TOP ACTIVATIONS
MAX = 5.293

stick the mustache on her upper lip with some tape .
say yes , yes , yes . They sit on the
say yes , yes , yes . They put on their
like a fair game , yes . Go ahead ."
" Yes , yes , yes ! I can 't wait
" Yes , yes , yes ! I want to see
. They say yes , yes , yes . They sit
we take them out . Okay ?" L ily
" Yes , yes , yes ." She holds the mixer
" yes , yes , yes ". He fl aps his
" Yes , yes , yes !" Sara said . She
" Yes , yes , yes !" Tom and Lily said
said yes , yes , yes ! They wanted to learn
" Yes , yes , yes !" the children shouted .
" Yes , yes , yes . I want to try
and eat the o me let and the toast . They
away from the fire . Okay ?" L ily
something fun and healthy . Okay ?" " Okay
hole in the fence . Okay ?" Tom and
" Yes , yes , yes !" Anna and Ben say

MIN ACTIVATIONS
MIN = -7.663

. After Wh isk ers got better , he
wished they had never qu arre led . They missed their
. The owl told Wh isk ers , " To be
together . They never qu arre led again . <|endoftext|> Once
on , they never qu arre led again over clothes .
B uddy and Wh isk ers started to fight over
friends didn 't stop qu arre ling and were getting louder
good friends and never qu arre led again . <|endoftext|> Once
together happily and never qu arre lled again . <|endoftext|> Once
on , they never qu arre led again and played together
him . Spot urged Wh isk ers to come play with
him outside . But Wh isk ers just wanted to sleep
the tree to its once former beauty . He was happy
Lily and Jack never qu arre led again . They learned
. So Wh isk ers continued to eat and
Ch ir py and Wh isk ers knew that poison was
bark ed , but Wh isk ers did not care .
ers . Lily and Wh isk ers loved to play with
day , Lily and Wh isk ers were playing with their
L ily and Wh isk ers were both sad .

INTERVAL 2.054 - 5.293
CONTAINS 2.062%

had told her . " If an earthquake happens , find
you and be polite , OK ?" Anna smiled
careful and check the rope first ." They held
was very happy and he promised to always remember where he
. Everything looked so small down below him . It felt

INTERVAL -1.185 - 2.054
CONTAINS 88.192%

s how the black rake went on its big adventure !
you so much ! You 're very kind ."
and the bird wandered in the forest together and listened to
envelop es in the box . One day ,
took turns covering their faces with cream and then they leaned

INTERVAL -4.424 - -1.185
CONTAINS 9.739%

" Hey , cat ! That is not your
's why we have to test things to make sure they
for his play room . Sammy just had to rest in
Another family was struggling with their own enormous luggage . And
stories . One day , Chloe was playing .

INTERVAL -7.663 - -4.424
CONTAINS 0.008%

Tom and Mia stop qu arre ling . They see the
much pasta you won 't grow fit like me !"
they just kept on qu arre ling !
promised herself to think before acting , so that she could
that her mom had sp ilt milk on the floor .
Token stick
Token ID4859
Feature activation-5.47e-01

Pos logit contributions
obe+0.025
ols+0.025
 rivals+0.024
occupied+0.024
arre+0.024
Neg logit contributions
 go-0.012
 touch-0.012
 dove-0.011
 sled-0.011
 palm-0.011
Token the
Token ID262
Feature activation-3.89e-01

Pos logit contributions
arre+0.020
obe+0.020
 rivals+0.018
ulating+0.018
iting+0.017
Neg logit contributions
adies-0.012
ira-0.012
 sled-0.012
 palm-0.012
 dove-0.011
Token mustache
Token ID49303
Feature activation-1.06e+00

Pos logit contributions
obe+0.015
arre+0.015
 rivals+0.014
anks+0.014
ols+0.014
Neg logit contributions
adies-0.007
ira-0.007
 dove-0.007
 palm-0.007
 sled-0.007
Token on
Token ID319
Feature activation+4.10e-01

Pos logit contributions
obe+0.038
arre+0.037
 rivals+0.036
ols+0.034
 cooperating+0.033
Neg logit contributions
 dove-0.022
 sled-0.022
ira-0.022
 palm-0.021
adies-0.020
Token her
Token ID607
Feature activation-7.55e-01

Pos logit contributions
ira+0.008
Mom+0.008
 palm+0.007
 top+0.007
adies+0.007
Neg logit contributions
arre-0.016
obe-0.016
iting-0.015
anks-0.015
 rivals-0.015
Token upper
Token ID6727
Feature activation+5.29e+00

Pos logit contributions
arre+0.027
obe+0.027
 rivals+0.025
stick+0.024
ols+0.024
Neg logit contributions
ira-0.017
adies-0.017
 palm-0.015
 dove-0.015
 sled-0.015
Token lip
Token ID10645
Feature activation+3.91e-01

Pos logit contributions
adies+0.157
ira+0.142
Ah+0.137
 dove+0.128
Help+0.126
Neg logit contributions
stick-0.165
obe-0.162
arre-0.155
anks-0.154
 rivals-0.147
Token with
Token ID351
Feature activation+2.55e-01

Pos logit contributions
ira+0.009
 sled+0.009
 palm+0.009
adies+0.009
 dove+0.009
Neg logit contributions
arre-0.013
obe-0.013
 rivals-0.012
ols-0.012
 rewarded-0.011
Token some
Token ID617
Feature activation+1.76e+00

Pos logit contributions
adies+0.006
ira+0.006
Ah+0.005
 palm+0.005
 dove+0.005
Neg logit contributions
obe-0.009
arre-0.009
 rivals-0.009
anks-0.008
stick-0.008
Token tape
Token ID9154
Feature activation-1.83e-01

Pos logit contributions
adies+0.042
ira+0.041
Ah+0.035
 dove+0.034
 palm+0.034
Neg logit contributions
obe-0.061
arre-0.060
 rivals-0.057
stick-0.057
anks-0.056
Token.
Token ID13
Feature activation+5.49e-01

Pos logit contributions
arre+0.007
obe+0.007
 rivals+0.007
isk+0.006
ulating+0.006
Neg logit contributions
ira-0.004
 sled-0.004
 dove-0.003
 palm-0.003
adies-0.003
Token say
Token ID910
Feature activation+1.69e+00

Pos logit contributions
ira+0.025
adies+0.024
 dove+0.024
 palm+0.021
 sled+0.020
Neg logit contributions
obe-0.053
arre-0.053
stick-0.051
 rivals-0.050
anks-0.050
Token yes
Token ID3763
Feature activation+4.12e+00

Pos logit contributions
adies+0.043
ira+0.042
 dove+0.037
Ah+0.036
 palm+0.036
Neg logit contributions
obe-0.057
arre-0.057
 rivals-0.053
stick-0.053
anks-0.051
Token,
Token ID11
Feature activation-6.53e-02

Pos logit contributions
ira+0.097
adies+0.095
 dove+0.086
 sled+0.083
Mom+0.082
Neg logit contributions
arre-0.142
obe-0.134
stick-0.133
 rivals-0.132
ols-0.129
Token yes
Token ID3763
Feature activation+4.76e+00

Pos logit contributions
obe+0.002
arre+0.002
 rivals+0.002
stick+0.002
ols+0.002
Neg logit contributions
adies-0.002
ira-0.002
Ah-0.002
 sled-0.002
 palm-0.002
Token,
Token ID11
Feature activation+4.40e-01

Pos logit contributions
ira+0.117
adies+0.116
 dove+0.104
 sled+0.100
 palm+0.098
Neg logit contributions
arre-0.166
obe-0.155
stick-0.152
 rivals-0.150
anks-0.146
Token yes
Token ID3763
Feature activation+5.11e+00

Pos logit contributions
adies+0.012
ira+0.012
Ah+0.010
Jen+0.010
 sled+0.010
Neg logit contributions
obe-0.013
arre-0.013
 rivals-0.013
stick-0.012
ols-0.012
Token.
Token ID13
Feature activation-2.14e-01

Pos logit contributions
adies+0.138
ira+0.138
 dove+0.124
 sled+0.120
 palm+0.119
Neg logit contributions
arre-0.167
obe-0.157
stick-0.150
 rivals-0.150
anks-0.146
Token They
Token ID1119
Feature activation+1.09e+00

Pos logit contributions
obe+0.005
arre+0.005
 rivals+0.005
stick+0.005
anks+0.005
Neg logit contributions
adies-0.007
ira-0.007
Ah-0.006
 dove-0.006
 palm-0.006
Token sit
Token ID1650
Feature activation+1.29e+00

Pos logit contributions
ira+0.021
adies+0.020
 dove+0.020
 sled+0.018
 palm+0.018
Neg logit contributions
obe-0.043
arre-0.043
 rivals-0.041
stick-0.041
anks-0.040
Token on
Token ID319
Feature activation+4.53e-01

Pos logit contributions
adies+0.050
ira+0.049
Ah+0.048
Help+0.045
 palm+0.044
Neg logit contributions
arre-0.023
obe-0.023
stick-0.021
anks-0.020
iting-0.020
Token the
Token ID262
Feature activation-3.34e-01

Pos logit contributions
adies+0.015
ira+0.014
Ah+0.013
 dove+0.013
Jen+0.013
Neg logit contributions
obe-0.011
arre-0.011
 rivals-0.010
stick-0.010
ols-0.010
Token say
Token ID910
Feature activation+1.29e+00

Pos logit contributions
adies+0.003
ira+0.003
 dove+0.002
 sled+0.002
 palm+0.002
Neg logit contributions
obe-0.005
arre-0.005
 rivals-0.005
stick-0.005
anks-0.005
Token yes
Token ID3763
Feature activation+3.80e+00

Pos logit contributions
adies+0.033
ira+0.033
Ah+0.030
 palm+0.029
Jen+0.028
Neg logit contributions
obe-0.040
arre-0.040
 rivals-0.039
stick-0.037
ols-0.037
Token,
Token ID11
Feature activation-2.34e-01

Pos logit contributions
ira+0.093
adies+0.091
 dove+0.083
 sled+0.081
 palm+0.078
Neg logit contributions
arre-0.130
obe-0.121
stick-0.120
 rivals-0.118
anks-0.115
Token yes
Token ID3763
Feature activation+4.52e+00

Pos logit contributions
arre+0.006
obe+0.006
 rivals+0.005
stick+0.005
ols+0.005
Neg logit contributions
adies-0.008
ira-0.008
Ah-0.007
 palm-0.007
Jen-0.007
Token,
Token ID11
Feature activation+3.41e-01

Pos logit contributions
ira+0.119
adies+0.118
 dove+0.107
 sled+0.104
 palm+0.101
Neg logit contributions
arre-0.152
obe-0.141
stick-0.137
 rivals-0.135
anks-0.132
Token yes
Token ID3763
Feature activation+4.89e+00

Pos logit contributions
ira+0.010
adies+0.010
Ah+0.009
Jen+0.009
agg+0.009
Neg logit contributions
 rivals-0.009
arre-0.009
obe-0.008
stick-0.008
 sharing-0.008
Token.
Token ID13
Feature activation-2.29e-01

Pos logit contributions
adies+0.141
ira+0.141
 dove+0.127
 sled+0.125
 palm+0.122
Neg logit contributions
arre-0.150
obe-0.143
stick-0.135
 rivals-0.134
anks-0.131
Token They
Token ID1119
Feature activation+7.43e-01

Pos logit contributions
arre+0.005
obe+0.005
 rivals+0.005
anks+0.005
ols+0.005
Neg logit contributions
adies-0.008
ira-0.008
Ah-0.007
 palm-0.007
 dove-0.007
Token put
Token ID1234
Feature activation-1.31e-01

Pos logit contributions
adies+0.014
ira+0.013
 dove+0.012
 sled+0.011
 palm+0.011
Neg logit contributions
obe-0.030
arre-0.029
 rivals-0.028
stick-0.028
anks-0.027
Token on
Token ID319
Feature activation-1.34e-01

Pos logit contributions
obe+0.002
arre+0.002
ols+0.002
 Ros+0.002
stick+0.002
Neg logit contributions
adies-0.005
ira-0.005
Ah-0.004
Jen-0.004
Help-0.004
Token their
Token ID511
Feature activation-9.47e-01

Pos logit contributions
 rivals+0.002
obe+0.002
 Ros+0.002
arre+0.002
stick+0.002
Neg logit contributions
adies-0.005
ira-0.005
Ah-0.005
Help-0.004
Jen-0.004
Token like
Token ID588
Feature activation+4.09e-01

