort | -0.016 |
eddy | -0.016 |
imi | -0.014 |
ucks | -0.014 |
Token | 's |
Token ID | 338 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
sel | +0.036 |
chie | +0.035 |
ued | +0.035 |
None | +0.033 |
top | +0.031 |
Neg logit contributions | |
eddy | -0.024 |
fort | -0.024 |
iring | -0.024 |
cartoons | -0.023 |
from | -0.023 |
Token | house |
Token ID | 2156 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
sel | +0.050 |
ued | +0.047 |
chie | +0.046 |
None | +0.045 |
top | +0.045 |
Neg logit contributions | |
fort | -0.013 |
eddy | -0.012 |
iring | -0.012 |
ucks | -0.010 |
doctors | -0.010 |
Token | for |
Token ID | 329 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
sel | +0.047 |
chie | +0.047 |
ued | +0.046 |
None | +0.043 |
| +0.041 |
Neg logit contributions | |
from | -0.017 |
fort | -0.015 |
iring | -0.014 |
about | -0.013 |
eddy | -0.013 |
Token | safe |
Token ID | 3338 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
accidents | +0.003 |
doctors | +0.003 |
cartoons | +0.003 |
honey | +0.003 |
iring | +0.003 |
Neg logit contributions | |
sel | -0.008 |
ued | -0.007 |
chie | -0.007 |
top | -0.007 |
None | -0.007 |
Token | keeping |
Token ID | 19934 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
sel | +0.015 |
ued | +0.014 |
chie | +0.014 |
None | +0.014 |
| +0.013 |
Neg logit contributions | |
iring | -0.010 |
eddy | -0.010 |
fort | -0.009 |
ucks | -0.009 |
accidents | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -7.72e-02 |
Pos logit contributions | |
sel | +0.174 |
chie | +0.173 |
ued | +0.162 |
None | +0.159 |
top | +0.151 |
Neg logit contributions | |
from | -0.102 |
eddy | -0.091 |
fort | -0.091 |
about | -0.087 |
iring | -0.085 |
Token | |
Token ID | 220 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
sel | +0.002 |
chie | +0.002 |
ued | +0.002 |
none | +0.002 |
pe | +0.002 |
Neg logit contributions | |
iring | -0.002 |
eddy | -0.002 |
ucks | -0.002 |
fort | -0.002 |
accidents | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -9.96e-02 |
Pos logit contributions | |
sel | +0.000 |
chie | +0.000 |
ued | +0.000 |
top | +0.000 |
none | +0.000 |
Neg logit contributions | |
iring | -0.000 |
eddy | -0.000 |
ucks | -0.000 |
imi | -0.000 |
check | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
sel | +0.003 |
chie | +0.003 |
ued | +0.002 |
none | +0.002 |
top | +0.002 |
Neg logit contributions | |
iring | -0.002 |
eddy | -0.002 |
ucks | -0.002 |
imi | -0.002 |
check | -0.002 |
Token | When |
Token ID | 2215 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
sel | +0.021 |
ued | +0.020 |
chie | +0.019 |
| +0.019 |
None | +0.019 |
Neg logit contributions | |
iring | -0.016 |
eddy | -0.015 |
ucks | -0.015 |
fort | -0.015 |
imi | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
sel | +0.048 |
ued | +0.045 |
None | +0.045 |
chie | +0.044 |
top | +0.043 |
Neg logit contributions | |
from | -0.020 |
iring | -0.019 |
animals | -0.019 |
honey | -0.018 |
dust | -0.018 |
Token | live |
Token ID | 2107 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
sel | +0.028 |
ued | +0.027 |
chie | +0.026 |
None | +0.026 |
pool | +0.025 |
Neg logit contributions | |
from | -0.009 |
iring | -0.009 |
wake | -0.009 |
animals | -0.009 |
check | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
sel | +0.017 |
ued | +0.017 |
chie | +0.017 |
None | +0.017 |
top | +0.016 |
Neg logit contributions | |
iring | -0.010 |
from | -0.009 |
fort | -0.009 |
eddy | -0.008 |
ucks | -0.008 |
Token | long |
Token ID | 890 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
sel | +0.004 |
ued | +0.004 |
chie | +0.004 |
None | +0.004 |
top | +0.003 |
Neg logit contributions | |
iring | -0.002 |
fort | -0.002 |
eddy | -0.002 |
mosquitoes | -0.002 |
cartoons | -0.002 |
Token | time |
Token ID | 640 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
sel | +0.033 |
chie | +0.032 |
ued | +0.031 |
None | +0.030 |
top | +0.029 |
Neg logit contributions | |
fort | -0.018 |
eddy | -0.015 |
cartoons | -0.015 |
mess | -0.015 |
dust | -0.015 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
sel | +0.065 |
chie | +0.061 |
ued | +0.060 |
None | +0.058 |
top | +0.055 |
Neg logit contributions | |
iring | -0.053 |
from | -0.053 |
fort | -0.050 |
cartoons | -0.049 |
animals | -0.049 |
Token | ." |
Token ID | 526 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
sel | +0.169 |
chie | +0.165 |
ued | +0.164 |
None | +0.162 |
top | +0.151 |
Neg logit contributions | |
from | -0.099 |
fort | -0.095 |
iring | -0.095 |
eddy | -0.093 |
ies | -0.091 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
sel | +0.050 |
chie | +0.047 |
ued | +0.046 |
none | +0.041 |
top | +0.040 |
Neg logit contributions | |
eddy | -0.040 |
fort | -0.038 |
ucks | -0.038 |
iring | -0.037 |
imi | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
sel | +0.026 |
chie | +0.024 |
ued | +0.023 |
none | +0.022 |
top | +0.022 |
Neg logit contributions | |
iring | -0.024 |
eddy | -0.023 |
ucks | -0.023 |
imi | -0.022 |
fort | -0.022 |
Token | The |
Token ID | 464 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
sel | +0.055 |
ued | +0.050 |
chie | +0.049 |
none | +0.048 |
None | +0.047 |
Neg logit contributions | |
iring | -0.030 |
eddy | -0.029 |
imi | -0.028 |
fort | -0.027 |
ucks | -0.026 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
sel | +0.033 |
ued | +0.032 |
chie | +0.031 |
| +0.031 |
None | +0.030 |
Neg logit contributions | |
iring | -0.017 |
ucks | -0.016 |
eddy | -0.016 |
fort | -0.015 |
imi | -0.015 |
Token | they |
Token ID | 484 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
iring | +0.032 |
mosquitoes | +0.029 |
accidents | +0.028 |
eddy | +0.028 |
pets | +0.028 |
Neg logit contributions | |
sel | -0.041 |
ued | -0.038 |
chie | -0.036 |
None | -0.036 |
ical | -0.035 |
Token | lived |
Token ID | 5615 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
chie | +0.014 |
ued | +0.014 |
sel | +0.013 |
None | +0.013 |
top | +0.012 |
Neg logit contributions | |
iring | -0.010 |
from | -0.009 |
animals | -0.009 |
dust | -0.009 |
pets | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
sel | +0.032 |
chie | +0.031 |
ued | +0.031 |
None | +0.030 |
| +0.029 |
Neg logit contributions | |
iring | -0.013 |
from | -0.012 |
fort | -0.012 |
eddy | -0.011 |
ucks | -0.011 |
Token | long |
Token ID | 890 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
fort | +0.002 |
cartoons | +0.002 |
eddy | +0.002 |
pets | +0.002 |
mess | +0.002 |
Neg logit contributions | |
ued | -0.004 |
sel | -0.003 |
chie | -0.003 |
None | -0.003 |
top | -0.003 |
Token | time |
Token ID | 640 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
chie | +0.027 |
sel | +0.027 |
ued | +0.027 |
None | +0.026 |
top | +0.025 |
Neg logit contributions | |
fort | -0.016 |
cartoons | -0.014 |
eddy | -0.013 |
animals | -0.013 |
mess | -0.013 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.07e+00 |
Pos logit contributions | |
sel | +0.058 |
chie | +0.057 |
ued | +0.056 |
None | +0.054 |
| +0.052 |
Neg logit contributions | |
iring | -0.030 |
from | -0.028 |
fort | -0.027 |
pets | -0.026 |
friends | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
chie | +0.184 |
sel | +0.177 |
ued | +0.176 |
None | +0.170 |
ounded | +0.157 |
Neg logit contributions | |
from | -0.091 |
iring | -0.083 |
fort | -0.081 |
ies | -0.081 |
friends | -0.080 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
sel | +0.006 |
chie | +0.006 |
ued | +0.005 |
pe | +0.005 |
Fer | +0.005 |
Neg logit contributions | |
ucks | -0.003 |
eddy | -0.003 |
Luna | -0.003 |
iring | -0.003 |
imi | -0.003 |
Token | listened |
Token ID | 16399 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
iring | +0.025 |
eddy | +0.024 |
fort | +0.023 |
ucks | +0.023 |
imi | +0.023 |
Neg logit contributions | |
sel | -0.034 |
chie | -0.032 |
ued | -0.032 |
None | -0.031 |
top | -0.030 |
Token | carefully |
Token ID | 7773 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
chie | +0.002 |
sel | +0.002 |
Fer | +0.002 |
ued | +0.002 |
None | +0.002 |
Neg logit contributions | |
from | -0.001 |
iring | -0.001 |
about | -0.000 |
accidents | -0.000 |
pets | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
sel | +0.046 |
chie | +0.046 |
ued | +0.044 |
None | +0.043 |
| +0.042 |
Neg logit contributions | |
from | -0.011 |
iring | -0.010 |
fort | -0.008 |
accidents | -0.008 |
cartoons | -0.007 |
Token | this |
Token ID | 428 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
sel | +0.034 |
ued | +0.033 |
chie | +0.031 |
None | +0.031 |
ical | +0.030 |
Neg logit contributions | |
from | -0.014 |
dust | -0.013 |
accidents | -0.013 |
honey | -0.013 |
iring | -0.013 |
Token | house |
Token ID | 2156 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
sel | +0.055 |
chie | +0.053 |
ued | +0.052 |
None | +0.050 |
none | +0.047 |
Neg logit contributions | |
fort | -0.026 |
iring | -0.024 |
eddy | -0.024 |
honey | -0.022 |
imi | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
sel | +0.041 |
ued | +0.040 |
chie | +0.039 |
None | +0.038 |
| +0.036 |
Neg logit contributions | |
iring | -0.018 |
from | -0.018 |
fort | -0.017 |
eddy | -0.016 |
cartoons | -0.015 |
Token | long |
Token ID | 890 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
sel | +0.025 |
ued | +0.024 |
chie | +0.024 |
None | +0.023 |
| +0.023 |
Neg logit contributions | |
iring | -0.015 |
fort | -0.014 |
eddy | -0.014 |
mosquitoes | -0.013 |
imi | -0.013 |
Token | time |
Token ID | 640 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
sel | +0.055 |
chie | +0.053 |
ued | +0.052 |
None | +0.051 |
top | +0.049 |
Neg logit contributions | |
fort | -0.033 |
eddy | -0.029 |
dust | -0.028 |
imi | -0.028 |
snow | -0.027 |
Token | ago |
Token ID | 2084 |
Feature activation | -6.04e+00 |
Pos logit contributions | |
sel | +0.047 |
ued | +0.045 |
chie | +0.044 |
None | +0.042 |
| +0.039 |
Neg logit contributions | |
iring | -0.061 |
from | -0.059 |
fort | -0.059 |
pets | -0.057 |
eddy | -0.057 |
Token | ." |
