TOP ACTIVATIONS
MAX = 5.966

day ever ! <|endoftext|> Mor ris was very excited . Today
the sun rises in the opposite direction ". Jack thought this
saw the great big Fer ris wheel and all the other
wanted to enter a cooking competition . Tim my was so
Jake started to run in opposite directions . Ber
's go on the fer ris wheel and see the whole
' d oll ' in Spanish . Lily , can you
old lady with a mis chie vous tw inkle in her
15 kilograms . Average for age : 3 years ."
they were walking in the opposite way . Jack
means ' car ' in English . Now , can you
could count and solve simple maths problems . Everyone cl apped
was determined to be the vict or . But
off the fence in the opposite direction . He fell on
only out for her own win . The fox
' l ion ' in Spanish . It is ' leon
man , and asked quizz ically , " Why does everyone
ready to run in the opposite direction . Instead , he
and started walking in the opposite way . After a while
soldier ran off in the opposite direction . Everything had happened

MIN ACTIVATIONS
MIN = -5.627

. Good night ." She c uddled her t eddy bear
feeling better soon . She c uddled up with her favorite
actus was complete . The c actus and the bird were
tired from playing . They c uddled with their t eddy
a little better . She c uddled with her mom and
actus was happy . The c actus was complete . The
no longer miserable . He c uddled up with the fabric
to his bed . He c uddled up under his blankets
Then , she put her t eddy bear back on the
the wonderful things ! They c uddled the baby and spoiled
on dry clothes . They c uddled with their dog and
into their beds . They c uddled with their t eddy
. They yawn . They c uddle with their t eddy
by the fireplace . They c uddled on the sofa .
happy and tired . They c uddled on the sofa and
she loved him . They c uddled on the couch and
baby ." They c uddled in the chair and
him a treat . They c uddled with him on the
actus was taller . The c actus was happy . The
a story . They all c uddled and laughed and enjoyed

INTERVAL 3.068 - 5.966
CONTAINS 0.168%

to be in the next show . Her brother was waiting
handed each slice to her children . They were so excited
to the sky in a show of thanks .
mom took her to the veterinarian . As they arrived at
pile of garbage on the street . He thought it was

INTERVAL 0.170 - 3.068
CONTAINS 43.003%

that the driver was stuck trying to fix the engine .
closer and saw a little girl playing in the water with
trunk . She liked to use her trunk to pick up
animals . She had a lion , a monkey , a
thin ." Lily said . They climbed the tree

INTERVAL -2.728 - 0.170
CONTAINS 56.391%

did everything together . One day , they
time , there was a little boy named Tim my .
match was always looking for things to play with .
race at his school . Tim was very excited to run
into the lemon , her face turned sour . The lemon

INTERVAL -5.627 - -2.728
CONTAINS 0.438%

The squirrel threw the peanut to Tom and Mia .
every day . She would drink from her big cup with
gob bled up the delicious berries until they were full .
a blanket , enjoying a cozy cup of hot chocolate .
that he let Benny take as many potatoes as he wanted
Token day
Token ID1110
Feature activation-5.40e-01

Pos logit contributions
 accidents+0.054
 bleed+0.054
 itch+0.053
burn+0.047
 stain+0.047
Neg logit contributions
ued-0.050
bank-0.050
roads-0.047
boat-0.045
mer-0.041
Token ever
Token ID1683
Feature activation-1.53e+00

Pos logit contributions
 accidents+0.008
 itch+0.006
 cookies+0.005
 babies+0.005
eddy+0.005
Neg logit contributions
ued-0.024
roads-0.023
bank-0.023
ving-0.022
ical-0.021
Token!
Token ID0
Feature activation-1.16e-01

Pos logit contributions
 accidents+0.035
 itch+0.031
 bleed+0.028
eddy+0.028
 stain+0.028
Neg logit contributions
ued-0.055
roads-0.052
bank-0.051
ving-0.049
ical-0.048
Token<|endoftext|>
Token ID50256
Feature activation+4.60e-01

Pos logit contributions
 accidents+0.002
eddy+0.002
 itch+0.002
 Mitt+0.002
 cat+0.002
Neg logit contributions
ued-0.004
roads-0.004
bank-0.004
ving-0.004
ical-0.004
TokenMor
Token ID20044
Feature activation+4.81e+00

Pos logit contributions
ued+0.016
bank+0.015
ical+0.015
roads+0.015
chie+0.014
Neg logit contributions
eddy-0.009
 accidents-0.009
 cat-0.009
 cookies-0.008
 from-0.008
Tokenris
Token ID2442
Feature activation+5.97e+00

Pos logit contributions
 gru+0.148
ued+0.145
bank+0.142
ical+0.136
roads+0.131
Neg logit contributions
 her-0.097
 kiss-0.094
eddy-0.094
 bless-0.093
 go-0.092
Token was
Token ID373
Feature activation+1.52e+00

Pos logit contributions
ued+0.217
roads+0.216
 gru+0.207
ical+0.203
bank+0.202
Neg logit contributions
 accidents-0.111
 itch-0.101
 stain-0.096
 babies-0.095
eddy-0.092
Token very
Token ID845
Feature activation+1.40e+00

Pos logit contributions
bank+0.062
ued+0.060
roads+0.059
sel+0.058
folk+0.057
Neg logit contributions
 itch-0.024
 accidents-0.019
 her-0.019
 cookies-0.017
 babies-0.016
Token excited
Token ID6568
Feature activation+3.13e-01

Pos logit contributions
bank+0.058
roads+0.058
ued+0.055
ical+0.054
sc+0.054
Neg logit contributions
 itch-0.019
 accidents-0.019
 her-0.018
 mom-0.016
 babies-0.016
Token.
Token ID13
Feature activation+1.44e+00

Pos logit contributions
ued+0.011
roads+0.010
bank+0.010
ving+0.010
sel+0.010
Neg logit contributions
 accidents-0.007
 itch-0.007
 bleed-0.006
 stain-0.006
eddy-0.006
Token Today
Token ID6288
Feature activation+2.55e-01

Pos logit contributions
ued+0.053
roads+0.047
ving+0.046
bank+0.045
mer+0.045
Neg logit contributions
 accidents-0.026
eddy-0.026
 her-0.025
 itch-0.024
 from-0.024
Token the
Token ID262
Feature activation+1.39e-01

Pos logit contributions
ued+0.049
bank+0.047
roads+0.046
ving+0.044
ical+0.044
Neg logit contributions
 accidents-0.029
 itch-0.025
 bleed-0.023
 cookies-0.022
 stain-0.022
Token sun
Token ID4252
Feature activation-2.03e+00

Pos logit contributions
ued+0.005
bank+0.005
roads+0.005
ving+0.005
ical+0.005
Neg logit contributions
 accidents-0.003
 itch-0.003
 bleed-0.002
 stain-0.002
eddy-0.002
Token rises
Token ID16736
Feature activation+8.94e-01

Pos logit contributions
 accidents+0.042
 itch+0.039
 bleed+0.036
eddy+0.034
 stain+0.033
Neg logit contributions
ued-0.072
bank-0.068
roads-0.068
ving-0.065
ical-0.064
Token in
Token ID287
Feature activation+1.04e+00

Pos logit contributions
ued+0.035
bank+0.033
roads+0.033
 gru+0.031
sel+0.031
Neg logit contributions
 accidents-0.016
 itch-0.015
 from-0.013
 bleed-0.012
burn-0.012
Token the
Token ID262
Feature activation+1.10e+00

Pos logit contributions
ued+0.042
bank+0.039
roads+0.038
ving+0.037
ical+0.037
Neg logit contributions
 accidents-0.021
 itch-0.018
 bleed-0.016
 stain-0.016
 cookies-0.015
Token opposite
Token ID6697
Feature activation+5.96e+00

Pos logit contributions
ued+0.035
bank+0.032
ving+0.031
roads+0.030
sel+0.030
Neg logit contributions
 itch-0.029
 accidents-0.029
 stain-0.026
 bleed-0.025
 cookies-0.024
Token direction
Token ID4571
Feature activation+2.79e+00

Pos logit contributions
ued+0.195
bank+0.174
ving+0.174
rob+0.168
sel+0.161
Neg logit contributions
 itch-0.144
 accidents-0.140
 mess-0.138
 from-0.132
 stain-0.123
Token".
Token ID1911
Feature activation+1.10e+00

Pos logit contributions
ued+0.107
bank+0.101
roads+0.098
ving+0.094
ical+0.093
Neg logit contributions
 accidents-0.057
 itch-0.048
 babies-0.047
 from-0.046
eddy-0.045
Token Jack
Token ID3619
Feature activation+1.16e-01

Pos logit contributions
ued+0.048
roads+0.043
boat+0.043
sel+0.042
chie+0.042
Neg logit contributions
 accidents-0.017
 itch-0.016
 cat-0.014
 Tom-0.013
 Mitt-0.013
Token thought
Token ID1807
Feature activation-5.96e-01

Pos logit contributions
ued+0.004
roads+0.004
bank+0.003
folk+0.003
sel+0.003
Neg logit contributions
 accidents-0.003
 itch-0.003
 stain-0.003
 bleed-0.003
 babies-0.002
Token this
Token ID428
Feature activation+5.76e-01

Pos logit contributions
 accidents+0.009
 itch+0.008
 cookies+0.006
 stain+0.006
 bleed+0.006
Neg logit contributions
bank-0.026
ued-0.026
roads-0.025
mer-0.025
sel-0.024
Token saw
Token ID2497
Feature activation-7.54e-01

Pos logit contributions
 accidents+0.020
 itch+0.020
 stain+0.018
 bleed+0.018
 cookies+0.017
Neg logit contributions
ued-0.025
bank-0.023
roads-0.023
ical-0.021
boat-0.021
Token the
Token ID262
Feature activation+2.34e-01

Pos logit contributions
 accidents+0.019
 bleed+0.019
 itch+0.018
 stain+0.017
eddy+0.017
Neg logit contributions
ued-0.023
roads-0.022
bank-0.021
 -0.019
top-0.019
Token great
Token ID1049
Feature activation+3.68e-01

Pos logit contributions
ued+0.007
roads+0.007
bank+0.007
ving+0.006
boat+0.006
Neg logit contributions
 accidents-0.006
 itch-0.006
 bleed-0.006
 stain-0.005
eddy-0.005
Token big
Token ID1263
Feature activation-2.98e-01

Pos logit contributions
ued+0.012
roads+0.011
bank+0.011
ving+0.010
boat+0.010
Neg logit contributions
 accidents-0.009
 itch-0.009
 bleed-0.009
 stain-0.008
 rash-0.008
Token Fer
Token ID12880
Feature activation+4.52e+00

Pos logit contributions
 accidents+0.008
 itch+0.007
 bleed+0.007
 stain+0.006
eddy+0.006
Neg logit contributions
ued-0.010
bank-0.009
roads-0.009
ving-0.008
sel-0.008
Tokenris
Token ID2442
Feature activation+5.87e+00

Pos logit contributions
ued+0.100
bank+0.087
ical+0.086
 gru+0.083
 ''+0.080
Neg logit contributions
eddy-0.152
 accidents-0.143
 itch-0.136
 stain-0.135
burn-0.133
Token wheel
Token ID7825
Feature activation+1.63e+00

Pos logit contributions
ued+0.178
bank+0.176
ical+0.170
 gru+0.168
sc+0.160
Neg logit contributions
 accidents-0.127
 grandma-0.127
 dog-0.125
 mom-0.121
 mess-0.119
Token and
Token ID290
Feature activation+3.99e-01

Pos logit contributions
ued+0.058
bank+0.053
roads+0.051
ical+0.051
 gru+0.051
Neg logit contributions
 accidents-0.036
 itch-0.034
 stain-0.031
 bleed-0.030
eddy-0.029
Token all
Token ID477
Feature activation+3.37e-02

Pos logit contributions
ued+0.013
bank+0.012
roads+0.011
ving+0.011
ical+0.011
Neg logit contributions
 accidents-0.011
 itch-0.010
 bleed-0.009
 stain-0.009
 cookies-0.009
Token the
Token ID262
Feature activation+1.12e+00

Pos logit contributions
ued+0.001
ical+0.001
bank+0.001
sel+0.001
ving+0.001
Neg logit contributions
 accidents-0.001
 itch-0.001
 her-0.001
 stain-0.001
 bleed-0.001
Token other
Token ID584
Feature activation+1.52e+00

Pos logit contributions
ued+0.045
bank+0.042
roads+0.041
ical+0.041
boat+0.040
Neg logit contributions
 accidents-0.022
 mess-0.020
 itch-0.019
 cookies-0.019
 babies-0.018
Token wanted
Token ID2227
Feature activation+9.42e-01

Pos logit contributions
ued+0.059
bank+0.053
roads+0.053
ving+0.049
ical+0.048
Neg logit contributions
 accidents-0.078
 itch-0.075
 bleed-0.071
 stain-0.068
eddy-0.067
Token to
Token ID284
Feature activation+3.49e-01

Pos logit contributions
ued+0.035
bank+0.032
roads+0.032
ving+0.031
ical+0.030
Neg logit contributions
 accidents-0.020
 itch-0.019
 bleed-0.017
 stain-0.016
 cookies-0.016
Token enter
Token ID3802
Feature activation+2.63e+00

Pos logit contributions
ued+0.012
bank+0.011
roads+0.011
ving+0.010
sel+0.010
Neg logit contributions
 accidents-0.008
 itch-0.007
 bleed-0.007
eddy-0.007
 stain-0.006
Token a
Token ID257
Feature activation+7.95e-01

Pos logit contributions
ued+0.109
bank+0.105
ical+0.099
ving+0.099
roads+0.098
Neg logit contributions
 accidents-0.048
 itch-0.041
 cookies-0.040
eddy-0.038
 her-0.038
Token cooking
Token ID10801
Feature activation+1.86e+00

Pos logit contributions
ued+0.027
bank+0.025
roads+0.025
ving+0.024
ical+0.024
Neg logit contributions
 accidents-0.019
 itch-0.018
 bleed-0.016
 stain-0.015
eddy-0.015
Token competition
Token ID5449
Feature activation+5.71e+00

Pos logit contributions
ued+0.073
bank+0.067
roads+0.065
ving+0.065
folk+0.064
Neg logit contributions
 accidents-0.035
 itch-0.034
 cookies-0.033
 stain-0.030
 mess-0.027
Token.
Token ID13
Feature activation-6.95e-02

Pos logit contributions
ued+0.237
sel+0.213
ving+0.211
bank+0.207
folk+0.201
Neg logit contributions
 from-0.094
 accidents-0.093
 cookies-0.089
 itch-0.084
 her-0.080
Token Tim
Token ID5045
Feature activation-4.88e-01

Pos logit contributions
 accidents+0.001
 itch+0.001
 cookies+0.001
 Mitt+0.001
eddy+0.001
Neg logit contributions
ued-0.003
sel-0.003
ving-0.003
roads-0.003
mer-0.003
Tokenmy
Token ID1820
Feature activation-9.86e-01

Pos logit contributions
 accidents+0.009
 itch+0.008
 bleed+0.007
 stain+0.007
eddy+0.007
Neg logit contributions
ued-0.020
bank-0.018
roads-0.018
ving-0.017
ical-0.017
Token was
Token ID373
Feature activation+4.78e-01

Pos logit contributions
 itch+0.022
 accidents+0.022
 stain+0.019
 cookies+0.018
 bleed+0.018
Neg logit contributions
ued-0.033
roads-0.033
bank-0.031
folk-0.030
sel-0.030
Token so
Token ID523
Feature activation+4.10e-01

Pos logit contributions
ued+0.016
bank+0.015
roads+0.015
ving+0.014
ical+0.014
Neg logit contributions
 accidents-0.012
 itch-0.011
 bleed-0.011
 stain-0.010
eddy-0.010
Token Jake
Token ID14757
Feature activation+1.96e+00

Pos logit contributions
 accidents+0.006
 itch+0.006
 bleed+0.005
 stain+0.005
eddy+0.005
Neg logit contributions
ued-0.009
bank-0.008
roads-0.008
ving-0.008
ical-0.008
Token started
Token ID2067
Feature activation-1.34e-01

Pos logit contributions
ued+0.064
roads+0.063
bank+0.062
ical+0.058
boat+0.057
Neg logit contributions
 itch-0.047
 accidents-0.045
 bleed-0.043
 stain-0.040
 babies-0.039
Token to
Token ID284
Feature activation-7.83e-01

Pos logit contributions
 accidents+0.003
 itch+0.003
 bleed+0.003
 stain+0.002
eddy+0.002
Neg logit contributions
ued-0.005
bank-0.005
roads-0.004
ving-0.004
ical-0.004
Token run
Token ID1057
Feature activation+1.80e+00

Pos logit contributions
 accidents+0.017
eddy+0.016
 itch+0.014
 cookies+0.013
imi+0.013
Neg logit contributions
ued-0.028
bank-0.027
roads-0.026
ving-0.024
ical-0.024
Token in
Token ID287
Feature activation+1.51e+00

Pos logit contributions
ued+0.058
bank+0.054
roads+0.054
ving+0.051
sel+0.050
Neg logit contributions
 accidents-0.046
 itch-0.044
 bleed-0.041
 stain-0.039
eddy-0.037
Token opposite
Token ID6697
Feature activation+5.71e+00

Pos logit contributions
ued+0.055
bank+0.050
sel+0.050
ving+0.050
ical+0.050
Neg logit contributions
 accidents-0.034
 itch-0.030
 bleed-0.029
 stain-0.028
 mess-0.027
Token directions
Token ID11678
Feature activation+2.19e+00

Pos logit contributions
ued+0.139
ving+0.129
sel+0.126
ical+0.124
rob+0.123
Neg logit contributions
 accidents-0.190
 itch-0.181
 mess-0.173
 from-0.166
 babies-0.164
Token.
Token ID13
Feature activation+2.76e-01

Pos logit contributions
ued+0.081
roads+0.077
sel+0.073
ical+0.072
ving+0.072
Neg logit contributions
 accidents-0.046
 itch-0.040
 from-0.038
 bleed-0.037
 babies-0.036
Token
Token ID198
Feature activation+2.35e-01

Pos logit contributions
ued+0.009
roads+0.009
sel+0.008
boat+0.008
mer+0.008
Neg logit contributions
 accidents-0.007
 itch-0.006
 bleed-0.006
 cat-0.006
 Mitt-0.005
Token
Token ID198
Feature activation+8.74e-01

Pos logit contributions
ued+0.008
bank+0.008
sel+0.008
roads+0.008
ical+0.007
Neg logit contributions
 accidents-0.005
 itch-0.004
eddy-0.004
 bleed-0.004
imi-0.004
TokenBer
Token ID24814
Feature activation-4.04e-01

Pos logit contributions
ued+0.026
bank+0.025
roads+0.024
sel+0.023
ving+0.023
Neg logit contributions
 accidents-0.024
 itch-0.023
 bleed-0.021
 stain-0.020
eddy-0.020
Token's
Token ID338
Feature activation-4.05e-01

Pos logit contributions
 accidents+0.046
 bleed+0.044
 itch+0.044
eddy+0.041
 stain+0.041
Neg logit contributions
ued-0.032
bank-0.029
roads-0.028
ving-0.026
sel-0.025
Token go
Token ID467
Feature activation-4.16e-01

Pos logit contributions
 accidents+0.010
eddy+0.008
 bleed+0.007
 itch+0.007
 cookies+0.007
Neg logit contributions
ued-0.014
bank-0.013
roads-0.013
 -0.012
ving-0.012
Token on
Token ID319
Feature activation+3.61e-01

Pos logit contributions
 accidents+0.008
 itch+0.008
 bleed+0.007
 stain+0.007
eddy+0.006
Neg logit contributions
ued-0.016
bank-0.015
roads-0.015
ving-0.014
ical-0.014
Token the
Token ID262
Feature activation+3.80e-01

Pos logit contributions
ued+0.014
bank+0.014
roads+0.013
boat+0.013
folk+0.013
Neg logit contributions
 accidents-0.007
 itch-0.006
 cookies-0.006
 bleed-0.006
burn-0.005
Token fer
Token ID11354
Feature activation+4.31e+00

Pos logit contributions
ued+0.013
bank+0.012
roads+0.012
ving+0.012
sel+0.012
Neg logit contributions
 accidents-0.009
 itch-0.009
 bleed-0.008
 stain-0.008
 cookies-0.007
Tokenris
Token ID2442
Feature activation+5.64e+00

Pos logit contributions
ued+0.098
bank+0.088
folk+0.084
ical+0.083
roads+0.081
Neg logit contributions
eddy-0.132
 accidents-0.131
 itch-0.129
 stain-0.124
 bleed-0.119
Token wheel
Token ID7825
Feature activation+1.38e+00

Pos logit contributions
ued+0.193
bank+0.183
 gru+0.181
ical+0.174
 None+0.164
Neg logit contributions
 grandma-0.107
 accidents-0.106
 go-0.102
eddy-0.100
 mom-0.099
Token and
Token ID290
Feature activation+8.54e-01

Pos logit contributions
ued+0.053
 gru+0.048
roads+0.046
bank+0.046
ving+0.046
Neg logit contributions
 accidents-0.025
 itch-0.024
eddy-0.023
burn-0.022
 cookies-0.022
Token see
Token ID766
Feature activation+3.78e-01

Pos logit contributions
ued+0.032
bank+0.030
roads+0.030
ving+0.028
ical+0.028
Neg logit contributions
 accidents-0.018
 itch-0.017
 bleed-0.015
 stain-0.014
eddy-0.014
Token the
Token ID262
Feature activation+9.13e-01

Pos logit contributions
ued+0.016
bank+0.015
roads+0.014
ical+0.014
mer+0.014
Neg logit contributions
 accidents-0.007
 itch-0.006
 cookies-0.006
 babies-0.005
eddy-0.005
Token whole
Token ID2187
Feature activation+3.85e-01

Pos logit contributions
ued+0.031
bank+0.029
roads+0.027
ical+0.026
ving+0.026
Neg logit contributions
 accidents-0.023
 itch-0.022
 stain-0.020
 mess-0.020
 cookies-0.020
Token '
Token ID705
Feature activation+3.17e+00

Pos logit contributions
ued+0.049
bank+0.048
roads+0.048
sel+0.046
ving+0.045
Neg logit contributions
 accidents-0.021
 cookies-0.015
 babies-0.015
 itch-0.014
 bleed-0.013
Tokend
Token ID67
Feature activation+3.09e+00

Pos logit contributions
bank+0.093
ued+0.093
 mast+0.085
 gru+0.082
roads+0.081
Neg logit contributions
 accidents-0.082
 itch-0.077
burn-0.075
 bleed-0.074
eddy-0.072
Tokenoll
Token ID692
Feature activation-7.38e-01

Pos logit contributions
bank+0.091
ued+0.087
roads+0.087
mer+0.081
 valleys+0.080
Neg logit contributions
 itch-0.079
 accidents-0.075
 cookies-0.069
 bleed-0.067
 babies-0.067
Token'
Token ID6
Feature activation+1.61e+00

Pos logit contributions
 accidents+0.019
 itch+0.018
 cookies+0.017
 bleed+0.016
 stain+0.016
Neg logit contributions
ued-0.023
bank-0.023
roads-0.022
 gru-0.020
ving-0.020
Token in
Token ID287
Feature activation+2.89e+00

Pos logit contributions
ued+0.056
bank+0.055
roads+0.055
sel+0.053
ving+0.052
Neg logit contributions
 accidents-0.036
 itch-0.034
 bleed-0.030
 babies-0.029
 from-0.028
Token Spanish
Token ID7897
Feature activation+5.51e+00

Pos logit contributions
ued+0.119
bank+0.116
ving+0.111
roads+0.109
mer+0.108
Neg logit contributions
 accidents-0.048
 itch-0.042
 cookies-0.038
 her-0.036
 bleed-0.035
Token.
Token ID13
Feature activation+3.18e-01

Pos logit contributions
bank+0.187
ued+0.180
roads+0.169
ving+0.164
boat+0.157
Neg logit contributions
 accidents-0.127
 cookies-0.111
 itch-0.110
 from-0.108
 cat-0.105
Token Lily
Token ID20037
Feature activation+2.29e-02