Pos logit contributions
obe+0.018
stick+0.018
arre+0.018
anks+0.018
ols+0.017
Neg logit contributions
adies-0.010
 yes-0.009
 dove-0.009
ira-0.009
 palm-0.008
Token a
Token ID257
Feature activation+1.08e-01

Pos logit contributions
adies+0.008
ira+0.008
Ah+0.008
 dove+0.008
 sled+0.007
Neg logit contributions
arre-0.016
obe-0.015
anks-0.014
stick-0.014
 rivals-0.014
Token fair
Token ID3148
Feature activation+4.44e-01

Pos logit contributions
 dove+0.002
ira+0.002
Ah+0.002
 sled+0.002
 palm+0.002
Neg logit contributions
obe-0.004
anks-0.004
stick-0.004
arre-0.004
ols-0.004
Token game
Token ID983
Feature activation+9.68e-01

Pos logit contributions
 dove+0.009
ira+0.009
 palm+0.008
adies+0.008
 sled+0.008
Neg logit contributions
obe-0.018
arre-0.017
stick-0.016
anks-0.016
isk-0.016
Token,
Token ID11
Feature activation+7.09e-01

Pos logit contributions
adies+0.019
ira+0.018
 dove+0.017
 yes+0.016
 sled+0.015
Neg logit contributions
arre-0.040
obe-0.038
occupied-0.033
 rivals-0.033
 punished-0.033
Token yes
Token ID3763
Feature activation+4.87e+00

Pos logit contributions
adies+0.022
ira+0.022
Ah+0.020
 dove+0.020
 palm+0.020
Neg logit contributions
obe-0.020
arre-0.019
anks-0.018
 rivals-0.018
stick-0.017
Token.
Token ID13
Feature activation-3.29e-01

Pos logit contributions
ira+0.120
adies+0.118
 dove+0.110
 sled+0.102
Mom+0.101
Neg logit contributions
arre-0.171
obe-0.159
stick-0.155
 rivals-0.154
anks-0.152
Token Go
Token ID1514
Feature activation+6.09e-01

Pos logit contributions
obe+0.011
arre+0.011
 rivals+0.010
stick+0.010
anks+0.010
Neg logit contributions
adies-0.008
ira-0.008
Ah-0.007
 dove-0.007
 sled-0.007
Token ahead
Token ID4058
Feature activation+1.53e+00

Pos logit contributions
adies+0.018
ira+0.017
 dove+0.016
 sled+0.016
Mom+0.016
Neg logit contributions
obe-0.018
arre-0.017
 rivals-0.016
anks-0.016
ols-0.016
Token."
Token ID526
Feature activation-1.85e-01

Pos logit contributions
adies+0.035
ira+0.034
Mom+0.031
 sled+0.030
 palm+0.029
Neg logit contributions
obe-0.059
arre-0.053
anks-0.052
ols-0.050
 rivals-0.050
Token
Token ID198
Feature activation+1.01e-01

Pos logit contributions
obe+0.006
arre+0.006
 rivals+0.006
anks+0.006
stick+0.006
Neg logit contributions
ira-0.004
adies-0.004
Ah-0.004
 palm-0.004
Mom-0.004
Token "
Token ID366
Feature activation+1.50e-01

Pos logit contributions
obe+0.020
arre+0.020
 rivals+0.019
anks+0.018
stick+0.018
Neg logit contributions
ira-0.019
adies-0.019
 dove-0.017
 palm-0.017
 sled-0.016
TokenYes
Token ID5297
Feature activation+3.92e+00

Pos logit contributions
adies+0.005
ira+0.004
 sled+0.004
 palm+0.004
 key+0.004
Neg logit contributions
obe-0.004
stick-0.003
 Sharing-0.003
arre-0.003
iting-0.003
Token,
Token ID11
Feature activation+2.32e-01

Pos logit contributions
Ah+0.173
ira+0.169
adies+0.168
Help+0.160
 palm+0.158
Neg logit contributions
obe-0.045
 Ros-0.043
arre-0.041
ols-0.040
 rivals-0.040
Token yes
Token ID3763
Feature activation+4.34e+00

Pos logit contributions
adies+0.007
Ah+0.007
agg+0.006
Help+0.006
ira+0.006
Neg logit contributions
 Ros-0.006
 sharing-0.006
 because-0.006
 that-0.006
 about-0.006
Token,
Token ID11
Feature activation+6.84e-01

Pos logit contributions
adies+0.138
ira+0.137
 dove+0.123
 sled+0.121
 palm+0.120
Neg logit contributions
arre-0.118
obe-0.114
 rivals-0.107
stick-0.107
anks-0.102
Token yes
Token ID3763
Feature activation+4.85e+00

Pos logit contributions
adies+0.017
Ah+0.015
ira+0.015
Help+0.013
Jen+0.013
Neg logit contributions
obe-0.022
arre-0.021
 Ros-0.021
 rivals-0.021
stick-0.020
Token!
Token ID0
Feature activation+1.95e-01

Pos logit contributions
adies+0.151
ira+0.149
 dove+0.134
 sled+0.131
 palm+0.130
Neg logit contributions
arre-0.137
obe-0.132
 rivals-0.124
stick-0.123
anks-0.118
Token I
Token ID314
Feature activation+2.32e+00

Pos logit contributions
adies+0.006
ira+0.006
 palm+0.006
 sled+0.006
 dove+0.006
Neg logit contributions
anks-0.004
obe-0.004
stick-0.004
ols-0.004
arre-0.004
Token can
Token ID460
Feature activation+1.40e+00

Pos logit contributions
adies+0.050
ira+0.049
Ah+0.042
 dove+0.042
 palm+0.041
Neg logit contributions
obe-0.085
arre-0.084
 rivals-0.081
stick-0.080
anks-0.079
Token't
Token ID470
Feature activation-1.91e-01

Pos logit contributions
adies+0.038
ira+0.037
Ah+0.035
 palm+0.031
Jen+0.031
Neg logit contributions
obe-0.044
arre-0.042
stick-0.042
 rivals-0.041
anks-0.040
Token wait
Token ID4043
Feature activation+6.76e-01

Pos logit contributions
obe+0.007
arre+0.006
 rivals+0.006
stick+0.006
ols+0.006
Neg logit contributions
adies-0.004
ira-0.004
Ah-0.004
 sled-0.004
 palm-0.004
Token "
Token ID366
Feature activation+1.64e-01

Pos logit contributions
obe+0.026
arre+0.025
 rivals+0.024
anks+0.023
stick+0.023
Neg logit contributions
ira-0.023
adies-0.023
 dove-0.021
 palm-0.020
 sled-0.020
TokenYes
Token ID5297
Feature activation+3.78e+00

Pos logit contributions
adies+0.006
ira+0.005
 sled+0.005
 palm+0.005
agg+0.004
Neg logit contributions
obe-0.004
 Sharing-0.004
ulating-0.004
manship-0.003
 rivals-0.003
Token,
Token ID11
Feature activation+1.88e-01

Pos logit contributions
ira+0.152
adies+0.152
Ah+0.151
 palm+0.141
Help+0.141
Neg logit contributions
obe-0.056
arre-0.054
 rivals-0.052
ols-0.050
 Ros-0.049
Token yes
Token ID3763
Feature activation+4.27e+00

Pos logit contributions
adies+0.005
ira+0.005
Ah+0.005
Jen+0.004
Help+0.004
Neg logit contributions
 Ros-0.005
 sharing-0.005
 rivals-0.005
 because-0.005
 rewarded-0.005
Token,
Token ID11
Feature activation+6.55e-01

Pos logit contributions
adies+0.132
ira+0.131
 dove+0.118
 sled+0.115
 palm+0.114
Neg logit contributions
arre-0.122
obe-0.117
stick-0.111
 rivals-0.110
anks-0.106
Token yes
Token ID3763
Feature activation+4.80e+00

Pos logit contributions
adies+0.015
ira+0.015
Ah+0.013
Jen+0.012
Help+0.012
Neg logit contributions
 rivals-0.022
arre-0.021
obe-0.021
ols-0.021
 Ros-0.021
Token!
Token ID0
Feature activation+3.27e-01

Pos logit contributions
adies+0.147
ira+0.146
 dove+0.131
 sled+0.128
 palm+0.126
Neg logit contributions
arre-0.139
obe-0.133
 rivals-0.125
stick-0.125
anks-0.121
Token I
Token ID314
Feature activation+2.37e+00

Pos logit contributions
adies+0.010
ira+0.010
 palm+0.010
 sled+0.009
Ah+0.009
Neg logit contributions
anks-0.008
ols-0.008
stick-0.007
 rivals-0.007
obe-0.007
Token want
Token ID765
Feature activation+2.83e+00

Pos logit contributions
adies+0.060
ira+0.058
Ah+0.052
 palm+0.051
 sled+0.049
Neg logit contributions
arre-0.077
obe-0.077
 rivals-0.072
stick-0.071
 rewarded-0.069
Token to
Token ID284
Feature activation-7.40e-01

Pos logit contributions
adies+0.091
ira+0.089
Ah+0.081
 dove+0.080
 palm+0.080
Neg logit contributions
obe-0.075
arre-0.075
 rivals-0.069
stick-0.068
anks-0.067
Token see
Token ID766
Feature activation+1.16e+00

Pos logit contributions
obe+0.024
 rivals+0.023
stick+0.023
arre+0.023
anks+0.022
Neg logit contributions
adies-0.019
ira-0.018
Ah-0.017
Jen-0.015
 palm-0.015
Token.
Token ID13
Feature activation-3.05e-01

Pos logit contributions
arre+0.013
isk+0.012
stick+0.012
iting+0.011
 rivals+0.011
Neg logit contributions
ira-0.004
 sled-0.003
adies-0.003
 dove-0.003
 palm-0.003
Token They
Token ID1119
Feature activation+1.33e+00

Pos logit contributions
obe+0.009
arre+0.009
 rivals+0.008
stick+0.008
anks+0.008
Neg logit contributions
ira-0.009
adies-0.009
Ah-0.008
 palm-0.008
 dove-0.008
Token say
Token ID910
Feature activation+1.69e+00

Pos logit contributions
ira+0.025
adies+0.024
 dove+0.024
 palm+0.021
 sled+0.020
Neg logit contributions
obe-0.053
arre-0.053
stick-0.051
 rivals-0.050
anks-0.050
Token yes
Token ID3763
Feature activation+4.12e+00

Pos logit contributions
adies+0.043
ira+0.042
 dove+0.037
Ah+0.036
 palm+0.036
Neg logit contributions
obe-0.057
arre-0.057
 rivals-0.053
stick-0.053
anks-0.051
Token,
Token ID11
Feature activation-6.53e-02

Pos logit contributions
ira+0.097
adies+0.095
 dove+0.086
 sled+0.083
Mom+0.082
Neg logit contributions
arre-0.142
obe-0.134
stick-0.133
 rivals-0.132
ols-0.129
Token yes
Token ID3763
Feature activation+4.76e+00

Pos logit contributions
obe+0.002
arre+0.002
 rivals+0.002
stick+0.002
ols+0.002
Neg logit contributions
adies-0.002
ira-0.002
Ah-0.002
 sled-0.002
 palm-0.002
Token,
Token ID11
Feature activation+4.40e-01

Pos logit contributions
ira+0.117
adies+0.116
 dove+0.104
 sled+0.100
 palm+0.098
Neg logit contributions
arre-0.166
obe-0.155
stick-0.152
 rivals-0.150
anks-0.146
Token yes
Token ID3763
Feature activation+5.11e+00

Pos logit contributions
adies+0.012
ira+0.012
Ah+0.010
Jen+0.010
 sled+0.010
Neg logit contributions
obe-0.013
arre-0.013
 rivals-0.013
stick-0.012
ols-0.012
Token.
Token ID13
Feature activation-2.14e-01

Pos logit contributions
adies+0.138
ira+0.138
 dove+0.124
 sled+0.120
 palm+0.119
Neg logit contributions
arre-0.167
obe-0.157
stick-0.150
 rivals-0.150
anks-0.146
Token They
Token ID1119
Feature activation+1.09e+00

Pos logit contributions
obe+0.005
arre+0.005
 rivals+0.005
stick+0.005
anks+0.005
Neg logit contributions
adies-0.007
ira-0.007
Ah-0.006
 dove-0.006
 palm-0.006
Token sit
Token ID1650
Feature activation+1.29e+00

Pos logit contributions
ira+0.021
adies+0.020
 dove+0.020
 sled+0.018
 palm+0.018
Neg logit contributions
obe-0.043
arre-0.043
 rivals-0.041
stick-0.041
anks-0.040
Token we
Token ID356
Feature activation+6.50e-01