Token ID | 526 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
sel | +0.166 |
chie | +0.163 |
ued | +0.163 |
None | +0.159 |
top | +0.149 |
Neg logit contributions | |
from | -0.100 |
fort | -0.097 |
iring | -0.096 |
eddy | -0.095 |
ies | -0.091 |
Token |
|
Token ID | 198 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
sel | +0.028 |
chie | +0.028 |
ued | +0.026 |
top | +0.024 |
none | +0.023 |
Neg logit contributions | |
ucks | -0.018 |
iring | -0.017 |
eddy | -0.017 |
imi | -0.016 |
pets | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
sel | +0.009 |
chie | +0.008 |
ued | +0.008 |
top | +0.007 |
None | +0.007 |
Neg logit contributions | |
iring | -0.010 |
eddy | -0.009 |
ucks | -0.009 |
imi | -0.009 |
fort | -0.009 |
Token | L |
Token ID | 43 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
sel | +0.031 |
ued | +0.029 |
chie | +0.029 |
None | +0.028 |
| +0.028 |
Neg logit contributions | |
iring | -0.018 |
eddy | -0.017 |
ucks | -0.017 |
fort | -0.016 |
imi | -0.016 |
Token | ily |
Token ID | 813 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
iring | +0.018 |
eddy | +0.017 |
fort | +0.017 |
ucks | +0.017 |
mosquitoes | +0.016 |
Neg logit contributions | |
sel | -0.021 |
chie | -0.019 |
ued | -0.019 |
| -0.018 |
None | -0.018 |
Token | display |
Token ID | 3359 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
sel | +0.027 |
ued | +0.026 |
chie | +0.025 |
None | +0.025 |
top | +0.024 |
Neg logit contributions | |
iring | -0.012 |
ucks | -0.010 |
eddy | -0.010 |
check | -0.010 |
imi | -0.010 |
Token | their |
Token ID | 511 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
ued | +0.053 |
sel | +0.053 |
chie | +0.053 |
None | +0.050 |
ical | +0.049 |
Neg logit contributions | |
from | -0.021 |
honey | -0.020 |
cartoons | -0.020 |
iring | -0.019 |
animals | -0.019 |
Token | favorite |
Token ID | 4004 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
sel | +0.000 |
ued | +0.000 |
None | +0.000 |
chie | +0.000 |
top | +0.000 |
Neg logit contributions | |
pets | -0.000 |
fort | -0.000 |
iring | -0.000 |
honey | -0.000 |
animals | -0.000 |
Token | things |
Token ID | 1243 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
sel | +0.002 |
chie | +0.001 |
ued | +0.001 |
None | +0.001 |
top | +0.001 |
Neg logit contributions | |
fort | -0.001 |
eddy | -0.001 |
iring | -0.001 |
cartoons | -0.001 |
honey | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
from | +0.000 |
about | +0.000 |
iring | +0.000 |
outside | +0.000 |
accidents | +0.000 |
Neg logit contributions | |
chie | -0.001 |
sel | -0.001 |
ued | -0.001 |
None | -0.001 |
ical | -0.000 |
Token | class |
Token ID | 1398 |
Feature activation | -6.00e+00 |
Pos logit contributions | |
ued | +0.084 |
sel | +0.084 |
chie | +0.079 |
ounded | +0.075 |
ical | +0.075 |
Neg logit contributions | |
cartoons | -0.029 |
from | -0.029 |
iring | -0.027 |
animals | -0.027 |
dust | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
chie | +0.199 |
sel | +0.198 |
ued | +0.183 |
None | +0.174 |
bar | +0.172 |
Neg logit contributions | |
from | -0.078 |
about | -0.077 |
friends | -0.077 |
room | -0.072 |
cartoons | -0.070 |
Token | The |
Token ID | 383 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
sel | +0.029 |
chie | +0.028 |
ued | +0.027 |
ret | +0.026 |
arest | +0.026 |
Neg logit contributions | |
cartoons | -0.019 |
Doctor | -0.017 |
pets | -0.017 |
from | -0.016 |
animals | -0.016 |
Token | cats |
Token ID | 11875 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
sel | +0.028 |
| +0.027 |
chie | +0.027 |
ued | +0.026 |
None | +0.026 |
Neg logit contributions | |
iring | -0.015 |
eddy | -0.014 |
ucks | -0.014 |
accidents | -0.013 |
imi | -0.012 |
Token | brought |
Token ID | 3181 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
from | +0.014 |
iring | +0.013 |
friends | +0.013 |
animals | +0.013 |
pets | +0.013 |
Neg logit contributions | |
sel | -0.022 |
chie | -0.022 |
top | -0.020 |
None | -0.019 |
ical | -0.019 |
Token | their |
Token ID | 511 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
sel | +0.004 |
ued | +0.004 |
chie | +0.004 |
None | +0.004 |
top | +0.004 |
Neg logit contributions | |
iring | -0.003 |
eddy | -0.002 |
ucks | -0.002 |
fort | -0.002 |
mosquitoes | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
iring | +0.021 |
ucks | +0.020 |
eddy | +0.020 |
fort | +0.019 |
imi | +0.018 |
Neg logit contributions | |
sel | -0.034 |
| -0.031 |
ued | -0.031 |
None | -0.031 |
chie | -0.030 |
Token | new |
Token ID | 649 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
iring | +0.013 |
ucks | +0.012 |
eddy | +0.011 |
check | +0.011 |
imi | +0.011 |
Neg logit contributions | |
sel | -0.015 |
| -0.014 |
chie | -0.014 |
ued | -0.014 |
top | -0.014 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
iring | +0.002 |
ucks | +0.002 |
eddy | +0.002 |
mosquitoes | +0.002 |
imi | +0.002 |
Neg logit contributions | |
sel | -0.003 |
ued | -0.003 |
chie | -0.003 |
| -0.003 |
None | -0.003 |
Token | in |
Token ID | 287 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
sel | +0.030 |
| +0.029 |
ued | +0.028 |
chie | +0.028 |
top | +0.028 |
Neg logit contributions | |
iring | -0.023 |
ucks | -0.021 |
eddy | -0.021 |
imi | -0.020 |
fort | -0.020 |
Token | her |
Token ID | 607 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
sel | +0.056 |
ued | +0.052 |
chie | +0.052 |
| +0.052 |
None | +0.051 |
Neg logit contributions | |
iring | -0.033 |
ucks | -0.031 |
eddy | -0.030 |
fort | -0.029 |
imi | -0.029 |
Token | class |
Token ID | 1398 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
sel | +0.035 |
| +0.034 |
ued | +0.034 |
chie | +0.033 |
None | +0.033 |
Neg logit contributions | |
iring | -0.018 |
ucks | -0.016 |
eddy | -0.016 |
mosquitoes | -0.015 |
accidents | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
sel | +0.187 |
chie | +0.187 |
ued | +0.171 |
None | +0.159 |
ical | +0.154 |
Neg logit contributions | |
from | -0.087 |
room | -0.086 |
iring | -0.084 |
fort | -0.084 |
friends | -0.083 |
Token | Her |
Token ID | 2332 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
sel | +0.005 |
ued | +0.005 |
chie | +0.005 |
top | +0.004 |
None | +0.004 |
Neg logit contributions | |
iring | -0.003 |
eddy | -0.003 |
ucks | -0.003 |
imi | -0.003 |
fort | -0.003 |
Token | name |
Token ID | 1438 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
iring | +0.016 |
ucks | +0.015 |
eddy | +0.014 |
mosquitoes | +0.014 |
check | +0.014 |
Neg logit contributions | |
| -0.027 |
sel | -0.027 |
None | -0.026 |
ued | -0.025 |
top | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
iring | +0.014 |
eddy | +0.013 |
ucks | +0.013 |
fort | +0.013 |
imi | +0.013 |
Neg logit contributions | |
sel | -0.017 |
chie | -0.016 |
ued | -0.016 |
| -0.016 |
None | -0.015 |
Token | Lily |
Token ID | 20037 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
sel | +0.067 |
ued | +0.065 |
chie | +0.065 |
top | +0.060 |
None | +0.059 |
Neg logit contributions | |
iring | -0.024 |
imi | -0.024 |
eddy | -0.023 |
cartoons | -0.021 |
mosquitoes | -0.021 |
Token | that |
Token ID | 326 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
iring | +0.014 |
fort | +0.014 |
mosquitoes | +0.013 |
from | +0.013 |
wolves | +0.013 |
Neg logit contributions | |
sel | -0.022 |
chie | -0.021 |
ued | -0.020 |
None | -0.020 |
| -0.019 |
Token | died |
Token ID | 3724 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
sel | +0.006 |
chie | +0.006 |
ued | +0.006 |
None | +0.005 |
top | +0.005 |
Neg logit contributions | |
fort | -0.004 |
iring | -0.004 |
from | -0.004 |
mosquitoes | -0.004 |
wolves | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
iring | +0.010 |
from | +0.010 |
fort | +0.009 |
eddy | +0.009 |
accidents | +0.009 |
Neg logit contributions | |
sel | -0.017 |
ued | -0.016 |
None | -0.016 |
chie | -0.015 |
top | -0.015 |
Token | long |
Token ID | 890 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
fort | +0.002 |
honey | +0.001 |
mosquitoes | +0.001 |
mess | +0.001 |
eddy | +0.001 |
Neg logit contributions | |
sel | -0.003 |
ued | -0.003 |
None | -0.003 |
chie | -0.003 |
top | -0.003 |
Token | time |
Token ID | 640 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
sel | +0.024 |
chie | +0.023 |
ued | +0.023 |
None | +0.022 |
top | +0.022 |
Neg logit contributions | |
fort | -0.012 |
itch | -0.011 |
dust | -0.010 |
mess | -0.010 |
snow | -0.010 |
Token | ago |
Token ID | 2084 |
Feature activation | -5.95e+00 |
Pos logit contributions | |
sel | +0.033 |
chie | +0.031 |
ued | +0.031 |
None | +0.030 |
Fer | +0.029 |
Neg logit contributions | |
from | -0.020 |
iring | -0.018 |
about | -0.017 |
here | -0.017 |
fort | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
chie | +0.178 |
sel | +0.178 |
ued | +0.171 |
None | +0.170 |
top | +0.158 |
Neg logit contributions | |
from | -0.089 |
fort | -0.078 |
iring | -0.077 |
eddy | -0.073 |
ies | -0.072 |
Token | It |
Token ID | 632 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
eddy | +0.006 |
iring | +0.006 |
ucks | +0.006 |
Doctor | +0.006 |
imi | +0.006 |
Neg logit contributions | |
sel | -0.009 |
ued | -0.009 |
chie | -0.009 |
top | -0.008 |
none | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
iring | +0.008 |
eddy | +0.007 |
ucks | +0.007 |
fort | +0.007 |
imi | +0.007 |
Neg logit contributions | |
sel | -0.008 |
ued | -0.008 |
chie | -0.008 |
| -0.007 |
None | -0.007 |
Token | not |
Token ID | 407 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
sel | +0.013 |
ued | +0.013 |
chie | +0.013 |
None | +0.012 |
top | +0.012 |
Neg logit contributions | |
iring | -0.010 |
eddy | -0.009 |
fort | -0.009 |
ucks | -0.009 |
imi | -0.009 |
Token | alive |
Token ID | 6776 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
iring | +0.008 |
fort | +0.008 |
accidents | +0.007 |
eddy | +0.007 |
mosquitoes | +0.007 |
Neg logit contributions | |
sel | -0.013 |
ued | -0.012 |
None | -0.012 |
chie | -0.012 |
top | -0.012 |
Token | tools |
Token ID | 4899 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