Pos logit contributions
ued+0.011
roads+0.010
bank+0.010
ving+0.009
mer+0.009
Neg logit contributions
 accidents-0.008
eddy-0.007
 itch-0.007
 bleed-0.007
 babies-0.006
Token,
Token ID11
Feature activation+2.99e-01

Pos logit contributions
ued+0.001
bank+0.001
roads+0.001
 gru+0.001
sel+0.001
Neg logit contributions
 accidents-0.000
 itch-0.000
 bleed-0.000
 stain-0.000
 cookies-0.000
Token can
Token ID460
Feature activation-1.76e-01

Pos logit contributions
ued+0.011
bank+0.011
roads+0.011
ving+0.010
sel+0.010
Neg logit contributions
 accidents-0.006
 itch-0.006
 bleed-0.005
 stain-0.005
 cookies-0.005
Token you
Token ID345
Feature activation+8.61e-01

Pos logit contributions
 accidents+0.003
 itch+0.003
 bleed+0.003
 stain+0.003
 babies+0.002
Neg logit contributions
ued-0.007
bank-0.007
roads-0.006
ving-0.006
sel-0.006
Token old
Token ID1468
Feature activation+2.77e+00

Pos logit contributions
ued+0.067
bank+0.061
sel+0.060
ving+0.060
roads+0.060
Neg logit contributions
 itch-0.043
 accidents-0.041
 cookies-0.037
 bleed-0.036
 stain-0.036
Token lady
Token ID10846
Feature activation+1.35e+00

Pos logit contributions
ued+0.122
ving+0.111
bank+0.109
sel+0.108
roads+0.108
Neg logit contributions
 itch-0.042
 accidents-0.038
 cookies-0.036
 cat-0.036
 dog-0.031
Token with
Token ID351
Feature activation+2.00e+00

Pos logit contributions
ued+0.048
bank+0.046
roads+0.045
sel+0.042
ving+0.041
Neg logit contributions
 accidents-0.029
 itch-0.026
 babies-0.024
 cookies-0.024
 cat-0.023
Token a
Token ID257
Feature activation+1.94e+00

Pos logit contributions
ued+0.079
bank+0.076
roads+0.074
ving+0.073
mer+0.072
Neg logit contributions
 accidents-0.038
 itch-0.036
 bleed-0.032
 cookies-0.031
 stain-0.030
Token mis
Token ID2984
Feature activation+8.64e-01

Pos logit contributions
ued+0.077
bank+0.073
roads+0.073
ving+0.071
folk+0.070
Neg logit contributions
 itch-0.036
 accidents-0.034
 bleed-0.030
 stain-0.030
 rash-0.029
Tokenchie
Token ID3043
Feature activation+5.50e+00

Pos logit contributions
ued+0.015
bank+0.014
roads+0.013
 +0.012
ving+0.011
Neg logit contributions
 itch-0.032
 bleed-0.031
 accidents-0.031
eddy-0.029
 babies-0.029
Tokenvous
Token ID31222
Feature activation+1.97e+00

Pos logit contributions
 mast+0.192
ued+0.191
bank+0.189
sel+0.187
field+0.181
Neg logit contributions
 itch-0.110
 sweet-0.084
 accidents-0.083
 cat-0.081
 cookies-0.078
Token tw
Token ID665
Feature activation+2.07e+00

Pos logit contributions
ued+0.079
roads+0.075
ving+0.073
bank+0.072
sel+0.070
Neg logit contributions
 itch-0.038
 accidents-0.035
 bleed-0.031
 stain-0.030
 rash-0.029
Tokeninkle
Token ID19894
Feature activation+1.01e+00

Pos logit contributions
ued+0.058
bank+0.055
roads+0.054
folk+0.051
ving+0.050
Neg logit contributions
 itch-0.059
 accidents-0.058
 bleed-0.054
 stain-0.053
 rash-0.051
Token in
Token ID287
Feature activation+2.64e+00

Pos logit contributions
ued+0.038
bank+0.036
roads+0.036
ving+0.033
ical+0.033
Neg logit contributions
 accidents-0.021
 itch-0.020
 bleed-0.018
 stain-0.017
burn-0.016
Token her
Token ID607
Feature activation+5.38e-01

Pos logit contributions
ued+0.109
bank+0.103
ving+0.101
ical+0.098
roads+0.098
Neg logit contributions
 accidents-0.047
 itch-0.043
 bleed-0.037
 stain-0.037
 her-0.036
Token 15
Token ID1315
Feature activation+2.54e+00

Pos logit contributions
ued+0.069
roads+0.063
boat+0.062
bank+0.062
mer+0.060
Neg logit contributions
 accidents-0.054
 itch-0.051
 cookies-0.047
 bleed-0.046
 babies-0.045
Token kilograms
Token ID37075
Feature activation+1.88e+00

Pos logit contributions
ued+0.088
bank+0.085
boat+0.085
roads+0.082
sel+0.077
Neg logit contributions
 accidents-0.060
 itch-0.054
 cookies-0.051
 babies-0.050
 mess-0.049
Token.
Token ID13
Feature activation+4.55e-01

Pos logit contributions
ued+0.070
bank+0.067
roads+0.066
 gru+0.064
boat+0.063
Neg logit contributions
 accidents-0.039
 itch-0.034
 cookies-0.033
 mess-0.031
 honey-0.031
Token Average
Token ID13475
Feature activation+1.95e+00

Pos logit contributions
ued+0.015
bank+0.013
roads+0.013
boat+0.013
mer+0.013
Neg logit contributions
 accidents-0.012
 itch-0.011
 bleed-0.010
 babies-0.010
eddy-0.010
Token for
Token ID329
Feature activation+1.24e+00

Pos logit contributions
ued+0.069
roads+0.069
bank+0.068
boat+0.063
sc+0.061
Neg logit contributions
 accidents-0.044
 babies-0.039
 itch-0.038
 honey-0.035
imi-0.035
Token age
Token ID2479
Feature activation+5.48e+00

Pos logit contributions
ued+0.048
roads+0.046
bank+0.045
boat+0.044
mer+0.043
Neg logit contributions
 accidents-0.026
 cookies-0.023
 itch-0.023
 babies-0.023
 honey-0.021
Token:
Token ID25
Feature activation+3.50e+00

Pos logit contributions
bank+0.212
ued+0.212
roads+0.211
boat+0.195
 gru+0.186
Neg logit contributions
 accidents-0.102
 babies-0.095
 cookies-0.091
 itch-0.083
 pets-0.083
Token 3
Token ID513
Feature activation+4.60e+00

Pos logit contributions
ued+0.135
bank+0.126
roads+0.123
ving+0.118
boat+0.116
Neg logit contributions
 accidents-0.077
 itch-0.069
 cookies-0.067
 babies-0.064
 cat-0.060
Token years
Token ID812
Feature activation+2.31e+00

Pos logit contributions
ued+0.170
roads+0.165
boat+0.163
bank+0.160
sel+0.153
Neg logit contributions
 accidents-0.095
 babies-0.091
 itch-0.088
 cookies-0.088
 mess-0.080
Token."
Token ID526
Feature activation+1.96e+00

Pos logit contributions
ued+0.097
bank+0.096
roads+0.094
boat+0.091
ving+0.089
Neg logit contributions
 accidents-0.035
 cookies-0.030
 babies-0.028
 itch-0.027
 honey-0.026
Token
Token ID198
Feature activation+1.59e+00

Pos logit contributions
ued+0.080
ving+0.076
bank+0.074
roads+0.073
ical+0.072
Neg logit contributions
 her-0.033
 grandma-0.032
 mom-0.032
 Mom-0.029
 cat-0.029
Token they
Token ID484
Feature activation+8.81e-01

Pos logit contributions
 accidents+0.022
 itch+0.018
 babies+0.016
 cookies+0.016
 bleed+0.015
Neg logit contributions
ued-0.036
roads-0.033
bank-0.033
ical-0.033
ving-0.033
Token were
Token ID547
Feature activation+5.83e-01

Pos logit contributions
ued+0.029
bank+0.027
roads+0.027
ical+0.026
ving+0.025
Neg logit contributions
 accidents-0.021
 itch-0.021
 bleed-0.019
 stain-0.019
 babies-0.018
Token walking
Token ID6155
Feature activation+1.99e+00

Pos logit contributions
ued+0.022
bank+0.020
roads+0.020
ving+0.019
ical+0.019
Neg logit contributions
 accidents-0.012
 itch-0.012
 bleed-0.011
 stain-0.010
 babies-0.009
Token in
Token ID287
Feature activation+1.05e+00

Pos logit contributions
ued+0.076
bank+0.070
ving+0.069
sel+0.069
roads+0.068
Neg logit contributions
 accidents-0.037
 itch-0.032
 from-0.030
 her-0.029
 bleed-0.028
Token the
Token ID262
Feature activation+1.12e+00

Pos logit contributions
ued+0.042
ving+0.039
bank+0.039
ical+0.038
sel+0.037
Neg logit contributions
 accidents-0.020
 itch-0.017
 her-0.015
 bleed-0.015
 cookies-0.015
Token opposite
Token ID6697
Feature activation+5.46e+00

Pos logit contributions
ued+0.038
ving+0.036
bank+0.035
sel+0.034
ical+0.034
Neg logit contributions
 itch-0.028
 accidents-0.027
 stain-0.024
 cookies-0.023
 mess-0.023
Token way
Token ID835
Feature activation+7.11e-01

Pos logit contributions
ued+0.136
ving+0.133
rob+0.127
sel+0.127
gency+0.122
Neg logit contributions
 accidents-0.164
 itch-0.159
 mess-0.153
 from-0.149
 babies-0.141
Token.
Token ID13
Feature activation+5.45e-01

Pos logit contributions
ued+0.027
ical+0.026
roads+0.025
bank+0.025
sel+0.025
Neg logit contributions
 accidents-0.014
 itch-0.011
 from-0.011
 her-0.011
 babies-0.010
Token
Token ID198
Feature activation+4.43e-01

Pos logit contributions
ued+0.018
roads+0.017
boat+0.017
sel+0.017
ving+0.016
Neg logit contributions
 Mitt-0.012
 accidents-0.012
 Mom-0.011
 cat-0.011
 Spot-0.011
Token
Token ID198
Feature activation+8.41e-01

Pos logit contributions
ued+0.016
ical+0.016
sel+0.015
bank+0.015
roads+0.015
Neg logit contributions
 accidents-0.008
eddy-0.007
 itch-0.007
imi-0.007
 cookies-0.007
TokenJack
Token ID14295
Feature activation+4.12e-01

Pos logit contributions
ued+0.026
bank+0.026
roads+0.024
ical+0.024
sel+0.024
Neg logit contributions
 accidents-0.021
 itch-0.019
 bleed-0.017
 cookies-0.017
eddy-0.017
Token means
Token ID1724
Feature activation+1.25e+00

Pos logit contributions
ued+0.027
bank+0.025
roads+0.025
ving+0.024
mer+0.024
Neg logit contributions
 accidents-0.014
 itch-0.014
 cookies-0.012
 stain-0.011
 cat-0.011
Token '
Token ID705
Feature activation+3.10e+00

Pos logit contributions
bank+0.050
ued+0.049
roads+0.049
sel+0.047
mer+0.046
Neg logit contributions
 accidents-0.022
 babies-0.016
 cookies-0.016
 itch-0.016
 grandma-0.015
Tokencar
Token ID7718
Feature activation+3.09e+00

Pos logit contributions
bank+0.093
ued+0.092
 mast+0.086
 gru+0.082
roads+0.080
Neg logit contributions
 accidents-0.078
 itch-0.072
burn-0.072
 bleed-0.069
eddy-0.069
Token'
Token ID6
Feature activation+1.04e+00

Pos logit contributions
ued+0.078
bank+0.077
roads+0.072
 valleys+0.070
ving+0.065
Neg logit contributions
 accidents-0.090
 itch-0.086
 cat-0.081
eddy-0.080
 bleed-0.079
Token in
Token ID287
Feature activation+2.94e+00

Pos logit contributions
ued+0.035
bank+0.035
roads+0.034
sel+0.033
ving+0.033
Neg logit contributions
 accidents-0.024
 itch-0.022
 bleed-0.020
 from-0.019
 babies-0.019
Token English
Token ID3594
Feature activation+5.46e+00

Pos logit contributions
ued+0.120
bank+0.118
ving+0.111
mer+0.110
roads+0.108
Neg logit contributions
 accidents-0.050
 itch-0.044
 her-0.041
 cookies-0.039
 stain-0.037
Token.
Token ID13
Feature activation+1.03e-01

Pos logit contributions
bank+0.203
ued+0.195
roads+0.180
ving+0.178
 gru+0.172
Neg logit contributions
 accidents-0.109
 from-0.093
 cookies-0.092
 itch-0.091
 babies-0.090
Token Now
Token ID2735
Feature activation+7.21e-01

Pos logit contributions
ued+0.004
bank+0.003
roads+0.003
mer+0.003
boat+0.003
Neg logit contributions
 accidents-0.002
eddy-0.002
 itch-0.002
 bleed-0.002
 babies-0.002
Token,
Token ID11
Feature activation-3.00e-01

Pos logit contributions
ued+0.027
bank+0.027
roads+0.026
ving+0.025
mer+0.024
Neg logit contributions
 accidents-0.014
 itch-0.013
 stain-0.011
 bleed-0.011
 cookies-0.011
Token can
Token ID460
Feature activation-3.69e-01

Pos logit contributions
 accidents+0.007
 itch+0.007
 bleed+0.006
 stain+0.006
eddy+0.006
Neg logit contributions
ued-0.010
roads-0.009
bank-0.009
ving-0.009
ical-0.009
Token you
Token ID345
Feature activation+7.04e-01

Pos logit contributions
 accidents+0.007
 itch+0.006
 bleed+0.005
 stain+0.005
 cookies+0.005
Neg logit contributions
ued-0.014
bank-0.014
roads-0.013
mer-0.013
ving-0.013
Token could
Token ID714
Feature activation-4.70e-01

Pos logit contributions
ued+0.049
bank+0.046
roads+0.045
ving+0.042
ical+0.041
Neg logit contributions
 accidents-0.049
 itch-0.047
 bleed-0.044
 stain-0.043
eddy-0.041
Token count
Token ID954
Feature activation+1.16e+00

Pos logit contributions
 accidents+0.009
 itch+0.008
 bleed+0.008
 stain+0.007
eddy+0.007
Neg logit contributions
ued-0.018
bank-0.017
roads-0.017
ving-0.016
ical-0.016
Token and
Token ID290
Feature activation+1.57e+00

Pos logit contributions
ued+0.049
bank+0.046
roads+0.044
ical+0.043
ving+0.043
Neg logit contributions
 accidents-0.021
 itch-0.016
 cookies-0.016
 her-0.015
 from-0.015
Token solve
Token ID8494
Feature activation+3.36e+00

Pos logit contributions
ued+0.053
bank+0.047
roads+0.047
sel+0.046
ving+0.046
Neg logit contributions
 accidents-0.039
 itch-0.035
 bleed-0.032
 cookies-0.031
 stain-0.031
Token simple
Token ID2829
Feature activation+2.98e+00

Pos logit contributions
ued+0.144
bank+0.137
ical+0.134
roads+0.129
boat+0.127
Neg logit contributions
 accidents-0.056
 her-0.054
 cookies-0.043
 from-0.040
 mess-0.039
Token maths
Token ID47761
Feature activation+5.44e+00

Pos logit contributions
ued+0.109
boat+0.106
bank+0.104
roads+0.100
sel+0.099
Neg logit contributions
 accidents-0.068
 itch-0.056
 mess-0.055
 cookies-0.054
 her-0.051
Token problems
Token ID2761
Feature activation+3.26e+00

Pos logit contributions
ued+0.211
bank+0.205
boat+0.197
 gru+0.190
sel+0.186
Neg logit contributions
 accidents-0.100
 mess-0.089
 cookies-0.088
 her-0.082
 from-0.077
Token.
Token ID13
Feature activation+2.33e-02

Pos logit contributions
ued+0.127
bank+0.119
roads+0.115
 gru+0.115
sel+0.112
Neg logit contributions
 accidents-0.059
 from-0.053
 her-0.048
 cookies-0.046
 itch-0.044
Token Everyone
Token ID11075
Feature activation+8.69e-02

Pos logit contributions
ued+0.001
sel+0.001
mer+0.001
chie+0.001
roads+0.001
Neg logit contributions
 accidents-0.000
 cat-0.000
 grandma-0.000
eddy-0.000
 Kitty-0.000
Token cl
Token ID537
Feature activation+2.96e-01

Pos logit contributions
ued+0.003
bank+0.003
roads+0.003
ical+0.003
sel+0.003
Neg logit contributions
 accidents-0.002
 itch-0.002
eddy-0.001
 stain-0.001
 from-0.001
Tokenapped
Token ID6320
Feature activation+2.72e-01

Pos logit contributions
ued+0.008
bank+0.007
roads+0.007
ving+0.007
ical+0.007
Neg logit contributions
 accidents-0.009
 itch-0.009
 bleed-0.008
 stain-0.008
 cookies-0.008
Token was
Token ID373
Feature activation+9.92e-01

Pos logit contributions
ued+0.034
roads+0.032
bank+0.032
sel+0.032
ving+0.031
Neg logit contributions
 accidents-0.025
 itch-0.024
 bleed-0.021
 cookies-0.019
 stain-0.019
Token determined
Token ID5295
Feature activation+2.07e+00

Pos logit contributions
ued+0.038
bank+0.035
roads+0.035
sel+0.035
ical+0.033
Neg logit contributions
 accidents-0.019
 itch-0.019
 bleed-0.017
 babies-0.015
 cookies-0.015
Token to
Token ID284
Feature activation-3.76e-01

Pos logit contributions
ued+0.105
sel+0.100
folk+0.098
roads+0.097
mer+0.096
Neg logit contributions
 accidents-0.021
 from-0.015
 her-0.015
 itch-0.014
 not-0.013
Token be
Token ID307
Feature activation+1.85e+00

Pos logit contributions
 accidents+0.009
 itch+0.009
 bleed+0.008
 stain+0.008
 cookies+0.007
Neg logit contributions
ued-0.013
bank-0.012
roads-0.012
ving-0.011
sel-0.011
Token the
Token ID262
Feature activation+1.47e-01

Pos logit contributions
ued+0.070
bank+0.065
roads+0.064
ving+0.061
sel+0.061
Neg logit contributions
 accidents-0.039
 itch-0.036
 bleed-0.033
 cookies-0.030
 babies-0.030
Token vict
Token ID2210
Feature activation+5.41e+00

Pos logit contributions
ued+0.004
bank+0.004
roads+0.004
ving+0.004
sel+0.004
Neg logit contributions
 accidents-0.004
 itch-0.004
 bleed-0.004
 stain-0.004
 cookies-0.004
Tokenor
Token ID273
Feature activation+3.02e+00

Pos logit contributions
bank+0.131
ued+0.123
roads+0.120
 valleys+0.115
 gru+0.113
Neg logit contributions
burn-0.158
eddy-0.156
oo-0.150
 accidents-0.148
 from-0.146
Token.
Token ID13
Feature activation+7.71e-02

Pos logit contributions
ued+0.109
roads+0.102
bank+0.098
 gru+0.095
sel+0.094
Neg logit contributions
 accidents-0.062
 itch-0.058
 babies-0.054
 bleed-0.051
burn-0.050
Token
Token ID198
Feature activation-9.75e-02

Pos logit contributions
sel+0.003
ued+0.003
mer+0.003
chie+0.003
boat+0.003
Neg logit contributions
 accidents-0.001
 Mitt-0.001
 Max-0.001
 mom-0.001
 cat-0.001
Token
Token ID198
Feature activation+4.89e-01

Pos logit contributions
 accidents+0.001
eddy+0.001
 itch+0.001
 her+0.001
 grandma+0.001
Neg logit contributions
sel-0.004
ued-0.004
ical-0.004
folk-0.004
bank-0.004
TokenBut
Token ID1537
Feature activation-4.29e-01

Pos logit contributions
ued+0.015
bank+0.014
roads+0.013
sel+0.013
ving+0.012
Neg logit contributions
 accidents-0.014
 itch-0.013
 bleed-0.012
 stain-0.012
eddy-0.011
Token off
Token ID572
Feature activation-1.67e+00

Pos logit contributions
ued+0.013
bank+0.013
roads+0.013
ving+0.012
ical+0.012
Neg logit contributions
 accidents-0.007
 itch-0.007
 bleed-0.006
 stain-0.006
eddy-0.005
Token the
Token ID262
Feature activation-8.60e-01

Pos logit contributions
 accidents+0.029
 itch+0.026
 bleed+0.024
 cookies+0.022
 from+0.021
Neg logit contributions
ued-0.069
bank-0.064
roads-0.063
ving-0.063
ical-0.063
Token fence
Token ID13990
Feature activation+3.34e-01

Pos logit contributions
 itch+0.023
 accidents+0.021
 bleed+0.019
 cookies+0.019
 cat+0.019
Neg logit contributions
ued-0.028
bank-0.026
roads-0.026
den-0.025
sel-0.025
Token in
Token ID287
Feature activation+2.13e+00

Pos logit contributions
ued+0.015
roads+0.014
ving+0.014
sel+0.014
den+0.014
Neg logit contributions
 itch-0.004
 accidents-0.004
 bleed-0.003
 from-0.003
 stain-0.003
Token the
Token ID262
Feature activation+1.28e+00

Pos logit contributions
ued+0.089
ving+0.083
ical+0.082
bank+0.080
sel+0.078
Neg logit contributions
 accidents-0.038
 itch-0.034
 bleed-0.033
 her-0.032
 pain-0.030
Token opposite
Token ID6697
Feature activation+5.41e+00

Pos logit contributions
ued+0.043
ving+0.039
den+0.039
sel+0.038
bank+0.038
Neg logit contributions
 itch-0.034
 accidents-0.030
 cat-0.028
 bleed-0.027
 cookies-0.027
Token direction
Token ID4571
Feature activation+2.30e+00

Pos logit contributions
ued+0.136
rob+0.135
ving+0.129
sel+0.124
vin+0.120
Neg logit contributions
 itch-0.166
 accidents-0.159
 mess-0.156
 from-0.151
 babies-0.144
Token.
Token ID13
Feature activation-5.68e-01

Pos logit contributions
ued+0.089
roads+0.081
ving+0.080
bank+0.079
sel+0.079
Neg logit contributions
 accidents-0.047
 itch-0.041
 bleed-0.037
 from-0.037
 babies-0.035
Token He
Token ID679
Feature activation+1.05e+00

Pos logit contributions
 accidents+0.014
 itch+0.013
 Mitt+0.012
 bleed+0.011
 cat+0.011
Neg logit contributions
ued-0.018
sel-0.018
roads-0.018
den-0.018
mer-0.017
Token fell
Token ID3214
Feature activation-1.10e+00

Pos logit contributions
ued+0.035
roads+0.033
bank+0.033
ical+0.032
folk+0.031
Neg logit contributions
 accidents-0.024
 itch-0.024
 bleed-0.021
 stain-0.021
 babies-0.020
Token on
Token ID319
Feature activation-3.71e-01

Pos logit contributions
 accidents+0.026
 itch+0.025
 bleed+0.023
 stain+0.022
 cookies+0.021
Neg logit contributions
ued-0.037
bank-0.035
roads-0.034
ving-0.032
boat-0.032
Token only
Token ID691
Feature activation+2.68e+00

Pos logit contributions
ued+0.065
roads+0.062
bank+0.061
ical+0.058
ving+0.057
Neg logit contributions
 accidents-0.031
 itch-0.030
 bleed-0.026
 babies-0.024
 cookies-0.024
Token out
Token ID503
Feature activation+1.02e+00

Pos logit contributions
ued+0.110
roads+0.105
bank+0.101
boat+0.096
folk+0.094
Neg logit contributions
 accidents-0.047
 itch-0.044
 babies-0.043
 pets-0.043
 cookies-0.041
Token for
Token ID329
Feature activation+8.01e-02

Pos logit contributions
ued+0.043
bank+0.042
roads+0.041
sel+0.039
ical+0.038
Neg logit contributions
 accidents-0.017
 itch-0.014
 bleed-0.012
 babies-0.011
 cookies-0.011
Token her
Token ID607
Feature activation+5.70e-01