Pos logit contributions
adies+0.022
ira+0.022
Ah+0.019
 dove+0.019
 palm+0.019
Neg logit contributions
obe-0.030
arre-0.030
 rivals-0.028
stick-0.028
anks-0.028
Token take
Token ID1011
Feature activation-4.21e-01

Pos logit contributions
adies+0.013
ira+0.012
 dove+0.011
 palm+0.011
 sled+0.011
Neg logit contributions
obe-0.025
arre-0.024
 rivals-0.024
stick-0.023
anks-0.023
Token them
Token ID606
Feature activation+3.13e-01

Pos logit contributions
obe+0.016
arre+0.016
 rivals+0.015
stick+0.015
anks+0.015
Neg logit contributions
adies-0.009
ira-0.008
Ah-0.008
 dove-0.007
Mom-0.007
Token out
Token ID503
Feature activation-1.31e-01

Pos logit contributions
adies+0.008
 sled+0.007
ira+0.007
 dove+0.006
Mom+0.006
Neg logit contributions
obe-0.011
arre-0.010
 rivals-0.010
ols-0.010
stick-0.010
Token.
Token ID13
Feature activation-5.75e-01

Pos logit contributions
obe+0.004
arre+0.004
 rivals+0.004
stick+0.004
anks+0.004
Neg logit contributions
adies-0.004
ira-0.003
 sled-0.003
 palm-0.003
 dove-0.003
Token Okay
Token ID16805
Feature activation+4.74e+00

Pos logit contributions
arre+0.014
obe+0.014
 rivals+0.013
ols+0.013
anks+0.013
Neg logit contributions
ira-0.019
adies-0.019
 dove-0.018
 palm-0.017
 sled-0.017
Token?"
Token ID1701
Feature activation+4.37e-01

Pos logit contributions
ira+0.120
adies+0.118
Mom+0.109
 dove+0.105
 sled+0.105
Neg logit contributions
arre-0.157
obe-0.155
 rivals-0.152
stick-0.144
anks-0.140
Token
Token ID198
Feature activation+1.00e+00

Pos logit contributions
adies+0.011
ira+0.011
Ah+0.009
 dove+0.009
 palm+0.009
Neg logit contributions
obe-0.015
arre-0.015
 rivals-0.014
stick-0.014
anks-0.014
Token
Token ID198
Feature activation+8.13e-01

Pos logit contributions
adies+0.034
ira+0.031
 palm+0.028
 dove+0.028
Ah+0.028
Neg logit contributions
obe-0.024
arre-0.024
 rivals-0.023
ols-0.022
anks-0.022
TokenL
Token ID43
Feature activation-6.56e-01

Pos logit contributions
adies+0.022
ira+0.020
 palm+0.018
 dove+0.018
 sled+0.018
Neg logit contributions
obe-0.026
arre-0.026
 rivals-0.024
ols-0.023
iting-0.023
Tokenily
Token ID813
Feature activation+2.67e-01

Pos logit contributions
obe+0.021
arre+0.021
isk+0.019
anks+0.019
 rivals+0.019
Neg logit contributions
 palm-0.017
 sled-0.017
Ah-0.016
ira-0.016
 spe-0.016
Token "
Token ID366
Feature activation-1.96e-01

Pos logit contributions
obe+0.033
arre+0.032
 rivals+0.030
stick+0.029
anks+0.029
Neg logit contributions
adies-0.034
ira-0.034
 dove-0.030
Ah-0.030
 palm-0.030
TokenYes
Token ID5297
Feature activation+3.56e+00

Pos logit contributions
obe+0.005
arre+0.005
 rivals+0.005
ols+0.005
ulating+0.005
Neg logit contributions
adies-0.006
ira-0.006
 sled-0.005
 palm-0.005
agg-0.005
Token,
Token ID11
Feature activation-9.63e-02

Pos logit contributions
ira+0.140
adies+0.139
Ah+0.137
 palm+0.128
 dove+0.128
Neg logit contributions
obe-0.061
arre-0.059
 rivals-0.056
ols-0.052
anks-0.051
Token yes
Token ID3763
Feature activation+4.08e+00

Pos logit contributions
 rivals+0.003
 Ros+0.003
 sharing+0.003
obe+0.003
arre+0.003
Neg logit contributions
adies-0.003
ira-0.002
Ah-0.002
Help-0.002
Jen-0.002
Token,
Token ID11
Feature activation+4.96e-01

Pos logit contributions
adies+0.123
ira+0.123
 dove+0.109
 sled+0.107
 palm+0.106
Neg logit contributions
arre-0.119
obe-0.114
stick-0.110
 rivals-0.108
anks-0.104
Token yes
Token ID3763
Feature activation+4.71e+00

Pos logit contributions
adies+0.011
ira+0.011
Ah+0.009
 palm+0.009
Jen+0.008
Neg logit contributions
obe-0.017
arre-0.017
 rivals-0.017
ols-0.016
stick-0.016
Token."
Token ID526
Feature activation+9.96e-02

Pos logit contributions
adies+0.138
ira+0.138
 dove+0.123
 sled+0.120
 palm+0.118
Neg logit contributions
arre-0.143
obe-0.136
stick-0.131
 rivals-0.128
anks-0.125
Token She
Token ID1375
Feature activation+1.45e-01

Pos logit contributions
adies+0.003
ira+0.003
Ah+0.002
 dove+0.002
 palm+0.002
Neg logit contributions
obe-0.003
arre-0.003
 rivals-0.003
stick-0.003
anks-0.003
Token holds
Token ID6622
Feature activation+3.02e-01

Pos logit contributions
adies+0.004
ira+0.004
Ah+0.003
 palm+0.003
 sled+0.003
Neg logit contributions
arre-0.005
obe-0.004
 rivals-0.004
stick-0.004
anks-0.004
Token the
Token ID262
Feature activation-2.36e-01

Pos logit contributions
adies+0.011
ira+0.011
Ah+0.010
Jen+0.010
 sled+0.010
Neg logit contributions
arre-0.006
obe-0.006
 Ros-0.006
anks-0.006
ols-0.005
Token mixer
Token ID33938
Feature activation+4.91e-01

Pos logit contributions
arre+0.007
obe+0.006
 rivals+0.006
stick+0.006
ols+0.006
Neg logit contributions
adies-0.007
ira-0.007
Ah-0.006
Jen-0.006
 dove-0.006
Token "
Token ID366
Feature activation-5.87e-01

Pos logit contributions
adies+0.007
ira+0.007
Ah+0.005
 dove+0.005
 sled+0.005
Neg logit contributions
obe-0.028
arre-0.027
 rivals-0.026
stick-0.026
anks-0.026
Tokenyes
Token ID8505
Feature activation+3.10e+00

Pos logit contributions
obe+0.024
arre+0.024
 rivals+0.023
anks+0.023
stick+0.023
Neg logit contributions
adies-0.010
ira-0.009
Ah-0.008
 dove-0.008
 sled-0.007
Token,
Token ID11
Feature activation-2.11e-01

Pos logit contributions
adies+0.090
ira+0.085
 dove+0.075
 sled+0.074
Ah+0.073
Neg logit contributions
obe-0.096
arre-0.095
 rivals-0.089
stick-0.086
anks-0.085
Token yes
Token ID3763
Feature activation+4.28e+00

Pos logit contributions
obe+0.008
arre+0.008
anks+0.008
 rivals+0.007
stick+0.007
Neg logit contributions
adies-0.004
ira-0.004
 dove-0.004
Ah-0.004
 sled-0.004
Token,
Token ID11
Feature activation+3.60e-01

Pos logit contributions
adies+0.104
ira+0.101
 dove+0.095
 sled+0.088
Mom+0.087
Neg logit contributions
arre-0.151
obe-0.139
stick-0.138
anks-0.134
 rivals-0.132
Token yes
Token ID3763
Feature activation+4.71e+00

Pos logit contributions
adies+0.008
ira+0.008
 dove+0.007
 sled+0.007
Ah+0.007
Neg logit contributions
obe-0.013
arre-0.013
anks-0.012
 rivals-0.012
stick-0.012
Token".
Token ID1911
Feature activation-4.25e-02

Pos logit contributions
adies+0.119
ira+0.115
 dove+0.107
 sled+0.102
Mom+0.099
Neg logit contributions
arre-0.164
obe-0.153
stick-0.149
anks-0.147
 rivals-0.143
Token He
Token ID679
Feature activation-1.01e-01

Pos logit contributions
obe+0.002
iting+0.002
arre+0.002
 rewarded+0.002
 believing+0.002
Neg logit contributions
ira-0.001
 sled-0.001
Jen-0.001
Mom-0.001
 Jen-0.001
Token fl
Token ID781
Feature activation+7.38e-01

Pos logit contributions
obe+0.004
arre+0.004
stick+0.004
anks+0.004
 rivals+0.004
Neg logit contributions
ira-0.002
adies-0.002
 dove-0.002
 sled-0.002
 palm-0.002
Tokenaps
Token ID1686
Feature activation-4.46e-01

Pos logit contributions
adies+0.024
ira+0.024
Ah+0.022
 palm+0.022
 dove+0.022
Neg logit contributions
arre-0.018
obe-0.018
 rivals-0.017
stick-0.017
anks-0.017
Token his
Token ID465
Feature activation+1.28e-02

Pos logit contributions
obe+0.013
arre+0.013
 rivals+0.012
stick+0.012
anks+0.011
Neg logit contributions
adies-0.013
ira-0.013
Ah-0.012
 dove-0.012
 palm-0.011
Token"
Token ID1
Feature activation-4.20e-01

Pos logit contributions
adies+0.012
ira+0.011
 sled+0.010
 palm+0.010
Ah+0.009
Neg logit contributions
arre-0.014
obe-0.014
ulating-0.013
 rewarded-0.013
 rivals-0.013
TokenYes
Token ID5297
Feature activation+3.50e+00

Pos logit contributions
obe+0.011
 rivals+0.010
arre+0.010
stick+0.010
ols+0.010
Neg logit contributions
adies-0.013
ira-0.013
 sled-0.012
 palm-0.011
 dove-0.010
Token,
Token ID11
Feature activation-2.16e-01

Pos logit contributions
adies+0.132
ira+0.131
Ah+0.126
 palm+0.119
 dove+0.119
Neg logit contributions
obe-0.067
arre-0.064
 rivals-0.061
stick-0.059
ols-0.057
Token yes
Token ID3763
Feature activation+4.09e+00

Pos logit contributions
 sharing+0.005
 because+0.005
obe+0.005
 rewarded+0.005
 rivals+0.005
Neg logit contributions
adies-0.006
Ah-0.006
ira-0.006
Help-0.005
Jen-0.005
Token,
Token ID11
Feature activation+4.06e-01

Pos logit contributions
adies+0.132
ira+0.130
 dove+0.117
 sled+0.116
 palm+0.115
Neg logit contributions
arre-0.110
obe-0.106
 rivals-0.100
stick-0.099
anks-0.096
Token yes
Token ID3763
Feature activation+4.70e+00

Pos logit contributions
adies+0.011
ira+0.010
Ah+0.010
Jen+0.009
Help+0.009
Neg logit contributions
obe-0.012
arre-0.012
 rivals-0.011
 rewarded-0.011
ols-0.011
Token!"
Token ID2474
Feature activation+5.76e-01

Pos logit contributions
adies+0.148
ira+0.146
 dove+0.132
 sled+0.130
 palm+0.129
Neg logit contributions
arre-0.129
obe-0.125
 rivals-0.118
stick-0.117
anks-0.114
Token Sara
Token ID24799
Feature activation+1.50e+00

Pos logit contributions
adies+0.014
ira+0.013
Ah+0.011
 sled+0.011
 palm+0.011
Neg logit contributions
obe-0.020
arre-0.019
 rivals-0.019
stick-0.018
anks-0.018
Token said
Token ID531
Feature activation+1.61e+00

Pos logit contributions
ira+0.043
 dove+0.039
adies+0.038
 palm+0.037
 sled+0.037
Neg logit contributions
obe-0.047
arre-0.047
ols-0.043
 rivals-0.043
anks-0.043
Token.
Token ID13
Feature activation-2.26e-01

Pos logit contributions
adies+0.059
ira+0.059
Ah+0.057
Help+0.053
 dove+0.053
Neg logit contributions
obe-0.033
anks-0.031
 rivals-0.031
stick-0.031
arre-0.030
Token She
Token ID1375
Feature activation+2.35e-02

Pos logit contributions
obe+0.007
arre+0.007
 rivals+0.006
stick+0.006
ols+0.006
Neg logit contributions
adies-0.006
ira-0.006
Ah-0.006
 dove-0.006
 palm-0.006
Token"
Token ID1
Feature activation-5.53e-01