iring | +0.018 |
honey | +0.018 |
fort | +0.018 |
mosquitoes | +0.018 |
accidents | +0.017 |
Neg logit contributions | |
sel | -0.030 |
ued | -0.030 |
chie | -0.029 |
None | -0.028 |
top | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
chie | +0.008 |
ued | +0.008 |
None | +0.008 |
sel | +0.008 |
ical | +0.007 |
Neg logit contributions | |
from | -0.003 |
iring | -0.003 |
eddy | -0.003 |
accidents | -0.002 |
ies | -0.002 |
Token | toys |
Token ID | 14958 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
iring | +0.008 |
fort | +0.008 |
mosquitoes | +0.007 |
honey | +0.007 |
accidents | +0.007 |
Neg logit contributions | |
sel | -0.012 |
ued | -0.012 |
chie | -0.012 |
None | -0.011 |
top | -0.011 |
Token | from |
Token ID | 422 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
from | +0.014 |
iring | +0.012 |
fort | +0.012 |
eddy | +0.011 |
dust | +0.011 |
Neg logit contributions | |
chie | -0.028 |
ued | -0.027 |
None | -0.026 |
sel | -0.026 |
| -0.024 |
Token | long |
Token ID | 890 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
from | +0.001 |
iring | +0.001 |
animals | +0.001 |
fort | +0.001 |
mosquitoes | +0.001 |
Neg logit contributions | |
sel | -0.002 |
chie | -0.002 |
ued | -0.002 |
ical | -0.002 |
None | -0.002 |
Token | ago |
Token ID | 2084 |
Feature activation | -5.92e+00 |
Pos logit contributions | |
sel | +0.038 |
chie | +0.038 |
ued | +0.038 |
None | +0.036 |
top | +0.035 |
Neg logit contributions | |
fort | -0.029 |
honey | -0.027 |
iring | -0.027 |
from | -0.027 |
pets | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
chie | +0.176 |
ued | +0.171 |
sel | +0.169 |
None | +0.162 |
ounded | +0.150 |
Neg logit contributions | |
from | -0.092 |
fort | -0.089 |
iring | -0.086 |
ies | -0.083 |
chefs | -0.080 |
Token | She |
Token ID | 1375 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
iring | +0.009 |
ucks | +0.008 |
imi | +0.007 |
eddy | +0.007 |
Luna | +0.007 |
Neg logit contributions | |
sel | -0.026 |
chie | -0.026 |
ued | -0.025 |
ical | -0.022 |
ience | -0.022 |
Token | wanted |
Token ID | 2227 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
iring | +0.003 |
ucks | +0.003 |
fort | +0.003 |
eddy | +0.003 |
imi | +0.003 |
Neg logit contributions | |
chie | -0.003 |
sel | -0.003 |
ued | -0.003 |
None | -0.003 |
top | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +6.52e-02 |
Pos logit contributions | |
honey | +0.000 |
doctors | +0.000 |
from | +0.000 |
animals | +0.000 |
pets | +0.000 |
Neg logit contributions | |
ued | -0.001 |
chie | -0.001 |
sel | -0.001 |
ical | -0.001 |
pool | -0.001 |
Token | touch |
Token ID | 3638 |
Feature activation | -6.51e-02 |
Pos logit contributions | |
iring | +0.001 |
eddy | +0.001 |
ucks | +0.001 |
fort | +0.001 |
imi | +0.001 |
Neg logit contributions | |
sel | -0.002 |
ued | -0.002 |
chie | -0.002 |
None | -0.002 |
| -0.002 |
Token | very |
Token ID | 845 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
| +0.011 |
sel | +0.010 |
none | +0.010 |
chie | +0.010 |
ued | +0.010 |
Neg logit contributions | |
ucks | -0.018 |
iring | -0.017 |
eddy | -0.017 |
fort | -0.017 |
imi | -0.016 |
Token | happy |
Token ID | 3772 |
Feature activation | -5.91e-02 |
Pos logit contributions | |
| +0.013 |
sel | +0.013 |
ued | +0.012 |
chie | +0.012 |
top | +0.011 |
Neg logit contributions | |
ucks | -0.015 |
eddy | -0.015 |
fort | -0.015 |
mosquitoes | -0.014 |
imi | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
sel | +0.001 |
| +0.001 |
None | +0.001 |
top | +0.001 |
none | +0.001 |
Neg logit contributions | |
iring | -0.001 |
ucks | -0.001 |
imi | -0.001 |
eddy | -0.001 |
mosquitoes | -0.001 |
Token | drank |
Token ID | 24070 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
| +0.004 |
sel | +0.003 |
none | +0.003 |
ued | +0.003 |
top | +0.003 |
Neg logit contributions | |
ucks | -0.005 |
iring | -0.005 |
fort | -0.004 |
eddy | -0.004 |
mosquitoes | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
iring | +0.025 |
eddy | +0.023 |
ucks | +0.023 |
fort | +0.022 |
mosquitoes | +0.022 |
Neg logit contributions | |
sel | -0.035 |
chie | -0.033 |
ued | -0.033 |
None | -0.032 |
| -0.032 |
Token | cocoa |
Token ID | 35845 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
iring | +0.020 |
ucks | +0.019 |
check | +0.018 |
eddy | +0.018 |
imi | +0.016 |
Neg logit contributions | |
sel | -0.050 |
ued | -0.049 |
| -0.049 |
top | -0.047 |
chie | -0.047 |
Token | together |
Token ID | 1978 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
iring | +0.050 |
eddy | +0.048 |
fort | +0.048 |
accidents | +0.044 |
from | +0.044 |
Neg logit contributions | |
sel | -0.084 |
chie | -0.082 |
ued | -0.080 |
None | -0.077 |
| -0.074 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
chie | +0.052 |
sel | +0.048 |
ued | +0.046 |
None | +0.045 |
ical | +0.042 |
Neg logit contributions | |
from | -0.024 |
about | -0.020 |
outside | -0.016 |
fort | -0.016 |
iring | -0.016 |
Token | The |
Token ID | 383 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
eddy | +0.003 |
iring | +0.003 |
ucks | +0.003 |
imi | +0.003 |
fort | +0.003 |
Neg logit contributions | |
sel | -0.003 |
chie | -0.003 |
ued | -0.003 |
top | -0.003 |
pe | -0.003 |
Token | end |
Token ID | 886 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
sel | +0.012 |
ued | +0.011 |
| +0.011 |
chie | +0.011 |
None | +0.011 |
Neg logit contributions | |
iring | -0.011 |
ucks | -0.010 |
eddy | -0.010 |
check | -0.009 |
imi | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
iring | +0.072 |
ucks | +0.068 |
check | +0.065 |
mosquitoes | +0.065 |
eddy | +0.065 |
Neg logit contributions | |
| -0.036 |
sel | -0.035 |
ued | -0.033 |
top | -0.032 |
None | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
iring | +0.030 |
ucks | +0.029 |
eddy | +0.029 |
fort | +0.027 |
imi | +0.027 |
Neg logit contributions | |
sel | -0.036 |
chie | -0.035 |
ued | -0.034 |
top | -0.031 |
none | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
iring | +0.026 |
ucks | +0.025 |
eddy | +0.025 |
imi | +0.024 |
fort | +0.023 |
Neg logit contributions | |
sel | -0.027 |
chie | -0.026 |
ued | -0.025 |
top | -0.023 |
None | -0.023 |
Token | L |
Token ID | 43 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
iring | +0.004 |
ucks | +0.004 |
eddy | +0.004 |
fort | +0.004 |
mosquitoes | +0.004 |
Neg logit contributions | |
sel | -0.007 |
chie | -0.007 |
ued | -0.007 |
None | -0.007 |
| -0.006 |
Token | ily |
Token ID | 813 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
iring | +0.025 |
eddy | +0.024 |
ucks | +0.023 |
fort | +0.023 |
accidents | +0.022 |
Neg logit contributions | |
sel | -0.029 |
chie | -0.027 |
ued | -0.027 |
None | -0.025 |
| -0.025 |
Token | felt |
Token ID | 2936 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
iring | +0.023 |
ucks | +0.021 |
eddy | +0.021 |
imi | +0.020 |
mosquitoes | +0.020 |
Neg logit contributions | |
sel | -0.029 |
| -0.027 |
ued | -0.027 |
top | -0.026 |
None | -0.026 |
Token | cold |
Token ID | 4692 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
iring | +0.015 |
eddy | +0.014 |
ucks | +0.014 |
imi | +0.014 |
fort | +0.014 |
Neg logit contributions | |
sel | -0.017 |
| -0.016 |
ued | -0.016 |
chie | -0.015 |
None | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
iring | +0.060 |
imi | +0.058 |
ucks | +0.057 |
check | +0.052 |
eddy | +0.050 |
Neg logit contributions | |
sel | -0.078 |
top | -0.073 |
| -0.073 |
None | -0.068 |
ued | -0.067 |
Token | scared |
Token ID | 12008 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
eddy | +0.011 |
iring | +0.011 |
ucks | +0.011 |
imi | +0.010 |
fort | +0.010 |
Neg logit contributions | |
| -0.012 |
sel | -0.011 |
ued | -0.011 |
none | -0.011 |
None | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
iring | +0.021 |
ucks | +0.020 |
eddy | +0.020 |
fort | +0.019 |
imi | +0.019 |
Neg logit contributions | |
sel | -0.016 |
ued | -0.015 |
chie | -0.015 |
| -0.015 |
None | -0.014 |
Token | She |
Token ID | 1375 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
iring | +0.020 |
eddy | +0.019 |
ucks | +0.018 |
fort | +0.018 |
imi | +0.018 |
Neg logit contributions | |
sel | -0.029 |
ued | -0.028 |
chie | -0.027 |
| -0.027 |
None | -0.027 |
Token | did |
Token ID | 750 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
iring | +0.017 |
eddy | +0.017 |
ucks | +0.017 |
fort | +0.016 |
imi | +0.015 |
Neg logit contributions | |
sel | -0.011 |
| -0.010 |
ued | -0.009 |
None | -0.009 |
chie | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
sel | +0.004 |
ued | +0.004 |
chie | +0.004 |
None | +0.003 |
top | +0.003 |
Neg logit contributions | |
iring | -0.002 |
from | -0.001 |
fort | -0.001 |
eddy | -0.001 |
honey | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
sel | +0.010 |
ued | +0.009 |
| +0.009 |
chie | +0.009 |
None | +0.009 |
Neg logit contributions | |
iring | -0.010 |
eddy | -0.010 |
ucks | -0.010 |
fort | -0.009 |
mosquitoes | -0.009 |
Token | ate |
Token ID | 15063 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
iring | +0.007 |
eddy | +0.007 |
ucks | +0.007 |
fort | +0.007 |
imi | +0.007 |
Neg logit contributions | |
sel | -0.008 |
ued | -0.008 |
chie | -0.007 |
| -0.007 |
None | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
iring | +0.045 |
eddy | +0.043 |
ucks | +0.042 |
fort | +0.041 |
imi | +0.041 |
Neg logit contributions | |
sel | -0.053 |
ued | -0.050 |
chie | -0.050 |
| -0.049 |
None | -0.048 |
Token | o |
Token ID | 267 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
iring | +0.028 |
eddy | +0.026 |
ucks | +0.026 |
fort | +0.025 |
imi | +0.024 |
Neg logit contributions | |
sel | -0.055 |
ued | -0.052 |
chie | -0.052 |
| -0.051 |
None | -0.050 |
Token | at |
Token ID | 265 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
iring | +0.034 |
eddy | +0.032 |
mosquitoes | +0.031 |
ucks | +0.031 |
fort | +0.031 |
Neg logit contributions | |
sel | -0.035 |
chie | -0.032 |
ued | -0.032 |
| -0.031 |
top | -0.031 |
Token | soup |