Pos logit contributions
ued+0.003
roads+0.003
ving+0.003
bank+0.003
ical+0.003
Neg logit contributions
 accidents-0.002
 itch-0.001
 babies-0.001
 cookies-0.001
 bleed-0.001
Token own
Token ID898
Feature activation+2.56e+00

Pos logit contributions
ued+0.021
roads+0.020
bank+0.019
ving+0.019
sel+0.019
Neg logit contributions
 accidents-0.013
 itch-0.012
 babies-0.011
 bleed-0.010
 stain-0.010
Token win
Token ID1592
Feature activation+5.37e+00

Pos logit contributions
ued+0.093
roads+0.087
ving+0.085
sel+0.084
bank+0.084
Neg logit contributions
 accidents-0.054
 itch-0.054
 babies-0.050
 cookies-0.048
 mess-0.047
Token.
Token ID13
Feature activation+4.34e-01

Pos logit contributions
ued+0.212
bank+0.207
sel+0.197
roads+0.193
 gru+0.193
Neg logit contributions
 accidents-0.087
 from-0.078
 itch-0.075
 her-0.075
 babies-0.073
Token
Token ID198
Feature activation+1.39e-01

Pos logit contributions
ued+0.016
roads+0.015
ving+0.014
sel+0.014
bank+0.014
Neg logit contributions
 accidents-0.009
eddy-0.008
 itch-0.008
 Mitt-0.008
 cat-0.007
Token
Token ID198
Feature activation+6.27e-01

Pos logit contributions
ued+0.005
sel+0.005
bank+0.005
ical+0.005
roads+0.005
Neg logit contributions
 accidents-0.003
eddy-0.003
imi-0.002
 itch-0.002
 bleed-0.002
TokenThe
Token ID464
Feature activation+5.28e-02

Pos logit contributions
ued+0.019
bank+0.018
roads+0.017
sel+0.017
ving+0.016
Neg logit contributions
 accidents-0.017
 itch-0.016
 bleed-0.015
eddy-0.014
 stain-0.014
Token fox
Token ID21831
Feature activation+2.69e-01

Pos logit contributions
ued+0.002
roads+0.002
bank+0.002
ving+0.002
boat+0.002
Neg logit contributions
 accidents-0.001
 itch-0.001
 bleed-0.001
 stain-0.001
eddy-0.001
Token '
Token ID705
Feature activation+3.02e+00

Pos logit contributions
ued+0.051
bank+0.048
roads+0.047
ving+0.045
boat+0.044
Neg logit contributions
 accidents-0.027
 itch-0.025
 bleed-0.023
 stain-0.021
 cookies-0.021
Tokenl
Token ID75
Feature activation+1.36e-02

Pos logit contributions
ued+0.091
bank+0.091
 mast+0.080
roads+0.078
ving+0.078
Neg logit contributions
 accidents-0.077
 itch-0.073
 bleed-0.069
eddy-0.068
 cookies-0.067
Tokenion
Token ID295
Feature activation-1.26e+00

Pos logit contributions
ued+0.000
bank+0.000
roads+0.000
 gru+0.000
boat+0.000
Neg logit contributions
 accidents-0.000
 itch-0.000
 bleed-0.000
eddy-0.000
 babies-0.000
Token'
Token ID6
Feature activation+1.05e+00

Pos logit contributions
 itch+0.037
 accidents+0.037
 cookies+0.034
 bleed+0.032
 cat+0.032
Neg logit contributions
ued-0.033
bank-0.032
roads-0.031
ving-0.029
 valleys-0.028
Token in
Token ID287
Feature activation+2.89e+00

Pos logit contributions
ued+0.036
bank+0.035
roads+0.034
ving+0.033
sel+0.032
Neg logit contributions
 accidents-0.023
 itch-0.022
 bleed-0.020
 babies-0.020
 cookies-0.019
Token Spanish
Token ID7897
Feature activation+5.34e+00

Pos logit contributions
ued+0.116
bank+0.110
roads+0.107
ving+0.106
mer+0.103
Neg logit contributions
 accidents-0.050
 itch-0.047
 her-0.041
 cookies-0.041
 cat-0.040
Token.
Token ID13
Feature activation+5.92e-01

Pos logit contributions
bank+0.156
ued+0.154
roads+0.146
ving+0.137
boat+0.135
Neg logit contributions
 accidents-0.142
 itch-0.133
 cookies-0.131
 cat-0.128
 babies-0.127
Token It
Token ID632
Feature activation-9.33e-03

Pos logit contributions
ued+0.019
roads+0.017
bank+0.017
ving+0.016
boat+0.016
Neg logit contributions
 accidents-0.016
 itch-0.015
 bleed-0.014
eddy-0.013
 stain-0.013
Token is
Token ID318
Feature activation+1.80e+00

Pos logit contributions
 accidents+0.000
 itch+0.000
 bleed+0.000
 cookies+0.000
 stain+0.000
Neg logit contributions
ued-0.000
bank-0.000
roads-0.000
boat-0.000
ving-0.000
Token '
Token ID705
Feature activation+2.75e+00

Pos logit contributions
ued+0.069
roads+0.064
bank+0.064
ving+0.061
boat+0.060
Neg logit contributions
 accidents-0.036
 itch-0.034
 bleed-0.031
 cookies-0.029
 stain-0.029
Tokenleon
Token ID38970
Feature activation+2.63e+00

Pos logit contributions
bank+0.081
ued+0.081
roads+0.071
 mast+0.071
 gru+0.070
Neg logit contributions
 accidents-0.071
 itch-0.069
eddy-0.065
burn-0.065
 bleed-0.065
Token man
Token ID582
Feature activation+2.83e-01

Pos logit contributions
ued+0.066
ving+0.059
bank+0.058
roads+0.058
ical+0.057
Neg logit contributions
 accidents-0.036
 itch-0.035
 bleed-0.030
 stain-0.030
 cookies-0.029
Token,
Token ID11
Feature activation+2.08e-01

Pos logit contributions
ued+0.012
bank+0.011
roads+0.011
sel+0.011
ving+0.011
Neg logit contributions
 accidents-0.004
 itch-0.004
 bleed-0.003
 stain-0.003
 cookies-0.003
Token and
Token ID290
Feature activation+3.08e-01

Pos logit contributions
ued+0.008
roads+0.007
bank+0.007
sel+0.007
mer+0.007
Neg logit contributions
 accidents-0.005
 itch-0.004
 bleed-0.004
 stain-0.004
 bleeding-0.004
Token asked
Token ID1965
Feature activation+1.19e+00

Pos logit contributions
ued+0.011
roads+0.010
bank+0.010
ical+0.009
ving+0.009
Neg logit contributions
 accidents-0.008
 itch-0.007
 her-0.006
 from-0.006
 cookies-0.006
Token quizz
Token ID48258
Feature activation+3.16e+00

Pos logit contributions
ued+0.052
bank+0.050
roads+0.050
ical+0.048
ving+0.047
Neg logit contributions
 accidents-0.019
 her-0.016
 from-0.014
 itch-0.014
 cookies-0.013
Tokenically
Token ID1146
Feature activation+5.32e+00

Pos logit contributions
ued+0.129
roads+0.128
bank+0.124
boat+0.116
 mast+0.115
Neg logit contributions
eddy-0.036
 accidents-0.034
 from-0.032
 her-0.032
 babies-0.032
Token,
Token ID11
Feature activation+7.62e-01

Pos logit contributions
roads+0.224
ued+0.224
rob+0.209
bank+0.205
boat+0.204
Neg logit contributions
 accidents-0.086
 from-0.075
 her-0.071
 itch-0.070
 and-0.062
Token "
Token ID366
Feature activation+1.51e+00

Pos logit contributions
ued+0.029
bank+0.027
boat+0.027
roads+0.027
mer+0.026
Neg logit contributions
 accidents-0.018
 itch-0.015
 from-0.014
 hugging-0.013
 her-0.013
TokenWhy
Token ID5195
Feature activation-1.00e+00

Pos logit contributions
ued+0.057
bank+0.054
roads+0.050
ical+0.049
ving+0.048
Neg logit contributions
 accidents-0.032
 itch-0.027
eddy-0.026
 stain-0.026
burn-0.025
Token does
Token ID857
Feature activation+1.77e+00

Pos logit contributions
 accidents+0.018
 itch+0.017
 bleed+0.015
 stain+0.014
eddy+0.014
Neg logit contributions
ued-0.040
bank-0.038
roads-0.037
ving-0.036
ical-0.035
Token everyone
Token ID2506
Feature activation+7.35e-01

Pos logit contributions
ued+0.069
bank+0.066
roads+0.065
ving+0.062
sel+0.062
Neg logit contributions
 accidents-0.034
 itch-0.031
 bleed-0.027
 cookies-0.026
 stain-0.026
Token ready
Token ID3492
Feature activation+2.04e-01

Pos logit contributions
ued+0.016
bank+0.015
roads+0.015
sel+0.014
ving+0.014
Neg logit contributions
 accidents-0.008
 itch-0.008
 bleed-0.007
 stain-0.007
 babies-0.006
Token to
Token ID284
Feature activation-1.08e+00

Pos logit contributions
ued+0.008
roads+0.008
bank+0.008
ving+0.008
sel+0.008
Neg logit contributions
 accidents-0.004
 itch-0.003
 bleed-0.003
 stain-0.003
 cookies-0.003
Token run
Token ID1057
Feature activation+1.85e+00

Pos logit contributions
 accidents+0.024
eddy+0.021
 itch+0.019
 bleed+0.018
 stain+0.017
Neg logit contributions
ued-0.039
bank-0.038
roads-0.037
ving-0.034
boat-0.034
Token in
Token ID287
Feature activation+7.62e-01

Pos logit contributions
ued+0.070
sel+0.066
bank+0.065
folk+0.064
ving+0.064
Neg logit contributions
 accidents-0.034
 itch-0.033
 bleed-0.031
 from-0.030
 her-0.029
Token the
Token ID262
Feature activation+9.96e-01

Pos logit contributions
ued+0.030
sel+0.029
ving+0.029
ical+0.028
bank+0.028
Neg logit contributions
 accidents-0.014
 itch-0.012
 her-0.012
 cookies-0.011
 bleed-0.011
Token opposite
Token ID6697
Feature activation+5.32e+00

Pos logit contributions
ued+0.036
bank+0.033
ving+0.033
sel+0.032
roads+0.032
Neg logit contributions
 accidents-0.022
 itch-0.022
 stain-0.019
 bleed-0.019
 cookies-0.018
Token direction
Token ID4571
Feature activation+2.59e+00

Pos logit contributions
ued+0.136
ving+0.133
sel+0.132
rob+0.122
ical+0.118
Neg logit contributions
 itch-0.160
 accidents-0.154
 mess-0.154
 from-0.141
 babies-0.136
Token.
Token ID13
Feature activation+7.06e-01

Pos logit contributions
ued+0.103
sel+0.098
ving+0.097
bank+0.095
ical+0.094
Neg logit contributions
 accidents-0.048
 itch-0.041
 her-0.038
 from-0.038
 babies-0.034
Token Instead
Token ID5455
Feature activation+1.09e-01

Pos logit contributions
ued+0.024
sel+0.024
ving+0.022
roads+0.022
boat+0.022
Neg logit contributions
 Mitt-0.016
 accidents-0.015
 Spot-0.014
 Mom-0.014
 Kitty-0.014
Token,
Token ID11
Feature activation+9.46e-01

Pos logit contributions
ued+0.004
bank+0.004
roads+0.004
ving+0.004
ical+0.004
Neg logit contributions
 accidents-0.002
 itch-0.002
 bleed-0.002
 cookies-0.002
 stain-0.002
Token he
Token ID339
Feature activation+9.04e-01

Pos logit contributions
ued+0.027
bank+0.025
roads+0.024
ving+0.024
ical+0.024
Neg logit contributions
 accidents-0.029
 itch-0.026
 bleed-0.025
 cookies-0.024
 stain-0.023
Token and
Token ID290
Feature activation+9.29e-01

Pos logit contributions
ued+0.073
bank+0.069
roads+0.069
ving+0.066
ical+0.065
Neg logit contributions
 accidents-0.029
 itch-0.025
 bleed-0.021
 stain-0.020
 cookies-0.020
Token started
Token ID2067
Feature activation-4.06e-01

Pos logit contributions
ued+0.029
bank+0.027
roads+0.027
ving+0.025
ical+0.025
Neg logit contributions
 accidents-0.025
 itch-0.024
 bleed-0.022
 stain-0.021
eddy-0.020
Token walking
Token ID6155
Feature activation+2.62e+00

Pos logit contributions
 accidents+0.008
 itch+0.007
 bleed+0.007
 stain+0.006
 cookies+0.006
Neg logit contributions
ued-0.016
roads-0.015
bank-0.014
ving-0.014
sel-0.014
Token in
Token ID287
Feature activation+1.25e+00

Pos logit contributions
ued+0.102
sel+0.095
ving+0.094
ical+0.093
bank+0.092
Neg logit contributions
 from-0.043
 accidents-0.042
 her-0.042
 itch-0.039
 babies-0.034
Token the
Token ID262
Feature activation+1.02e+00

Pos logit contributions
ued+0.052
ving+0.048
bank+0.048
ical+0.047
sel+0.047
Neg logit contributions
 accidents-0.022
 itch-0.019
 her-0.018
 cookies-0.017
 mess-0.016
Token opposite
Token ID6697
Feature activation+5.32e+00

Pos logit contributions
ued+0.037
ving+0.035
sel+0.034
bank+0.033
ical+0.033
Neg logit contributions
 itch-0.022
 accidents-0.022
 stain-0.019
 mess-0.018
 cookies-0.018
Token way
Token ID835
Feature activation+7.63e-01

Pos logit contributions
ued+0.137
ving+0.132
sel+0.125
rob+0.125
gency+0.120
Neg logit contributions
 accidents-0.154
 itch-0.153
 mess-0.150
 from-0.142
 her-0.138
Token.
Token ID13
Feature activation+6.72e-01

Pos logit contributions
ued+0.029
ical+0.027
roads+0.027
bank+0.027
sel+0.027
Neg logit contributions
 accidents-0.015
 itch-0.012
 her-0.012
 from-0.012
 babies-0.011
Token After
Token ID2293
Feature activation-9.90e-01

Pos logit contributions
ued+0.022
boat+0.021
roads+0.021
sel+0.020
mer+0.020
Neg logit contributions
 accidents-0.014
 Mitt-0.014
 itch-0.013
 cat-0.013
 Mom-0.013
Token a
Token ID257
Feature activation+2.42e-01

Pos logit contributions
 accidents+0.020
 itch+0.017
 cookies+0.016
 bleed+0.015
 babies+0.015
Neg logit contributions
ued-0.038
bank-0.036
roads-0.036
mer-0.035
ving-0.035
Token while
Token ID981
Feature activation-1.02e+00

Pos logit contributions
roads+0.008
ued+0.008
bank+0.008
sel+0.007
ving+0.007
Neg logit contributions
 accidents-0.006
 itch-0.005
 sweet-0.005
 stain-0.005
 mess-0.005
Token soldier
Token ID10686
Feature activation+1.12e+00

Pos logit contributions
 accidents+0.001
 itch+0.001
 bleed+0.000
eddy+0.000
 stain+0.000
Neg logit contributions
ued-0.001
roads-0.001
bank-0.001
ving-0.001
ical-0.001
Token ran
Token ID4966
Feature activation+1.18e+00

Pos logit contributions
ued+0.036
bank+0.034
roads+0.033
 gru+0.031
ical+0.031
Neg logit contributions
 accidents-0.027
 itch-0.027
 bleed-0.024
 stain-0.024
 babies-0.022
Token off
Token ID572
Feature activation-1.04e+00

Pos logit contributions
ued+0.040
bank+0.037
roads+0.037
ving+0.035
sel+0.035
Neg logit contributions
 accidents-0.028
 itch-0.027
 bleed-0.025
 stain-0.024
eddy-0.022
Token in
Token ID287
Feature activation+1.85e+00

Pos logit contributions
 accidents+0.017
 itch+0.015
 her+0.014
 bleed+0.014
 from+0.013
Neg logit contributions
ued-0.043
roads-0.040
bank-0.040
ving-0.039
sel-0.039
Token the
Token ID262
Feature activation+9.79e-01

Pos logit contributions
ued+0.070
bank+0.066
ving+0.065
ical+0.063
roads+0.063
Neg logit contributions
 accidents-0.038
 itch-0.035
 bleed-0.032
 stain-0.031
 cookies-0.029
Token opposite
Token ID6697
Feature activation+5.30e+00

Pos logit contributions
ued+0.038
ving+0.035
bank+0.035
sel+0.034
ical+0.033
Neg logit contributions
 itch-0.020
 accidents-0.019
 stain-0.017
 bleed-0.016
 mess-0.016
Token direction
Token ID4571
Feature activation+2.37e+00

Pos logit contributions
ued+0.148
ving+0.141
rob+0.135
sel+0.129
gency+0.126
Neg logit contributions
 itch-0.147
 accidents-0.146
 mess-0.145
 from-0.136
 stain-0.130
Token.
Token ID13
Feature activation+5.13e-01

Pos logit contributions
ued+0.097
bank+0.091
roads+0.090
ving+0.090
sel+0.087
Neg logit contributions
 accidents-0.043
 itch-0.036
 bleed-0.031
 stain-0.029
 her-0.029
Token Everything
Token ID11391
Feature activation-5.12e-01

Pos logit contributions
ued+0.017
boat+0.016
mer+0.016
sel+0.016
roads+0.016
Neg logit contributions
 accidents-0.011
 itch-0.011
 Mitt-0.011
 her-0.011
 cat-0.010
Token had
Token ID550
Feature activation+4.23e-01

Pos logit contributions
 accidents+0.014
 itch+0.013
 bleed+0.012
 stain+0.011
 cookies+0.010
Neg logit contributions
ued-0.016
bank-0.015
roads-0.015
sel-0.014
ving-0.014
Token happened
Token ID3022
Feature activation+1.66e+00

Pos logit contributions
ued+0.014
roads+0.013
bank+0.013
ving+0.012
ical+0.012
Neg logit contributions
 accidents-0.011
 itch-0.010
 bleed-0.009
 stain-0.009
 cookies-0.009
Token.
Token ID13
Feature activation-1.50e+00

Pos logit contributions
 accidents+0.028
 itch+0.026
 bleed+0.024
 babies+0.023
 stain+0.023
Neg logit contributions
ued-0.037
roads-0.036
bank-0.035
boat-0.033
ving-0.032
Token Good
Token ID4599
Feature activation-2.09e+00

Pos logit contributions
 accidents+0.043
 itch+0.041
 bleed+0.039
 stain+0.037
burn+0.035
Neg logit contributions
ued-0.043
bank-0.040
roads-0.039
ical-0.038
ving-0.037
Token night
Token ID1755
Feature activation-7.83e-01

Pos logit contributions
 accidents+0.064
 itch+0.062
 bleed+0.060
 stain+0.057
 mosquitoes+0.056
Neg logit contributions
ued-0.046
mer-0.044
bank-0.040
boat-0.039
roads-0.038
Token."
Token ID526
Feature activation-4.86e-01

Pos logit contributions
 accidents+0.022
 itch+0.021
 bleed+0.020
 stain+0.019
eddy+0.018
Neg logit contributions
ued-0.023
bank-0.021
roads-0.021
ving-0.020
ical-0.020
Token She
Token ID1375
Feature activation-1.03e-01

Pos logit contributions
 accidents+0.014
 itch+0.013
 bleed+0.013
 stain+0.012
burn+0.012
Neg logit contributions
ued-0.014
bank-0.013
roads-0.012
 -0.012
ical-0.012
Token c
Token ID269
Feature activation-5.32e+00

Pos logit contributions
 accidents+0.003
 itch+0.003
 bleed+0.003
eddy+0.002
arter+0.002
Neg logit contributions
ued-0.003
sel-0.003
ving-0.003
bank-0.002
roads-0.002
Tokenuddled
Token ID32745
Feature activation-3.08e+00

Pos logit contributions
 itch+0.178
 bleed+0.171
 accidents+0.160
 mosquitoes+0.158
 spill+0.156
Neg logit contributions
ued-0.123
ving-0.106
ement-0.100
ar-0.099
orted-0.094
Token her
Token ID607
Feature activation-3.16e+00

Pos logit contributions
 accidents+0.064
 itch+0.061
 bleed+0.055
 stain+0.054
imi+0.051
Neg logit contributions
ued-0.110
bank-0.105
roads-0.104
ving-0.099
 gru-0.097
Token t
Token ID256
Feature activation-4.73e+00

Pos logit contributions
 accidents+0.070
 itch+0.064
 bleed+0.060
 mosquitoes+0.059
burn+0.057
Neg logit contributions
ued-0.094
 gru-0.085
vin-0.084
roads-0.083
ving-0.082
Tokeneddy
Token ID21874
Feature activation-3.38e+00

Pos logit contributions
 itch+0.101
 accidents+0.086
 mosquitoes+0.085
 cookies+0.079
 honey+0.075
Neg logit contributions
boat-0.169
ued-0.161
mer-0.161
den-0.160
vin-0.159
Token bear
Token ID6842
Feature activation-1.87e+00

Pos logit contributions
 accidents+0.090
 itch+0.084
 bleed+0.079
 stain+0.075
 rash+0.075
Neg logit contributions
ued-0.094
boat-0.084
roads-0.084
ving-0.084
bank-0.083
Token feeling
Token ID4203
Feature activation+3.74e-01

Pos logit contributions
ued+0.003
bank+0.003
ving+0.003
ical+0.003
 gru+0.002
Neg logit contributions
 accidents-0.003
imi-0.003
 stain-0.003
 itch-0.003
eddy-0.003
Token better
Token ID1365
Feature activation-5.94e-01

Pos logit contributions
ued+0.013
bank+0.012
roads+0.012
ving+0.011
ical+0.011
Neg logit contributions
 accidents-0.008
 itch-0.007
eddy-0.007
 bleed-0.007
imi-0.007
Token soon
Token ID2582
Feature activation+3.07e-01

Pos logit contributions
 accidents+0.015
 itch+0.015
 bleed+0.014
 stain+0.014
eddy+0.013
Neg logit contributions
ued-0.018
bank-0.017
roads-0.016
mer-0.016
ving-0.016
Token.
Token ID13
Feature activation-7.79e-01

Pos logit contributions
ued+0.010
bank+0.009
roads+0.009
ving+0.008
sel+0.008
Neg logit contributions
 accidents-0.008
 itch-0.008
 bleed-0.007
 stain-0.007
 cookies-0.007
Token She
Token ID1375
Feature activation-4.44e-01

Pos logit contributions
 accidents+0.021
 itch+0.020
 bleed+0.020
burn+0.018
 stain+0.018
Neg logit contributions
ued-0.023
bank-0.022
roads-0.021
ical-0.020
ving-0.020
Token c
Token ID269
Feature activation-5.31e+00

Pos logit contributions
 accidents+0.014
 itch+0.013
 bleed+0.013
eddy+0.013
burn+0.012
Neg logit contributions
ued-0.011
bank-0.010
ving-0.010
roads-0.009
sel-0.009
Tokenuddled
Token ID32745
Feature activation-2.73e+00

Pos logit contributions
 bleed+0.155
 itch+0.153
 from+0.146
 wake+0.143
 accidents+0.141
Neg logit contributions
ued-0.138
ving-0.115
ised-0.113
bank-0.105
ement-0.098
Token up
Token ID510
Feature activation-1.72e+00

Pos logit contributions
 accidents+0.061
 itch+0.058
 stain+0.057
 bleed+0.055
eddy+0.054
Neg logit contributions
ued-0.090
bank-0.087
roads-0.084
ving-0.080
 -0.079
Token with
Token ID351
Feature activation-1.25e+00

Pos logit contributions
 accidents+0.039
 itch+0.036
 bleed+0.036
 stain+0.035
eddy+0.032
Neg logit contributions
ued-0.057
roads-0.052
bank-0.052
ving-0.050
mer-0.050
Token her
Token ID607
Feature activation-1.46e+00

Pos logit contributions
eddy+0.029
 bleed+0.028
 accidents+0.028
burn+0.027
imi+0.027
Neg logit contributions
 -0.035
ued-0.031
top-0.029
sel-0.028
 one-0.028
Token favorite
Token ID4004
Feature activation-1.42e-01