Pos logit contributions
adies+0.005
ira+0.005
 palm+0.005
 dove+0.004
Ah+0.004
Neg logit contributions
arre-0.007
obe-0.007
 rivals-0.007
iting-0.006
ulating-0.006
TokenYes
Token ID5297
Feature activation+3.25e+00

Pos logit contributions
arre+0.014
obe+0.014
 rivals+0.013
ulating+0.012
iting+0.012
Neg logit contributions
adies-0.017
ira-0.016
 palm-0.015
 sled-0.014
 dove-0.014
Token,
Token ID11
Feature activation-3.07e-01

Pos logit contributions
adies+0.114
ira+0.112
Ah+0.103
 dove+0.101
 palm+0.101
Neg logit contributions
obe-0.075
arre-0.075
 rivals-0.069
stick-0.067
anks-0.066
Token yes
Token ID3763
Feature activation+4.05e+00

Pos logit contributions
arre+0.009
obe+0.009
 rivals+0.009
 sharing+0.009
 Ros+0.009
Neg logit contributions
adies-0.008
ira-0.007
Ah-0.007
 palm-0.006
Help-0.006
Token,
Token ID11
Feature activation+4.01e-01

Pos logit contributions
ira+0.118
adies+0.117
 dove+0.105
 sled+0.104
 palm+0.101
Neg logit contributions
arre-0.121
obe-0.119
stick-0.113
 rivals-0.112
anks-0.110
Token yes
Token ID3763
Feature activation+4.68e+00

Pos logit contributions
adies+0.009
ira+0.009
Ah+0.008
 palm+0.008
Jen+0.007
Neg logit contributions
arre-0.013
obe-0.013
 rivals-0.013
stick-0.012
ols-0.012
Token!"
Token ID2474
Feature activation-3.61e-02

Pos logit contributions
ira+0.133
adies+0.132
 dove+0.118
 sled+0.117
 palm+0.114
Neg logit contributions
arre-0.143
obe-0.140
stick-0.132
 rivals-0.132
anks-0.129
Token Tom
Token ID4186
Feature activation+1.36e+00

Pos logit contributions
obe+0.001
arre+0.001
stick+0.001
 rivals+0.001
anks+0.001
Neg logit contributions
ira-0.001
adies-0.001
Mom-0.001
Jen-0.001
 dove-0.001
Token and
Token ID290
Feature activation+6.86e-01

Pos logit contributions
ira+0.033
 dove+0.028
 sled+0.027
adies+0.027
 palm+0.025
Neg logit contributions
arre-0.050
obe-0.049
ols-0.049
anks-0.047
 rivals-0.046
Token Lily
Token ID20037
Feature activation-3.19e-01

Pos logit contributions
ira+0.019
Ah+0.018
 dove+0.017
Mom+0.017
adies+0.017
Neg logit contributions
obe-0.023
arre-0.022
anks-0.022
ols-0.021
 rivals-0.020
Token said
Token ID531
Feature activation+8.36e-01

Pos logit contributions
obe+0.009
arre+0.009
 rivals+0.008
stick+0.008
anks+0.008
Neg logit contributions
adies-0.010
ira-0.010
 dove-0.009
Ah-0.009
 sled-0.008
Token said
Token ID531
Feature activation+8.39e-01

Pos logit contributions
ira+0.028
adies+0.027
 dove+0.027
 palm+0.024
Ah+0.024
Neg logit contributions
obe-0.047
arre-0.045
anks-0.044
 rivals-0.042
stick-0.042
Token yes
Token ID3763
Feature activation+3.75e+00

Pos logit contributions
adies+0.025
ira+0.024
 dove+0.022
Ah+0.021
 palm+0.021
Neg logit contributions
obe-0.025
arre-0.024
stick-0.023
 rivals-0.022
anks-0.022
Token,
Token ID11
Feature activation-1.10e-01

Pos logit contributions
ira+0.085
adies+0.081
 dove+0.075
 sled+0.072
Mom+0.070
Neg logit contributions
arre-0.133
stick-0.125
obe-0.125
 rivals-0.123
ols-0.121
Token yes
Token ID3763
Feature activation+4.36e+00

Pos logit contributions
obe+0.003
arre+0.003
 rivals+0.003
stick+0.003
anks+0.003
Neg logit contributions
adies-0.003
ira-0.003
 dove-0.003
Ah-0.003
 palm-0.003
Token,
Token ID11
Feature activation+3.88e-01

Pos logit contributions
ira+0.098
adies+0.094
 dove+0.088
 sled+0.084
 palm+0.080
Neg logit contributions
arre-0.161
obe-0.148
stick-0.148
 rivals-0.143
ols-0.143
Token yes
Token ID3763
Feature activation+4.67e+00

Pos logit contributions
adies+0.012
ira+0.012
Ah+0.011
 dove+0.010
 palm+0.010
Neg logit contributions
obe-0.010
arre-0.010
 rivals-0.010
stick-0.010
anks-0.009
Token!
Token ID0
Feature activation+4.99e-01

Pos logit contributions
ira+0.114
adies+0.111
 dove+0.103
 sled+0.100
 palm+0.094
Neg logit contributions
arre-0.168
obe-0.154
stick-0.152
 rivals-0.147
ols-0.146
Token They
Token ID1119
Feature activation+9.23e-01

Pos logit contributions
ira+0.012
adies+0.011
Ah+0.011
Mom+0.011
Jen+0.011
Neg logit contributions
obe-0.018
arre-0.017
 rivals-0.016
stick-0.016
iting-0.016
Token wanted
Token ID2227
Feature activation+2.60e+00

Pos logit contributions
ira+0.022
 dove+0.022
adies+0.021
 palm+0.020
 sled+0.019
Neg logit contributions
obe-0.034
arre-0.032
anks-0.031
stick-0.030
ols-0.030
Token to
Token ID284
Feature activation-5.90e-01

Pos logit contributions
adies+0.075
ira+0.074
 dove+0.068
Ah+0.068
 palm+0.067
Neg logit contributions
arre-0.078
obe-0.077
stick-0.071
ols-0.070
anks-0.070
Token learn
Token ID2193
Feature activation-6.57e-01

Pos logit contributions
arre+0.020
obe+0.020
 rivals+0.019
stick+0.019
anks+0.018
Neg logit contributions
adies-0.014
ira-0.014
 dove-0.013
 sled-0.012
 palm-0.012
Token"
Token ID1
Feature activation-6.05e-01

Pos logit contributions
adies+0.008
ira+0.007
Ah+0.006
 dove+0.006
 palm+0.006
Neg logit contributions
obe-0.011
arre-0.011
 rivals-0.010
stick-0.010
anks-0.010
TokenYes
Token ID5297
Feature activation+3.36e+00

Pos logit contributions
obe+0.015
arre+0.015
 rivals+0.014
manship+0.014
 congratulated+0.014
Neg logit contributions
adies-0.019
ira-0.017
 palm-0.016
 sled-0.015
 upper-0.014
Token,
Token ID11
Feature activation-4.19e-01

Pos logit contributions
adies+0.131
ira+0.131
Ah+0.128
 palm+0.121
 dove+0.119
Neg logit contributions
obe-0.054
arre-0.052
 rivals-0.050
stick-0.048
ols-0.048
Token yes
Token ID3763
Feature activation+4.05e+00

Pos logit contributions
 Ros+0.011
ols+0.011
 rewarded+0.011
obe+0.011
 rivals+0.011
Neg logit contributions
adies-0.011
ira-0.011
Ah-0.010
 upper-0.009
 palm-0.009
Token,
Token ID11
Feature activation+1.85e-01

Pos logit contributions
adies+0.129
ira+0.128
 dove+0.115
Ah+0.114
 sled+0.114
Neg logit contributions
arre-0.107
obe-0.107
 rivals-0.099
stick-0.098
anks-0.096
Token yes
Token ID3763
Feature activation+4.67e+00

Pos logit contributions
ira+0.004
adies+0.004
Ah+0.004
 palm+0.004
Jen+0.004
Neg logit contributions
obe-0.006
arre-0.006
 rivals-0.006
stick-0.006
ols-0.006
Token!"
Token ID2474
Feature activation+4.97e-01

Pos logit contributions
adies+0.146
ira+0.145
 dove+0.130
Ah+0.128
 sled+0.128
Neg logit contributions
arre-0.127
obe-0.126
 rivals-0.118
stick-0.116
anks-0.113
Token the
Token ID262
Feature activation+1.31e+00

Pos logit contributions
ira+0.011
 dove+0.010
Ah+0.009
adies+0.009
 palm+0.009
Neg logit contributions
arre-0.020
obe-0.020
iting-0.019
isk-0.019
anks-0.018
Token children
Token ID1751
Feature activation+5.33e-01

Pos logit contributions
adies+0.032
ira+0.032
Ah+0.028
 dove+0.027
 palm+0.027
Neg logit contributions
obe-0.043
arre-0.043
 rivals-0.041
stick-0.041
anks-0.040
Token shouted
Token ID17293
Feature activation+7.83e-01

Pos logit contributions
adies+0.017
ira+0.017
 dove+0.016
 sled+0.015
Ah+0.015
Neg logit contributions
obe-0.014
arre-0.014
 rivals-0.013
anks-0.012
stick-0.012
Token.
Token ID13
Feature activation-4.25e-01

Pos logit contributions
ira+0.027
adies+0.026
Ah+0.025
 palm+0.024
 dove+0.024
Neg logit contributions
obe-0.018
arre-0.018
 rivals-0.017
stick-0.017
anks-0.017
Token "
Token ID366
Feature activation-3.43e-01

Pos logit contributions
obe+0.036
arre+0.035
 rivals+0.033
stick+0.032
anks+0.032
Neg logit contributions
adies-0.038
ira-0.038
Ah-0.034
 dove-0.034
 sled-0.034
TokenYes
Token ID5297
Feature activation+3.62e+00

Pos logit contributions
obe+0.011
arre+0.010
 rivals+0.010
stick+0.010
ols+0.010
Neg logit contributions
adies-0.010
ira-0.009
 sled-0.008
 palm-0.007
 dove-0.007
Token,
Token ID11
Feature activation-1.60e-01

Pos logit contributions
Ah+0.153
ira+0.151
adies+0.149
Help+0.142
 palm+0.140
Neg logit contributions
obe-0.047
arre-0.044
 rivals-0.044
ols-0.042
 Ros-0.041
Token yes
Token ID3763
Feature activation+4.10e+00

Pos logit contributions
 sharing+0.004
 because+0.004
 about+0.004
 that+0.004
 so+0.004
Neg logit contributions
adies-0.005
ira-0.005
Ah-0.004
Help-0.004
Jen-0.004
Token,
Token ID11
Feature activation+3.98e-01

Pos logit contributions
adies+0.125
ira+0.124
 dove+0.110
 sled+0.108
 palm+0.106
Neg logit contributions
arre-0.120
obe-0.114
stick-0.110
 rivals-0.108
anks-0.103
Token yes
Token ID3763
Feature activation+4.67e+00

Pos logit contributions
adies+0.009
ira+0.009
Ah+0.008
Jen+0.007
Help+0.007
Neg logit contributions
 rivals-0.013
 sharing-0.013
 Ros-0.012
arre-0.012
obe-0.012
Token.
Token ID13
Feature activation-7.87e-01

Pos logit contributions
adies+0.139
ira+0.137
 dove+0.122
 sled+0.119
 palm+0.117
Neg logit contributions
arre-0.141
obe-0.134
stick-0.128
 rivals-0.127
anks-0.122
Token I
Token ID314
Feature activation+2.23e+00

Pos logit contributions
obe+0.022
arre+0.021
 rivals+0.021
stick+0.021
anks+0.021
Neg logit contributions
ira-0.023
adies-0.023
Ah-0.020
 palm-0.020
 sled-0.020
Token want
Token ID765
Feature activation+2.80e+00

Pos logit contributions
adies+0.052
ira+0.051
Ah+0.045
 dove+0.044
 palm+0.044
Neg logit contributions
obe-0.077
arre-0.077
 rivals-0.073
stick-0.072
anks-0.071
Token to
Token ID284
Feature activation-6.81e-01

Pos logit contributions
adies+0.088
ira+0.087
Ah+0.079
 dove+0.079
 palm+0.078
Neg logit contributions
obe-0.075
arre-0.075
 rivals-0.069
stick-0.068
anks-0.067
Token try
Token ID1949
Feature activation+2.08e+00