Token ID | 17141 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
iring | +0.044 |
eddy | +0.041 |
ucks | +0.040 |
fort | +0.039 |
imi | +0.038 |
Neg logit contributions | |
sel | -0.083 |
ued | -0.080 |
chie | -0.079 |
None | -0.077 |
| -0.077 |
Token | happily |
Token ID | 18177 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
iring | +0.042 |
eddy | +0.038 |
fort | +0.038 |
ucks | +0.036 |
imi | +0.036 |
Neg logit contributions | |
sel | -0.086 |
chie | -0.084 |
ued | -0.084 |
None | -0.081 |
| -0.080 |
Token | and |
Token ID | 290 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
chie | +0.013 |
None | +0.013 |
sel | +0.012 |
ued | +0.012 |
One | +0.011 |
Neg logit contributions | |
from | -0.004 |
iring | -0.003 |
ies | -0.003 |
eddy | -0.003 |
pets | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
sel | +0.013 |
| +0.012 |
none | +0.011 |
ued | +0.011 |
top | +0.011 |
Neg logit contributions | |
iring | -0.017 |
ucks | -0.016 |
eddy | -0.016 |
imi | -0.015 |
fort | -0.015 |
Token | made |
Token ID | 925 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
iring | +0.004 |
eddy | +0.004 |
ucks | +0.004 |
fort | +0.004 |
imi | +0.004 |
Neg logit contributions | |
sel | -0.005 |
ued | -0.005 |
chie | -0.004 |
| -0.004 |
None | -0.004 |
Token | 's |
Token ID | 338 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
iring | +0.020 |
ucks | +0.019 |
eddy | +0.019 |
fort | +0.018 |
mosquitoes | +0.018 |
Neg logit contributions | |
sel | -0.015 |
| -0.014 |
ued | -0.014 |
top | -0.014 |
None | -0.013 |
Token | right |
Token ID | 826 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
iring | +0.007 |
ucks | +0.007 |
eddy | +0.007 |
fort | +0.007 |
imi | +0.006 |
Neg logit contributions | |
sel | -0.008 |
ued | -0.007 |
chie | -0.007 |
| -0.007 |
None | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
sel | +0.000 |
ued | +0.000 |
chie | +0.000 |
None | +0.000 |
| +0.000 |
Neg logit contributions | |
iring | -0.000 |
eddy | -0.000 |
fort | -0.000 |
imi | -0.000 |
accidents | -0.000 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
| +0.013 |
sel | +0.013 |
none | +0.012 |
None | +0.012 |
chie | +0.012 |
Neg logit contributions | |
ucks | -0.012 |
iring | -0.012 |
eddy | -0.011 |
check | -0.011 |
asc | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
eddy | +0.003 |
iring | +0.003 |
fort | +0.003 |
imi | +0.003 |
accidents | +0.003 |
Neg logit contributions | |
sel | -0.004 |
ued | -0.004 |
chie | -0.004 |
None | -0.003 |
top | -0.003 |
Token | When |
Token ID | 1649 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
iring | +0.014 |
eddy | +0.013 |
ucks | +0.013 |
imi | +0.012 |
fort | +0.012 |
Neg logit contributions | |
sel | -0.016 |
ued | -0.015 |
chie | -0.015 |
| -0.014 |
top | -0.014 |
Token | you |
Token ID | 345 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
iring | +0.057 |
eddy | +0.053 |
ucks | +0.053 |
fort | +0.051 |
imi | +0.050 |
Neg logit contributions | |
sel | -0.081 |
ued | -0.077 |
chie | -0.076 |
| -0.075 |
None | -0.074 |
Token | exercise |
Token ID | 5517 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
iring | +0.016 |
eddy | +0.015 |
ucks | +0.015 |
fort | +0.014 |
imi | +0.014 |
Neg logit contributions | |
sel | -0.023 |
ued | -0.021 |
chie | -0.021 |
| -0.021 |
None | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
mosquitoes | +0.002 |
from | +0.002 |
accidents | +0.002 |
iring | +0.002 |
cartoons | +0.002 |
Neg logit contributions | |
sel | -0.005 |
chie | -0.005 |
None | -0.005 |
ued | -0.005 |
top | -0.005 |
Token | you |
Token ID | 345 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
| +0.003 |
none | +0.003 |
sel | +0.003 |
ued | +0.003 |
None | +0.003 |
Neg logit contributions | |
ucks | -0.004 |
eddy | -0.004 |
iring | -0.003 |
fort | -0.003 |
imi | -0.003 |
Token | take |
Token ID | 1011 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
iring | +0.007 |
fort | +0.006 |
ucks | +0.006 |
eddy | +0.006 |
imi | +0.006 |
Neg logit contributions | |
sel | -0.009 |
chie | -0.009 |
ued | -0.009 |
None | -0.008 |
top | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
sel | +0.030 |
chie | +0.029 |
ued | +0.028 |
None | +0.027 |
| +0.025 |
Neg logit contributions | |
iring | -0.023 |
fort | -0.022 |
from | -0.021 |
eddy | -0.021 |
imi | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
sel | +0.004 |
chie | +0.004 |
ued | +0.004 |
None | +0.004 |
top | +0.004 |
Neg logit contributions | |
iring | -0.004 |
ucks | -0.004 |
eddy | -0.004 |
fort | -0.004 |
imi | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
sel | +0.001 |
chie | +0.001 |
ued | +0.001 |
top | +0.001 |
None | +0.001 |
Neg logit contributions | |
iring | -0.001 |
eddy | -0.001 |
ucks | -0.001 |
imi | -0.001 |
fort | -0.001 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
sel | +0.030 |
ued | +0.028 |
chie | +0.028 |
None | +0.027 |
| +0.026 |
Neg logit contributions | |
iring | -0.023 |
eddy | -0.021 |
ucks | -0.021 |
imi | -0.021 |
fort | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
sel | +0.008 |
chie | +0.008 |
ued | +0.008 |
top | +0.007 |
None | +0.007 |
Neg logit contributions | |
iring | -0.007 |
imi | -0.006 |
mosquitoes | -0.006 |
fort | -0.006 |
accidents | -0.006 |
Token | M |
Token ID | 337 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
iring | +0.005 |
eddy | +0.005 |
ucks | +0.005 |
fort | +0.004 |
imi | +0.004 |
Neg logit contributions | |
sel | -0.004 |
ued | -0.004 |
| -0.004 |
chie | -0.004 |
None | -0.004 |
Token | andy |
Token ID | 10757 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
iring | +0.044 |
ucks | +0.043 |
check | +0.042 |
eddy | +0.042 |
fort | +0.042 |
Neg logit contributions | |
sel | -0.081 |
chie | -0.078 |
ued | -0.075 |
| -0.074 |
top | -0.074 |
Token | noticed |
Token ID | 6810 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
iring | +0.030 |
fort | +0.029 |
mosquitoes | +0.028 |
eddy | +0.028 |
imi | +0.028 |
Neg logit contributions | |
sel | -0.036 |
chie | -0.036 |
ued | -0.035 |
None | -0.033 |
top | -0.032 |
Token | something |
Token ID | 1223 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
iring | +0.008 |
accidents | +0.008 |
honey | +0.008 |
mosquitoes | +0.008 |
imi | +0.008 |
Neg logit contributions | |
chie | -0.014 |
sel | -0.014 |
ued | -0.013 |
ical | -0.013 |
None | -0.012 |
Token | shiny |
Token ID | 22441 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
iring | +0.032 |
eddy | +0.029 |
mosquitoes | +0.029 |
accidents | +0.029 |
fort | +0.029 |
Neg logit contributions | |
sel | -0.044 |
chie | -0.042 |
ued | -0.041 |
None | -0.040 |
| -0.039 |
Token | on |
Token ID | 319 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
iring | +0.024 |
eddy | +0.021 |
accidents | +0.020 |
fort | +0.020 |
mosquitoes | +0.019 |
Neg logit contributions | |
sel | -0.054 |
chie | -0.053 |
ued | -0.052 |
| -0.051 |
None | -0.051 |
Token | ground |
Token ID | 2323 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
sel | +0.020 |
None | +0.018 |
ued | +0.018 |
chie | +0.018 |
| +0.017 |
Neg logit contributions | |
fort | -0.010 |
mosquitoes | -0.009 |
iring | -0.009 |
mess | -0.009 |
dust | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
sel | +0.044 |
chie | +0.043 |
ued | +0.042 |
None | +0.040 |
| +0.038 |
Neg logit contributions | |
from | -0.026 |
fort | -0.024 |
iring | -0.023 |
mess | -0.020 |
dust | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
iring | +0.017 |
ucks | +0.017 |
eddy | +0.017 |
Luna | +0.017 |
Doctor | +0.016 |
Neg logit contributions | |
sel | -0.035 |
chie | -0.035 |
ued | -0.033 |
top | -0.030 |
ience | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
ucks | +0.011 |
eddy | +0.010 |
iring | +0.010 |
imi | +0.010 |
Luna | +0.009 |
Neg logit contributions | |
sel | -0.018 |
chie | -0.016 |
ued | -0.016 |
ical | -0.015 |
none | -0.015 |
Token | They |
Token ID | 2990 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
sel | +0.001 |
chie | +0.001 |
ued | +0.001 |
None | +0.001 |
top | +0.001 |
Neg logit contributions | |
iring | -0.001 |
ucks | -0.001 |
eddy | -0.001 |
imi | -0.001 |
mosquitoes | -0.001 |
Token | felt |
Token ID | 2936 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
dust | +0.005 |
from | +0.005 |
fort | +0.005 |
itch | +0.005 |
mess | +0.005 |
Neg logit contributions | |
chie | -0.007 |
sel | -0.007 |
ued | -0.007 |
ical | -0.007 |
None | -0.007 |
Token | sad |
Token ID | 6507 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
iring | +0.011 |
mosquitoes | +0.011 |
accidents | +0.011 |
itch | +0.010 |
from | +0.010 |
Neg logit contributions | |
sel | -0.015 |
chie | -0.013 |
ued | -0.013 |
top | -0.013 |
None | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
iring | +0.024 |
ucks | +0.024 |
eddy | +0.023 |
check | +0.022 |
imi | +0.022 |
Neg logit contributions | |
sel | -0.035 |
| -0.034 |
ued | -0.033 |
None | -0.033 |
top | -0.032 |
Token | sorry |
Token ID | 7926 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
iring | +0.000 |
eddy | +0.000 |
ucks | +0.000 |
imi | +0.000 |
fort | +0.000 |
Neg logit contributions | |
sel | -0.000 |
ued | -0.000 |
| -0.000 |
chie | -0.000 |
None | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
iring | +0.024 |
ucks | +0.023 |
eddy | +0.023 |
imi | +0.023 |
mosquitoes | +0.022 |
Neg logit contributions | |
sel | -0.019 |
| -0.018 |
ued | -0.017 |
None | -0.017 |
chie | -0.017 |
Token | They |
Token ID | 1119 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
iring | +0.012 |
ucks | +0.011 |
eddy | +0.011 |
from | +0.011 |
imi | +0.010 |
Neg logit contributions | |
sel | -0.029 |
chie | -0.029 |
ued | -0.028 |
bar | -0.026 |
top | -0.025 |
Token | poem |
Token ID | 21247 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
iring | +0.011 |
eddy | +0.010 |
ucks | +0.010 |
check | +0.009 |
imi | +0.009 |
Neg logit contributions | |
| -0.015 |
sel | -0.015 |
chie | -0.015 |
None | -0.014 |
top | -0.014 |
Token | in |
Token ID | 287 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