Pos logit contributions
 accidents+0.025
 bleed+0.023
 itch+0.022
burn+0.020
eddy+0.019
Neg logit contributions
ued-0.051
bank-0.047
mer-0.047
 -0.047
 bank-0.046
Tokenactus
Token ID34144
Feature activation-2.91e+00

Pos logit contributions
 cookies+0.182
 bleed+0.182
 accidents+0.180
 itch+0.178
burn+0.175
Neg logit contributions
mer-0.074
bank-0.071
ued-0.069
pe-0.060
or-0.059
Token was
Token ID373
Feature activation-7.77e-01

Pos logit contributions
 accidents+0.080
 itch+0.074
 bleed+0.072
 stain+0.068
burn+0.067
Neg logit contributions
ued-0.088
bank-0.081
roads-0.079
ving-0.078
boat-0.075
Token complete
Token ID1844
Feature activation+4.33e-01

Pos logit contributions
 accidents+0.018
 itch+0.016
 bleed+0.016
 stain+0.015
eddy+0.015
Neg logit contributions
ued-0.026
bank-0.024
boat-0.024
roads-0.024
 -0.023
Token.
Token ID13
Feature activation-4.63e-01

Pos logit contributions
ued+0.017
roads+0.016
bank+0.015
ical+0.015
folk+0.015
Neg logit contributions
 accidents-0.009
 itch-0.008
 cookies-0.007
 bleed-0.007
 from-0.007
Token The
Token ID383
Feature activation-6.49e-01

Pos logit contributions
 accidents+0.011
 itch+0.010
eddy+0.010
 cookies+0.009
 bleed+0.009
Neg logit contributions
ued-0.016
roads-0.015
bank-0.015
ving-0.014
den-0.014
Token c
Token ID269
Feature activation-5.26e+00

Pos logit contributions
 accidents+0.015
 bleed+0.015
eddy+0.014
burn+0.014
 itch+0.014
Neg logit contributions
ued-0.018
roads-0.017
 -0.017
boat-0.016
bank-0.016
Tokenactus
Token ID34144
Feature activation-2.95e+00

Pos logit contributions
 bleed+0.184
 cookies+0.183
 accidents+0.180
 itch+0.179
burn+0.177
Neg logit contributions
mer-0.076
bank-0.073
ued-0.071
or-0.061
pe-0.059
Token and
Token ID290
Feature activation-1.69e+00

Pos logit contributions
 accidents+0.083
 itch+0.077
 bleed+0.076
 stain+0.071
burn+0.071
Neg logit contributions
ued-0.087
bank-0.080
roads-0.078
ving-0.077
boat-0.074
Token the
Token ID262
Feature activation-6.81e-01

Pos logit contributions
 accidents+0.047
 bleed+0.044
eddy+0.044
 itch+0.044
burn+0.043
Neg logit contributions
ued-0.041
bank-0.040
 -0.040
boat-0.040
roads-0.039
Token bird
Token ID6512
Feature activation-1.87e+00

Pos logit contributions
 accidents+0.014
eddy+0.013
 bleed+0.013
 itch+0.013
burn+0.012
Neg logit contributions
ued-0.021
bank-0.020
roads-0.020
 -0.020
boat-0.020
Token were
Token ID547
Feature activation-5.57e-01

Pos logit contributions
 accidents+0.051
 itch+0.048
 bleed+0.045
 stain+0.043
eddy+0.042
Neg logit contributions
ued-0.058
bank-0.053
roads-0.052
ving-0.050
sel-0.049
Token tired
Token ID10032
Feature activation-3.32e+00

Pos logit contributions
ued+0.004
bank+0.004
 +0.004
 gru+0.004
 2+0.004
Neg logit contributions
 accidents-0.005
eddy-0.004
 stain-0.004
 itch-0.004
burn-0.004
Token from
Token ID422
Feature activation-1.45e+00

Pos logit contributions
 accidents+0.074
 itch+0.073
 bleed+0.070
imi+0.070
burn+0.065
Neg logit contributions
bank-0.098
roads-0.094
boat-0.092
ued-0.091
sc-0.090
Token playing
Token ID2712
Feature activation-9.66e-01

Pos logit contributions
 accidents+0.033
 itch+0.031
 bleed+0.029
eddy+0.029
 stain+0.027
Neg logit contributions
ued-0.048
bank-0.047
roads-0.045
ving-0.042
den-0.041
Token.
Token ID13
Feature activation-8.81e-01

Pos logit contributions
 accidents+0.023
 itch+0.021
 bleed+0.020
 stain+0.019
eddy+0.019
Neg logit contributions
ued-0.032
bank-0.031
roads-0.031
ving-0.029
ical-0.028
Token They
Token ID1119
Feature activation-1.39e+00

Pos logit contributions
 accidents+0.025
 itch+0.023
 bleed+0.022
eddy+0.021
 stain+0.021
Neg logit contributions
ued-0.027
roads-0.025
bank-0.025
ving-0.023
boat-0.023
Token c
Token ID269
Feature activation-5.23e+00

Pos logit contributions
 accidents+0.039
 itch+0.036
 bleed+0.034
 stain+0.033
eddy+0.032
Neg logit contributions
ued-0.042
bank-0.039
roads-0.038
ving-0.036
sel-0.036
Tokenuddled
Token ID32745
Feature activation-2.95e+00

Pos logit contributions
 itch+0.163
 bleed+0.156
 accidents+0.155
 mosquitoes+0.149
 wake+0.144
Neg logit contributions
ued-0.127
ised-0.108
ving-0.102
sel-0.100
mer-0.098
Token with
Token ID351
Feature activation-1.52e+00

Pos logit contributions
 accidents+0.063
 itch+0.059
 bleed+0.053
 stain+0.052
eddy+0.049
Neg logit contributions
ued-0.107
bank-0.101
roads-0.100
ving-0.096
mer-0.093
Token their
Token ID511
Feature activation-1.15e+00

Pos logit contributions
 accidents+0.037
 itch+0.035
 bleed+0.033
 stain+0.031
eddy+0.031
Neg logit contributions
ued-0.047
bank-0.045
roads-0.044
sel-0.043
boat-0.041
Token t
Token ID256
Feature activation-3.55e+00

Pos logit contributions
 accidents+0.025
 itch+0.025
 bleed+0.023
burn+0.020
 rash+0.020
Neg logit contributions
ued-0.037
mer-0.033
bank-0.032
 -0.032
 banks-0.032
Tokeneddy
Token ID21874
Feature activation-2.41e+00

Pos logit contributions
 itch+0.066
 accidents+0.056
 bleed+0.049
 mosquitoes+0.048
 cookies+0.044
Neg logit contributions
boat-0.137
ued-0.133
den-0.130
mer-0.129
sel-0.129
Token a
Token ID257
Feature activation-1.77e+00

Pos logit contributions
 accidents+0.016
burn+0.016
imi+0.016
eddy+0.015
 stain+0.014
Neg logit contributions
ued-0.020
 -0.018
roads-0.017
bank-0.017
 gru-0.017
Token little
Token ID1310
Feature activation-1.93e+00

Pos logit contributions
 accidents+0.043
eddy+0.040
burn+0.040
 cookies+0.038
imi+0.038
Neg logit contributions
ued-0.051
sel-0.045
 -0.045
ving-0.043
ical-0.043
Token better
Token ID1365
Feature activation-1.64e+00

Pos logit contributions
 accidents+0.046
imi+0.044
eddy+0.042
burn+0.040
 itch+0.040
Neg logit contributions
ued-0.060
bank-0.052
roads-0.052
mer-0.052
 gru-0.052
Token.
Token ID13
Feature activation-1.06e+00

Pos logit contributions
 accidents+0.051
 itch+0.046
 bleed+0.044
eddy+0.044
imi+0.043
Neg logit contributions
ued-0.041
bank-0.039
roads-0.038
mer-0.037
ical-0.036
Token She
Token ID1375
Feature activation-2.14e-01

Pos logit contributions
 accidents+0.025
 itch+0.023
 bleed+0.022
 stain+0.021
burn+0.021
Neg logit contributions
ued-0.035
bank-0.033
roads-0.032
ical-0.032
 -0.031
Token c
Token ID269
Feature activation-5.22e+00

Pos logit contributions
 accidents+0.007
eddy+0.007
 bleed+0.007
 itch+0.007
burn+0.007
Neg logit contributions
ued-0.005
bank-0.004
roads-0.004
sel-0.004
ving-0.004
Tokenuddled
Token ID32745
Feature activation-2.86e+00

Pos logit contributions
 itch+0.156
 bleed+0.152
 accidents+0.148
 from+0.144
 mosquitoes+0.140
Neg logit contributions
ued-0.127
ving-0.112
ar-0.107
sel-0.107
mer-0.106
Token with
Token ID351
Feature activation-1.63e+00

Pos logit contributions
 accidents+0.062
 itch+0.058
 stain+0.054
 bleed+0.054
eddy+0.051
Neg logit contributions
ued-0.099
bank-0.094
roads-0.094
ving-0.089
 gru-0.087
Token her
Token ID607
Feature activation-1.27e+00

Pos logit contributions
 accidents+0.030
eddy+0.029
 bleed+0.028
 itch+0.028
burn+0.028
Neg logit contributions
 -0.053
ued-0.049
sel-0.047
top-0.047
roads-0.046
Token mom
Token ID1995
Feature activation-6.69e-01

Pos logit contributions
 accidents+0.022
 itch+0.019
 bleed+0.018
eddy+0.018
burn+0.017
Neg logit contributions
ued-0.046
bank-0.042
mer-0.042
pe-0.041
roads-0.041
Token and
Token ID290
Feature activation-1.32e+00

Pos logit contributions
 accidents+0.012
 itch+0.011
 bleed+0.011
 stain+0.010
eddy+0.009
Neg logit contributions
ued-0.026
bank-0.025
roads-0.024
ving-0.024
sel-0.023
Tokenactus
Token ID34144
Feature activation-2.62e+00

Pos logit contributions
 bleed+0.173
 accidents+0.172
 cookies+0.171
 itch+0.168
burn+0.166
Neg logit contributions
mer-0.075
bank-0.072
ued-0.069
sel-0.062
ar-0.061
Token was
Token ID373
Feature activation-4.63e-01

Pos logit contributions
 accidents+0.077
 itch+0.072
 bleed+0.070
eddy+0.066
 stain+0.066
Neg logit contributions
ued-0.074
bank-0.068
roads-0.067
ving-0.065
boat-0.062
Token happy
Token ID3772
Feature activation-1.66e+00

Pos logit contributions
 accidents+0.011
 itch+0.010
 bleed+0.010
eddy+0.010
 stain+0.010
Neg logit contributions
ued-0.015
bank-0.014
roads-0.014
boat-0.013
 -0.013
Token.
Token ID13
Feature activation-5.80e-01

Pos logit contributions
 itch+0.045
 accidents+0.044
 bleed+0.043
burn+0.040
 stain+0.040
Neg logit contributions
ued-0.047
bank-0.045
roads-0.043
ving-0.041
mer-0.041
Token The
Token ID383
Feature activation-6.65e-01

Pos logit contributions
 accidents+0.013
eddy+0.012
 itch+0.012
 cat+0.011
 cookies+0.011
Neg logit contributions
ued-0.021
roads-0.019
bank-0.019
ving-0.018
den-0.018
Token c
Token ID269
Feature activation-5.22e+00

Pos logit contributions
 accidents+0.015
 bleed+0.015
eddy+0.014
burn+0.014
 itch+0.013
Neg logit contributions
ued-0.019
 -0.018
roads-0.018
boat-0.017
bank-0.017
Tokenactus
Token ID34144
Feature activation-2.91e+00

Pos logit contributions
 cookies+0.182
 bleed+0.182
 accidents+0.180
 itch+0.178
burn+0.175
Neg logit contributions
mer-0.074
bank-0.071
ued-0.069
pe-0.060
or-0.059
Token was
Token ID373
Feature activation-7.77e-01

Pos logit contributions
 accidents+0.080
 itch+0.074
 bleed+0.072
 stain+0.068
burn+0.067
Neg logit contributions
ued-0.088
bank-0.081
roads-0.079
ving-0.078
boat-0.075
Token complete
Token ID1844
Feature activation+4.33e-01

Pos logit contributions
 accidents+0.018
 itch+0.016
 bleed+0.016
 stain+0.015
eddy+0.015
Neg logit contributions
ued-0.026
bank-0.024
boat-0.024
roads-0.024
 -0.023
Token.
Token ID13
Feature activation-4.63e-01

Pos logit contributions
ued+0.017
roads+0.016
bank+0.015
ical+0.015
folk+0.015
Neg logit contributions
 accidents-0.009
 itch-0.008
 cookies-0.007
 bleed-0.007
 from-0.007
Token The
Token ID383
Feature activation-6.49e-01

Pos logit contributions
 accidents+0.011
 itch+0.010
eddy+0.010
 cookies+0.009
 bleed+0.009
Neg logit contributions
ued-0.016
roads-0.015
bank-0.015
ving-0.014
den-0.014
Token no
Token ID645
Feature activation+1.18e-01

Pos logit contributions
ued+0.013
bank+0.012
roads+0.012
ving+0.011
ical+0.011
Neg logit contributions
 accidents-0.008
 itch-0.008
 bleed-0.007
 stain-0.007
eddy-0.007
Token longer
Token ID2392
Feature activation+1.45e+00

Pos logit contributions
ued+0.003
bank+0.003
roads+0.003
ving+0.003
ical+0.003
Neg logit contributions
 accidents-0.003
 itch-0.003
 bleed-0.003
 stain-0.003
eddy-0.003
Token miserable
Token ID22444
Feature activation+4.14e-01

Pos logit contributions
ued+0.056
roads+0.053
bank+0.053
ving+0.050
ical+0.049
Neg logit contributions
 accidents-0.030
 itch-0.028
 bleed-0.025
 stain-0.023
 babies-0.022
Token.
Token ID13
Feature activation-7.17e-01

Pos logit contributions
ued+0.012
bank+0.011
roads+0.011
ving+0.011
ical+0.010
Neg logit contributions
 accidents-0.012
 itch-0.011
 bleed-0.010
 stain-0.010
eddy-0.010
Token He
Token ID679
Feature activation+4.05e-01

Pos logit contributions
 accidents+0.020
 itch+0.018
eddy+0.017
 bleed+0.016
 Mitt+0.016
Neg logit contributions
ued-0.023
roads-0.021
sel-0.021
ving-0.021
bank-0.021
Token c
Token ID269
Feature activation-5.21e+00

Pos logit contributions
ued+0.012
bank+0.011
roads+0.011
ving+0.011
ical+0.010
Neg logit contributions
 accidents-0.011
 itch-0.011
 bleed-0.010
 stain-0.010
eddy-0.009
Tokenuddled
Token ID32745
Feature activation-2.90e+00

Pos logit contributions
 itch+0.144
 bleed+0.143
 accidents+0.133
burn+0.128
 mosquitoes+0.125
Neg logit contributions
ued-0.149
ving-0.131
sel-0.124
bank-0.124
mer-0.123
Token up
Token ID510
Feature activation-1.60e+00

Pos logit contributions
 accidents+0.058
 itch+0.054
 bleed+0.050
 stain+0.047
eddy+0.045
Neg logit contributions
ued-0.110
bank-0.103
roads-0.102
ving-0.097
ical-0.096
Token with
Token ID351
Feature activation-9.98e-01

Pos logit contributions
 accidents+0.028
 itch+0.026
 bleed+0.023
 stain+0.021
eddy+0.020
Neg logit contributions
ued-0.065
bank-0.061
roads-0.061
ving-0.058
ical-0.058
Token the
Token ID262
Feature activation-4.64e-01

Pos logit contributions
 accidents+0.023
 itch+0.021
 bleed+0.020
 stain+0.019
eddy+0.018
Neg logit contributions
ued-0.035
bank-0.033
roads-0.033
ving-0.031
ical-0.031
Token fabric
Token ID9664
Feature activation-1.31e+00

Pos logit contributions
 accidents+0.011
 itch+0.010
 bleed+0.010
eddy+0.009
 stain+0.009
Neg logit contributions
ued-0.016
bank-0.014
roads-0.014
ving-0.014
sel-0.014
Token to
Token ID284
Feature activation-2.12e-01

Pos logit contributions
 accidents+0.021
 itch+0.017
 bleed+0.017
 cookies+0.016
eddy+0.016
Neg logit contributions
ued-0.049
roads-0.044
ving-0.044
ical-0.044
bank-0.043
Token his
Token ID465
Feature activation+2.25e-01

Pos logit contributions
 accidents+0.005
 itch+0.005
 bleed+0.005
 stain+0.005
eddy+0.004
Neg logit contributions
ued-0.007
bank-0.006
roads-0.006
ving-0.006
ical-0.006
Token bed
Token ID3996
Feature activation-1.49e+00

Pos logit contributions
ued+0.008
bank+0.008
roads+0.008
 gru+0.007
ical+0.007
Neg logit contributions
 accidents-0.005
 itch-0.004
 bleed-0.004
burn-0.004
eddy-0.004
Token.
Token ID13
Feature activation+2.65e-01

Pos logit contributions
 accidents+0.030
 itch+0.028
 stain+0.025
 cookies+0.024
 bleed+0.024
Neg logit contributions
ued-0.056
roads-0.052
bank-0.051
ving-0.050
ical-0.048
Token He
Token ID679
Feature activation+6.61e-01

Pos logit contributions
ued+0.009
roads+0.009
mer+0.009
sel+0.008
ving+0.008
Neg logit contributions
 accidents-0.006
 itch-0.005
eddy-0.005
 Mitt-0.005
 grandma-0.005
Token c
Token ID269
Feature activation-5.17e+00

Pos logit contributions
ued+0.021
bank+0.019
roads+0.019
ving+0.018
sel+0.018
Neg logit contributions
 accidents-0.018
 itch-0.017
 bleed-0.016
 stain-0.015
eddy-0.015
Tokenuddled
Token ID32745
Feature activation-2.55e+00

Pos logit contributions
 itch+0.143
 bleed+0.138
 accidents+0.131
 mosquitoes+0.125
burn+0.122
Neg logit contributions
ued-0.152
ving-0.134
bank-0.130
sel-0.126
top-0.121
Token up
Token ID510
Feature activation-1.53e+00

Pos logit contributions
 accidents+0.053
 itch+0.050
 bleed+0.046
 stain+0.043
eddy+0.041
Neg logit contributions
ued-0.094
bank-0.088
roads-0.088
ving-0.084
ical-0.083
Token under
Token ID739
Feature activation-7.21e-02

Pos logit contributions
 accidents+0.028
 itch+0.025
 bleed+0.023
 stain+0.021
eddy+0.020
Neg logit contributions
ued-0.062
bank-0.058
roads-0.057
ving-0.055
ical-0.055
Token his
Token ID465
Feature activation-3.04e-02

Pos logit contributions
 accidents+0.002
 itch+0.002
 bleed+0.002
 stain+0.001
eddy+0.001
Neg logit contributions
ued-0.002
bank-0.002
roads-0.002
ving-0.002
ical-0.002
Token blankets
Token ID34794
Feature activation-2.27e+00

Pos logit contributions
 accidents+0.001
burn+0.001
 itch+0.001
 bleed+0.001
eddy+0.001
Neg logit contributions
ued-0.001
bank-0.001
 gru-0.001
roads-0.001
ical-0.001
Token Then
Token ID3244
Feature activation+7.10e-01

Pos logit contributions
 accidents+0.007
 itch+0.006
 bleed+0.006
eddy+0.006
 stain+0.006
Neg logit contributions
ued-0.008
roads-0.008
bank-0.007
ving-0.007
boat-0.007
Token,
Token ID11
Feature activation+1.09e-01

Pos logit contributions
ued+0.019
roads+0.017
 +0.016
bank+0.016
ving+0.015
Neg logit contributions
 itch-0.021
 accidents-0.021
eddy-0.020
 bleed-0.020
 stain-0.019
Token she
Token ID673
Feature activation-8.09e-01

Pos logit contributions
ued+0.003
roads+0.003
 +0.003
bank+0.003
 1+0.003
Neg logit contributions
eddy-0.003
 accidents-0.003
 bleed-0.003
 itch-0.003
 stain-0.003
Token put
Token ID1234
Feature activation-1.12e+00

Pos logit contributions
 accidents+0.025
 itch+0.023
 bleed+0.022
eddy+0.020
 rash+0.020
Neg logit contributions
ued-0.021
sel-0.020
ving-0.019
bank-0.019
roads-0.019
Token her
Token ID607
Feature activation-2.31e+00

Pos logit contributions
 accidents+0.028
 itch+0.027
 bleed+0.025
 stain+0.023
eddy+0.022
Neg logit contributions
ued-0.037
roads-0.034
bank-0.033
sel-0.032
ving-0.032
Token t
Token ID256
Feature activation-5.15e+00

Pos logit contributions
 accidents+0.043
 itch+0.040
 bleed+0.036
 stain+0.033
eddy+0.031
Neg logit contributions
ued-0.090
roads-0.081
bank-0.081
ving-0.080
boat-0.078
Tokeneddy
Token ID21874
Feature activation-3.62e+00

Pos logit contributions
 itch+0.086
 accidents+0.079
 mosquitoes+0.072
 mess+0.064
 bleed+0.063
Neg logit contributions
ued-0.205
boat-0.203
vin-0.191
mer-0.189
sel-0.189
Token bear
Token ID6842
Feature activation-1.65e+00

Pos logit contributions
 accidents+0.090
 itch+0.087
 bleed+0.081
 stain+0.076
 rash+0.074
Neg logit contributions
ued-0.113
ving-0.100
roads-0.100
boat-0.099
bank-0.098
Token back
Token ID736
Feature activation-2.72e+00

Pos logit contributions
 accidents+0.040
 itch+0.037
 bleed+0.034
 stain+0.033
eddy+0.032
Neg logit contributions
ued-0.056
roads-0.050
ving-0.050
bank-0.049
boat-0.049
Token on
Token ID319
Feature activation+9.41e-01

Pos logit contributions
 accidents+0.052
 itch+0.048
 bleed+0.043
 stain+0.041
eddy+0.040
Neg logit contributions
ued-0.106
bank-0.100
roads-0.099
ving-0.094
ical-0.094
Token the
Token ID262
Feature activation+1.76e-01

Pos logit contributions
ued+0.033
bank+0.031
roads+0.031
ving+0.029
sel+0.029
Neg logit contributions
 accidents-0.021
 itch-0.020
 bleed-0.019
 stain-0.017
eddy-0.017
Token the
Token ID262
Feature activation-9.24e-01

Pos logit contributions
 accidents+0.034
 itch+0.032
 bleed+0.030
 stain+0.028
eddy+0.027
Neg logit contributions
ued-0.051
bank-0.048
roads-0.047
ving-0.044
boat-0.044
Token wonderful
Token ID7932
Feature activation-1.21e+00

Pos logit contributions
 accidents+0.018
 itch+0.016
 bleed+0.015
eddy+0.014
burn+0.014
Neg logit contributions
ued-0.035
bank-0.032
roads-0.032
ving-0.030
ical-0.030
Token things
Token ID1243
Feature activation-2.65e+00

Pos logit contributions
 bleed+0.027
 itch+0.026
 accidents+0.026
burn+0.024
eddy+0.023
Neg logit contributions
ued-0.039
bank-0.036
roads-0.036
folk-0.032
mer-0.032
Token!
Token ID0
Feature activation-3.78e-01

Pos logit contributions
 accidents+0.066
 itch+0.063
 bleed+0.059
 stain+0.056
eddy+0.054
Neg logit contributions
ued-0.087
bank-0.080
roads-0.079
ving-0.076
sel-0.074
Token They
Token ID1119
Feature activation-1.16e+00

Pos logit contributions
 accidents+0.010
 itch+0.010
 bleed+0.009
eddy+0.009
 stain+0.009
Neg logit contributions
ued-0.012
roads-0.011
bank-0.011
ving-0.010
ical-0.010
Token c
Token ID269
Feature activation-5.14e+00

Pos logit contributions
 accidents+0.033
 itch+0.031
 bleed+0.029
 stain+0.028
eddy+0.027
Neg logit contributions
ued-0.035
bank-0.032
roads-0.031
ving-0.030
sel-0.030
Tokenuddled
Token ID32745
Feature activation-2.75e+00