Pos logit contributions
obe+0.023
arre+0.023
 rivals+0.022
stick+0.022
anks+0.021
Neg logit contributions
adies-0.016
ira-0.016
Ah-0.014
 dove-0.014
 palm-0.014
Token and
Token ID290
Feature activation+3.26e-02

Pos logit contributions
obe+0.017
arre+0.017
beh+0.016
 rivals+0.016
ols+0.016
Neg logit contributions
ira-0.010
adies-0.009
 sled-0.008
 palm-0.008
 dove-0.008
Token eat
Token ID4483
Feature activation+8.35e-02

Pos logit contributions
adies+0.001
ira+0.001
Ah+0.001
 dove+0.001
 palm+0.001
Neg logit contributions
obe-0.001
arre-0.001
 rivals-0.001
stick-0.001
anks-0.001
Token the
Token ID262
Feature activation-8.27e-01

Pos logit contributions
adies+0.002
ira+0.002
 sled+0.002
 dove+0.002
 palm+0.002
Neg logit contributions
obe-0.003
arre-0.003
 rivals-0.002
stick-0.002
anks-0.002
Token o
Token ID267
Feature activation+1.74e+00

Pos logit contributions
obe+0.023
arre+0.023
 rivals+0.021
anks+0.020
stick+0.020
Neg logit contributions
adies-0.025
ira-0.024
Ah-0.022
Jen-0.021
 dove-0.021
Tokenme
Token ID1326
Feature activation+1.69e+00

Pos logit contributions
adies+0.056
ira+0.054
Ah+0.051
 dove+0.050
 palm+0.049
Neg logit contributions
obe-0.046
arre-0.045
anks-0.041
 rivals-0.040
ols-0.040
Tokenlet
Token ID1616
Feature activation+4.64e+00

Pos logit contributions
adies+0.050
ira+0.049
Ah+0.044
 dove+0.043
 palm+0.043
Neg logit contributions
obe-0.049
arre-0.049
 rivals-0.046
stick-0.045
ols-0.044
Token and
Token ID290
Feature activation-5.30e-02

Pos logit contributions
adies+0.126
ira+0.124
Ah+0.110
 dove+0.110
 palm+0.108
Neg logit contributions
obe-0.144
arre-0.142
 rivals-0.138
stick-0.131
anks-0.129
Token the
Token ID262
Feature activation-1.97e-01

Pos logit contributions
arre+0.002
obe+0.002
 rivals+0.002
anks+0.002
ols+0.002
Neg logit contributions
ira-0.001
adies-0.001
 dove-0.001
 sled-0.001
 palm-0.001
Token toast
Token ID27805
Feature activation+1.90e-01

Pos logit contributions
obe+0.006
arre+0.006
 rivals+0.006
stick+0.006
anks+0.006
Neg logit contributions
adies-0.005
ira-0.005
Ah-0.004
 dove-0.004
 palm-0.004
Token.
Token ID13
Feature activation-1.83e-01

Pos logit contributions
ira+0.005
adies+0.004
 dove+0.004
 sled+0.004
 palm+0.004
Neg logit contributions
arre-0.007
obe-0.007
 rivals-0.006
ols-0.006
stick-0.006
Token They
Token ID1119
Feature activation+6.37e-01

Pos logit contributions
obe+0.005
arre+0.005
 rivals+0.004
stick+0.004
anks+0.004
Neg logit contributions
adies-0.006
ira-0.006
Ah-0.005
 dove-0.005
 palm-0.005
Token away
Token ID1497
Feature activation-8.36e-01

Pos logit contributions
adies+0.021
ira+0.021
 dove+0.019
 sled+0.019
 palm+0.019
Neg logit contributions
arre-0.022
obe-0.022
 rivals-0.020
stick-0.020
anks-0.020
Token from
Token ID422
Feature activation-1.76e+00

Pos logit contributions
arre+0.028
obe+0.027
 rivals+0.025
stick+0.025
ols+0.024
Neg logit contributions
adies-0.022
ira-0.021
 palm-0.019
 sled-0.019
Mom-0.018
Token the
Token ID262
Feature activation-2.20e-01

Pos logit contributions
arre+0.056
obe+0.054
anks+0.050
 rivals+0.050
stick+0.050
Neg logit contributions
ira-0.047
adies-0.047
 palm-0.043
 dove-0.042
 sled-0.042
Token fire
Token ID2046
Feature activation+2.21e-01

Pos logit contributions
arre+0.008
obe+0.008
 rivals+0.007
stick+0.007
anks+0.007
Neg logit contributions
adies-0.005
ira-0.005
 palm-0.005
 dove-0.005
 sled-0.004
Token.
Token ID13
Feature activation-1.85e-01

Pos logit contributions
ira+0.004
 sled+0.004
adies+0.004
 palm+0.004
 dove+0.003
Neg logit contributions
obe-0.008
arre-0.008
 rivals-0.008
beh-0.008
ulating-0.008
Token Okay
Token ID16805
Feature activation+4.63e+00

Pos logit contributions
arre+0.004
obe+0.004
 rivals+0.004
ols+0.004
anks+0.004
Neg logit contributions
adies-0.006
ira-0.006
 dove-0.006
 sled-0.005
 palm-0.005
Token?"
Token ID1701
Feature activation+4.94e-01

Pos logit contributions
adies+0.127
ira+0.126
Mom+0.112
 dove+0.111
 sled+0.111
Neg logit contributions
arre-0.143
obe-0.141
 rivals-0.137
stick-0.129
anks-0.128
Token
Token ID198
Feature activation+9.91e-01

Pos logit contributions
adies+0.012
ira+0.012
Ah+0.011
 dove+0.010
 palm+0.010
Neg logit contributions
obe-0.016
arre-0.016
 rivals-0.015
stick-0.015
anks-0.015
Token
Token ID198
Feature activation+7.96e-01

Pos logit contributions
adies+0.029
ira+0.028
Ah+0.025
 dove+0.025
 palm+0.024
Neg logit contributions
obe-0.029
arre-0.029
 rivals-0.027
stick-0.026
ols-0.026
TokenL
Token ID43
Feature activation-6.23e-01

Pos logit contributions
adies+0.021
ira+0.020
 dove+0.018
Ah+0.018
 palm+0.017
Neg logit contributions
obe-0.026
arre-0.026
 rivals-0.024
stick-0.024
ols-0.023
Tokenily
Token ID813
Feature activation+1.85e-01

Pos logit contributions
arre+0.022
obe+0.021
isk+0.019
 rivals+0.019
anks+0.019
Neg logit contributions
 sled-0.015
ira-0.015
 palm-0.014
adies-0.014
Ah-0.014
Token something
Token ID1223
Feature activation-4.61e-01

Pos logit contributions
obe+0.003
arre+0.003
 rivals+0.003
stick+0.003
anks+0.003
Neg logit contributions
ira-0.002
adies-0.002
Ah-0.002
Jen-0.002
 sled-0.002
Token fun
Token ID1257
Feature activation-7.09e-01

Pos logit contributions
arre+0.018
stick+0.018
obe+0.018
isk+0.017
ols+0.016
Neg logit contributions
ira-0.009
adies-0.009
 dove-0.009
 corn-0.009
 palm-0.008
Token and
Token ID290
Feature activation-3.39e-01

Pos logit contributions
arre+0.027
obe+0.026
isk+0.026
stick+0.024
ols+0.024
Neg logit contributions
adies-0.015
ira-0.014
 dove-0.012
 key-0.012
 sled-0.011
Token healthy
Token ID5448
Feature activation-4.74e-02

Pos logit contributions
arre+0.012
obe+0.011
stick+0.011
anks+0.010
 rivals+0.010
Neg logit contributions
adies-0.008
ira-0.008
 dove-0.008
 palm-0.007
Ah-0.007
Token.
Token ID13
Feature activation-4.91e-01

Pos logit contributions
arre+0.002
obe+0.002
ols+0.002
iting+0.002
 rivals+0.002
Neg logit contributions
adies-0.001
ira-0.001
 corn-0.001
 dove-0.001
 sled-0.001
Token Okay
Token ID16805
Feature activation+4.62e+00

Pos logit contributions
obe+0.011
arre+0.011
 rivals+0.010
anks+0.010
 Ros+0.010
Neg logit contributions
ira-0.017
adies-0.017
 dove-0.016
 sled-0.016
 palm-0.015
Token?"
Token ID1701
Feature activation+2.86e-01

Pos logit contributions
adies+0.138
ira+0.137
Ah+0.122
 dove+0.121
 sled+0.120
Neg logit contributions
obe-0.131
arre-0.130
 rivals-0.123
stick-0.120
anks-0.117
Token
Token ID198
Feature activation+9.09e-01

Pos logit contributions
adies+0.010
ira+0.009
Ah+0.008
 dove+0.008
 palm+0.008
Neg logit contributions
obe-0.007
arre-0.007
 Ros-0.007
 rivals-0.006
ols-0.006
Token
Token ID198
Feature activation+7.38e-01

Pos logit contributions
adies+0.031
ira+0.029
Ah+0.026
 dove+0.026
 palm+0.026
Neg logit contributions
obe-0.022
arre-0.022
 Ros-0.020
 rivals-0.020
ols-0.020
Token"
Token ID1
Feature activation-1.34e-01

Pos logit contributions
adies+0.023
ira+0.021
 palm+0.019
Ah+0.019
 dove+0.019
Neg logit contributions
obe-0.021
arre-0.021
 rivals-0.019
iting-0.019
ols-0.018
TokenOkay
Token ID16454
Feature activation+3.76e+00

Pos logit contributions
obe+0.003
arre+0.003
 Sharing+0.003
iting+0.003
 rivals+0.003
Neg logit contributions
adies-0.005
ira-0.004
 palm-0.004
 sled-0.004
 dove-0.004
Token hole
Token ID7604
Feature activation-8.52e-01

Pos logit contributions
adies+0.007
ira+0.007
 palm+0.006
 dove+0.006
 sled+0.006
Neg logit contributions
obe-0.010
arre-0.010
 rivals-0.010
stick-0.009
anks-0.009
Token in
Token ID287
Feature activation-4.80e-01

Pos logit contributions
obe+0.029
arre+0.028
 rivals+0.026
anks+0.026
stick+0.025
Neg logit contributions
adies-0.022
ira-0.021
 dove-0.019
 palm-0.019
 sled-0.019
Token the
Token ID262
Feature activation-5.16e-01

Pos logit contributions
arre+0.018
obe+0.017
anks+0.016
 rivals+0.016
iting+0.016
Neg logit contributions
ira-0.011
 palm-0.010
 sled-0.010
adies-0.010
Mom-0.009
Token fence
Token ID13990
Feature activation+6.02e-01

Pos logit contributions
obe+0.018
arre+0.018
 rivals+0.017
stick+0.017
anks+0.017
Neg logit contributions
adies-0.012
ira-0.012
 palm-0.011
 dove-0.011
 sled-0.011
Token.
Token ID13
Feature activation-5.45e-01

Pos logit contributions
adies+0.014
ira+0.012
 palm+0.012
 dove+0.012
 sled+0.012
Neg logit contributions
obe-0.021
arre-0.021
anks-0.020
 rivals-0.019
ols-0.019
Token Okay
Token ID16805
Feature activation+4.59e+00

Pos logit contributions
obe+0.013
arre+0.013
 rivals+0.012
anks+0.012
ols+0.012
Neg logit contributions
adies-0.018
ira-0.018
 dove-0.017
 sled-0.017
 palm-0.016
Token?"
Token ID1701
Feature activation+3.15e-01

Pos logit contributions
adies+0.120
ira+0.120
Mom+0.107
 dove+0.106
 sled+0.105
Neg logit contributions
arre-0.149
obe-0.146
 rivals-0.143
stick-0.135
anks-0.133
Token
Token ID198
Feature activation+1.13e+00

Pos logit contributions
adies+0.009
ira+0.009
Ah+0.008
 dove+0.008
 sled+0.008
Neg logit contributions
obe-0.009
arre-0.009
 rivals-0.009
stick-0.008
ols-0.008
Token
Token ID198
Feature activation+9.68e-01

Pos logit contributions
adies+0.041
ira+0.036
 palm+0.035
 dove+0.034
 upper+0.034
Neg logit contributions
obe-0.024
arre-0.022
ols-0.022
 rivals-0.022
 Ros-0.021
TokenTom
Token ID13787
Feature activation+9.75e-01

Pos logit contributions
adies+0.023
ira+0.019
 palm+0.018
 dove+0.018
 sled+0.017
Neg logit contributions
obe-0.033
arre-0.031
 rivals-0.031
 rewarded-0.030
iting-0.030
Token and
Token ID290
Feature activation+4.35e-01