sel | +0.003 |
ued | +0.003 |
| +0.003 |
chie | +0.003 |
None | +0.003 |
Neg logit contributions | |
iring | -0.002 |
eddy | -0.002 |
ucks | -0.002 |
imi | -0.001 |
mosquitoes | -0.001 |
Token | her |
Token ID | 607 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
ued | +0.043 |
sel | +0.042 |
chie | +0.040 |
ounded | +0.039 |
None | +0.038 |
Neg logit contributions | |
mosquitoes | -0.015 |
honey | -0.015 |
dust | -0.015 |
iring | -0.014 |
from | -0.014 |
Token | head |
Token ID | 1182 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
sel | +0.023 |
ued | +0.022 |
chie | +0.021 |
None | +0.021 |
top | +0.020 |
Neg logit contributions | |
iring | -0.015 |
fort | -0.015 |
eddy | -0.015 |
ucks | -0.014 |
imi | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ued | +0.057 |
chie | +0.056 |
sel | +0.055 |
None | +0.052 |
Fer | +0.049 |
Neg logit contributions | |
from | -0.020 |
iring | -0.019 |
eddy | -0.018 |
ucks | -0.016 |
honey | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
iring | +0.020 |
ucks | +0.020 |
eddy | +0.019 |
imi | +0.018 |
Doctor | +0.018 |
Neg logit contributions | |
sel | -0.046 |
chie | -0.046 |
ued | -0.045 |
top | -0.040 |
none | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
iring | +0.014 |
ucks | +0.014 |
eddy | +0.013 |
imi | +0.013 |
mosquitoes | +0.012 |
Neg logit contributions | |
sel | -0.021 |
chie | -0.019 |
ued | -0.018 |
none | -0.018 |
ical | -0.018 |
Token | She |
Token ID | 3347 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
sel | +0.005 |
ued | +0.004 |
chie | +0.004 |
None | +0.004 |
none | +0.004 |
Neg logit contributions | |
iring | -0.003 |
ucks | -0.003 |
eddy | -0.003 |
imi | -0.003 |
mosquitoes | -0.003 |
Token | says |
Token ID | 1139 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
iring | +0.006 |
eddy | +0.006 |
accidents | +0.005 |
imi | +0.005 |
ucks | +0.005 |
Neg logit contributions | |
sel | -0.007 |
ued | -0.006 |
| -0.006 |
top | -0.006 |
None | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
mosquitoes | +0.008 |
from | +0.008 |
honey | +0.008 |
iring | +0.007 |
accidents | +0.007 |
Neg logit contributions | |
sel | -0.013 |
chie | -0.012 |
ued | -0.012 |
top | -0.012 |
ical | -0.011 |
Token | poem |
Token ID | 21247 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
iring | +0.014 |
eddy | +0.012 |
ucks | +0.012 |
imi | +0.011 |
accidents | +0.011 |
Neg logit contributions | |
sel | -0.030 |
| -0.028 |
ued | -0.028 |
chie | -0.027 |
None | -0.027 |
Token | One |
Token ID | 1881 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
sel | +0.015 |
chie | +0.014 |
ued | +0.014 |
top | +0.012 |
None | +0.012 |
Neg logit contributions | |
iring | -0.018 |
ucks | -0.017 |
eddy | -0.017 |
imi | -0.017 |
fort | -0.017 |
Token | day |
Token ID | 1110 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
| +0.005 |
sel | +0.004 |
top | +0.004 |
One | +0.004 |
ued | +0.004 |
Neg logit contributions | |
ucks | -0.009 |
iring | -0.009 |
mosquitoes | -0.008 |
check | -0.008 |
adoes | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
sel | +0.024 |
| +0.022 |
ued | +0.022 |
None | +0.021 |
chie | +0.021 |
Neg logit contributions | |
iring | -0.035 |
eddy | -0.034 |
ucks | -0.034 |
fort | -0.033 |
check | -0.032 |
Token | Molly |
Token ID | 30236 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
| +0.007 |
sel | +0.007 |
none | +0.006 |
None | +0.006 |
ued | +0.006 |
Neg logit contributions | |
eddy | -0.008 |
ucks | -0.008 |
iring | -0.007 |
fort | -0.007 |
check | -0.007 |
Token | opened |
Token ID | 4721 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
iring | +0.016 |
ucks | +0.015 |
eddy | +0.015 |
imi | +0.015 |
mosquitoes | +0.015 |
Neg logit contributions | |
sel | -0.012 |
| -0.011 |
ued | -0.011 |
top | -0.011 |
None | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
sel | +0.014 |
ued | +0.013 |
chie | +0.013 |
None | +0.012 |
| +0.012 |
Neg logit contributions | |
iring | -0.008 |
eddy | -0.007 |
ucks | -0.007 |
fort | -0.007 |
imi | -0.007 |
Token | drawer |
Token ID | 33451 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ucks | +0.009 |
iring | +0.009 |
mosquitoes | +0.009 |
eddy | +0.009 |
imi | +0.008 |
Neg logit contributions | |
sel | -0.008 |
| -0.007 |
ued | -0.007 |
top | -0.007 |
chie | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
sel | +0.038 |
chie | +0.038 |
ued | +0.037 |
None | +0.036 |
| +0.035 |
Neg logit contributions | |
iring | -0.013 |
fort | -0.011 |
eddy | -0.011 |
ucks | -0.010 |
from | -0.010 |
Token | peek |
Token ID | 27185 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
sel | +0.005 |
| +0.005 |
ued | +0.005 |
top | +0.005 |
None | +0.004 |
Neg logit contributions | |
iring | -0.007 |
eddy | -0.007 |
ucks | -0.007 |
imi | -0.007 |
mosquitoes | -0.006 |
Token | ed |
Token ID | 276 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
sel | +0.027 |
ued | +0.024 |
chie | +0.024 |
| +0.023 |
None | +0.023 |
Neg logit contributions | |
iring | -0.024 |
eddy | -0.023 |
imi | -0.023 |
ucks | -0.023 |
mosquitoes | -0.022 |
Token | inside |
Token ID | 2641 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
sel | +0.011 |
| +0.010 |
ued | +0.010 |
top | +0.010 |
None | +0.010 |
Neg logit contributions | |
iring | -0.007 |
ucks | -0.007 |
imi | -0.007 |
eddy | -0.006 |
mosquitoes | -0.006 |
Token | olly |
Token ID | 5098 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
iring | +0.041 |
ucks | +0.041 |
eddy | +0.041 |
fort | +0.040 |
check | +0.040 |
Neg logit contributions | |
sel | -0.040 |
ued | -0.039 |
chie | -0.036 |
top | -0.035 |
None | -0.035 |
Token | asked |
Token ID | 1965 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
iring | +0.004 |
fort | +0.003 |
from | +0.003 |
pets | +0.003 |
check | +0.003 |
Neg logit contributions | |
sel | -0.006 |
chie | -0.006 |
ued | -0.005 |
None | -0.005 |
top | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
sel | +0.022 |
chie | +0.021 |
ued | +0.020 |
top | +0.019 |
None | +0.019 |
Neg logit contributions | |
iring | -0.012 |
eddy | -0.011 |
ucks | -0.011 |
imi | -0.010 |
accidents | -0.010 |
Token | " |
Token ID | 366 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
sel | +0.011 |
chie | +0.011 |
ued | +0.011 |
ret | +0.010 |
top | +0.010 |
Neg logit contributions | |
from | -0.005 |
iring | -0.005 |
Doctor | -0.004 |
honey | -0.004 |
chefs | -0.004 |
Token | What |
Token ID | 2061 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
sel | +0.067 |
ued | +0.064 |
chie | +0.063 |
| +0.062 |
None | +0.061 |
Neg logit contributions | |
iring | -0.039 |
eddy | -0.036 |
ucks | -0.036 |
fort | -0.035 |
imi | -0.034 |
Token | kind |
Token ID | 1611 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
iring | +0.015 |
ucks | +0.015 |
eddy | +0.014 |
fort | +0.014 |
imi | +0.013 |
Neg logit contributions | |
sel | -0.020 |
| -0.019 |
ued | -0.019 |
None | -0.019 |
none | -0.018 |
Token | of |
Token ID | 286 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
sel | +0.008 |
ued | +0.008 |
| +0.008 |
chie | +0.008 |
None | +0.008 |
Neg logit contributions | |
iring | -0.003 |
ucks | -0.003 |
eddy | -0.003 |
fort | -0.003 |
imi | -0.003 |
Token | test |
Token ID | 1332 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
iring | +0.035 |
ucks | +0.033 |
eddy | +0.032 |
fort | +0.032 |
mosquitoes | +0.032 |
Neg logit contributions | |
sel | -0.062 |
ued | -0.057 |
chie | -0.057 |
None | -0.056 |
| -0.055 |
Token | ?" |
Token ID | 1701 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
sel | +0.074 |
chie | +0.069 |
ued | +0.067 |
None | +0.067 |
top | +0.065 |
Neg logit contributions | |
iring | -0.038 |
accidents | -0.034 |
mosquitoes | -0.034 |
imi | -0.034 |
from | -0.033 |
Token | Her |
Token ID | 2332 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
sel | +0.029 |
chie | +0.027 |
ued | +0.026 |
top | +0.023 |
none | +0.023 |
Neg logit contributions | |
iring | -0.018 |
eddy | -0.017 |
imi | -0.017 |
ucks | -0.017 |
cartoons | -0.016 |
Token | mom |
Token ID | 1995 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
ucks | +0.008 |
iring | +0.008 |
check | +0.008 |
rim | +0.007 |
mosquitoes | +0.007 |
Neg logit contributions | |
| -0.010 |
None | -0.009 |
none | -0.009 |
One | -0.009 |
second | -0.009 |
Token | elderly |
Token ID | 13830 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
iring | +0.013 |
ucks | +0.013 |
eddy | +0.012 |
fort | +0.012 |
imi | +0.012 |
Neg logit contributions | |
sel | -0.017 |
ued | -0.016 |
chie | -0.016 |
| -0.015 |
None | -0.015 |
Token | lady |
Token ID | 10846 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
sel | +0.023 |
| +0.022 |
ued | +0.021 |
chie | +0.021 |
None | +0.021 |
Neg logit contributions | |
iring | -0.015 |
ucks | -0.014 |
fort | -0.013 |
accidents | -0.013 |
imi | -0.013 |
Token | named |
Token ID | 3706 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
iring | +0.008 |
mosquitoes | +0.007 |
accidents | +0.007 |
fort | +0.007 |
ucks | +0.007 |
Neg logit contributions | |
sel | -0.006 |
| -0.005 |
ued | -0.005 |
top | -0.005 |
None | -0.005 |
Token | Sue |
Token ID | 26089 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
sel | +0.082 |
ued | +0.078 |
chie | +0.078 |
top | +0.075 |
None | +0.074 |
Neg logit contributions | |
iring | -0.038 |
eddy | -0.035 |
ucks | -0.034 |
imi | -0.034 |
fort | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
iring | +0.006 |
ucks | +0.006 |
accidents | +0.006 |
mosquitoes | +0.006 |
cartoons | +0.006 |
Neg logit contributions | |
sel | -0.005 |
| -0.005 |
ued | -0.004 |
top | -0.004 |
One | -0.004 |
Token | walking |
Token ID | 6155 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
ucks | +0.009 |
iring | +0.009 |
eddy | +0.009 |
fort | +0.008 |
imi | +0.008 |
Neg logit contributions | |
| -0.011 |
sel | -0.010 |
ued | -0.010 |
chie | -0.010 |
none | -0.010 |
Token | in |
Token ID | 287 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
sel | +0.008 |