Pos logit contributions
 bleed+0.157
 itch+0.155
 accidents+0.141
 Luna+0.135
burn+0.134
Neg logit contributions
ued-0.142
ised-0.114
ving-0.113
bank-0.104
mer-0.104
Token the
Token ID262
Feature activation-2.03e+00

Pos logit contributions
 accidents+0.062
 itch+0.060
 bleed+0.055
 stain+0.053
eddy+0.050
Neg logit contributions
ued-0.096
bank-0.090
roads-0.089
ving-0.085
ical-0.083
Token baby
Token ID5156
Feature activation-2.85e+00

Pos logit contributions
 accidents+0.041
 bleed+0.038
 itch+0.038
imi+0.032
 stain+0.031
Neg logit contributions
ued-0.075
roads-0.067
bank-0.066
ving-0.064
mer-0.064
Token and
Token ID290
Feature activation-4.02e-01

Pos logit contributions
 accidents+0.061
 itch+0.060
 bleed+0.058
 stain+0.053
imi+0.052
Neg logit contributions
ued-0.096
roads-0.089
bank-0.088
mer-0.087
folk-0.087
Token spoiled
Token ID34781
Feature activation-1.32e-01

Pos logit contributions
 accidents+0.012
 itch+0.011
 bleed+0.011
eddy+0.011
 stain+0.010
Neg logit contributions
bank-0.010
ued-0.010
 -0.009
roads-0.009
sel-0.009
Token on
Token ID319
Feature activation+1.47e-01

Pos logit contributions
 accidents+0.038
 itch+0.036
 bleed+0.033
 stain+0.032
eddy+0.031
Neg logit contributions
ued-0.055
bank-0.051
roads-0.051
ving-0.048
sel-0.048
Token dry
Token ID5894
Feature activation-6.16e-01

Pos logit contributions
ued+0.005
bank+0.004
roads+0.004
 +0.004
ving+0.004
Neg logit contributions
 accidents-0.004
 itch-0.004
 bleed-0.003
 stain-0.003
eddy-0.003
Token clothes
Token ID8242
Feature activation-1.47e+00

Pos logit contributions
 accidents+0.014
 itch+0.013
 bleed+0.012
 stain+0.011
eddy+0.011
Neg logit contributions
ued-0.021
bank-0.020
roads-0.020
ving-0.019
sel-0.019
Token.
Token ID13
Feature activation-1.41e+00

Pos logit contributions
 accidents+0.025
 itch+0.023
 bleed+0.021
 stain+0.019
eddy+0.018
Neg logit contributions
ued-0.059
bank-0.056
roads-0.056
ving-0.054
sel-0.053
Token They
Token ID1119
Feature activation-1.12e+00

Pos logit contributions
 accidents+0.045
 itch+0.044
 bleed+0.041
 stain+0.039
burn+0.038
Neg logit contributions
ued-0.036
bank-0.033
roads-0.032
ical-0.030
ving-0.030
Token c
Token ID269
Feature activation-5.10e+00

Pos logit contributions
 accidents+0.028
 itch+0.027
 bleed+0.025
 stain+0.024
eddy+0.023
Neg logit contributions
ued-0.036
bank-0.034
roads-0.034
ving-0.032
ical-0.031
Tokenuddled
Token ID32745
Feature activation-2.79e+00

Pos logit contributions
 itch+0.147
 accidents+0.138
 bleed+0.137
 cat+0.126
 stain+0.126
Neg logit contributions
ued-0.135
ving-0.115
bank-0.112
sel-0.112
ised-0.111
Token with
Token ID351
Feature activation-1.48e+00

Pos logit contributions
 accidents+0.057
 itch+0.054
 bleed+0.048
 stain+0.047
eddy+0.044
Neg logit contributions
ued-0.104
bank-0.098
roads-0.097
ving-0.093
ical-0.091
Token their
Token ID511
Feature activation-3.64e-01

Pos logit contributions
 accidents+0.034
 itch+0.032
 bleed+0.030
eddy+0.029
 stain+0.029
Neg logit contributions
ued-0.047
bank-0.044
roads-0.043
 -0.042
sel-0.041
Token dog
Token ID3290
Feature activation+4.70e-01

Pos logit contributions
 accidents+0.008
 itch+0.007
 bleed+0.007
arter+0.007
eddy+0.007
Neg logit contributions
ued-0.011
 banks-0.010
bank-0.010
 bank-0.010
mer-0.010
Token and
Token ID290
Feature activation-8.86e-01

Pos logit contributions
ued+0.014
bank+0.013
roads+0.013
ving+0.012
ical+0.012
Neg logit contributions
 accidents-0.013
 itch-0.012
 bleed-0.011
 stain-0.011
eddy-0.011
Token into
Token ID656
Feature activation+2.83e-01

Pos logit contributions
ued+0.025
bank+0.023
roads+0.023
ical+0.022
ving+0.022
Neg logit contributions
 accidents-0.010
 itch-0.009
 bleed-0.008
 cookies-0.008
eddy-0.008
Token their
Token ID511
Feature activation+4.38e-01

Pos logit contributions
ued+0.011
bank+0.010
roads+0.010
ving+0.010
ical+0.010
Neg logit contributions
 accidents-0.006
 itch-0.005
 bleed-0.005
 stain-0.005
 cookies-0.004
Token beds
Token ID20237
Feature activation-1.40e+00

Pos logit contributions
ued+0.012
bank+0.012
roads+0.012
 gru+0.011
 +0.011
Neg logit contributions
 accidents-0.012
 bleed-0.011
 itch-0.011
burn-0.010
eddy-0.009
Token.
Token ID13
Feature activation-9.22e-01

Pos logit contributions
 accidents+0.032
 itch+0.031
 bleed+0.028
 stain+0.028
eddy+0.027
Neg logit contributions
ued-0.049
roads-0.045
bank-0.043
ving-0.043
ical-0.041
Token They
Token ID1119
Feature activation-1.07e+00

Pos logit contributions
 accidents+0.019
 itch+0.017
eddy+0.016
 bleed+0.016
 Mitt+0.016
Neg logit contributions
ued-0.034
roads-0.031
boat-0.031
bank-0.031
sel-0.030
Token c
Token ID269
Feature activation-5.10e+00

Pos logit contributions
 accidents+0.028
 itch+0.028
 bleed+0.026
 stain+0.025
 cookies+0.024
Neg logit contributions
ued-0.034
bank-0.031
roads-0.031
ving-0.029
ical-0.029
Tokenuddled
Token ID32745
Feature activation-2.79e+00

Pos logit contributions
 itch+0.153
 bleed+0.147
 accidents+0.145
 mosquitoes+0.132
 from+0.129
Neg logit contributions
ued-0.138
ving-0.118
bank-0.114
sel-0.114
mer-0.108
Token with
Token ID351
Feature activation-1.19e+00

Pos logit contributions
 accidents+0.066
 itch+0.063
 bleed+0.058
 stain+0.057
eddy+0.053
Neg logit contributions
ued-0.093
bank-0.088
roads-0.087
ving-0.083
boat-0.080
Token their
Token ID511
Feature activation-2.56e-01

Pos logit contributions
 accidents+0.030
 itch+0.028
 bleed+0.026
eddy+0.025
 stain+0.025
Neg logit contributions
ued-0.036
bank-0.033
sel-0.033
 -0.033
roads-0.032
Token t
Token ID256
Feature activation-3.33e+00

Pos logit contributions
 accidents+0.006
 bleed+0.005
burn+0.005
 itch+0.005
eddy+0.005
Neg logit contributions
ued-0.008
mer-0.007
 banks-0.007
 bank-0.007
bank-0.007
Tokeneddy
Token ID21874
Feature activation-1.77e+00

Pos logit contributions
 itch+0.058
 accidents+0.050
 bleed+0.046
 mosquitoes+0.044
 stain+0.037
Neg logit contributions
boat-0.128
ued-0.128
mer-0.124
den-0.124
sel-0.123
Token.
Token ID13
Feature activation-7.42e-01

Pos logit contributions
 accidents+0.098
 itch+0.096
 bleed+0.093
imi+0.089
burn+0.087
Neg logit contributions
bank-0.056
ued-0.053
roads-0.052
mer-0.049
boat-0.048
Token They
Token ID1119
Feature activation-9.62e-01

Pos logit contributions
 accidents+0.020
 itch+0.019
 bleed+0.018
 stain+0.017
eddy+0.017
Neg logit contributions
ued-0.024
roads-0.022
bank-0.022
ving-0.020
boat-0.020
Token yawn
Token ID40908
Feature activation-2.91e+00

Pos logit contributions
 accidents+0.024
eddy+0.021
 itch+0.019
burn+0.019
 cookies+0.018
Neg logit contributions
ued-0.033
roads-0.030
bank-0.030
sel-0.029
ving-0.029
Token.
Token ID13
Feature activation-5.10e-01

Pos logit contributions
 accidents+0.099
 itch+0.097
 bleed+0.093
 stain+0.088
 mosquitoes+0.088
Neg logit contributions
ued-0.061
ical-0.056
sel-0.055
mer-0.055
ving-0.055
Token They
Token ID1119
Feature activation-6.30e-01

Pos logit contributions
 accidents+0.012
 itch+0.012
 bleed+0.011
 stain+0.010
eddy+0.010
Neg logit contributions
ued-0.018
roads-0.017
bank-0.016
boat-0.015
ving-0.015
Token c
Token ID269
Feature activation-5.09e+00

Pos logit contributions
 accidents+0.015
eddy+0.012
 itch+0.012
burn+0.011
 bleed+0.011
Neg logit contributions
ued-0.022
roads-0.021
bank-0.021
ving-0.020
sel-0.020
Tokenuddle
Token ID24500
Feature activation-3.29e+00

Pos logit contributions
 itch+0.161
 accidents+0.156
 bleed+0.152
burn+0.148
 hugging+0.144
Neg logit contributions
ued-0.107
ving-0.094
sel-0.090
top-0.087
ways-0.085
Token with
Token ID351
Feature activation-8.47e-01

Pos logit contributions
 itch+0.082
 accidents+0.078
 bleed+0.071
burn+0.069
 stain+0.068
Neg logit contributions
ued-0.096
bank-0.094
sc-0.094
mer-0.094
roads-0.093
Token their
Token ID511
Feature activation-1.07e-01

Pos logit contributions
 accidents+0.020
 itch+0.019
 bleed+0.018
eddy+0.017
burn+0.017
Neg logit contributions
ued-0.026
bank-0.025
roads-0.024
sel-0.024
 -0.023
Token t
Token ID256
Feature activation-3.03e+00

Pos logit contributions
 accidents+0.003
 itch+0.002
 bleed+0.002
burn+0.002
eddy+0.002
Neg logit contributions
ued-0.003
bank-0.003
roads-0.003
mer-0.003
sel-0.003
Tokeneddy
Token ID21874
Feature activation-2.01e+00

Pos logit contributions
 itch+0.052
 accidents+0.041
 bleed+0.039
 mosquitoes+0.034
 cookies+0.031
Neg logit contributions
boat-0.121
ued-0.118
sel-0.117
den-0.117
mer-0.114
Token by
Token ID416
Feature activation+5.22e-01

Pos logit contributions
 accidents+0.011
 itch+0.011
 bleed+0.010
 stain+0.010
burn+0.009
Neg logit contributions
ued-0.017
bank-0.016
roads-0.016
ving-0.015
sel-0.015
Token the
Token ID262
Feature activation-2.14e-01

Pos logit contributions
ued+0.018
bank+0.017
roads+0.017
ving+0.016
sel+0.016
Neg logit contributions
 accidents-0.012
 itch-0.011
 bleed-0.010
 stain-0.010
eddy-0.010
Token fireplace
Token ID44250
Feature activation-6.52e-01

Pos logit contributions
 accidents+0.006
 itch+0.006
 bleed+0.005
 stain+0.005
burn+0.005
Neg logit contributions
ued-0.006
bank-0.006
roads-0.006
 gru-0.005
ving-0.005
Token.
Token ID13
Feature activation-8.47e-01

Pos logit contributions
 accidents+0.016
 itch+0.016
 bleed+0.014
 stain+0.014
eddy+0.014
Neg logit contributions
ued-0.022
roads-0.020
bank-0.019
ving-0.019
ical-0.018
Token They
Token ID1119
Feature activation-7.20e-01

Pos logit contributions
 accidents+0.025
 itch+0.024
 bleed+0.022
 stain+0.021
eddy+0.021
Neg logit contributions
ued-0.025
bank-0.023
roads-0.022
ving-0.021
ical-0.021
Token c
Token ID269
Feature activation-5.08e+00

Pos logit contributions
 accidents+0.020
 itch+0.019
 bleed+0.018
 stain+0.017
eddy+0.017
Neg logit contributions
ued-0.021
bank-0.020
roads-0.019
ving-0.018
sel-0.018
Tokenuddled
Token ID32745
Feature activation-2.60e+00

Pos logit contributions
 itch+0.151
 accidents+0.140
 bleed+0.140
 stain+0.132
 mosquitoes+0.131
Neg logit contributions
ued-0.138
ving-0.118
bank-0.118
sel-0.111
ised-0.110
Token on
Token ID319
Feature activation-2.75e-01

Pos logit contributions
 accidents+0.055
 itch+0.052
 bleed+0.047
 stain+0.046
eddy+0.042
Neg logit contributions
ued-0.095
bank-0.090
roads-0.089
ving-0.085
sel-0.083
Token the
Token ID262
Feature activation-9.20e-01

Pos logit contributions
 accidents+0.006
 itch+0.006
 bleed+0.006
 stain+0.005
eddy+0.005
Neg logit contributions
ued-0.009
bank-0.009
roads-0.009
ving-0.008
sel-0.008
Token sofa
Token ID34902
Feature activation-7.62e-01

Pos logit contributions
 accidents+0.021
 itch+0.019
 bleed+0.018
 stain+0.017
eddy+0.016
Neg logit contributions
ued-0.032
bank-0.030
roads-0.030
ving-0.028
boat-0.028
Token.
Token ID13
Feature activation-1.01e+00

Pos logit contributions
 accidents+0.016
 itch+0.015
 bleed+0.014
 stain+0.013
 cookies+0.013
Neg logit contributions
ued-0.028
roads-0.026
bank-0.026
ving-0.025
ical-0.024
Token happy
Token ID3772
Feature activation-2.01e+00

Pos logit contributions
 accidents+0.018
 stain+0.017
 bleed+0.016
eddy+0.016
 itch+0.015
Neg logit contributions
ued-0.018
 -0.016
bank-0.016
ving-0.015
roads-0.015
Token and
Token ID290
Feature activation-6.85e-02

Pos logit contributions
 itch+0.053
 bleed+0.053
 stain+0.046
burn+0.046
 accidents+0.045
Neg logit contributions
bank-0.054
ued-0.052
 -0.049
mer-0.046
top-0.046
Token tired
Token ID10032
Feature activation-2.90e+00

Pos logit contributions
 accidents+0.002
 itch+0.002
 stain+0.002
 bleed+0.002
imi+0.002
Neg logit contributions
ued-0.002
bank-0.002
 -0.002
boat-0.002
sel-0.002
Token.
Token ID13
Feature activation-9.25e-01

Pos logit contributions
 accidents+0.073
 itch+0.070
 bleed+0.067
 stain+0.063
eddy+0.062
Neg logit contributions
ued-0.092
bank-0.087
roads-0.084
boat-0.079
ving-0.079
Token They
Token ID1119
Feature activation-1.52e+00

Pos logit contributions
 accidents+0.020
 itch+0.018
eddy+0.017
 Mitt+0.017
 grandma+0.016
Neg logit contributions
ued-0.035
roads-0.033
bank-0.032
ving-0.031
boat-0.031
Token c
Token ID269
Feature activation-5.08e+00

Pos logit contributions
 accidents+0.041
 itch+0.040
 bleed+0.037
 stain+0.036
eddy+0.034
Neg logit contributions
ued-0.047
bank-0.043
roads-0.043
ving-0.041
ical-0.040
Tokenuddled
Token ID32745
Feature activation-2.79e+00

Pos logit contributions
 bleed+0.140
 itch+0.140
 accidents+0.136
 stain+0.127
 wake+0.125
Neg logit contributions
ued-0.137
mer-0.116
ised-0.115
bank-0.113
ving-0.112
Token on
Token ID319
Feature activation-8.83e-01

Pos logit contributions
 accidents+0.064
 itch+0.061
 bleed+0.057
 stain+0.056
eddy+0.053
Neg logit contributions
ued-0.094
bank-0.089
roads-0.087
ving-0.083
boat-0.081
Token the
Token ID262
Feature activation-1.13e+00

Pos logit contributions
 accidents+0.022
 itch+0.021
 bleed+0.020
 stain+0.019
eddy+0.018
Neg logit contributions
ued-0.028
bank-0.027
roads-0.026
ving-0.025
sel-0.024
Token sofa
Token ID34902
Feature activation-1.10e+00

Pos logit contributions
 accidents+0.030
 bleed+0.026
 itch+0.025
burn+0.024
eddy+0.023
Neg logit contributions
ued-0.033
bank-0.032
roads-0.031
 banks-0.029
boat-0.029
Token and
Token ID290
Feature activation-1.02e+00

Pos logit contributions
 accidents+0.016
 itch+0.015
 bleed+0.013
 stain+0.012
 cookies+0.012
Neg logit contributions
ued-0.047
roads-0.044
bank-0.044
ving-0.043
ical-0.042
Token she
Token ID673
Feature activation+5.54e-01

Pos logit contributions
 accidents+0.014
 itch+0.013
 bleed+0.013
 stain+0.012
eddy+0.012
Neg logit contributions
ued-0.016
bank-0.014
roads-0.014
ving-0.013
ical-0.013
Token loved
Token ID6151
Feature activation-1.30e+00

Pos logit contributions
ued+0.014
bank+0.013
ving+0.012
roads+0.012
sel+0.012
Neg logit contributions
 accidents-0.018
 itch-0.017
 bleed-0.016
 stain-0.015
eddy-0.015
Token him
Token ID683
Feature activation+5.02e-01

Pos logit contributions
 accidents+0.024
 itch+0.024
 bleed+0.021
 stain+0.020
eddy+0.019
Neg logit contributions
ued-0.049
bank-0.047
roads-0.046
ving-0.043
sel-0.043
Token.
Token ID13
Feature activation-2.68e-01

Pos logit contributions
ued+0.019
bank+0.018
roads+0.017
ving+0.017
ical+0.016
Neg logit contributions
 accidents-0.011
 itch-0.010
 bleed-0.009
 stain-0.008
 cookies-0.008
Token They
Token ID1119
Feature activation-8.99e-01

Pos logit contributions
 accidents+0.006
 itch+0.006
 bleed+0.006
 stain+0.005
eddy+0.005
Neg logit contributions
ued-0.009
bank-0.008
roads-0.008
ving-0.008
sel-0.008
Token c
Token ID269
Feature activation-5.04e+00

Pos logit contributions
 accidents+0.024
 itch+0.023
 bleed+0.021
 stain+0.021
 cookies+0.020
Neg logit contributions
ued-0.028
bank-0.026
roads-0.026
ving-0.025
ical-0.024
Tokenuddled
Token ID32745
Feature activation-2.52e+00

Pos logit contributions
 itch+0.151
 bleed+0.141
 accidents+0.141
 stain+0.133
 mosquitoes+0.131
Neg logit contributions
ued-0.134
ving-0.110
sel-0.109
mer-0.109
ar-0.109
Token on
Token ID319
Feature activation-6.48e-02

Pos logit contributions
 accidents+0.052
 itch+0.049
 bleed+0.045
 stain+0.044
eddy+0.041
Neg logit contributions
ued-0.093
bank-0.088
roads-0.087
ving-0.082
sel-0.081
Token the
Token ID262
Feature activation-4.08e-01

Pos logit contributions
 accidents+0.001
 itch+0.001
 bleed+0.001
 stain+0.001
eddy+0.001
Neg logit contributions
ued-0.002
bank-0.002
roads-0.002
ving-0.002
sel-0.002
Token couch
Token ID18507
Feature activation-1.08e+00

Pos logit contributions
 accidents+0.011
 itch+0.009
 bleed+0.009
burn+0.008
imi+0.008
Neg logit contributions
ued-0.012
bank-0.011
roads-0.011
 bank-0.011
boat-0.010
Token and
Token ID290
Feature activation-8.14e-01

Pos logit contributions
 accidents+0.016
 itch+0.015
 bleed+0.013
 cookies+0.012
 stain+0.012
Neg logit contributions
ued-0.046
roads-0.043
bank-0.043
ving-0.042
sel-0.041
Token baby
Token ID5156
Feature activation-3.04e-01

Pos logit contributions
 accidents+0.002
 itch+0.002
 bleed+0.002
 stain+0.002
burn+0.002
Neg logit contributions
ued-0.005
bank-0.004
roads-0.004
mer-0.004
 gru-0.004
Token."
Token ID526
Feature activation-3.43e-01

Pos logit contributions
 accidents+0.008
 itch+0.008
 bleed+0.007
 stain+0.007
eddy+0.007
Neg logit contributions
ued-0.009
bank-0.009
roads-0.009
ving-0.008
ical-0.008
Token
Token ID198
Feature activation-3.19e-01

Pos logit contributions
 accidents+0.009
 itch+0.009
 bleed+0.008
eddy+0.008
 cookies+0.008
Neg logit contributions
ued-0.011
roads-0.010
bank-0.010
ving-0.009
ical-0.009
Token
Token ID198
Feature activation+3.77e-02

Pos logit contributions
 accidents+0.010
 itch+0.010
 bleed+0.009
 stain+0.009
burn+0.009
Neg logit contributions
ued-0.008
bank-0.008
roads-0.007
ving-0.007
sel-0.007
TokenThey
Token ID2990
Feature activation-7.24e-01

Pos logit contributions
ued+0.001
bank+0.001
roads+0.001
ving+0.001
ical+0.001
Neg logit contributions
 accidents-0.001
 itch-0.001
 bleed-0.001
 stain-0.001
eddy-0.001
Token c
Token ID269
Feature activation-5.04e+00

Pos logit contributions
 accidents+0.018
 itch+0.017
 bleed+0.016
 stain+0.015
eddy+0.015
Neg logit contributions
ued-0.024
bank-0.022
roads-0.022
ving-0.021
sel-0.021
Tokenuddled
Token ID32745
Feature activation-2.88e+00

Pos logit contributions
 itch+0.163
 bleed+0.157
 accidents+0.151
 mosquitoes+0.142
 wake+0.140
Neg logit contributions
ued-0.130
ving-0.106
ised-0.099
orted-0.097
ar-0.096
Token in
Token ID287
Feature activation-1.20e-02

Pos logit contributions
 accidents+0.066
 itch+0.062
 stain+0.057
 bleed+0.056
imi+0.053
Neg logit contributions
ued-0.099
bank-0.094
roads-0.092
ving-0.088
mer-0.087
Token the
Token ID262
Feature activation-5.81e-01

Pos logit contributions
 accidents+0.000
 itch+0.000
 bleed+0.000
 stain+0.000
eddy+0.000
Neg logit contributions
ued-0.000
roads-0.000
bank-0.000
 -0.000
sel-0.000
Token chair
Token ID5118
Feature activation-1.09e+00

Pos logit contributions
 accidents+0.015
 itch+0.014
 bleed+0.014
burn+0.012
eddy+0.012
Neg logit contributions
ued-0.017
roads-0.017
bank-0.016
 gru-0.015
 -0.015
Token and
Token ID290
Feature activation-4.43e-01

Pos logit contributions
 accidents+0.016
 itch+0.015
 bleed+0.013
 stain+0.012
 cookies+0.012
Neg logit contributions
ued-0.047
roads-0.044
bank-0.044
ving-0.042
ical-0.042
Token him
Token ID683
Feature activation+3.82e-01

Pos logit contributions
 accidents+0.037
 itch+0.035
 bleed+0.032
 stain+0.030
eddy+0.028
Neg logit contributions
ued-0.066
bank-0.062
roads-0.061
ving-0.058
sel-0.058
Token a
Token ID257
Feature activation+1.44e-01

Pos logit contributions
ued+0.013
bank+0.012
roads+0.011
ving+0.011
sel+0.011
Neg logit contributions
 accidents-0.009
 itch-0.009
 bleed-0.008
 stain-0.008
eddy-0.008
Token treat
Token ID2190
Feature activation-5.39e-01