Pos logit contributions
ira+0.023
adies+0.020
 dove+0.020
Mom+0.019
 palm+0.019
Neg logit contributions
ols-0.034
obe-0.034
anks-0.033
arre-0.033
 rivals-0.032
Token"
Token ID1
Feature activation-4.43e-01

Pos logit contributions
adies+0.012
ira+0.011
 palm+0.010
 sled+0.010
 footh+0.009
Neg logit contributions
 rivals-0.014
obe-0.014
arre-0.014
ols-0.013
stick-0.013
TokenYes
Token ID5297
Feature activation+3.41e+00

Pos logit contributions
obe+0.012
 rivals+0.011
arre+0.011
ols+0.011
manship+0.010
Neg logit contributions
adies-0.014
ira-0.013
 sled-0.012
 palm-0.011
 dove-0.011
Token,
Token ID11
Feature activation-2.82e-01

Pos logit contributions
Ah+0.141
ira+0.141
adies+0.138
Help+0.130
 dove+0.129
Neg logit contributions
obe-0.049
arre-0.044
 rivals-0.044
ols-0.043
 Ros-0.042
Token yes
Token ID3763
Feature activation+4.00e+00

Pos logit contributions
 Ros+0.008
 sharing+0.007
 that+0.007
 because+0.007
 Penny+0.007
Neg logit contributions
Ah-0.008
ira-0.008
adies-0.008
 upper-0.007
Higher-0.007
Token,
Token ID11
Feature activation+3.00e-01

Pos logit contributions
adies+0.135
ira+0.134
Ah+0.122
 dove+0.120
 palm+0.119
Neg logit contributions
obe-0.097
arre-0.097
 rivals-0.090
stick-0.088
anks-0.086
Token yes
Token ID3763
Feature activation+4.58e+00

Pos logit contributions
ira+0.006
adies+0.006
Ah+0.006
Jen+0.006
 sled+0.005
Neg logit contributions
 rivals-0.010
obe-0.010
 Ros-0.009
 sharing-0.009
ols-0.009
Token!"
Token ID2474
Feature activation+5.01e-01

Pos logit contributions
adies+0.150
ira+0.148
Ah+0.133
 dove+0.132
 palm+0.131
Neg logit contributions
obe-0.117
arre-0.117
 rivals-0.109
stick-0.106
anks-0.104
Token Anna
Token ID11735
Feature activation+9.67e-01

Pos logit contributions
adies+0.015
ira+0.014
Ah+0.013
 palm+0.013
 sled+0.013
Neg logit contributions
obe-0.014
arre-0.013
 rivals-0.013
stick-0.013
ols-0.012
Token and
Token ID290
Feature activation+7.38e-01

Pos logit contributions
ira+0.026
adies+0.026
 dove+0.023
 sled+0.022
 palm+0.022
Neg logit contributions
obe-0.030
arre-0.030
 rivals-0.028
stick-0.028
ols-0.027
Token Ben
Token ID3932
Feature activation+9.85e-02

Pos logit contributions
adies+0.023
ira+0.022
Ah+0.020
 sled+0.019
 palm+0.019
Neg logit contributions
obe-0.020
arre-0.020
 rivals-0.019
stick-0.019
anks-0.018
Token say
Token ID910
Feature activation+1.93e+00

Pos logit contributions
adies+0.002
ira+0.002
 dove+0.002
 sled+0.002
 palm+0.002
Neg logit contributions
arre-0.003
obe-0.003
 rivals-0.003
stick-0.003
anks-0.003
Token.
Token ID13
Feature activation+2.63e-01

Pos logit contributions
arre+0.076
obe+0.071
 rivals+0.071
anks+0.069
beh+0.068
Neg logit contributions
 yes-0.030
 dove-0.028
 go-0.026
ira-0.025
 key-0.024
Token
Token ID198
Feature activation+1.70e-01

Pos logit contributions
ira+0.005
Mom+0.004
Jen+0.004
Ah+0.004
 sled+0.004
Neg logit contributions
obe-0.010
arre-0.010
 rivals-0.010
iting-0.009
 rewarded-0.009
Token
Token ID198
Feature activation+1.85e-01

Pos logit contributions
ira+0.004
adies+0.004
Ah+0.003
 dove+0.003
 sled+0.003
Neg logit contributions
obe-0.006
arre-0.006
 rivals-0.006
stick-0.006
anks-0.006
TokenAfter
Token ID3260
Feature activation-5.08e-01

Pos logit contributions
ira+0.003
adies+0.003
Mom+0.003
Ah+0.003
Jen+0.003
Neg logit contributions
arre-0.007
obe-0.007
 rivals-0.007
anks-0.007
stick-0.007
Token Wh
Token ID854
Feature activation-2.21e+00

Pos logit contributions
arre+0.019
obe+0.019
 rivals+0.018
iting+0.018
ulating+0.017
Neg logit contributions
ira-0.011
 sled-0.011
 dove-0.010
Ah-0.009
 palm-0.009
Tokenisk
Token ID1984
Feature activation-6.81e+00

Pos logit contributions
obe+0.013
arre+0.013
 rivals+0.012
stick+0.010
ols+0.008
Neg logit contributions
adies-0.113
ira-0.113
Ah-0.104
Jen-0.104
 dove-0.104
Tokeners
Token ID364
Feature activation-2.68e+00

Pos logit contributions
arre+0.131
obe+0.131
 rivals+0.121
stick+0.114
anks+0.113
Neg logit contributions
adies-0.265
ira-0.261
Ah-0.241
 dove-0.236
Jen-0.233
Token got
Token ID1392
Feature activation-1.90e+00

Pos logit contributions
obe+0.096
 rivals+0.095
arre+0.093
anks+0.093
ols+0.088
Neg logit contributions
ira-0.061
 dove-0.058
adies-0.057
 palm-0.050
 sled-0.050
Token better
Token ID1365
Feature activation-2.16e+00

Pos logit contributions
obe+0.060
arre+0.058
ols+0.056
 rivals+0.056
stick+0.054
Neg logit contributions
adies-0.050
ira-0.049
 sled-0.046
 dove-0.045
Ah-0.045
Token,
Token ID11
Feature activation-9.09e-01

Pos logit contributions
ols+0.073
 rivals+0.073
isk+0.071
stick+0.071
arre+0.069
Neg logit contributions
ira-0.053
 sled-0.046
 dove-0.045
 palm-0.042
adies-0.041
Token he
Token ID339
Feature activation+2.43e-01

Pos logit contributions
arre+0.032
obe+0.031
iting+0.030
 rivals+0.030
ulating+0.028
Neg logit contributions
 sled-0.024
ira-0.023
 dove-0.022
Jen-0.021
 palm-0.020
Token wished
Token ID16555
Feature activation+3.19e-01

Pos logit contributions
arre+0.031
iting+0.030
obe+0.030
anks+0.029
igsaw+0.029
Neg logit contributions
 dove-0.016
 palm-0.014
Help-0.014
ira-0.014
Ah-0.014
Token they
Token ID484
Feature activation-6.68e-01

Pos logit contributions
ira+0.008
adies+0.008
 sled+0.007
 dove+0.006
 palm+0.006
Neg logit contributions
arre-0.011
obe-0.011
 rivals-0.010
stick-0.010
anks-0.010
Token had
Token ID550
Feature activation-1.74e+00

Pos logit contributions
obe+0.023
arre+0.023
 rivals+0.021
anks+0.021
stick+0.021
Neg logit contributions
adies-0.016
ira-0.015
 dove-0.014
Ah-0.014
 sled-0.014
Token never
Token ID1239
Feature activation+3.33e-01

Pos logit contributions
arre+0.054
obe+0.054
ols+0.051
stick+0.050
anks+0.050
Neg logit contributions
adies-0.045
ira-0.044
 dove-0.041
Ah-0.041
 sled-0.039
Token qu
Token ID627
Feature activation-3.89e+00

Pos logit contributions
ira+0.010
adies+0.010
Ah+0.009
 sled+0.009
 palm+0.009
Neg logit contributions
obe-0.010
arre-0.009
 rivals-0.009
stick-0.009
anks-0.008
Tokenarre
Token ID9624
Feature activation-6.60e+00

Pos logit contributions
obe+0.026
 Ros+0.020
stick+0.020
ols+0.020
 rivals+0.018
Neg logit contributions
adies-0.191
ira-0.182
Ah-0.174
Jen-0.173
Help-0.173
Tokenled
Token ID992
Feature activation-1.65e+00

Pos logit contributions
 Ros+0.209
ols+0.202
anks+0.200
stick+0.194
obe+0.190
Neg logit contributions
adies-0.159
osh-0.137
Ah-0.134
ira-0.133
Help-0.133
Token.
Token ID13
Feature activation-8.80e-01

Pos logit contributions
arre+0.067
obe+0.063
ols+0.062
isk+0.062
anks+0.061
Neg logit contributions
adies-0.026
 sled-0.023
 closer-0.023
 dove-0.022
 touch-0.021
Token They
Token ID1119
Feature activation+1.26e-03

Pos logit contributions
iting+0.034
obe+0.033
ming+0.033
 rewarded+0.032
arre+0.032
Neg logit contributions
ira-0.016
adies-0.014
Ah-0.014
 palm-0.013
Mom-0.012
Token missed
Token ID6825
Feature activation-8.86e-01

Pos logit contributions
 dove+0.000
 palm+0.000
ira+0.000
adies+0.000
 sled+0.000
Neg logit contributions
obe-0.000
arre-0.000
anks-0.000
iting-0.000
 rivals-0.000
Token their
Token ID511
Feature activation-1.13e+00

Pos logit contributions
stick+0.032
arre+0.032
anks+0.031
ols+0.031
obe+0.031
Neg logit contributions
ira-0.018
 sled-0.017
 palm-0.017
 dove-0.016
 corn-0.016
Token.
Token ID13
Feature activation-5.18e-01

Pos logit contributions
arre+0.100
obe+0.093
isk+0.085
 rivals+0.084
anks+0.084
Neg logit contributions
ira-0.048
 dove-0.045
 palm-0.044
 corn-0.040
 sled-0.039
Token The
Token ID383
Feature activation-7.68e-02

Pos logit contributions
arre+0.018
 rivals+0.016
obe+0.016
 rewarded+0.015
iting+0.015
Neg logit contributions
ira-0.013
adies-0.013
 sled-0.012
Jen-0.012
 dove-0.011
Token owl
Token ID39610
Feature activation-1.87e+00

Pos logit contributions
obe+0.002
arre+0.002
 rivals+0.002
stick+0.002
anks+0.002
Neg logit contributions
adies-0.003
ira-0.002
Ah-0.002
 sled-0.002
 dove-0.002
Token told
Token ID1297
Feature activation+4.17e-01

Pos logit contributions
anks+0.066
obe+0.065
arre+0.065
 rivals+0.063
igsaw+0.060
Neg logit contributions
ira-0.047
 dove-0.045
adies-0.040
 palm-0.039
Ah-0.037
Token Wh
Token ID854
Feature activation-2.49e+00

Pos logit contributions
ira+0.012
adies+0.012
 sled+0.011
 dove+0.011
Jen+0.010
Neg logit contributions
arre-0.013
 rivals-0.012
iting-0.012
 rewarded-0.011
obe-0.011
Tokenisk
Token ID1984
Feature activation-6.56e+00

Pos logit contributions
arre+0.021
 rivals+0.020
obe+0.019
stick+0.017
ols+0.015
Neg logit contributions
adies-0.122
ira-0.120
Jen-0.111
 sled-0.109
 dove-0.108
Tokeners
Token ID364
Feature activation-2.55e+00

Pos logit contributions
obe+0.125
arre+0.125
 rivals+0.113
stick+0.109
anks+0.107
Neg logit contributions
adies-0.257
ira-0.253
Ah-0.234
 dove-0.230
 palm-0.227
Token,
Token ID11
Feature activation-1.66e+00

Pos logit contributions
obe+0.065
arre+0.065
 rivals+0.058
anks+0.058
stick+0.057
Neg logit contributions
adies-0.086
ira-0.084
 palm-0.078
 dove-0.076
 sled-0.074
Token "
Token ID366
Feature activation-3.45e-01

Pos logit contributions
arre+0.050
obe+0.050
 rivals+0.047
anks+0.046
stick+0.046
Neg logit contributions
adies-0.047
ira-0.047
 dove-0.042
 palm-0.042
Ah-0.042
TokenTo
Token ID2514
Feature activation-1.09e+00