ued | +0.007 |
chie | +0.007 |
| +0.007 |
None | +0.007 |
Neg logit contributions | |
iring | -0.004 |
ucks | -0.004 |
eddy | -0.004 |
imi | -0.003 |
fort | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
sel | +0.013 |
| +0.013 |
ued | +0.012 |
chie | +0.012 |
None | +0.012 |
Neg logit contributions | |
iring | -0.012 |
ucks | -0.011 |
eddy | -0.011 |
imi | -0.011 |
fort | -0.011 |
Token | park |
Token ID | 3952 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
| +0.015 |
sel | +0.014 |
top | +0.014 |
One | +0.013 |
ued | +0.013 |
Neg logit contributions | |
iring | -0.013 |
ucks | -0.012 |
mosquitoes | -0.011 |
accidents | -0.011 |
imi | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
sel | +0.053 |
chie | +0.050 |
ued | +0.048 |
None | +0.044 |
ience | +0.044 |
Neg logit contributions | |
iring | -0.024 |
from | -0.022 |
ucks | -0.021 |
eddy | -0.020 |
fort | -0.020 |
Token | She |
Token ID | 1375 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
| +0.001 |
None | +0.001 |
One | +0.001 |
sel | +0.001 |
ued | +0.001 |
Neg logit contributions | |
iring | -0.001 |
eddy | -0.001 |
ucks | -0.001 |
imi | -0.001 |
accidents | -0.001 |
Token | You |
Token ID | 921 |
Feature activation | -8.46e-02 |
Pos logit contributions | |
iring | +0.026 |
eddy | +0.025 |
ucks | +0.024 |
fort | +0.023 |
imi | +0.023 |
Neg logit contributions | |
sel | -0.033 |
ued | -0.032 |
chie | -0.031 |
| -0.030 |
top | -0.030 |
Token | are |
Token ID | 389 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
sel | +0.002 |
ued | +0.002 |
chie | +0.002 |
| +0.002 |
None | +0.002 |
Neg logit contributions | |
iring | -0.002 |
eddy | -0.002 |
ucks | -0.002 |
fort | -0.002 |
imi | -0.002 |
Token | kind |
Token ID | 1611 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
| +0.010 |
sel | +0.010 |
none | +0.009 |
chie | +0.009 |
ued | +0.009 |
Neg logit contributions | |
ucks | -0.015 |
eddy | -0.015 |
iring | -0.015 |
imi | -0.014 |
fort | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
sel | +0.031 |
| +0.029 |
None | +0.028 |
chie | +0.028 |
top | +0.027 |
Neg logit contributions | |
iring | -0.039 |
imi | -0.037 |
ucks | -0.036 |
mosquitoes | -0.036 |
fort | -0.036 |
Token | depend |
Token ID | 4745 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
iring | +0.005 |
eddy | +0.005 |
ucks | +0.005 |
imi | +0.005 |
mosquitoes | +0.004 |
Neg logit contributions | |
sel | -0.006 |
chie | -0.006 |
ued | -0.006 |
| -0.006 |
top | -0.005 |
Token | able |
Token ID | 540 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
sel | +0.028 |
ued | +0.027 |
chie | +0.027 |
None | +0.025 |
| +0.024 |
Neg logit contributions | |
ucks | -0.028 |
eddy | -0.027 |
iring | -0.027 |
check | -0.026 |
mosquitoes | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
sel | +0.063 |
ued | +0.060 |
chie | +0.058 |
| +0.055 |
None | +0.055 |
Neg logit contributions | |
iring | -0.057 |
eddy | -0.054 |
ucks | -0.054 |
fort | -0.052 |
accidents | -0.051 |
Token | You |
Token ID | 921 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
iring | +0.030 |
eddy | +0.028 |
ucks | +0.028 |
fort | +0.027 |
imi | +0.027 |
Neg logit contributions | |
sel | -0.036 |
ued | -0.034 |
chie | -0.034 |
| -0.033 |
None | -0.032 |
Token | are |
Token ID | 389 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
sel | +0.005 |
ued | +0.005 |
chie | +0.005 |
| +0.005 |
None | +0.005 |
Neg logit contributions | |
iring | -0.004 |
eddy | -0.004 |
ucks | -0.004 |
fort | -0.004 |
imi | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
sel | +0.010 |
| +0.010 |
chie | +0.010 |
none | +0.010 |
ued | +0.010 |
Neg logit contributions | |
ucks | -0.013 |
iring | -0.013 |
eddy | -0.013 |
imi | -0.012 |
fort | -0.012 |
Token | true |
Token ID | 2081 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
iring | +0.004 |
ucks | +0.003 |
eddy | +0.003 |
imi | +0.003 |
fort | +0.003 |
Neg logit contributions | |
sel | -0.005 |
chie | -0.004 |
ued | -0.004 |
| -0.004 |
None | -0.004 |
Token | bricks |
Token ID | 28902 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
iring | +0.002 |
fort | +0.002 |
eddy | +0.002 |
mosquitoes | +0.002 |
imi | +0.001 |
Neg logit contributions | |
sel | -0.004 |
ued | -0.004 |
chie | -0.003 |
None | -0.003 |
| -0.003 |
Token | of |
Token ID | 286 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
iring | +0.057 |
accidents | +0.053 |
from | +0.053 |
fort | +0.052 |
dust | +0.051 |
Neg logit contributions | |
sel | -0.058 |
chie | -0.055 |
ued | -0.052 |
None | -0.052 |
| -0.049 |
Token | the |
Token ID | 262 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
mosquitoes | +0.043 |
cartoons | +0.042 |
iring | +0.042 |
accidents | +0.041 |
honey | +0.041 |
Neg logit contributions | |
sel | -0.092 |
ued | -0.090 |
chie | -0.085 |
ical | -0.084 |
None | -0.083 |
Token | house |
Token ID | 2156 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
sel | +0.006 |
ued | +0.006 |
chie | +0.006 |
None | +0.006 |
| +0.006 |
Neg logit contributions | |
fort | -0.003 |
iring | -0.003 |
eddy | -0.003 |
mosquitoes | -0.003 |
cartoons | -0.003 |
Token | were |
Token ID | 547 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
iring | +0.001 |
from | +0.001 |
fort | +0.001 |
accidents | +0.001 |
dust | +0.001 |
Neg logit contributions | |
chie | -0.002 |
sel | -0.002 |
ued | -0.002 |
None | -0.002 |
ical | -0.002 |
Token | cracked |
Token ID | 21368 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
sel | +0.017 |
ued | +0.016 |
chie | +0.016 |
None | +0.015 |
| +0.015 |
Neg logit contributions | |
iring | -0.011 |
fort | -0.010 |
eddy | -0.010 |
accidents | -0.010 |
mosquitoes | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
ued | +0.015 |
sel | +0.014 |
chie | +0.014 |
None | +0.014 |
| +0.014 |
Neg logit contributions | |
iring | -0.008 |
eddy | -0.008 |
fort | -0.007 |
ucks | -0.007 |
accidents | -0.007 |
Token | ch |
Token ID | 442 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
sel | +0.022 |
ued | +0.021 |
chie | +0.021 |
None | +0.020 |
ical | +0.020 |
Neg logit contributions | |
accidents | -0.014 |
honey | -0.014 |
dust | -0.013 |
mosquitoes | -0.013 |
iring | -0.013 |
Token | ipped |
Token ID | 3949 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
iring | +0.006 |
ucks | +0.006 |
mosquitoes | +0.005 |
imi | +0.005 |
eddy | +0.005 |
Neg logit contributions | |
sel | -0.008 |
| -0.008 |
ued | -0.008 |
top | -0.007 |
None | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
chie | +0.044 |
sel | +0.044 |
ued | +0.043 |
None | +0.041 |
ical | +0.039 |
Neg logit contributions | |
from | -0.019 |
fort | -0.017 |
dust | -0.016 |
iring | -0.016 |
honey | -0.015 |
Token | Some |
Token ID | 2773 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
sel | +0.007 |
chie | +0.006 |
ued | +0.006 |
arest | +0.005 |
ounded | +0.005 |
Neg logit contributions | |
Doctor | -0.004 |
Luna | -0.004 |
iring | -0.003 |
Nurse | -0.003 |
ucks | -0.003 |
Token | liked |
Token ID | 8288 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
iring | +0.016 |
ucks | +0.015 |
eddy | +0.015 |
imi | +0.014 |
mosquitoes | +0.014 |
Neg logit contributions | |
sel | -0.013 |
| -0.012 |
ued | -0.012 |
chie | -0.012 |
top | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
iring | +0.023 |
ucks | +0.021 |
eddy | +0.021 |
imi | +0.021 |
fort | +0.020 |
Neg logit contributions | |
sel | -0.025 |
| -0.024 |
ued | -0.023 |
top | -0.023 |
chie | -0.023 |
Token | go |
Token ID | 467 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
iring | +0.005 |
ucks | +0.005 |
eddy | +0.005 |
fort | +0.005 |
imi | +0.005 |
Neg logit contributions | |
sel | -0.009 |
ued | -0.008 |
chie | -0.008 |
None | -0.008 |
| -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
iring | +0.012 |
eddy | +0.011 |
ucks | +0.011 |
fort | +0.010 |
imi | +0.010 |
Neg logit contributions | |
sel | -0.020 |
ued | -0.019 |
chie | -0.019 |
| -0.018 |
None | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
iring | +0.022 |
eddy | +0.021 |
ucks | +0.021 |
fort | +0.020 |
imi | +0.020 |
Neg logit contributions | |
sel | -0.032 |
ued | -0.030 |
chie | -0.030 |
None | -0.028 |
| -0.028 |
Token | grocery |
Token ID | 16918 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
iring | +0.001 |
ucks | +0.001 |
imi | +0.001 |
eddy | +0.001 |
accidents | +0.001 |
Neg logit contributions | |
sel | -0.001 |
| -0.001 |
top | -0.001 |
ued | -0.001 |
None | -0.001 |
Token | store |
Token ID | 3650 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
sel | +0.026 |
chie | +0.025 |
ued | +0.025 |
None | +0.024 |
| +0.022 |
Neg logit contributions | |
iring | -0.018 |
fort | -0.017 |
eddy | -0.017 |
ucks | -0.016 |
from | -0.016 |
Token | because |
Token ID | 780 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
chie | +0.050 |
sel | +0.049 |
ued | +0.049 |
None | +0.046 |
| +0.044 |
Neg logit contributions | |
iring | -0.025 |
from | -0.022 |
eddy | -0.022 |
ucks | -0.021 |
fort | -0.020 |
Token | she |
Token ID | 673 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
iring | +0.038 |
ucks | +0.037 |
eddy | +0.037 |
fort | +0.036 |
imi | +0.036 |
Neg logit contributions | |
sel | -0.033 |
| -0.031 |
ued | -0.031 |
None | -0.030 |
top | -0.030 |
Token | could |
Token ID | 714 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
sel | +0.018 |
ued | +0.016 |
chie | +0.016 |
| +0.016 |
top | +0.015 |
Neg logit contributions | |
iring | -0.024 |
ucks | -0.023 |
eddy | -0.023 |
fort | -0.023 |
mosquitoes | -0.022 |
Token | see |
Token ID | 766 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
iring | +0.011 |
eddy | +0.011 |
ucks | +0.010 |
imi | +0.010 |
fort | +0.010 |
Neg logit contributions | |
sel | -0.012 |
ued | -0.012 |
| -0.012 |
chie | -0.011 |
None | -0.011 |
Token | slide |
Token ID | 10649 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
sel | +0.001 |
ued | +0.001 |
chie | +0.001 |
| +0.001 |
None | +0.000 |
Neg logit contributions | |
iring | -0.000 |
eddy | -0.000 |
ucks | -0.000 |