Pos logit contributions
ued+0.006
bank+0.005
roads+0.005
boat+0.005
ical+0.005
Neg logit contributions
 accidents-0.003
 itch-0.002
 bleed-0.002
 stain-0.002
eddy-0.002
Token.
Token ID13
Feature activation-1.06e+00

Pos logit contributions
 accidents+0.013
 itch+0.013
eddy+0.012
 cookies+0.012
 bleed+0.011
Neg logit contributions
ued-0.018
roads-0.017
bank-0.016
ving-0.016
ical-0.015
Token They
Token ID1119
Feature activation-1.05e+00

Pos logit contributions
 accidents+0.026
 itch+0.024
eddy+0.022
 bleed+0.022
 stain+0.022
Neg logit contributions
ued-0.037
roads-0.034
bank-0.033
ving-0.033
mer-0.032
Token c
Token ID269
Feature activation-5.03e+00

Pos logit contributions
 accidents+0.030
 itch+0.028
 bleed+0.027
 stain+0.026
eddy+0.025
Neg logit contributions
ued-0.031
bank-0.028
roads-0.028
ving-0.027
sel-0.026
Tokenuddled
Token ID32745
Feature activation-2.57e+00

Pos logit contributions
 itch+0.149
 accidents+0.139
 bleed+0.137
 mosquitoes+0.133
 cat+0.127
Neg logit contributions
ued-0.131
sel-0.118
bank-0.114
ving-0.113
ar-0.110
Token with
Token ID351
Feature activation-1.47e+00

Pos logit contributions
 accidents+0.056
 itch+0.053
 bleed+0.048
 stain+0.047
eddy+0.044
Neg logit contributions
ued-0.091
bank-0.087
roads-0.086
ving-0.081
sel-0.080
Token him
Token ID683
Feature activation-3.88e-01

Pos logit contributions
 accidents+0.033
 itch+0.031
 bleed+0.029
 stain+0.027
eddy+0.026
Neg logit contributions
ued-0.050
bank-0.047
roads-0.046
sel-0.045
boat-0.043
Token on
Token ID319
Feature activation+4.42e-01

Pos logit contributions
 accidents+0.008
 itch+0.008
 bleed+0.007
 stain+0.007
eddy+0.006
Neg logit contributions
ued-0.014
bank-0.013
roads-0.013
ving-0.013
sel-0.012
Token the
Token ID262
Feature activation+3.77e-01

Pos logit contributions
ued+0.016
roads+0.015
bank+0.015
ving+0.015
ical+0.015
Neg logit contributions
 accidents-0.009
 itch-0.009
 bleed-0.008
 stain-0.008
 cookies-0.008
Tokenactus
Token ID34144
Feature activation-2.56e+00

Pos logit contributions
 bleed+0.167
 accidents+0.167
 cookies+0.163
 itch+0.162
burn+0.155
Neg logit contributions
bank-0.071
mer-0.070
ued-0.062
sel-0.060
ard-0.058
Token was
Token ID373
Feature activation-2.64e-01

Pos logit contributions
 accidents+0.078
 itch+0.073
 bleed+0.071
eddy+0.067
 stain+0.067
Neg logit contributions
ued-0.070
bank-0.064
roads-0.062
ving-0.060
sel-0.058
Token taller
Token ID25242
Feature activation-2.61e-01

Pos logit contributions
 accidents+0.005
 itch+0.005
 bleed+0.005
 stain+0.004
eddy+0.004
Neg logit contributions
ued-0.010
bank-0.009
roads-0.009
ving-0.009
sel-0.009
Token.
Token ID13
Feature activation-5.11e-01

Pos logit contributions
 accidents+0.007
 itch+0.007
 bleed+0.006
 stain+0.006
burn+0.006
Neg logit contributions
ued-0.008
bank-0.007
roads-0.007
mer-0.007
sel-0.007
Token The
Token ID383
Feature activation-3.71e-01

Pos logit contributions
 accidents+0.012
 itch+0.011
eddy+0.011
 cookies+0.010
 cat+0.010
Neg logit contributions
ued-0.018
roads-0.017
bank-0.016
den-0.016
ving-0.015
Token c
Token ID269
Feature activation-5.03e+00

Pos logit contributions
 accidents+0.008
 bleed+0.008
eddy+0.008
 itch+0.007
burn+0.007
Neg logit contributions
ued-0.011
roads-0.010
bank-0.010
boat-0.010
 -0.010
Tokenactus
Token ID34144
Feature activation-2.62e+00

Pos logit contributions
 bleed+0.173
 accidents+0.172
 cookies+0.171
 itch+0.168
burn+0.166
Neg logit contributions
mer-0.075
bank-0.072
ued-0.069
sel-0.062
ar-0.061
Token was
Token ID373
Feature activation-4.63e-01

Pos logit contributions
 accidents+0.077
 itch+0.072
 bleed+0.070
eddy+0.066
 stain+0.066
Neg logit contributions
ued-0.074
bank-0.068
roads-0.067
ving-0.065
boat-0.062
Token happy
Token ID3772
Feature activation-1.66e+00

Pos logit contributions
 accidents+0.011
 itch+0.010
 bleed+0.010
eddy+0.010
 stain+0.010
Neg logit contributions
ued-0.015
bank-0.014
roads-0.014
boat-0.013
 -0.013
Token.
Token ID13
Feature activation-5.80e-01

Pos logit contributions
 itch+0.045
 accidents+0.044
 bleed+0.043
burn+0.040
 stain+0.040
Neg logit contributions
ued-0.047
bank-0.045
roads-0.043
ving-0.041
mer-0.041
Token The
Token ID383
Feature activation-6.65e-01

Pos logit contributions
 accidents+0.013
eddy+0.012
 itch+0.012
 cat+0.011
 cookies+0.011
Neg logit contributions
ued-0.021
roads-0.019
bank-0.019
ving-0.018
den-0.018
Token a
Token ID257
Feature activation-1.33e-01

Pos logit contributions
 accidents+0.004
 cookies+0.004
 itch+0.004
 bleed+0.003
 her+0.003
Neg logit contributions
ued-0.007
roads-0.007
bank-0.007
boat-0.006
folk-0.006
Token story
Token ID1621
Feature activation+7.14e-01

Pos logit contributions
 accidents+0.003
 itch+0.003
 bleed+0.002
 stain+0.002
eddy+0.002
Neg logit contributions
ued-0.005
bank-0.005
roads-0.005
ving-0.004
ical-0.004
Token.
Token ID13
Feature activation-1.01e+00

Pos logit contributions
ued+0.024
bank+0.023
roads+0.023
ving+0.021
boat+0.021
Neg logit contributions
 accidents-0.017
 itch-0.016
 cookies-0.014
 bleed-0.014
 stain-0.014
Token They
Token ID1119
Feature activation-1.02e+00

Pos logit contributions
 accidents+0.022
 itch+0.020
eddy+0.018
 bleed+0.018
 cookies+0.018
Neg logit contributions
ued-0.037
roads-0.035
bank-0.035
boat-0.033
ving-0.033
Token all
Token ID477
Feature activation-1.47e+00

Pos logit contributions
 accidents+0.026
 itch+0.025
 bleed+0.023
 stain+0.022
eddy+0.021
Neg logit contributions
ued-0.033
bank-0.030
roads-0.030
ving-0.029
ical-0.028
Token c
Token ID269
Feature activation-5.01e+00

Pos logit contributions
 itch+0.036
 accidents+0.036
 bleed+0.033
 stain+0.032
 cookies+0.030
Neg logit contributions
ued-0.048
bank-0.045
roads-0.044
ving-0.042
ical-0.042
Tokenuddled
Token ID32745
Feature activation-2.66e+00

Pos logit contributions
 itch+0.139
 bleed+0.132
 accidents+0.130
 stain+0.124
 bleeding+0.113
Neg logit contributions
ued-0.145
sel-0.127
ving-0.126
bank-0.125
mer-0.125
Token and
Token ID290
Feature activation-4.03e-03

Pos logit contributions
 accidents+0.061
 itch+0.058
 bleed+0.054
 stain+0.052
eddy+0.048
Neg logit contributions
ued-0.092
bank-0.086
roads-0.086
ving-0.082
sel-0.080
Token laughed
Token ID13818
Feature activation-9.94e-01

Pos logit contributions
 accidents+0.000
eddy+0.000
 itch+0.000
imi+0.000
 bleed+0.000
Neg logit contributions
ued-0.000
bank-0.000
roads-0.000
 -0.000
sel-0.000
Token and
Token ID290
Feature activation+4.67e-01

Pos logit contributions
 accidents+0.025
 itch+0.023
 bleed+0.023
 stain+0.021
 rash+0.020
Neg logit contributions
ued-0.032
bank-0.029
roads-0.028
ving-0.028
ical-0.028
Token enjoyed
Token ID8359
Feature activation-1.64e+00

Pos logit contributions
ued+0.015
bank+0.014
roads+0.013
ving+0.013
ical+0.012
Neg logit contributions
 accidents-0.012
 itch-0.012
 bleed-0.011
 stain-0.010
eddy-0.010
Token to
Token ID284
Feature activation-5.59e-01

Pos logit contributions
ued+0.012
bank+0.011
roads+0.011
ving+0.011
ical+0.010
Neg logit contributions
 accidents-0.008
 itch-0.007
 bleed-0.006
 stain-0.006
 cookies-0.006
Token be
Token ID307
Feature activation+2.15e+00

Pos logit contributions
 accidents+0.009
 itch+0.008
 bleed+0.007
 stain+0.007
 cookies+0.006
Neg logit contributions
ued-0.024
bank-0.022
roads-0.022
ving-0.022
ical-0.021
Token in
Token ID287
Feature activation+1.70e+00

Pos logit contributions
ued+0.079
bank+0.074
roads+0.073
ving+0.069
ical+0.068
Neg logit contributions
 accidents-0.047
 itch-0.045
 bleed-0.039
 cookies-0.039
 stain-0.038
Token the
Token ID262
Feature activation+1.38e+00

Pos logit contributions
ued+0.064
bank+0.060
roads+0.059
ving+0.058
ical+0.057
Neg logit contributions
 accidents-0.035
 itch-0.032
 bleed-0.029
 stain-0.028
 cookies-0.026
Token next
Token ID1306
Feature activation+1.43e+00

Pos logit contributions
ued+0.046
bank+0.043
roads+0.041
ving+0.041
sel+0.040
Neg logit contributions
 accidents-0.034
 itch-0.033
 stain-0.030
 bleed-0.030
 cookies-0.029
Token show
Token ID905
Feature activation+3.14e+00

Pos logit contributions
ued+0.054
bank+0.050
sel+0.049
roads+0.048
ving+0.048
Neg logit contributions
 accidents-0.028
 itch-0.026
 cookies-0.025
 stain-0.025
 cat-0.025
Token.
Token ID13
Feature activation+1.36e-01

Pos logit contributions
ued+0.111
bank+0.105
roads+0.101
ving+0.097
ical+0.096
Neg logit contributions
 accidents-0.071
 itch-0.063
 cookies-0.059
 babies-0.058
 stain-0.058
Token Her
Token ID2332
Feature activation-1.27e+00

Pos logit contributions
ued+0.006
roads+0.005
boat+0.005
bank+0.005
ving+0.005
Neg logit contributions
 accidents-0.002
 itch-0.002
 stain-0.002
eddy-0.002
 bleed-0.002
Token brother
Token ID3956
Feature activation+1.09e+00

Pos logit contributions
 accidents+0.028
 bleed+0.027
 itch+0.025
burn+0.023
eddy+0.023
Neg logit contributions
ued-0.044
ving-0.038
ical-0.038
 1-0.038
 2-0.038
Token was
Token ID373
Feature activation+8.34e-01

Pos logit contributions
ued+0.036
roads+0.034
bank+0.033
ving+0.031
ical+0.031
Neg logit contributions
 accidents-0.027
 itch-0.026
 stain-0.023
 bleed-0.023
 babies-0.022
Token waiting
Token ID4953
Feature activation-4.86e-01

Pos logit contributions
ued+0.028
bank+0.026
roads+0.026
ving+0.025
ical+0.024
Neg logit contributions
 accidents-0.020
 itch-0.019
 bleed-0.018
 stain-0.017
eddy-0.016
Token handed
Token ID10158
Feature activation+9.63e-01

Pos logit contributions
 accidents+0.003
 itch+0.003
 bleed+0.003
 stain+0.003
 cookies+0.003
Neg logit contributions
ued-0.004
roads-0.003
bank-0.003
ving-0.003
boat-0.003
Token each
Token ID1123
Feature activation+8.56e-01

Pos logit contributions
ued+0.043
roads+0.041
bank+0.041
ving+0.040
ical+0.039
Neg logit contributions
 accidents-0.013
 itch-0.011
 bleed-0.009
 cookies-0.009
eddy-0.008
Token slice
Token ID16416
Feature activation-7.11e-01

Pos logit contributions
ued+0.031
bank+0.030
roads+0.030
ving+0.029
ical+0.028
Neg logit contributions
 itch-0.019
 accidents-0.018
 cookies-0.016
 bleed-0.015
 cat-0.015
Token to
Token ID284
Feature activation+7.30e-01

Pos logit contributions
 accidents+0.012
 itch+0.011
 cookies+0.010
eddy+0.010
 bleed+0.009
Neg logit contributions
ued-0.029
roads-0.027
bank-0.027
ving-0.027
ical-0.026
Token her
Token ID607
Feature activation+8.18e-01

Pos logit contributions
ued+0.030
roads+0.028
bank+0.028
ving+0.027
ical+0.027
Neg logit contributions
 accidents-0.012
 itch-0.012
 bleed-0.010
 stain-0.010
 cookies-0.009
Token children
Token ID1751
Feature activation+3.07e+00

Pos logit contributions
ued+0.033
roads+0.032
bank+0.031
ving+0.030
sel+0.030
Neg logit contributions
 accidents-0.014
 itch-0.014
 bleed-0.012
 cookies-0.011
 stain-0.011
Token.
Token ID13
Feature activation+1.08e+00

Pos logit contributions
ued+0.111
roads+0.104
bank+0.100
ving+0.100
sel+0.099
Neg logit contributions
 itch-0.066
 accidents-0.063
 cookies-0.056
 bleed-0.055
 babies-0.054
Token They
Token ID1119
Feature activation+5.00e-02

Pos logit contributions
ued+0.042
roads+0.038
ving+0.037
mer+0.037
boat+0.037
Neg logit contributions
 accidents-0.021
 itch-0.020
 cookies-0.017
 Mitt-0.017
eddy-0.017
Token were
Token ID547
Feature activation+5.69e-01

Pos logit contributions
ued+0.002
roads+0.002
bank+0.002
ving+0.002
ical+0.002
Neg logit contributions
 itch-0.001
 accidents-0.001
 bleed-0.001
 stain-0.001
 cookies-0.001
Token so
Token ID523
Feature activation+3.59e-01

Pos logit contributions
ued+0.018
bank+0.017
roads+0.017
ving+0.016
sel+0.016
Neg logit contributions
 accidents-0.015
 itch-0.014
 bleed-0.013
 stain-0.013
eddy-0.012
Token excited
Token ID6568
Feature activation-3.46e-01

Pos logit contributions
ued+0.013
bank+0.012
roads+0.012
ving+0.011
sel+0.011
Neg logit contributions
 accidents-0.008
 itch-0.007
 bleed-0.007
 stain-0.007
burn-0.006
Token to
Token ID284
Feature activation+4.19e-01

Pos logit contributions
ued+0.006
bank+0.005
roads+0.005
ving+0.005
ical+0.005
Neg logit contributions
 accidents-0.003
 itch-0.003
 bleed-0.002
 cookies-0.002
 stain-0.002
Token the
Token ID262
Feature activation+7.50e-01

Pos logit contributions
ued+0.016
bank+0.015
roads+0.015
ving+0.014
ical+0.014
Neg logit contributions
 accidents-0.009
 itch-0.008
 bleed-0.007
 stain-0.007
 cookies-0.007
Token sky
Token ID6766
Feature activation+5.39e-01

Pos logit contributions
ued+0.024
bank+0.023
roads+0.022
ving+0.021
ical+0.021
Neg logit contributions
 accidents-0.019
 itch-0.018
 bleed-0.017
 stain-0.016
eddy-0.016
Token in
Token ID287
Feature activation+2.37e+00

Pos logit contributions
ued+0.022
roads+0.020
bank+0.020
ving+0.019
 gru+0.019
Neg logit contributions
 accidents-0.010
 itch-0.009
 bleed-0.008
 stain-0.008
 cookies-0.007
Token a
Token ID257
Feature activation+1.85e+00

Pos logit contributions
ued+0.102
bank+0.095
ving+0.092
ical+0.091
roads+0.090
Neg logit contributions
 accidents-0.042
 itch-0.038
 cookies-0.033
 bleed-0.032
 stain-0.031
Token show
Token ID905
Feature activation+3.25e+00

Pos logit contributions
ued+0.072
bank+0.066
ving+0.065
roads+0.064
ical+0.064
Neg logit contributions
 itch-0.036
 accidents-0.035
 stain-0.030
 cookies-0.029
 mess-0.029
Token of
Token ID286
Feature activation+1.48e-01

Pos logit contributions
ued+0.121
bank+0.118
roads+0.113
 gru+0.111
ical+0.109
Neg logit contributions
 accidents-0.061
 itch-0.055
 from-0.055
 babies-0.054
 cookies-0.054
Token thanks
Token ID5176
Feature activation+6.48e-01

Pos logit contributions
ued+0.006
bank+0.005
roads+0.005
ving+0.005
ical+0.005
Neg logit contributions
 accidents-0.003
 itch-0.003
 cookies-0.002
 babies-0.002
 bleed-0.002
Token.
Token ID13
Feature activation+1.12e-01

Pos logit contributions
ued+0.025
roads+0.023
bank+0.023
ving+0.022
sel+0.022
Neg logit contributions
 accidents-0.013
 itch-0.012
 bleed-0.011
 cookies-0.010
 stain-0.010
Token
Token ID198
Feature activation+3.10e-01

Pos logit contributions
sel+0.004
ued+0.004
chie+0.004
mer+0.004
ving+0.004
Neg logit contributions
 grandma-0.002
 Mom-0.002
 Aunt-0.002
 cat-0.002
 mom-0.002
Token
Token ID198
Feature activation+9.24e-01

Pos logit contributions
sel+0.012
ued+0.012
ical+0.012
bank+0.011
folk+0.011
Neg logit contributions
eddy-0.005
 accidents-0.005
imi-0.004
 grandma-0.004
 itch-0.004
Token mom
Token ID1995
Feature activation-1.06e+00

Pos logit contributions
 accidents+0.024
 bleed+0.020
 stain+0.018
 itch+0.017
eddy+0.017
Neg logit contributions
ued-0.041
bank-0.037
 gru-0.036
ical-0.035
 bank-0.034
Token took
Token ID1718
Feature activation+1.27e+00

Pos logit contributions
 accidents+0.032
 itch+0.029
 bleed+0.029
 stain+0.026
eddy+0.026
Neg logit contributions
ued-0.029
bank-0.027
roads-0.026
ving-0.025
boat-0.025
Token her
Token ID607
Feature activation+3.37e-01

Pos logit contributions
ued+0.043
bank+0.039
roads+0.039
sel+0.037
den+0.037
Neg logit contributions
 accidents-0.030
 itch-0.029
 stain-0.027
 bleed-0.026
eddy-0.025
Token to
Token ID284
Feature activation+1.13e+00

Pos logit contributions
ued+0.013
bank+0.012
roads+0.012
ving+0.011
sel+0.011
Neg logit contributions
 accidents-0.007
 itch-0.007
 bleed-0.006
 stain-0.006
 cookies-0.005
Token the
Token ID262
Feature activation+9.55e-01

Pos logit contributions
ued+0.033
bank+0.032
roads+0.031
 +0.029
 2+0.028
Neg logit contributions
 accidents-0.030
 itch-0.028
eddy-0.027
 bleed-0.026
 stain-0.026
Token veterinarian
Token ID41404
Feature activation+3.37e+00

Pos logit contributions
bank+0.028
ued+0.028
roads+0.028
 bank+0.025
top+0.024
Neg logit contributions
 accidents-0.026
 bleed-0.024
 itch-0.022
eddy-0.021
 stain-0.020
Token.
Token ID13
Feature activation+8.31e-01

Pos logit contributions
ued+0.135
boat+0.120
roads+0.120
folk+0.119
sel+0.117
Neg logit contributions
 her-0.053
 itch-0.053
 accidents-0.051
 cookies-0.051
 from-0.051
Token As
Token ID1081
Feature activation-9.81e-01

Pos logit contributions
ued+0.025
bank+0.023
roads+0.023
ving+0.022
sel+0.022
Neg logit contributions
 accidents-0.023
 itch-0.022
 bleed-0.020
 stain-0.019
eddy-0.019
Token they
Token ID484
Feature activation-3.69e-01

Pos logit contributions
 accidents+0.025
 itch+0.024
 bleed+0.022
 stain+0.022
eddy+0.020
Neg logit contributions
ued-0.032
bank-0.030
roads-0.029
ving-0.028
ical-0.027
Token arrived
Token ID5284
Feature activation+7.13e-01

Pos logit contributions
 accidents+0.011
 itch+0.010
 bleed+0.010
 stain+0.009
eddy+0.009
Neg logit contributions
ued-0.011
bank-0.010
roads-0.010
ving-0.009
sel-0.009
Token at
Token ID379
Feature activation-1.28e+00

Pos logit contributions
ued+0.025
bank+0.023
roads+0.023
ving+0.022
sel+0.022
Neg logit contributions
 accidents-0.017
 itch-0.015
 bleed-0.014
 stain-0.013
 cookies-0.013
Token pile
Token ID14540
Feature activation+8.04e-01

Pos logit contributions
 accidents+0.033
 bleed+0.032
 itch+0.031
burn+0.029
eddy+0.028
Neg logit contributions
ued-0.034
roads-0.033
bank-0.032
boat-0.030
 gru-0.030
Token of
Token ID286
Feature activation-1.57e+00

Pos logit contributions
ued+0.039
bank+0.037
ical+0.037
roads+0.036
ving+0.036
Neg logit contributions
 accidents-0.007
 itch-0.006
 stain-0.004
 from-0.004
eddy-0.004
Token garbage
Token ID15413
Feature activation-2.46e-01

Pos logit contributions
 accidents+0.038
 itch+0.036
 bleed+0.033
 stain+0.031
eddy+0.031
Neg logit contributions
ued-0.053
bank-0.049
roads-0.049
ving-0.046
ical-0.045
Token on
Token ID319
Feature activation+1.79e+00

Pos logit contributions
 accidents+0.005
 itch+0.005
 stain+0.004
 cookies+0.004
eddy+0.004
Neg logit contributions
ued-0.009
roads-0.008
bank-0.008
ical-0.008
ving-0.008
Token the
Token ID262
Feature activation+1.71e+00

Pos logit contributions
ued+0.077
ical+0.071
bank+0.070
ving+0.070
roads+0.067
Neg logit contributions
 accidents-0.030
 itch-0.026
 cookies-0.024
 her-0.023
 stain-0.023
Token street
Token ID4675
Feature activation+3.69e+00

Pos logit contributions
ued+0.055
roads+0.049
bank+0.048
ving+0.048
sel+0.047
Neg logit contributions
 itch-0.043
 accidents-0.043
 stain-0.039
 bleed-0.038
 cookies-0.037
Token.
Token ID13
Feature activation+5.95e-01

Pos logit contributions
ued+0.156
sel+0.141
ving+0.139
chie+0.138
den+0.137
Neg logit contributions
 accidents-0.058
 from-0.051
 itch-0.050
 mess-0.047
 stain-0.045
Token He
Token ID679
Feature activation+8.73e-01

Pos logit contributions
ued+0.019
boat+0.019
roads+0.018
bank+0.018
mer+0.018
Neg logit contributions
 accidents-0.014
 itch-0.013
eddy-0.012
 cookies-0.012
 her-0.012
Token thought
Token ID1807
Feature activation-2.99e-01