Pos logit contributions
obe+0.013
arre+0.013
 rivals+0.012
stick+0.012
anks+0.012
Neg logit contributions
adies-0.007
ira-0.007
Ah-0.006
 dove-0.006
 palm-0.006
Token be
Token ID307
Feature activation-9.10e-01

Pos logit contributions
arre+0.044
obe+0.041
 rivals+0.041
iting+0.039
storms+0.039
Neg logit contributions
adies-0.022
ira-0.020
 dove-0.018
 palm-0.017
 touch-0.016
Token together
Token ID1978
Feature activation-4.94e-01

Pos logit contributions
obe+0.001
arre+0.001
anks+0.001
ilda+0.001
cess+0.001
Neg logit contributions
adies-0.001
 yes-0.001
 dove-0.001
 sled-0.001
Ah-0.001
Token.
Token ID13
Feature activation-7.46e-02

Pos logit contributions
arre+0.020
obe+0.020
anks+0.018
cess+0.018
 rivals+0.018
Neg logit contributions
 yes-0.008
 dove-0.008
 sled-0.007
 palm-0.007
adies-0.006
Token They
Token ID1119
Feature activation+3.55e-02

Pos logit contributions
obe+0.002
arre+0.002
stick+0.002
 rivals+0.002
 punished+0.002
Neg logit contributions
ira-0.002
adies-0.002
 palm-0.002
Ah-0.002
Jen-0.002
Token never
Token ID1239
Feature activation+7.74e-01

Pos logit contributions
 dove+0.001
 palm+0.001
ira+0.001
 sled+0.001
osh+0.001
Neg logit contributions
obe-0.001
anks-0.001
arre-0.001
cess-0.001
ols-0.001
Token qu
Token ID627
Feature activation-3.12e+00

Pos logit contributions
 dove+0.017
 touch+0.015
Help+0.015
adies+0.015
 palm+0.014
Neg logit contributions
anks-0.027
ols-0.026
obe-0.026
stick-0.025
arre-0.025
Tokenarre
Token ID9624
Feature activation-6.48e+00

Pos logit contributions
obe+0.038
 Ros+0.035
 rewarded+0.032
cess+0.032
bank+0.031
Neg logit contributions
adies-0.130
osh-0.125
Jen-0.118
Ah-0.118
ira-0.118
Tokenled
Token ID992
Feature activation-1.51e+00

Pos logit contributions
anks+0.215
 Ros+0.214
obe+0.203
cess+0.200
stick+0.199
Neg logit contributions
adies-0.144
osh-0.136
Ah-0.124
ira-0.117
Help-0.115
Token again
Token ID757
Feature activation+4.78e-01

Pos logit contributions
obe+0.056
anks+0.053
ols+0.053
arre+0.052
isk+0.051
Neg logit contributions
adies-0.030
 dove-0.028
 closer-0.026
 yes-0.026
 sled-0.026
Token.
Token ID13
Feature activation-4.66e-01

Pos logit contributions
ira+0.007
 dove+0.007
 palm+0.007
 sled+0.007
 touch+0.007
Neg logit contributions
stick-0.018
ols-0.018
anks-0.018
obe-0.018
 rivals-0.017
Token<|endoftext|>
Token ID50256
Feature activation-1.59e+00

Pos logit contributions
obe+0.015
arre+0.014
stick+0.014
 rivals+0.014
anks+0.013
Neg logit contributions
ira-0.012
adies-0.012
 palm-0.011
Ah-0.011
Jen-0.010
TokenOnce
Token ID7454
Feature activation-7.54e-01

Pos logit contributions
obe+0.053
arre+0.053
 rivals+0.050
stick+0.049
anks+0.049
Neg logit contributions
adies-0.039
ira-0.038
Ah-0.034
 dove-0.033
 palm-0.033
Token on
Token ID319
Feature activation-2.58e-01

Pos logit contributions
obe+0.005
arre+0.005
 rivals+0.005
stick+0.005
anks+0.005
Neg logit contributions
adies-0.006
ira-0.006
Ah-0.005
 dove-0.005
 sled-0.005
Token,
Token ID11
Feature activation-8.17e-01

Pos logit contributions
obe+0.011
arre+0.010
anks+0.010
beh+0.010
stick+0.010
Neg logit contributions
ira-0.006
 sled-0.005
 dove-0.004
adies-0.004
 palm-0.004
Token they
Token ID484
Feature activation+7.38e-01

Pos logit contributions
obe+0.036
anks+0.033
arre+0.032
stick+0.032
iting+0.031
Neg logit contributions
ira-0.013
 dove-0.012
Me-0.011
 other-0.010
 sled-0.010
Token never
Token ID1239
Feature activation+8.67e-01

Pos logit contributions
 dove+0.018
ira+0.018
 palm+0.016
adies+0.016
Mom+0.016
Neg logit contributions
obe-0.025
anks-0.025
 rivals-0.024
arre-0.023
ulating-0.023
Token qu
Token ID627
Feature activation-3.05e+00

Pos logit contributions
 dove+0.020
 touch+0.018
Help+0.017
 palm+0.017
ira+0.017
Neg logit contributions
anks-0.029
ols-0.029
obe-0.028
arre-0.028
stick-0.027
Tokenarre
Token ID9624
Feature activation-6.39e+00

Pos logit contributions
obe+0.033
bank+0.029
 Ros+0.028
 bothering+0.026
 Mickey+0.025
Neg logit contributions
adies-0.130
osh-0.125
ira-0.122
Ah-0.120
Jen-0.120
Tokenled
Token ID992
Feature activation-1.33e+00

Pos logit contributions
anks+0.208
 Ros+0.207
bank+0.200
obe+0.196
isk+0.194
Neg logit contributions
osh-0.135
adies-0.133
Ah-0.124
ira-0.113
Help-0.113
Token again
Token ID757
Feature activation+9.37e-01

Pos logit contributions
obe+0.048
ols+0.047
anks+0.046
arre+0.046
stick+0.045
Neg logit contributions
adies-0.027
 dove-0.025
ira-0.023
 closer-0.022
 yes-0.022
Token over
Token ID625
Feature activation+9.16e-01

Pos logit contributions
ira+0.017
 dove+0.016
 palm+0.016
 sled+0.014
adies+0.014
Neg logit contributions
ols-0.034
stick-0.034
anks-0.033
obe-0.033
arre-0.033
Token clothes
Token ID8242
Feature activation+5.73e-01

Pos logit contributions
ira+0.020
 palm+0.019
adies+0.019
 dove+0.018
 sled+0.018
Neg logit contributions
obe-0.031
stick-0.031
arre-0.030
ols-0.030
ulating-0.030
Token.
Token ID13
Feature activation+2.52e-01

Pos logit contributions
adies+0.011
 yes+0.011
 dove+0.011
 sled+0.011
ira+0.010
Neg logit contributions
obe-0.020
arre-0.019
 rivals-0.019
ols-0.019
anks-0.018
Token
Token ID198
Feature activation-2.69e-01

Pos logit contributions
obe+0.010
arre+0.010
 rivals+0.009
stick+0.009
ols+0.009
Neg logit contributions
adies-0.008
ira-0.008
Ah-0.007
 palm-0.007
 dove-0.007
TokenB
Token ID33
Feature activation-7.90e-01

Pos logit contributions
obe+0.010
arre+0.010
anks+0.010
 rivals+0.010
stick+0.009
Neg logit contributions
ira-0.005
adies-0.005
Mom-0.005
Ah-0.005
Jen-0.005
Tokenuddy
Token ID21584
Feature activation-2.02e+00

Pos logit contributions
obe+0.024
arre+0.023
 rivals+0.022
 rewarded+0.022
stick+0.022
Neg logit contributions
adies-0.021
ira-0.021
Jen-0.019
 dove-0.018
Ah-0.018
Token and
Token ID290
Feature activation-1.32e-01

Pos logit contributions
anks+0.089
igsaw+0.089
obe+0.085
 cooperating+0.084
arre+0.083
Neg logit contributions
 dove-0.037
ira-0.031
Help-0.026
 palm-0.026
adies-0.025
Token Wh
Token ID854
Feature activation-2.59e+00

Pos logit contributions
arre+0.005
obe+0.004
 rivals+0.004
ulating+0.004
anks+0.004
Neg logit contributions
ira-0.003
 dove-0.003
 sled-0.003
Jen-0.003
 pine-0.003
Tokenisk
Token ID1984
Feature activation-6.37e+00

Pos logit contributions
 rivals+0.032
 rewarded+0.030
arre+0.028
obe+0.027
 practicing+0.027
Neg logit contributions
adies-0.113
ira-0.110
Jen-0.106
ila-0.100
Mom-0.099
Tokeners
Token ID364
Feature activation-1.67e+00

Pos logit contributions
arre+0.148
obe+0.146
 rivals+0.139
anks+0.132
ols+0.124
Neg logit contributions
adies-0.229
ira-0.216
Ah-0.205
Jen-0.201
 dove-0.196
Token started
Token ID2067
Feature activation+6.68e-01

Pos logit contributions
obe+0.058
arre+0.056
anks+0.055
 rivals+0.054
ols+0.052
Neg logit contributions
adies-0.039
ira-0.037
 dove-0.037
 palm-0.035
Help-0.033
Token to
Token ID284
Feature activation-3.60e-01

Pos logit contributions
 palm+0.011
 sled+0.010
 touch+0.010
 dove+0.010
 hand+0.009
Neg logit contributions
ols-0.025
anks-0.025
cess-0.025
obe-0.025
 rewarded-0.024
Token fight
Token ID1907
Feature activation-9.15e-01

Pos logit contributions
anks+0.013
ables+0.013
arre+0.013
 rivals+0.012
obe+0.012
Neg logit contributions
 touch-0.008
 run-0.007
 climb-0.007
 gaze-0.007
 go-0.007
Token over
Token ID625
Feature activation+1.05e+00

Pos logit contributions
arre+0.034
igsaw+0.032
obe+0.032
eline+0.032
 rewarded+0.031
Neg logit contributions
 go-0.016
 touch-0.015
Mom-0.015
 top-0.015
Help-0.014
Token friends
Token ID2460
Feature activation-7.45e-01

Pos logit contributions
adies+0.033
ira+0.033
 dove+0.031
 palm+0.030
Ah+0.030
Neg logit contributions
obe-0.032
arre-0.031
stick-0.029
anks-0.029
 rivals-0.028
Token didn
Token ID1422
Feature activation-7.30e-01

Pos logit contributions
anks+0.030
obe+0.030
igsaw+0.028
arre+0.028
 rivals+0.027
Neg logit contributions
 dove-0.014
adies-0.012
 palm-0.012
ira-0.012
osh-0.011
Token't
Token ID470
Feature activation-6.56e-01

Pos logit contributions
obe+0.023
arre+0.023
 rivals+0.022
stick+0.021
anks+0.021
Neg logit contributions
adies-0.019
ira-0.019
Ah-0.017
 sled-0.017
 dove-0.017
Token stop
Token ID2245
Feature activation-7.65e-01

Pos logit contributions
anks+0.026
ols+0.026
arre+0.025
stick+0.025
 rivals+0.025
Neg logit contributions
adies-0.011
 dove-0.010
Help-0.010
Jen-0.010
 dare-0.010
Token qu
Token ID627
Feature activation-3.39e+00

Pos logit contributions
arre+0.021
isk+0.021
anks+0.021
obe+0.020
ables+0.020
Neg logit contributions
 sled-0.021
 palm-0.021
 dove-0.021
ira-0.020
adies-0.019
Tokenarre
Token ID9624
Feature activation-6.34e+00

Pos logit contributions
obe+0.030
 Ros+0.030
stick+0.029
 rewarded+0.029
 Mickey+0.025
Neg logit contributions
adies-0.148
ira-0.141
Jen-0.139
 palm-0.138
osh-0.137
Tokenling
Token ID1359
Feature activation-2.33e+00

Pos logit contributions
 Ros+0.183
anks+0.179
stick+0.166
isk+0.165
ravings+0.163
Neg logit contributions
adies-0.170
ira-0.153
osh-0.153
Run-0.145
 lever-0.140
Token and
Token ID290
Feature activation-1.15e+00

Pos logit contributions
obe+0.088
arre+0.084
anks+0.081
isk+0.080
iting+0.079
Neg logit contributions
 sled-0.041
 palm-0.040
adies-0.039
 dove-0.038
 yes-0.037
Token were
Token ID547
Feature activation-8.06e-01

Pos logit contributions
obe+0.047
anks+0.046
igsaw+0.045
arre+0.045
ables+0.042
Neg logit contributions
 dove-0.023
 palm-0.021
 sled-0.019
 touch-0.019
Help-0.018
Token getting
Token ID1972
Feature activation-1.56e+00