fort | -0.000 |
imi | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
sel | +0.030 |
chie | +0.028 |
ued | +0.027 |
None | +0.026 |
ical | +0.026 |
Neg logit contributions | |
iring | -0.014 |
from | -0.012 |
eddy | -0.011 |
fort | -0.011 |
ucks | -0.010 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
sel | +0.021 |
chie | +0.020 |
ued | +0.019 |
None | +0.018 |
top | +0.018 |
Neg logit contributions | |
iring | -0.017 |
mosquitoes | -0.016 |
accidents | -0.015 |
honey | -0.015 |
pets | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
sel | +0.009 |
ued | +0.008 |
chie | +0.008 |
ical | +0.008 |
pool | +0.007 |
Neg logit contributions | |
honey | -0.002 |
from | -0.002 |
snow | -0.001 |
accidents | -0.001 |
doctors | -0.001 |
Token | go |
Token ID | 467 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
iring | +0.008 |
eddy | +0.007 |
ucks | +0.007 |
imi | +0.007 |
fort | +0.007 |
Neg logit contributions | |
sel | -0.013 |
ued | -0.013 |
| -0.013 |
chie | -0.013 |
None | -0.012 |
Token | down |
Token ID | 866 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
iring | +0.005 |
ucks | +0.005 |
eddy | +0.005 |
fort | +0.004 |
imi | +0.004 |
Neg logit contributions | |
sel | -0.011 |
ued | -0.011 |
chie | -0.011 |
None | -0.010 |
| -0.010 |
Token | it |
Token ID | 340 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
sel | +0.023 |
chie | +0.021 |
ical | +0.021 |
ued | +0.021 |
None | +0.019 |
Neg logit contributions | |
from | -0.009 |
iring | -0.008 |
ucks | -0.008 |
mosquitoes | -0.008 |
eddy | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
sel | +0.007 |
chie | +0.006 |
ued | +0.006 |
None | +0.006 |
ical | +0.006 |
Neg logit contributions | |
from | -0.003 |
fort | -0.003 |
outside | -0.003 |
iring | -0.002 |
here | -0.002 |
Token | She |
Token ID | 1375 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
sel | +0.028 |
chie | +0.026 |
ued | +0.026 |
top | +0.024 |
None | +0.024 |
Neg logit contributions | |
iring | -0.019 |
eddy | -0.017 |
ucks | -0.017 |
fort | -0.017 |
imi | -0.017 |
Token | took |
Token ID | 1718 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
iring | +0.001 |
ucks | +0.001 |
eddy | +0.001 |
fort | +0.001 |
imi | +0.001 |
Neg logit contributions | |
sel | -0.002 |
chie | -0.001 |
ued | -0.001 |
None | -0.001 |
top | -0.001 |
Token | off |
Token ID | 572 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
iring | +0.000 |
eddy | +0.000 |
imi | +0.000 |
ucks | +0.000 |
fort | +0.000 |
Neg logit contributions | |
sel | -0.001 |
| -0.000 |
ued | -0.000 |
chie | -0.000 |
None | -0.000 |
Token | make |
Token ID | 787 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
sel | +0.027 |
ued | +0.026 |
chie | +0.024 |
None | +0.024 |
top | +0.024 |
Neg logit contributions | |
from | -0.008 |
wake | -0.007 |
sleep | -0.007 |
honey | -0.007 |
mess | -0.007 |
Token | him |
Token ID | 683 |
Feature activation | +6.96e-02 |
Pos logit contributions | |
sel | +0.016 |
ued | +0.016 |
chie | +0.016 |
None | +0.015 |
| +0.015 |
Neg logit contributions | |
iring | -0.010 |
eddy | -0.009 |
ucks | -0.009 |
fort | -0.009 |
accidents | -0.009 |
Token | learn |
Token ID | 2193 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
iring | +0.001 |
fort | +0.001 |
eddy | +0.001 |
cartoons | +0.001 |
ucks | +0.001 |
Neg logit contributions | |
sel | -0.002 |
ued | -0.002 |
chie | -0.002 |
None | -0.002 |
top | -0.002 |
Token | new |
Token ID | 649 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
sel | +0.053 |
chie | +0.052 |
ued | +0.051 |
None | +0.049 |
top | +0.048 |
Neg logit contributions | |
iring | -0.025 |
from | -0.025 |
accidents | -0.023 |
fort | -0.023 |
eddy | -0.023 |
Token | things |
Token ID | 1243 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
sel | +0.040 |
ued | +0.038 |
chie | +0.038 |
None | +0.036 |
top | +0.036 |
Neg logit contributions | |
iring | -0.017 |
ucks | -0.015 |
eddy | -0.015 |
fort | -0.015 |
accidents | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
from | +0.021 |
iring | +0.020 |
eddy | +0.018 |
accidents | +0.018 |
fort | +0.017 |
Neg logit contributions | |
sel | -0.036 |
chie | -0.036 |
ued | -0.035 |
None | -0.034 |
| -0.032 |
Token | have |
Token ID | 423 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
sel | +0.020 |
ued | +0.019 |
chie | +0.019 |
| +0.019 |
None | +0.019 |
Neg logit contributions | |
iring | -0.013 |
eddy | -0.012 |
ucks | -0.012 |
fort | -0.012 |
imi | -0.011 |
Token | new |
Token ID | 649 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
chie | +0.020 |
ued | +0.020 |
sel | +0.020 |
ical | +0.019 |
pool | +0.018 |
Neg logit contributions | |
honey | -0.007 |
friends | -0.007 |
animals | -0.006 |
snow | -0.006 |
pets | -0.006 |
Token | adventures |
Token ID | 17545 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
sel | +0.036 |
chie | +0.035 |
ued | +0.035 |
None | +0.033 |
top | +0.033 |
Neg logit contributions | |
ucks | -0.012 |
iring | -0.012 |
fort | -0.012 |
pets | -0.012 |
honey | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
chie | +0.038 |
ued | +0.038 |
sel | +0.037 |
None | +0.037 |
| +0.034 |
Neg logit contributions | |
from | -0.022 |
eddy | -0.021 |
iring | -0.020 |
cartoons | -0.019 |
fort | -0.019 |
Token | He |
Token ID | 679 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
iring | +0.023 |
ucks | +0.023 |
eddy | +0.022 |
fort | +0.021 |
Doctor | +0.021 |
Neg logit contributions | |
sel | -0.035 |
chie | -0.034 |
ued | -0.034 |
top | -0.030 |
none | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
sel | +0.026 |
chie | +0.024 |
none | +0.023 |
ical | +0.022 |
ience | +0.022 |
Neg logit contributions | |
ucks | -0.009 |
eddy | -0.009 |
iring | -0.008 |
imi | -0.007 |
Luna | -0.007 |
Token | They |
Token ID | 2990 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
sel | +0.043 |
chie | +0.038 |
none | +0.037 |
ued | +0.037 |
None | +0.036 |
Neg logit contributions | |
iring | -0.023 |
eddy | -0.021 |
mosquitoes | -0.021 |
check | -0.020 |
ucks | -0.020 |
Token | both |
Token ID | 1111 |
Feature activation | +6.46e-03 |
Pos logit contributions | |
dust | +0.009 |
from | +0.009 |
check | +0.008 |
pets | +0.008 |
iring | +0.008 |
Neg logit contributions | |
chie | -0.014 |
sel | -0.014 |
ued | -0.014 |
None | -0.013 |
ical | -0.013 |
Token | wanted |
Token ID | 2227 |
Feature activation | -5.67e-02 |
Pos logit contributions | |
dust | +0.000 |
from | +0.000 |
itch | +0.000 |
pets | +0.000 |
friends | +0.000 |
Neg logit contributions | |
chie | -0.000 |
ued | -0.000 |
sel | -0.000 |
None | -0.000 |
side | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
sel | +0.002 |
chie | +0.002 |
ued | +0.002 |
None | +0.002 |
ical | +0.002 |
Neg logit contributions | |
iring | -0.001 |
from | -0.001 |
accidents | -0.001 |
mosquitoes | -0.001 |
honey | -0.001 |
Token | win |
Token ID | 1592 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
iring | +0.003 |
eddy | +0.003 |
ucks | +0.003 |
fort | +0.003 |
imi | +0.003 |
Neg logit contributions | |
sel | -0.006 |
ued | -0.006 |
chie | -0.005 |
| -0.005 |
None | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
sel | +0.146 |
ued | +0.140 |
bar | +0.139 |
chie | +0.136 |
ical | +0.135 |
Neg logit contributions | |
from | -0.053 |
about | -0.042 |
accidents | -0.040 |
animals | -0.040 |
friends | -0.039 |
Token | delicate |
Token ID | 19217 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
fort | +0.023 |
honey | +0.022 |
mosquitoes | +0.022 |
iring | +0.022 |
from | +0.020 |
Neg logit contributions | |
sel | -0.045 |
None | -0.043 |
| -0.042 |
chie | -0.042 |
top | -0.041 |
Token | flower |
Token ID | 15061 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
fort | +0.004 |
honey | +0.004 |
iring | +0.004 |
mosquitoes | +0.004 |
eddy | +0.004 |
Neg logit contributions | |
sel | -0.013 |
chie | -0.012 |
ued | -0.012 |
None | -0.012 |
| -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
fort | +0.017 |
from | +0.017 |
iring | +0.017 |
honey | +0.016 |
mosquitoes | +0.016 |
Neg logit contributions | |
sel | -0.031 |
ued | -0.029 |
chie | -0.029 |
None | -0.028 |
top | -0.027 |
Token | so |
Token ID | 523 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
sel | +0.046 |
ued | +0.044 |
chie | +0.043 |
None | +0.042 |
top | +0.041 |
Neg logit contributions | |
iring | -0.026 |
fort | -0.023 |
ucks | -0.023 |
mosquitoes | -0.023 |
eddy | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
sel | +0.042 |
chie | +0.041 |
ued | +0.040 |
None | +0.039 |
top | +0.037 |
Neg logit contributions | |
fort | -0.030 |
eddy | -0.030 |
from | -0.030 |
iring | -0.029 |
honey | -0.029 |
Token | He |
Token ID | 679 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
iring | +0.019 |
eddy | +0.018 |
ucks | +0.018 |
imi | +0.017 |
fort | +0.016 |
Neg logit contributions | |
sel | -0.018 |
ued | -0.018 |
chie | -0.017 |
top | -0.016 |
None | -0.016 |
Token | is |
Token ID | 318 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
sel | +0.022 |
chie | +0.021 |
ued | +0.021 |
None | +0.021 |
| +0.020 |
Neg logit contributions | |
iring | -0.013 |
ucks | -0.012 |
eddy | -0.012 |
fort | -0.011 |
check | -0.011 |
Token | in |
Token ID | 287 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
sel | +0.016 |
ued | +0.015 |
chie | +0.015 |
None | +0.015 |
| +0.014 |
Neg logit contributions | |
iring | -0.011 |
eddy | -0.010 |
ucks | -0.009 |
fort | -0.009 |
mosquitoes | -0.009 |
Token | our |
Token ID | 674 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
ued | +0.044 |
sel | +0.044 |
chie | +0.043 |
None | +0.041 |
top | +0.040 |
Neg logit contributions | |
iring | -0.023 |
eddy | -0.022 |
from | -0.022 |
mosquitoes | -0.022 |
ucks | -0.022 |
Token | class |
Token ID | 1398 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
sel | +0.070 |
| +0.068 |
ued | +0.067 |
chie | +0.066 |
top | +0.066 |
Neg logit contributions | |
iring | -0.036 |
ucks | -0.032 |
eddy | -0.031 |
imi | -0.030 |