Pos logit contributions
ued+0.030
roads+0.029
bank+0.028
boat+0.027
ical+0.027
Neg logit contributions
 itch-0.019
 accidents-0.019
 stain-0.017
 her-0.016
 cat-0.016
Token it
Token ID340
Feature activation+1.27e-01

Pos logit contributions
 accidents+0.007
 itch+0.006
 cookies+0.005
 stain+0.005
 bleed+0.005
Neg logit contributions
ued-0.011
bank-0.010
roads-0.010
ical-0.010
mer-0.010
Token was
Token ID373
Feature activation+1.79e+00

Pos logit contributions
ued+0.005
roads+0.005
folk+0.004
sel+0.004
bank+0.004
Neg logit contributions
 accidents-0.002
 itch-0.002
 stain-0.002
 cat-0.002
 bleed-0.002
Token that
Token ID326
Feature activation+9.23e-01

Pos logit contributions
 accidents+0.009
 itch+0.008
 cookies+0.007
 bleed+0.007
 stain+0.006
Neg logit contributions
ued-0.017
bank-0.015
roads-0.015
ving-0.015
ical-0.015
Token the
Token ID262
Feature activation-4.72e-01

Pos logit contributions
ued+0.038
bank+0.034
ical+0.034
ving+0.034
roads+0.033
Neg logit contributions
 accidents-0.019
 itch-0.016
 cookies-0.014
 bleed-0.013
 cat-0.013
Token driver
Token ID4639
Feature activation+7.56e-01

Pos logit contributions
 accidents+0.011
 itch+0.010
 cookies+0.009
 stain+0.009
 bleed+0.009
Neg logit contributions
ued-0.017
bank-0.015
roads-0.015
ving-0.015
ical-0.014
Token was
Token ID373
Feature activation+6.15e-01

Pos logit contributions
ued+0.025
bank+0.024
roads+0.023
ical+0.022
sel+0.022
Neg logit contributions
 accidents-0.019
 itch-0.017
 bleed-0.016
 stain-0.015
 cookies-0.014
Token stuck
Token ID7819
Feature activation+8.84e-01

Pos logit contributions
ued+0.023
bank+0.022
roads+0.022
ical+0.021
sel+0.021
Neg logit contributions
 accidents-0.013
 itch-0.012
 bleed-0.011
 stain-0.010
 babies-0.010
Token trying
Token ID2111
Feature activation+1.39e+00

Pos logit contributions
ued+0.038
bank+0.035
roads+0.035
ical+0.034
ving+0.033
Neg logit contributions
 accidents-0.014
 itch-0.012
 bleed-0.011
eddy-0.010
 stain-0.010
Token to
Token ID284
Feature activation-4.42e-01

Pos logit contributions
ued+0.058
roads+0.055
folk+0.053
sel+0.053
bank+0.053
Neg logit contributions
 accidents-0.025
 itch-0.022
 bleed-0.019
 cookies-0.018
 stain-0.018
Token fix
Token ID4259
Feature activation+1.31e+00

Pos logit contributions
 accidents+0.010
 itch+0.009
 bleed+0.008
eddy+0.008
 stain+0.008
Neg logit contributions
ued-0.016
bank-0.015
roads-0.015
ving-0.014
boat-0.014
Token the
Token ID262
Feature activation-3.29e-01

Pos logit contributions
ued+0.056
bank+0.050
ical+0.050
roads+0.050
ving+0.050
Neg logit contributions
 accidents-0.025
 itch-0.019
 cookies-0.019
 bleed-0.017
 mess-0.017
Token engine
Token ID3113
Feature activation+1.97e+00

Pos logit contributions
 accidents+0.008
 itch+0.007
 bleed+0.007
 stain+0.007
 cookies+0.007
Neg logit contributions
ued-0.011
bank-0.011
roads-0.010
ving-0.010
sel-0.010
Token.
Token ID13
Feature activation+5.11e-01

Pos logit contributions
ued+0.073
roads+0.066
ving+0.064
sel+0.063
bank+0.063
Neg logit contributions
 accidents-0.042
 itch-0.041
 bleed-0.037
 stain-0.034
 from-0.034
Token closer
Token ID5699
Feature activation-2.27e-01

Pos logit contributions
ued+0.045
bank+0.042
roads+0.042
ving+0.040
ical+0.039
Neg logit contributions
 accidents-0.031
 itch-0.030
 bleed-0.027
 stain-0.026
eddy-0.025
Token and
Token ID290
Feature activation+4.17e-01

Pos logit contributions
 accidents+0.002
 itch+0.001
 her+0.001
 from+0.001
 and+0.001
Neg logit contributions
ued-0.011
roads-0.011
sel-0.011
folk-0.011
boat-0.010
Token saw
Token ID2497
Feature activation-8.26e-02

Pos logit contributions
ued+0.015
bank+0.014
roads+0.013
bench+0.013
folk+0.013
Neg logit contributions
 accidents-0.009
 itch-0.008
 her-0.008
 bleed-0.007
 pets-0.007
Token a
Token ID257
Feature activation-1.42e-01

Pos logit contributions
 accidents+0.002
 itch+0.002
 bleed+0.002
 stain+0.002
eddy+0.001
Neg logit contributions
ued-0.003
bank-0.003
roads-0.003
ving-0.003
ical-0.003
Token little
Token ID1310
Feature activation-3.67e-02

Pos logit contributions
 accidents+0.003
 itch+0.003
 bleed+0.003
 stain+0.002
eddy+0.002
Neg logit contributions
ued-0.005
bank-0.005
roads-0.005
ving-0.004
ical-0.004
Token girl
Token ID2576
Feature activation+1.14e+00

Pos logit contributions
 accidents+0.001
 itch+0.001
 bleed+0.001
 stain+0.001
eddy+0.001
Neg logit contributions
ued-0.001
bank-0.001
roads-0.001
mer-0.001
 gru-0.001
Token playing
Token ID2712
Feature activation+4.17e-01

Pos logit contributions
ued+0.038
bank+0.036
roads+0.035
ving+0.033
 gru+0.032
Neg logit contributions
 accidents-0.027
 itch-0.026
 bleed-0.024
 stain-0.023
eddy-0.022
Token in
Token ID287
Feature activation+5.21e-01

Pos logit contributions
ued+0.015
roads+0.014
bank+0.014
ving+0.013
ical+0.013
Neg logit contributions
 accidents-0.009
 itch-0.008
 bleed-0.008
 stain-0.008
eddy-0.007
Token the
Token ID262
Feature activation+6.59e-01

Pos logit contributions
ued+0.018
roads+0.017
bank+0.017
 gru+0.016
ving+0.016
Neg logit contributions
 accidents-0.011
 itch-0.011
 bleed-0.010
eddy-0.010
 stain-0.009
Token water
Token ID1660
Feature activation+6.56e-02

Pos logit contributions
ued+0.022
bank+0.021
roads+0.021
ving+0.020
ical+0.019
Neg logit contributions
 accidents-0.016
 itch-0.015
 bleed-0.014
 stain-0.013
eddy-0.013
Token with
Token ID351
Feature activation+1.16e+00

Pos logit contributions
ued+0.002
ving+0.002
ical+0.002
sel+0.002
roads+0.002
Neg logit contributions
 accidents-0.001
 itch-0.001
 stain-0.001
 bleed-0.001
 cookies-0.001
Token trunk
Token ID21427
Feature activation-3.45e-01

Pos logit contributions
ued+0.029
roads+0.027
bank+0.026
ving+0.025
sel+0.025
Neg logit contributions
 itch-0.020
 accidents-0.019
 bleed-0.018
 stain-0.017
 babies-0.016
Token.
Token ID13
Feature activation-7.89e-01

Pos logit contributions
 itch+0.006
 accidents+0.006
 bleed+0.005
eddy+0.005
 stain+0.005
Neg logit contributions
ued-0.014
bank-0.013
roads-0.013
sel-0.013
ical-0.012
Token She
Token ID1375
Feature activation-3.69e-01

Pos logit contributions
 accidents+0.017
eddy+0.016
 itch+0.016
 bleed+0.014
 her+0.014
Neg logit contributions
ued-0.027
roads-0.026
bank-0.025
mer-0.025
sel-0.025
Token liked
Token ID8288
Feature activation-1.67e+00

Pos logit contributions
 accidents+0.010
 itch+0.010
 bleed+0.009
 stain+0.009
eddy+0.008
Neg logit contributions
ued-0.011
roads-0.010
bank-0.010
ving-0.010
ical-0.010
Token to
Token ID284
Feature activation-6.30e-01

Pos logit contributions
 accidents+0.048
 itch+0.047
 bleed+0.046
 stain+0.045
eddy+0.042
Neg logit contributions
bank-0.044
ued-0.043
roads-0.039
 1-0.038
ving-0.037
Token use
Token ID779
Feature activation+1.25e+00

Pos logit contributions
 accidents+0.014
 itch+0.012
 bleed+0.011
eddy+0.011
 stain+0.010
Neg logit contributions
ued-0.023
bank-0.022
roads-0.022
ving-0.021
ical-0.020
Token her
Token ID607
Feature activation+1.61e-01

Pos logit contributions
ued+0.053
bank+0.050
roads+0.050
ving+0.048
ical+0.047
Neg logit contributions
 accidents-0.020
 itch-0.018
 bleed-0.016
 stain-0.014
 cookies-0.014
Token trunk
Token ID21427
Feature activation-9.49e-02

Pos logit contributions
ued+0.005
roads+0.004
bank+0.004
ving+0.004
sel+0.004
Neg logit contributions
 accidents-0.005
 itch-0.005
 bleed-0.004
 stain-0.004
 cookies-0.004
Token to
Token ID284
Feature activation-2.11e-01

Pos logit contributions
 accidents+0.002
 itch+0.001
 bleed+0.001
 cookies+0.001
 stain+0.001
Neg logit contributions
ued-0.004
bank-0.004
roads-0.004
sel-0.004
 gru-0.004
Token pick
Token ID2298
Feature activation+3.38e-01

Pos logit contributions
 accidents+0.005
 itch+0.004
 bleed+0.004
 stain+0.004
 cookies+0.004
Neg logit contributions
ued-0.008
bank-0.007
roads-0.007
ving-0.007
sel-0.007
Token up
Token ID510
Feature activation+2.48e-01

Pos logit contributions
ued+0.013
bank+0.012
roads+0.012
ving+0.011
ical+0.011
Neg logit contributions
 accidents-0.007
 itch-0.007
 bleed-0.006
 stain-0.006
eddy-0.005
Token animals
Token ID4695
Feature activation-3.44e-01

Pos logit contributions
 accidents+0.007
 itch+0.006
 bleed+0.006
 stain+0.006
eddy+0.005
Neg logit contributions
ued-0.009
bank-0.009
roads-0.009
ving-0.008
ical-0.008
Token.
Token ID13
Feature activation-2.25e-01

Pos logit contributions
 itch+0.007
 accidents+0.006
 cookies+0.005
 cat+0.005
 stain+0.005
Neg logit contributions
ued-0.013
bank-0.013
roads-0.012
 gru-0.012
sel-0.012
Token She
Token ID1375
Feature activation-3.04e-01

Pos logit contributions
 accidents+0.005
 itch+0.005
 bleed+0.005
 stain+0.005
 cookies+0.005
Neg logit contributions
ued-0.008
bank-0.007
roads-0.007
ving-0.007
boat-0.006
Token had
Token ID550
Feature activation-4.51e-01

Pos logit contributions
 itch+0.008
 accidents+0.007
 stain+0.007
 bleed+0.007
 cookies+0.007
Neg logit contributions
ued-0.010
roads-0.009
bank-0.009
ical-0.008
ving-0.008
Token a
Token ID257
Feature activation-5.46e-01

Pos logit contributions
 accidents+0.009
 itch+0.009
 bleed+0.008
 cookies+0.008
 stain+0.008
Neg logit contributions
ued-0.017
roads-0.016
bank-0.016
ving-0.015
ical-0.015
Token lion
Token ID18744
Feature activation+4.01e-01

Pos logit contributions
 accidents+0.013
 itch+0.012
 bleed+0.012
eddy+0.010
 stain+0.010
Neg logit contributions
ued-0.018
bank-0.017
roads-0.016
ical-0.016
ving-0.016
Token,
Token ID11
Feature activation-1.65e-01

Pos logit contributions
ued+0.012
bank+0.012
roads+0.011
ving+0.011
ical+0.011
Neg logit contributions
 accidents-0.011
 itch-0.010
 bleed-0.010
 stain-0.009
eddy-0.009
Token a
Token ID257
Feature activation-3.82e-03

Pos logit contributions
 accidents+0.003
 itch+0.003
 bleed+0.003
 stain+0.003
 cookies+0.003
Neg logit contributions
ued-0.006
bank-0.006
roads-0.006
ving-0.006
ical-0.005
Token monkey
Token ID21657
Feature activation-9.82e-02

Pos logit contributions
 accidents+0.000
 itch+0.000
 bleed+0.000
 stain+0.000
eddy+0.000
Neg logit contributions
ued-0.000
bank-0.000
roads-0.000
ving-0.000
ical-0.000
Token,
Token ID11
Feature activation-8.26e-01

Pos logit contributions
 accidents+0.002
 itch+0.002
 bleed+0.002
 stain+0.002
eddy+0.002
Neg logit contributions
ued-0.003
bank-0.003
roads-0.003
ving-0.003
ical-0.003
Token a
Token ID257
Feature activation+3.80e-02

Pos logit contributions
 accidents+0.019
 itch+0.018
 bleed+0.017
 stain+0.016
eddy+0.015
Neg logit contributions
ued-0.028
bank-0.026
roads-0.026
ving-0.025
ical-0.025
Token thin
Token ID7888
Feature activation+4.48e-01

Pos logit contributions
ued+0.009
bank+0.009
roads+0.008
ving+0.008
ical+0.008
Neg logit contributions
 accidents-0.007
 itch-0.006
 bleed-0.006
 stain-0.006
eddy-0.005
Token."
Token ID526
Feature activation+2.79e-01

Pos logit contributions
ued+0.016
bank+0.015
roads+0.015
ving+0.014
sel+0.014
Neg logit contributions
 accidents-0.011
 itch-0.010
 bleed-0.009
 cookies-0.009
 stain-0.009
Token Lily
Token ID20037
Feature activation-5.11e-01

Pos logit contributions
ued+0.013
bank+0.013
ving+0.013
roads+0.013
sel+0.012
Neg logit contributions
 accidents-0.003
 itch-0.003
 bleed-0.002
 cookies-0.002
 stain-0.002
Token said
Token ID531
Feature activation+1.25e-01

Pos logit contributions
 itch+0.012
 accidents+0.012
 stain+0.011
 bleed+0.011
 cookies+0.011
Neg logit contributions
ued-0.017
roads-0.016
bank-0.016
boat-0.015
ving-0.015
Token.
Token ID13
Feature activation-2.89e-01

Pos logit contributions
roads+0.004
ued+0.004
bank+0.004
boat+0.004
mer+0.004
Neg logit contributions
 accidents-0.003
 itch-0.003
 bleed-0.002
 cookies-0.002
 her-0.002
Token
Token ID198
Feature activation+2.59e-01

Pos logit contributions
 accidents+0.008
 itch+0.008
 bleed+0.007
 stain+0.007
eddy+0.007
Neg logit contributions
ued-0.009
bank-0.008
roads-0.008
ving-0.007
sel-0.007
Token
Token ID198
Feature activation+7.68e-01

Pos logit contributions
ued+0.007
bank+0.006
roads+0.006
ving+0.006
ical+0.006
Neg logit contributions
 accidents-0.008
 itch-0.008
 bleed-0.007
 stain-0.007
eddy-0.007
TokenThey
Token ID2990
Feature activation-1.19e-01

Pos logit contributions
ued+0.024
roads+0.022
bank+0.022
ving+0.021
ical+0.020
Neg logit contributions
 accidents-0.021
 itch-0.020
 bleed-0.019
 stain-0.018
eddy-0.017
Token climbed
Token ID19952
Feature activation+6.44e-02

Pos logit contributions
 itch+0.003
 accidents+0.002
 bleed+0.002
 stain+0.002
 cookies+0.002
Neg logit contributions
ued-0.004
bank-0.004
roads-0.004
ical-0.004
 gru-0.004
Token the
Token ID262
Feature activation-1.17e+00

Pos logit contributions
ued+0.002
bank+0.002
roads+0.002
ving+0.002
ical+0.002
Neg logit contributions
 accidents-0.001
 itch-0.001
 bleed-0.001
 stain-0.001
eddy-0.001
Token tree
Token ID5509
Feature activation-1.27e+00

Pos logit contributions
 accidents+0.032
 itch+0.031
 bleed+0.029
 stain+0.028
eddy+0.026
Neg logit contributions
ued-0.036
bank-0.033
roads-0.033
ving-0.031
ical-0.031
Token did
Token ID750
Feature activation+6.86e-01

Pos logit contributions
ued+0.010
roads+0.010
bank+0.009
ving+0.009
ical+0.009
Neg logit contributions
 accidents-0.008
 itch-0.008
 bleed-0.007
 cookies-0.007
 stain-0.007
Token everything
Token ID2279
Feature activation-1.71e+00

Pos logit contributions
ued+0.028
roads+0.027
bank+0.026
sel+0.026
boat+0.026
Neg logit contributions
 accidents-0.011
 itch-0.011
 bleed-0.009
 cookies-0.009
 babies-0.008
Token together
Token ID1978
Feature activation+1.15e+00

Pos logit contributions
 accidents+0.048
 itch+0.046
 bleed+0.043
 stain+0.041
eddy+0.040
Neg logit contributions
ued-0.052
bank-0.047
roads-0.047
ving-0.044
ical-0.044
Token.
Token ID13
Feature activation+8.28e-04

Pos logit contributions
ued+0.046
roads+0.044
 gru+0.043
bank+0.042
ical+0.041
Neg logit contributions
 itch-0.020
 accidents-0.020
 her-0.019
 from-0.018
 babies-0.017
Token
Token ID220
Feature activation-9.01e-01

Pos logit contributions
sel+0.000
ued+0.000
roads+0.000
 gru+0.000
ical+0.000
Neg logit contributions
 Mom-0.000
 cat-0.000
 Lily-0.000
 Mitt-0.000
 mom-0.000
Token
Token ID198
Feature activation+1.43e-01

Pos logit contributions
 accidents+0.016
eddy+0.016
 itch+0.015
imi+0.014
 her+0.014
Neg logit contributions
ued-0.034
roads-0.032
ical-0.031
bank-0.031
sel-0.031
Token
Token ID198
Feature activation+8.28e-01

Pos logit contributions
ical+0.006
ued+0.006
sel+0.006
 mast+0.006
bank+0.006
Neg logit contributions
eddy-0.002
 her-0.002
 grandma-0.001
imi-0.001
 mom-0.001
TokenOne
Token ID3198
Feature activation+1.22e+00

Pos logit contributions
ued+0.024
bank+0.022
sel+0.022
ical+0.021
roads+0.021
Neg logit contributions
 itch-0.021
 accidents-0.020
 cat-0.019
 her-0.019
eddy-0.018
Token day
Token ID1110
Feature activation+9.22e-01

Pos logit contributions
ued+0.034
bank+0.031
roads+0.031
ving+0.029
ical+0.029
Neg logit contributions
 accidents-0.036
 itch-0.035
 bleed-0.033
 stain-0.032
eddy-0.031
Token,
Token ID11
Feature activation+4.21e-01

Pos logit contributions
ued+0.036
bank+0.035
roads+0.035
ical+0.032
sel+0.032
Neg logit contributions
 accidents-0.018
 itch-0.015
 cookies-0.014
 cat-0.013
 babies-0.013
Token they
Token ID484
Feature activation-2.91e-01

Pos logit contributions
ued+0.016
bank+0.015
roads+0.015
ving+0.014
ical+0.014
Neg logit contributions
 accidents-0.009
 itch-0.008
 bleed-0.007
 cookies-0.007
 stain-0.007
Token time
Token ID640
Feature activation+1.17e+00

Pos logit contributions
 accidents+0.011
 itch+0.010
 bleed+0.010
 stain+0.009
eddy+0.009
Neg logit contributions
ued-0.010
bank-0.009
roads-0.009
ving-0.008
ical-0.008
Token,
Token ID11
Feature activation-1.70e-02

Pos logit contributions
ued+0.038
bank+0.035
roads+0.035
ving+0.033
ical+0.033
Neg logit contributions
 accidents-0.030
 itch-0.028
 bleed-0.026
 stain-0.025
eddy-0.024
Token there
Token ID612
Feature activation+8.11e-01

Pos logit contributions
 accidents+0.000
 itch+0.000
 bleed+0.000
 stain+0.000
eddy+0.000
Neg logit contributions
ued-0.001
bank-0.001
roads-0.001
ical-0.000
sel-0.000
Token was
Token ID373
Feature activation-6.60e-01

Pos logit contributions
ued+0.021
bank+0.019
roads+0.019
 +0.018
ving+0.017
Neg logit contributions
 accidents-0.026
 itch-0.025
 bleed-0.024
burn-0.023
 stain-0.022
Token a
Token ID257
Feature activation-1.01e+00

Pos logit contributions
 accidents+0.022
 bleed+0.021
 stain+0.020
 itch+0.020
 mess+0.019
Neg logit contributions
ued-0.015
 -0.013
 One-0.012
 2-0.012
 1-0.012
Token little
Token ID1310
Feature activation-1.16e+00

Pos logit contributions
 accidents+0.029
 bleed+0.027
 itch+0.024
burn+0.023
 stain+0.022
Neg logit contributions
mer-0.026
ued-0.025
 gru-0.025
 2-0.025
iden-0.024
Token boy
Token ID2933
Feature activation+3.13e-02

Pos logit contributions
 accidents+0.031
 bleed+0.030
 itch+0.028
 stain+0.025
burn+0.025
Neg logit contributions
mer-0.031
ued-0.031
boat-0.030
bank-0.029
sel-0.029
Token named
Token ID3706
Feature activation+1.33e+00

Pos logit contributions
ued+0.001
bank+0.001
roads+0.001
ving+0.001
ical+0.001
Neg logit contributions
 accidents-0.001
 itch-0.001
 bleed-0.001
 stain-0.001
eddy-0.001
Token Tim
Token ID5045
Feature activation-2.41e-01

Pos logit contributions
ued+0.055
bank+0.052
roads+0.052
ving+0.050
ical+0.049
Neg logit contributions
 accidents-0.022
 itch-0.021
 bleed-0.018
 stain-0.017
eddy-0.016
Tokenmy
Token ID1820
Feature activation-1.77e+00

Pos logit contributions
 accidents+0.004
 itch+0.004
 bleed+0.004
 stain+0.003
eddy+0.003
Neg logit contributions
ued-0.010
roads-0.009
bank-0.009
ical-0.009
ving-0.009
Token.
Token ID13
Feature activation-1.01e+00

Pos logit contributions
 accidents+0.054
 itch+0.051
 bleed+0.049
 stain+0.047
 cookies+0.045
Neg logit contributions
ued-0.048
bank-0.044
roads-0.043
ving-0.041
boat-0.040
Token match
Token ID2872
Feature activation+2.21e-01

Pos logit contributions
ued+0.005
bank+0.004
roads+0.004
ving+0.004
mer+0.004
Neg logit contributions
 accidents-0.005
 itch-0.004
 bleed-0.004
burn-0.004
eddy-0.004
Token was
Token ID373
Feature activation+2.16e-01

Pos logit contributions
ued+0.008
roads+0.008
bank+0.008
ical+0.008
 gru+0.007
Neg logit contributions
 accidents-0.004
 itch-0.004
 stain-0.004
eddy-0.004
 cat-0.004
Token always
Token ID1464
Feature activation+1.43e+00

Pos logit contributions
ued+0.007
bank+0.006
roads+0.006
ving+0.006
ical+0.006
Neg logit contributions
 accidents-0.006
 itch-0.005
 bleed-0.005
 stain-0.005
eddy-0.005
Token looking
Token ID2045
Feature activation-5.82e-01

Pos logit contributions
ued+0.056
roads+0.051
bank+0.051
ving+0.049
sel+0.048
Neg logit contributions
 accidents-0.030
 itch-0.027
 bleed-0.024
 stain-0.023
 cookies-0.022
Token for
Token ID329
Feature activation+2.54e-01

Pos logit contributions
 accidents+0.010
 itch+0.009
 bleed+0.008
 stain+0.008
eddy+0.007
Neg logit contributions
ued-0.024
bank-0.023
roads-0.022
ving-0.022
ical-0.021
Token things
Token ID1243
Feature activation-1.14e+00

Pos logit contributions
ued+0.011
roads+0.010
bank+0.010
ving+0.010
ical+0.010
Neg logit contributions
 accidents-0.005
 itch-0.004
 cookies-0.004
 babies-0.004
 honey-0.004
Token to
Token ID284
Feature activation-1.77e-01

Pos logit contributions
 accidents+0.018
 itch+0.015
 bleed+0.014
 cookies+0.014
 from+0.013
Neg logit contributions
ued-0.049
roads-0.047
bank-0.045
ving-0.044
 gru-0.044
Token play
Token ID711
Feature activation-5.55e-02

Pos logit contributions
 accidents+0.004
 itch+0.003
 bleed+0.003
eddy+0.003
 stain+0.003
Neg logit contributions
ued-0.007
bank-0.006
roads-0.006
boat-0.006
sel-0.006
Token with
Token ID351
Feature activation-1.07e-01

Pos logit contributions
 accidents+0.001
 itch+0.001
 cookies+0.001
 stain+0.001
 bleed+0.001
Neg logit contributions
ued-0.002
bank-0.002
roads-0.002
sel-0.002
den-0.002
Token.
Token ID13
Feature activation+2.62e-01

Pos logit contributions
 accidents+0.002
 itch+0.002
 her+0.002
 cookies+0.002
 from+0.002
Neg logit contributions
ued-0.004
ical-0.004
roads-0.004
bank-0.004
sel-0.004
Token
Token ID198
Feature activation+6.69e-01

Pos logit contributions
ued+0.009
mer+0.009
sel+0.009
ving+0.008
chie+0.008
Neg logit contributions
 cat-0.006
 Mom-0.006
 grandma-0.006
 Lily-0.006
 Max-0.006
Token race
Token ID3234
Feature activation+2.67e+00

Pos logit contributions
 bleed+0.054
 accidents+0.054
eddy+0.049
Sweet+0.048
burn+0.047
Neg logit contributions
roads-0.046
bank-0.046
ued-0.046
boat-0.043
 Fer-0.043
Token at
Token ID379
Feature activation-1.38e+00

Pos logit contributions
ued+0.106
sel+0.099
bank+0.098
ving+0.094
den+0.094
Neg logit contributions
 accidents-0.047
 itch-0.046
 cat-0.040
 from-0.039
 stain-0.037
Token his
Token ID465
Feature activation+6.69e-01

Pos logit contributions
 accidents+0.030
 itch+0.028
 bleed+0.026
 stain+0.025
eddy+0.024
Neg logit contributions
ued-0.050
bank-0.046
roads-0.046
ving-0.044
ical-0.044
Token school
Token ID1524
Feature activation+3.37e+00

Pos logit contributions
ued+0.022
bank+0.020
roads+0.020
ving+0.019
top+0.019
Neg logit contributions
 accidents-0.017
 bleed-0.016
 itch-0.016
 stain-0.014
 rash-0.013
Token.
Token ID13
Feature activation-4.59e-01

Pos logit contributions
ued+0.136
sel+0.128
bank+0.121
chie+0.120
den+0.119
Neg logit contributions
 accidents-0.056
 cat-0.055
 itch-0.054
 cookies-0.052
 mess-0.050
Token Tim
Token ID5045
Feature activation-7.00e-01

Pos logit contributions
 accidents+0.010
 itch+0.010
 bleed+0.009
 cookies+0.009
 stain+0.008
Neg logit contributions
ued-0.017
roads-0.015
sel-0.015
bank-0.015
ving-0.015
Token was
Token ID373
Feature activation-2.33e-02

Pos logit contributions
 itch+0.015
 accidents+0.014
 bleed+0.013
 stain+0.013
 cat+0.013
Neg logit contributions
ued-0.025
bank-0.023
roads-0.023
sel-0.023
 gru-0.023
Token very
Token ID845
Feature activation+3.18e-01

Pos logit contributions
 accidents+0.001
 itch+0.001
 stain+0.001
 bleed+0.001
eddy+0.001
Neg logit contributions
ued-0.001
roads-0.001
bank-0.001
ving-0.001
ical-0.001
Token excited
Token ID6568
Feature activation-2.89e-01

Pos logit contributions
ued+0.011
bank+0.010
roads+0.010
ving+0.009
mer+0.009
Neg logit contributions
 accidents-0.008
 itch-0.007
 bleed-0.007
 stain-0.007
eddy-0.007
Token to
Token ID284
Feature activation-4.11e-01

Pos logit contributions
 accidents+0.007
 itch+0.006
 bleed+0.006
 stain+0.006
eddy+0.005
Neg logit contributions
ued-0.010
bank-0.009
roads-0.009
ving-0.009
ical-0.008
Token run
Token ID1057
Feature activation+1.58e+00

Pos logit contributions
 accidents+0.008
 itch+0.007
 bleed+0.007
eddy+0.006
 stain+0.006
Neg logit contributions
ued-0.016
roads-0.015
bank-0.015
ving-0.014
boat-0.014
Token into
Token ID656
Feature activation+2.02e-01

Pos logit contributions
 accidents+0.028
 itch+0.026
 bleed+0.026
 babies+0.025
eddy+0.025
Neg logit contributions
ued-0.033
roads-0.032
bank-0.032
top-0.030
boat-0.030
Token the
Token ID262
Feature activation+1.02e-01

Pos logit contributions
ued+0.008
roads+0.007
bank+0.007
ical+0.007
ving+0.007
Neg logit contributions
 accidents-0.004
 itch-0.004
 bleed-0.004
 stain-0.003
 cookies-0.003
Token lemon
Token ID18873
Feature activation-1.21e+00

Pos logit contributions
ued+0.004
bank+0.004
roads+0.003
ving+0.003
ical+0.003
Neg logit contributions
 accidents-0.002
 itch-0.002
 bleed-0.002
eddy-0.002
burn-0.002
Token,
Token ID11
Feature activation+8.55e-01

Pos logit contributions
 accidents+0.031
 itch+0.029
 bleed+0.027
eddy+0.026
 stain+0.026
Neg logit contributions
ued-0.039
bank-0.036
roads-0.036
ving-0.033
sel-0.033
Token her
Token ID607
Feature activation-1.31e+00

Pos logit contributions
ued+0.025
roads+0.023
bank+0.023
ving+0.021
sel+0.021
Neg logit contributions
 accidents-0.024
 itch-0.023
 bleed-0.022
eddy-0.021
 stain-0.021
Token face
Token ID1986
Feature activation-1.37e+00

Pos logit contributions
 accidents+0.028
 bleed+0.026
eddy+0.024
burn+0.024
 itch+0.023
Neg logit contributions
ued-0.041
bank-0.038
sel-0.038
mer-0.037
ving-0.036
Token turned
Token ID2900
Feature activation-3.22e-01

Pos logit contributions
 accidents+0.040
eddy+0.037
 itch+0.037
 bleed+0.036
 babies+0.035
Neg logit contributions
ued-0.035
bank-0.032
ving-0.031
sel-0.031
roads-0.030
Token sour
Token ID11348
Feature activation-7.05e-01

Pos logit contributions
 accidents+0.007
 itch+0.006
 bleed+0.006
 stain+0.006
eddy+0.005
Neg logit contributions
ued-0.012
bank-0.011
roads-0.011
ving-0.011
ical-0.011
Token.
Token ID13
Feature activation-2.73e-01

Pos logit contributions
 accidents+0.022
 itch+0.021
 bleed+0.020
eddy+0.020
 babies+0.019
Neg logit contributions
ued-0.017
bank-0.016
roads-0.015
ving-0.014
sel-0.014
Token The
Token ID383
Feature activation+2.63e-01

Pos logit contributions
 accidents+0.006
 itch+0.006
 bleed+0.006
 stain+0.005
 cookies+0.005
Neg logit contributions
ued-0.010
roads-0.009
ving-0.009
bank-0.008
boat-0.008
Token lemon
Token ID18873
Feature activation-2.95e+00

Pos logit contributions
ued+0.008
bank+0.008
 +0.007
roads+0.007
top+0.007
Neg logit contributions
 accidents-0.006
eddy-0.006
 bleed-0.005
burn-0.005
imi-0.005
Token
Token ID198
Feature activation+7.03e-01

Pos logit contributions
ued+0.009
bank+0.008
roads+0.008
ving+0.008
ical+0.008
Neg logit contributions
 accidents-0.010
 itch-0.010
 bleed-0.009
 stain-0.009
eddy-0.009
TokenThe
Token ID464
Feature activation+3.50e-02

Pos logit contributions
ued+0.026
bank+0.024
roads+0.024
ving+0.023
ical+0.023
Neg logit contributions
 accidents-0.015
 itch-0.013
 bleed-0.013
eddy-0.012
 stain-0.012
Token squirrel
Token ID33039
Feature activation-1.25e+00

Pos logit contributions
ued+0.001
roads+0.001
bank+0.001
 gru+0.001
boat+0.001
Neg logit contributions
 accidents-0.001
 bleed-0.001
 itch-0.001
eddy-0.001
 stain-0.001
Token threw
Token ID9617
Feature activation+7.06e-01

Pos logit contributions
 accidents+0.035
 itch+0.032
 bleed+0.031
eddy+0.030
burn+0.030
Neg logit contributions
ued-0.037
bank-0.035
roads-0.034
ving-0.033
sel-0.032
Token the
Token ID262
Feature activation-8.08e-01

Pos logit contributions
ued+0.022
bank+0.020
roads+0.020
sel+0.019
ving+0.019
Neg logit contributions
 accidents-0.019
 itch-0.018
 bleed-0.016
 stain-0.016
eddy-0.016
Token peanut
Token ID26636
Feature activation-3.50e+00

Pos logit contributions
 accidents+0.018
 itch+0.017
 bleed+0.015
 stain+0.014
eddy+0.014
Neg logit contributions
ued-0.029
bank-0.027
roads-0.026
sel-0.025
ving-0.025
Token to
Token ID284
Feature activation-3.65e-01

Pos logit contributions
 accidents+0.083
 itch+0.076
 bleed+0.071
 stain+0.070
imi+0.070
Neg logit contributions
ued-0.114
sel-0.106
bank-0.106
boat-0.105
ving-0.104
Token Tom
Token ID4186
Feature activation+1.13e+00

Pos logit contributions
 accidents+0.008
 itch+0.007
 bleed+0.007
 stain+0.006
eddy+0.006
Neg logit contributions
ued-0.013
bank-0.012
roads-0.012
ving-0.012
sel-0.012
Token and
Token ID290
Feature activation-1.89e-01

Pos logit contributions
ued+0.047
roads+0.044
bank+0.044
ving+0.042
ical+0.042
Neg logit contributions
 accidents-0.018
 itch-0.018
 bleed-0.015
 stain-0.014
eddy-0.014
Token Mia
Token ID32189
Feature activation+5.97e-01

Pos logit contributions
 accidents+0.004
 itch+0.004
 bleed+0.004
 stain+0.003
eddy+0.003
Neg logit contributions
ued-0.007
bank-0.006
roads-0.006
ving-0.006
sel-0.006
Token.
Token ID13
Feature activation-7.98e-01

Pos logit contributions
ued+0.022
roads+0.021
bank+0.020
 gru+0.020
ical+0.019
Neg logit contributions
 itch-0.012
 accidents-0.012
 bleed-0.011
 stain-0.010
 pets-0.010
Token every
Token ID790
Feature activation+3.09e-01

Pos logit contributions
 accidents+0.045
 itch+0.040
 bleed+0.039
 stain+0.036
eddy+0.035
Neg logit contributions
ued-0.070
bank-0.069
roads-0.065
boat-0.063
sc-0.063
Token day
Token ID1110
Feature activation+1.32e+00

Pos logit contributions
ued+0.009
bank+0.009
roads+0.009
ving+0.008
ical+0.008
Neg logit contributions
 accidents-0.009
 itch-0.008
 bleed-0.008
 stain-0.008
 cookies-0.007
Token.
Token ID13
Feature activation-4.26e-01

Pos logit contributions
ued+0.048
roads+0.046
bank+0.045
ving+0.044
 gru+0.042
Neg logit contributions
 itch-0.028
 accidents-0.028
 cookies-0.025
 her-0.023
 bleed-0.023
Token She
Token ID1375
Feature activation-2.24e-01

Pos logit contributions
 accidents+0.013
 itch+0.012
 bleed+0.011
 stain+0.011
eddy+0.011
Neg logit contributions
ued-0.012
roads-0.011
bank-0.011
ving-0.010
sel-0.010
Token would
Token ID561
Feature activation-8.17e-01

Pos logit contributions
 accidents+0.006
 itch+0.006
 bleed+0.006
 stain+0.006
 cookies+0.005
Neg logit contributions
ued-0.007
roads-0.006
bank-0.006
ving-0.006
ical-0.006
Token drink
Token ID4144
Feature activation-2.80e+00

Pos logit contributions
 accidents+0.019
eddy+0.015
 bleed+0.015
 itch+0.014
 stain+0.013
Neg logit contributions
ued-0.030
bank-0.028
roads-0.027
ving-0.026
ical-0.026
Token from
Token ID422
Feature activation-2.36e-01

Pos logit contributions
 bleed+0.076
 accidents+0.075
arter+0.074
 itch+0.074
eddy+0.074
Neg logit contributions
 -0.065
ued-0.065
sc-0.064
bank-0.059
top-0.057
Token her
Token ID607
Feature activation-4.47e-03

Pos logit contributions
 accidents+0.004
 itch+0.004
 bleed+0.004
eddy+0.004
 stain+0.003
Neg logit contributions
ued-0.009
bank-0.008
roads-0.008
ving-0.008
sel-0.008
Token big
Token ID1263
Feature activation+7.65e-01

Pos logit contributions
 accidents+0.000
 bleed+0.000
 itch+0.000
eddy+0.000
 stain+0.000
Neg logit contributions
ued-0.000
bank-0.000
mer-0.000
 banks-0.000
 bank-0.000
Token cup
Token ID6508
Feature activation-2.11e+00

Pos logit contributions
ued+0.025
bank+0.023
roads+0.023
ving+0.021
ical+0.021
Neg logit contributions
 accidents-0.019
 itch-0.018
 bleed-0.017
 stain-0.016
eddy-0.016
Token with
Token ID351
Feature activation+1.68e+00

Pos logit contributions
 accidents+0.045
 itch+0.042
 bleed+0.039
 stain+0.037
eddy+0.035
Neg logit contributions
ued-0.077
bank-0.072
roads-0.072
ving-0.068
ical-0.067
Token gob
Token ID48484
Feature activation-2.44e+00

Pos logit contributions
 accidents+0.018
 itch+0.017
 bleed+0.016
 stain+0.016
 cookies+0.015
Neg logit contributions
ued-0.022
roads-0.020
bank-0.020
ving-0.019
ical-0.019
Tokenbled
Token ID9342
Feature activation+1.28e-02

Pos logit contributions
 accidents+0.088
 itch+0.087
 stain+0.083
 bleed+0.083
 mess+0.079
Neg logit contributions
ued-0.056
ving-0.047
bank-0.046
sel-0.045
roads-0.041
Token up
Token ID510
Feature activation+2.41e-02

Pos logit contributions
ued+0.000
bank+0.000
roads+0.000
ving+0.000
sel+0.000
Neg logit contributions
 accidents-0.000
 itch-0.000
 bleed-0.000
 stain-0.000
eddy-0.000
Token the
Token ID262
Feature activation-1.26e+00

Pos logit contributions
ued+0.001
roads+0.001
bank+0.001
ving+0.001
ical+0.001
Neg logit contributions
 accidents-0.001
 itch-0.001
 bleed-0.000
 cookies-0.000
 stain-0.000
Token delicious
Token ID12625
Feature activation-2.36e+00

Pos logit contributions
 accidents+0.025
 itch+0.022
 bleed+0.021
eddy+0.019
 stain+0.019
Neg logit contributions
ued-0.048
bank-0.045
roads-0.044
ving-0.042
ical-0.042
Token berries
Token ID36322
Feature activation-2.75e+00

Pos logit contributions
 accidents+0.054
 bleed+0.052
 itch+0.048
eddy+0.048
burn+0.047
Neg logit contributions
bank-0.076
ued-0.074
mer-0.067
 bank-0.066
 banks-0.066
Token until
Token ID1566
Feature activation-8.70e-01

Pos logit contributions
 accidents+0.042
 itch+0.039
 bleed+0.033
 stain+0.030
 cookies+0.030
Neg logit contributions
ued-0.116
roads-0.111
bank-0.108
ving-0.105
ical-0.105
Token they
Token ID484
Feature activation+5.66e-01

Pos logit contributions
 accidents+0.017
 itch+0.015
 cookies+0.013
 her+0.013
 stain+0.012
Neg logit contributions
ued-0.034
roads-0.033
ical-0.033
bank-0.032
ving-0.031
Token were
Token ID547
Feature activation+4.28e-01

Pos logit contributions
ued+0.016
bank+0.015
roads+0.015
ving+0.014
ical+0.014
Neg logit contributions
 accidents-0.016
 itch-0.016
 bleed-0.015
 stain-0.014
eddy-0.014
Token full
Token ID1336
Feature activation+4.72e-03

Pos logit contributions
ued+0.015
bank+0.014
roads+0.013
ving+0.013
sel+0.013
Neg logit contributions
 accidents-0.010
 itch-0.009
 bleed-0.009
 stain-0.008
eddy-0.008
Token.
Token ID13
Feature activation+2.90e-02

Pos logit contributions
ued+0.000
roads+0.000
bank+0.000
ving+0.000
ical+0.000
Neg logit contributions
 accidents-0.000
 itch-0.000
 cookies-0.000
 stain-0.000
 bleed-0.000
Token a
Token ID257
Feature activation+4.88e-01

Pos logit contributions
ued+0.046
bank+0.043
roads+0.043
ving+0.041
ical+0.040
Neg logit contributions
 accidents-0.026
 itch-0.024
 bleed-0.022
 stain-0.021
 cookies-0.020
Token blanket
Token ID18447
Feature activation-2.48e+00

Pos logit contributions
ued+0.018
bank+0.017
roads+0.017
ical+0.016
boat+0.016
Neg logit contributions
 accidents-0.010
 itch-0.009
 bleed-0.008
eddy-0.008
 stain-0.007
Token,
Token ID11
Feature activation-6.67e-01

Pos logit contributions
 accidents+0.052
 itch+0.050
 bleed+0.045
 stain+0.043
eddy+0.042
Neg logit contributions
ued-0.091
roads-0.085
bank-0.084
ving-0.081
ical-0.079
Token enjoying
Token ID13226
Feature activation-3.42e-01

Pos logit contributions
 accidents+0.014
 itch+0.012
 bleed+0.012
eddy+0.011
 stain+0.011
Neg logit contributions
ued-0.023
bank-0.022
roads-0.022
ving-0.021
sel-0.021
Token a
Token ID257
Feature activation-1.25e+00

Pos logit contributions
 accidents+0.008
 itch+0.007
 bleed+0.007
 stain+0.007
eddy+0.006
Neg logit contributions
ued-0.012
bank-0.011
roads-0.011
ving-0.011
sel-0.010
Token cozy
Token ID37438
Feature activation-3.63e+00

Pos logit contributions
 accidents+0.029
 bleed+0.026
 itch+0.025
eddy+0.023
burn+0.022
Neg logit contributions
ued-0.041
bank-0.037
 -0.037
 gru-0.037
 lifetime-0.036
Token cup
Token ID6508
Feature activation-3.42e+00

Pos logit contributions
 accidents+0.082
 bleed+0.072
 itch+0.071
 mosquitoes+0.060
 stain+0.059
Neg logit contributions
ued-0.124
bank-0.122
boat-0.113
roads-0.112
 -0.112
Token of
Token ID286
Feature activation-2.36e+00

Pos logit contributions
 accidents+0.084
 itch+0.079
 bleed+0.076
 stain+0.069
 rash+0.067
Neg logit contributions
ued-0.111
bank-0.105
roads-0.102
boat-0.098
ical-0.098
Token hot
Token ID3024
Feature activation-1.95e+00

Pos logit contributions
 accidents+0.046
 itch+0.041
 bleed+0.040
eddy+0.037
 stain+0.036
Neg logit contributions
ued-0.086
bank-0.082
roads-0.081
boat-0.075
 gru-0.075
Token chocolate
Token ID11311
Feature activation-2.72e+00

Pos logit contributions
 accidents+0.039
 bleed+0.039
 itch+0.037
 rash+0.031
 stain+0.030
Neg logit contributions
bank-0.064
ued-0.063
roads-0.062
mer-0.059
ical-0.059
Token.
Token ID13
Feature activation+1.76e-01

Pos logit contributions
 accidents+0.076
 itch+0.072
 bleed+0.070
 stain+0.064
 rash+0.063
Neg logit contributions
ued-0.077
bank-0.074
roads-0.070
ical-0.067
mer-0.066
Token that
Token ID326
Feature activation-9.67e-02

Pos logit contributions
 accidents+0.039
 itch+0.037
 bleed+0.034
 stain+0.032
eddy+0.031
Neg logit contributions
ued-0.059
bank-0.055
roads-0.055
ving-0.052
ical-0.051
Token he
Token ID339
Feature activation+4.36e-01

Pos logit contributions
 accidents+0.003
 itch+0.003
 bleed+0.003
 stain+0.003
eddy+0.003
Neg logit contributions
ued-0.002
bank-0.002
roads-0.002
ving-0.002
ical-0.002
Token let
Token ID1309
Feature activation-1.12e+00

Pos logit contributions
ued+0.012
bank+0.011
roads+0.011
ving+0.011
sel+0.010
Neg logit contributions
 accidents-0.013
 itch-0.012
 bleed-0.012
 stain-0.011
eddy-0.011
Token Benny
Token ID44275
Feature activation-1.41e-01

Pos logit contributions
 accidents+0.024
 itch+0.023
 bleed+0.021
 stain+0.020
eddy+0.020
Neg logit contributions
ued-0.040
bank-0.038
roads-0.037
ving-0.036
ical-0.035
Token take
Token ID1011
Feature activation+4.35e-01

Pos logit contributions
 accidents+0.003
 itch+0.003
 bleed+0.002
 stain+0.002
eddy+0.002
Neg logit contributions
ued-0.005
bank-0.005
roads-0.005
ving-0.005
ical-0.005
Token as
Token ID355
Feature activation-2.94e+00

Pos logit contributions
ued+0.015
roads+0.014
bank+0.014
ving+0.013
ical+0.013
Neg logit contributions
 accidents-0.010
 itch-0.010
 bleed-0.009
 stain-0.008
 cookies-0.008
Token many
Token ID867
Feature activation+7.51e-01

Pos logit contributions
 accidents+0.079
 itch+0.076
 bleed+0.071
 stain+0.069
eddy+0.066
Neg logit contributions
ued-0.091
bank-0.083
roads-0.082
ving-0.078
sel-0.076
Token potatoes
Token ID18821
Feature activation+7.89e-03

Pos logit contributions
ued+0.027
bank+0.025
roads+0.025
ving+0.024
ical+0.024
Neg logit contributions
 accidents-0.017
 itch-0.016
 bleed-0.014
 cookies-0.014
 stain-0.014
Token as
Token ID355
Feature activation-1.93e+00

Pos logit contributions
ued+0.000
roads+0.000
bank+0.000
 gru+0.000
ving+0.000
Neg logit contributions
 accidents-0.000
 itch-0.000
 bleed-0.000
 stain-0.000
 from-0.000
Token he
Token ID339
Feature activation+1.92e+00

Pos logit contributions
 accidents+0.049
 itch+0.048
 bleed+0.045
 stain+0.043
eddy+0.041
Neg logit contributions
ued-0.061
bank-0.056
roads-0.055
ving-0.053
sel-0.052
Token wanted
Token ID2227
Feature activation+6.29e-01

Pos logit contributions
ued+0.059
roads+0.055
bank+0.054
folk+0.050
 gru+0.050
Neg logit contributions
 itch-0.051
 accidents-0.050
 bleed-0.047
 stain-0.045
 cookies-0.043