mosquitoes | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
sel | +0.156 |
chie | +0.154 |
None | +0.145 |
ued | +0.142 |
pool | +0.130 |
Neg logit contributions | |
from | -0.083 |
fort | -0.081 |
room | -0.080 |
mess | -0.078 |
about | -0.076 |
Token | He |
Token ID | 679 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
iring | +0.016 |
ucks | +0.016 |
eddy | +0.016 |
imi | +0.015 |
fort | +0.015 |
Neg logit contributions | |
sel | -0.016 |
ued | -0.016 |
chie | -0.016 |
top | -0.015 |
None | -0.014 |
Token | is |
Token ID | 318 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
sel | +0.018 |
chie | +0.018 |
ued | +0.017 |
None | +0.017 |
| +0.017 |
Neg logit contributions | |
iring | -0.010 |
ucks | -0.010 |
eddy | -0.010 |
fort | -0.009 |
imi | -0.009 |
Token | nice |
Token ID | 3621 |
Feature activation | +6.98e-03 |
Pos logit contributions | |
sel | +0.017 |
ued | +0.016 |
chie | +0.016 |
None | +0.015 |
| +0.015 |
Neg logit contributions | |
iring | -0.011 |
eddy | -0.010 |
ucks | -0.010 |
fort | -0.010 |
mosquitoes | -0.010 |
Token | ." |
Token ID | 526 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
iring | +0.000 |
ucks | +0.000 |
eddy | +0.000 |
imi | +0.000 |
fort | +0.000 |
Neg logit contributions | |
sel | -0.000 |
ued | -0.000 |
chie | -0.000 |
| -0.000 |
None | -0.000 |
Token | see |
Token ID | 766 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
cartoons | +0.002 |
fort | +0.002 |
itch | +0.002 |
mosquitoes | +0.002 |
check | +0.002 |
Neg logit contributions | |
sel | -0.007 |
ued | -0.006 |
chie | -0.006 |
None | -0.006 |
top | -0.006 |
Token | who |
Token ID | 508 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
sel | +0.022 |
ued | +0.021 |
chie | +0.021 |
None | +0.020 |
ical | +0.020 |
Neg logit contributions | |
iring | -0.011 |
from | -0.010 |
eddy | -0.009 |
accidents | -0.009 |
animals | -0.009 |
Token | could |
Token ID | 714 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
sel | +0.052 |
ued | +0.049 |
chie | +0.049 |
None | +0.046 |
ical | +0.045 |
Neg logit contributions | |
from | -0.036 |
iring | -0.035 |
check | -0.033 |
mosquitoes | -0.033 |
dust | -0.032 |
Token | hide |
Token ID | 7808 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
sel | +0.004 |
ued | +0.004 |
chie | +0.004 |
| +0.004 |
None | +0.004 |
Neg logit contributions | |
iring | -0.002 |
eddy | -0.002 |
ucks | -0.002 |
fort | -0.002 |
imi | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
iring | +0.006 |
from | +0.006 |
fort | +0.005 |
mosquitoes | +0.005 |
accidents | +0.005 |
Neg logit contributions | |
ued | -0.014 |
sel | -0.014 |
None | -0.014 |
| -0.014 |
chie | -0.013 |
Token | quickest |
Token ID | 46264 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
iring | +0.004 |
eddy | +0.004 |
fort | +0.004 |
ucks | +0.004 |
mosquitoes | +0.004 |
Neg logit contributions | |
sel | -0.007 |
ued | -0.007 |
chie | -0.007 |
| -0.007 |
None | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
sel | +0.103 |
ued | +0.099 |
chie | +0.097 |
| +0.093 |
None | +0.092 |
Neg logit contributions | |
fort | -0.065 |
iring | -0.060 |
from | -0.059 |
mosquitoes | -0.058 |
wolves | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
sel | +0.025 |
chie | +0.024 |
ued | +0.023 |
none | +0.020 |
pe | +0.020 |
Neg logit contributions | |
iring | -0.017 |
Doctor | -0.017 |
ucks | -0.017 |
eddy | -0.016 |
check | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
sel | +0.015 |
chie | +0.014 |
none | +0.012 |
ical | +0.012 |
ued | +0.012 |
Neg logit contributions | |
iring | -0.008 |
eddy | -0.008 |
ucks | -0.008 |
imi | -0.008 |
fort | -0.007 |
Token | The |
Token ID | 464 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
sel | +0.030 |
chie | +0.027 |
ued | +0.026 |
None | +0.025 |
top | +0.025 |
Neg logit contributions | |
iring | -0.023 |
check | -0.021 |
eddy | -0.021 |
mosquitoes | -0.020 |
ucks | -0.020 |
Token | little |
Token ID | 1310 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
sel | +0.040 |
chie | +0.038 |
ued | +0.038 |
None | +0.037 |
top | +0.037 |
Neg logit contributions | |
iring | -0.015 |
fort | -0.014 |
eddy | -0.014 |
imi | -0.013 |
mosquitoes | -0.013 |
Token | eating |
Token ID | 6600 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
accidents | +0.011 |
iring | +0.011 |
mosquitoes | +0.010 |
eddy | +0.010 |
fort | +0.010 |
Neg logit contributions | |
sel | -0.017 |
chie | -0.016 |
ued | -0.015 |
top | -0.015 |
None | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
mosquitoes | +0.011 |
accidents | +0.011 |
iring | +0.010 |
honey | +0.010 |
fort | +0.010 |
Neg logit contributions | |
sel | -0.024 |
chie | -0.023 |
ued | -0.023 |
None | -0.022 |
| -0.021 |
Token | playing |
Token ID | 2712 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
sel | +0.028 |
ued | +0.026 |
chie | +0.026 |
None | +0.025 |
| +0.025 |
Neg logit contributions | |
iring | -0.015 |
eddy | -0.014 |
ucks | -0.014 |
fort | -0.013 |
accidents | -0.013 |
Token | by |
Token ID | 416 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
fort | +0.004 |
cartoons | +0.004 |
iring | +0.004 |
mosquitoes | +0.004 |
accidents | +0.004 |
Neg logit contributions | |
sel | -0.012 |
chie | -0.011 |
ued | -0.011 |
None | -0.010 |
top | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
cartoons | +0.009 |
accidents | +0.009 |
friends | +0.008 |
animals | +0.008 |
mess | +0.008 |
Neg logit contributions | |
sel | -0.023 |
ued | -0.022 |
ical | -0.021 |
chie | -0.021 |
pool | -0.020 |
Token | rules |
Token ID | 3173 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
iring | +0.008 |
ucks | +0.008 |
imi | +0.007 |
eddy | +0.007 |
accidents | +0.007 |
Neg logit contributions | |
sel | -0.011 |
ued | -0.010 |
top | -0.010 |
| -0.010 |
chie | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
sel | +0.106 |
chie | +0.105 |
ued | +0.098 |
None | +0.095 |
ical | +0.092 |
Neg logit contributions | |
from | -0.060 |
about | -0.050 |
iring | -0.050 |
eddy | -0.049 |
cartoons | -0.049 |
Token | Jack |
Token ID | 3619 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
chie | +0.004 |
sel | +0.004 |
ued | +0.004 |
pe | +0.003 |
arest | +0.003 |
Neg logit contributions | |
fort | -0.003 |
cartoons | -0.003 |
iring | -0.003 |
ucks | -0.003 |
about | -0.003 |
Token | always |
Token ID | 1464 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
eddy | +0.009 |
iring | +0.009 |
imi | +0.009 |
fort | +0.009 |
pets | +0.009 |
Neg logit contributions | |
sel | -0.014 |
chie | -0.014 |
ued | -0.013 |
None | -0.013 |
top | -0.012 |
Token | tried |
Token ID | 3088 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
sel | +0.010 |
chie | +0.010 |
ued | +0.010 |
None | +0.009 |
top | +0.009 |
Neg logit contributions | |
ucks | -0.006 |
imi | -0.006 |
check | -0.006 |
pets | -0.006 |
eddy | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
sel | +0.022 |
chie | +0.021 |
ued | +0.021 |
None | +0.019 |
top | +0.019 |
Neg logit contributions | |
iring | -0.012 |
accidents | -0.011 |
mosquitoes | -0.011 |
eddy | -0.011 |
ucks | -0.011 |
Token | ; |
Token ID | 26 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
iring | +0.011 |
eddy | +0.010 |
fort | +0.010 |
imi | +0.010 |
accidents | +0.010 |
Neg logit contributions | |
sel | -0.014 |
ued | -0.013 |
chie | -0.012 |
None | -0.012 |
| -0.012 |
Token | our |
Token ID | 674 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
sel | +0.029 |
ued | +0.027 |
chie | +0.027 |
| +0.026 |
None | +0.026 |
Neg logit contributions | |
iring | -0.024 |
eddy | -0.023 |
ucks | -0.023 |
fort | -0.022 |
imi | -0.022 |
Token | music |
Token ID | 2647 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
sel | +0.022 |
ued | +0.021 |
chie | +0.021 |
| +0.020 |
None | +0.020 |
Neg logit contributions | |
iring | -0.011 |
eddy | -0.011 |
ucks | -0.010 |
fort | -0.010 |
imi | -0.010 |
Token | is |
Token ID | 318 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
sel | +0.060 |
ued | +0.056 |
chie | +0.056 |
None | +0.055 |
| +0.053 |
Neg logit contributions | |
fort | -0.035 |
iring | -0.035 |
eddy | -0.034 |
accidents | -0.033 |
from | -0.033 |
Token | still |
Token ID | 991 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
sel | +0.062 |
ued | +0.058 |
chie | +0.057 |
None | +0.056 |
top | +0.055 |
Neg logit contributions | |
iring | -0.036 |
accidents | -0.034 |
eddy | -0.033 |
mosquitoes | -0.033 |
fort | -0.033 |
Token | sounding |
Token ID | 22655 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
sel | +0.036 |
ued | +0.034 |
chie | +0.034 |
None | +0.033 |
| +0.032 |
Neg logit contributions | |
iring | -0.021 |
eddy | -0.020 |
fort | -0.019 |
accidents | -0.019 |
mosquitoes | -0.018 |
Token | great |
Token ID | 1049 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
sel | +0.107 |
ued | +0.100 |
chie | +0.099 |
None | +0.099 |
top | +0.094 |
Neg logit contributions | |
from | -0.058 |
accidents | -0.055 |
iring | -0.054 |
mess | -0.051 |
cartoons | -0.051 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
sel | +0.039 |
chie | +0.037 |
ued | +0.037 |
None | +0.036 |
| +0.036 |
Neg logit contributions | |
iring | -0.031 |
eddy | -0.030 |
fort | -0.029 |
accidents | -0.029 |
ucks | -0.028 |
Token | Everyone |
Token ID | 11075 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
sel | +0.042 |
chie | +0.040 |
ued | +0.037 |
none | +0.034 |
ical | +0.033 |
Neg logit contributions | |
from | -0.022 |
Doctor | -0.021 |
Nurse | -0.019 |
cartoons | -0.019 |
Luna | -0.018 |
Token | laughed |
Token ID | 13818 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
sel | +0.019 |
chie | +0.017 |
None | +0.017 |
top | +0.017 |
ical | +0.016 |
Neg logit contributions | |
from | -0.014 |
iring | -0.013 |
accidents | -0.012 |
about | -0.012 |
eddy | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
sel | +0.002 |
chie | +0.002 |
ued | +0.002 |
top | +0.002 |
None | +0.002 |
Neg logit contributions | |
iring | -0.001 |
eddy | -0.001 |
from | -0.000 |
accidents | -0.000 |
ucks | -0.000 |