Pos logit contributions
obe+0.030
anks+0.029
ols+0.028
igsaw+0.027
ables+0.026
Neg logit contributions
 dove-0.018
 palm-0.016
 sled-0.016
 hand-0.016
 no-0.016
Token louder
Token ID27089
Feature activation-8.86e-01

Pos logit contributions
obe+0.050
arre+0.048
cess+0.046
anks+0.046
isk+0.046
Neg logit contributions
 sled-0.037
 dove-0.036
Help-0.036
Ah-0.035
 palm-0.035
Token good
Token ID922
Feature activation-9.86e-01

Pos logit contributions
obe+0.008
anks+0.008
ols+0.008
igsaw+0.008
stick+0.008
Neg logit contributions
ira-0.004
Mom-0.004
 dove-0.004
 palm-0.004
 sled-0.004
Token friends
Token ID2460
Feature activation+5.07e-01

Pos logit contributions
stick+0.031
bank+0.031
isk+0.031
ols+0.030
obe+0.030
Neg logit contributions
ira-0.024
adies-0.024
 dove-0.022
 sled-0.022
Mom-0.020
Token and
Token ID290
Feature activation+2.10e-01

Pos logit contributions
adies+0.009
ira+0.008
 dove+0.008
 sled+0.008
 yes+0.008
Neg logit contributions
arre-0.020
obe-0.020
anks-0.019
ols-0.019
 rivals-0.018
Token never
Token ID1239
Feature activation+1.35e+00

Pos logit contributions
ira+0.006
adies+0.005
 dove+0.005
 palm+0.005
 sled+0.005
Neg logit contributions
obe-0.007
arre-0.007
anks-0.006
ols-0.006
 rivals-0.006
Token qu
Token ID627
Feature activation-3.33e+00

Pos logit contributions
 touch+0.028
 dove+0.027
Help+0.025
 palm+0.024
 go+0.024
Neg logit contributions
anks-0.046
ols-0.046
arre-0.045
obe-0.043
stick-0.043
Tokenarre
Token ID9624
Feature activation-6.31e+00

Pos logit contributions
 Ros+0.032
obe+0.030
stick+0.028
 rewarded+0.027
bank+0.026
Neg logit contributions
adies-0.146
ira-0.134
osh-0.134
Jen-0.133
Ah-0.132
Tokenled
Token ID992
Feature activation-1.29e+00

Pos logit contributions
anks+0.213
 Ros+0.210
ols+0.204
 Oliver+0.200
cess+0.194
Neg logit contributions
adies-0.129
osh-0.117
Ah-0.114
Help-0.111
Over-0.105
Token again
Token ID757
Feature activation+1.02e+00

Pos logit contributions
arre+0.047
obe+0.046
ols+0.044
anks+0.044
isk+0.042
Neg logit contributions
adies-0.027
ira-0.023
 dove-0.023
Mom-0.022
 closer-0.022
Token.
Token ID13
Feature activation-4.73e-01

Pos logit contributions
ira+0.013
 palm+0.012
 sled+0.011
 touch+0.011
 dove+0.011
Neg logit contributions
arre-0.042
stick-0.041
 rivals-0.040
ols-0.040
obe-0.040
Token<|endoftext|>
Token ID50256
Feature activation-1.80e+00

Pos logit contributions
obe+0.017
stick+0.016
arre+0.016
 punished+0.016
iting+0.015
Neg logit contributions
ira-0.011
adies-0.010
Jen-0.009
Mom-0.009
 palm-0.009
TokenOnce
Token ID7454
Feature activation-5.04e-01

Pos logit contributions
obe+0.058
arre+0.058
 rivals+0.054
stick+0.053
anks+0.053
Neg logit contributions
adies-0.046
ira-0.045
Ah-0.040
 dove-0.039
 palm-0.039
Token together
Token ID1978
Feature activation-5.41e-02

Pos logit contributions
obe+0.015
beh+0.014
stick+0.014
any+0.013
storms+0.013
Neg logit contributions
 dove-0.017
adies-0.017
 sled-0.016
ira-0.016
 rope-0.016
Token happily
Token ID18177
Feature activation+9.08e-01

Pos logit contributions
obe+0.002
anks+0.002
arre+0.002
beh+0.002
ols+0.002
Neg logit contributions
 dove-0.001
 palm-0.001
 top-0.001
 sled-0.001
adies-0.001
Token and
Token ID290
Feature activation-4.13e-01

Pos logit contributions
 dove+0.018
ira+0.018
 palm+0.017
adies+0.017
 sled+0.016
Neg logit contributions
arre-0.032
obe-0.031
 rewarded-0.030
 Ros-0.030
ols-0.029
Token never
Token ID1239
Feature activation+9.70e-01

Pos logit contributions
obe+0.014
anks+0.014
arre+0.013
ols+0.013
stick+0.013
Neg logit contributions
ira-0.010
 dove-0.009
 palm-0.009
adies-0.009
Ah-0.009
Token qu
Token ID627
Feature activation-3.29e+00

Pos logit contributions
 touch+0.021
 dove+0.020
Help+0.018
 go+0.017
 palm+0.017
Neg logit contributions
anks-0.032
ols-0.032
ables-0.032
igsaw-0.032
arre-0.031
Tokenarre
Token ID9624
Feature activation-6.31e+00

Pos logit contributions
obe+0.034
 Ros+0.032
stick+0.029
bank+0.028
 Mickey+0.026
Neg logit contributions
adies-0.143
osh-0.135
ira-0.134
Ah-0.131
Jen-0.131
Tokenlled
Token ID3353
Feature activation-1.14e+00

Pos logit contributions
 Ros+0.203
anks+0.199
bank+0.195
stick+0.191
ols+0.190
Neg logit contributions
adies-0.133
osh-0.130
Ah-0.121
ira-0.113
Help-0.112
Token again
Token ID757
Feature activation+9.56e-01

Pos logit contributions
obe+0.039
stick+0.038
arre+0.038
isk+0.038
ols+0.037
Neg logit contributions
adies-0.024
 dove-0.024
 palm-0.022
ira-0.022
 sled-0.021
Token.
Token ID13
Feature activation-6.76e-03

Pos logit contributions
ira+0.016
 palm+0.016
 sled+0.015
 dove+0.014
adies+0.014
Neg logit contributions
arre-0.037
stick-0.036
anks-0.036
ols-0.036
obe-0.036
Token<|endoftext|>
Token ID50256
Feature activation-1.58e+00

Pos logit contributions
obe+0.000
arre+0.000
 rivals+0.000
stick+0.000
anks+0.000
Neg logit contributions
ira-0.000
adies-0.000
Jen-0.000
 palm-0.000
Ah-0.000
TokenOnce
Token ID7454
Feature activation-8.61e-01

Pos logit contributions
arre+0.046
obe+0.046
 rivals+0.043
stick+0.042
anks+0.042
Neg logit contributions
adies-0.045
ira-0.044
 dove-0.039
Ah-0.039
 palm-0.038
Token on
Token ID319
Feature activation-4.33e-01

Pos logit contributions
arre+0.004
obe+0.003
 rivals+0.003
anks+0.003
ols+0.003
Neg logit contributions
ira-0.007
adies-0.007
Ah-0.007
 palm-0.007
 dove-0.007
Token,
Token ID11
Feature activation-8.48e-01

Pos logit contributions
obe+0.015
arre+0.015
stick+0.014
anks+0.014
 rivals+0.014
Neg logit contributions
ira-0.011
 sled-0.010
adies-0.010
 dove-0.009
Mom-0.009
Token they
Token ID484
Feature activation+6.49e-01

Pos logit contributions
obe+0.027
stick+0.027
arre+0.026
anks+0.026
ols+0.025
Neg logit contributions
adies-0.021
ira-0.021
 sled-0.020
Mom-0.019
 dove-0.019
Token never
Token ID1239
Feature activation+7.92e-01

Pos logit contributions
ira+0.017
 dove+0.017
adies+0.017
 palm+0.016
Mom+0.016
Neg logit contributions
obe-0.020
anks-0.019
 rivals-0.018
arre-0.018
stick-0.018
Token qu
Token ID627
Feature activation-3.22e+00

Pos logit contributions
 dove+0.019
adies+0.019
ira+0.018
 touch+0.018
Help+0.017
Neg logit contributions
anks-0.024
ols-0.024
arre-0.024
stick-0.024
obe-0.024
Tokenarre
Token ID9624
Feature activation-6.30e+00

Pos logit contributions
obe+0.031
 Ros+0.028
bank+0.026
 rewarded+0.026
stick+0.025
Neg logit contributions
adies-0.143
ira-0.135
osh-0.135
Jen-0.130
Ah-0.130
Tokenled
Token ID992
Feature activation-1.22e+00

Pos logit contributions
anks+0.198
 Ros+0.197
bank+0.194
ols+0.189
stick+0.187
Neg logit contributions
adies-0.143
osh-0.133
Ah-0.126
ira-0.122
Help-0.116
Token again
Token ID757
Feature activation+9.26e-01

Pos logit contributions
obe+0.044
ols+0.044
anks+0.043
arre+0.042
stick+0.042
Neg logit contributions
adies-0.024
 dove-0.022
ira-0.021
 closer-0.021
 sled-0.020
Token and
Token ID290
Feature activation-8.31e-01

Pos logit contributions
ira+0.018
 dove+0.016
 palm+0.016
 sled+0.015
adies+0.015
Neg logit contributions
ols-0.034
stick-0.033
anks-0.032
obe-0.032
arre-0.031
Token played
Token ID2826
Feature activation-6.85e-01

Pos logit contributions
obe+0.027
anks+0.027
arre+0.026
stick+0.026
 rivals+0.026
Neg logit contributions
 dove-0.018
ira-0.018
 palm-0.017
adies-0.017
osh-0.016
Token together
Token ID1978
Feature activation-8.91e-03

Pos logit contributions
obe+0.018
stick+0.017
beh+0.017
osity+0.017
arre+0.017
Neg logit contributions
adies-0.019
 dove-0.019
 sled-0.018
ira-0.017
 yes-0.017
Token him
Token ID683
Feature activation+7.03e-01

Pos logit contributions
adies+0.005
ira+0.004
 sled+0.004
Mom+0.004
 corn+0.004
Neg logit contributions
arre-0.008
 rivals-0.007
iting-0.007
anks-0.007
obe-0.007
Token.
Token ID13
Feature activation-2.80e-01

Pos logit contributions
 sled+0.008
adies+0.007
 palm+0.007
 corn+0.006
 top+0.006
Neg logit contributions
arre-0.031
 disl-0.029
 rivals-0.029
obe-0.029
ols-0.028
Token Spot
Token ID15899
Feature activation-1.22e+00

Pos logit contributions
arre+0.010
 rewarded+0.009
obe+0.009
iting+0.009
 rivals+0.009
Neg logit contributions
ira-0.006
 sled-0.006
adies-0.006
 dove-0.005
Help-0.005
Token urged
Token ID11643
Feature activation+1.77e+00

Pos logit contributions
anks+0.057
igsaw+0.056
stick+0.053
ols+0.053
obe+0.052
Neg logit contributions
 dove-0.019
ira-0.017
 rose-0.012
Help-0.011
 peek-0.011
Token Wh
Token ID854
Feature activation-2.17e+00

Pos logit contributions
adies+0.049
ira+0.048
 sled+0.044
 dove+0.043
Mom+0.042
Neg logit contributions
arre-0.057
obe-0.052
 rivals-0.052
iting-0.050
anks-0.050
Tokenisk
Token ID1984
Feature activation-6.23e+00

Pos logit contributions
 rivals+0.019
arre+0.019
obe+0.017
stick+0.017
 rewarded+0.016
Neg logit contributions
adies-0.105
ira-0.103
Jen-0.096
ila-0.093
 dove-0.093
Tokeners
Token ID364
Feature activation-1.70e+00

Pos logit contributions
obe+0.124
arre+0.123
 rivals+0.111
stick+0.106
anks+0.106
Neg logit contributions
adies-0.242
ira-0.236
Ah-0.219
 dove-0.215
Jen-0.210
Token to
Token ID284
Feature activation-6.89e-01

Pos logit contributions
arre+0.063
obe+0.063
ols+0.058
acking+0.058
ulating+0.057
Neg logit contributions
adies-0.037
ira-0.033
 sled-0.032
 yes-0.032
 palm-0.031
Token come
Token ID1282
Feature activation+1.43e+00

Pos logit contributions
arre+0.029
obe+0.028
 rivals+0.027
anks+0.026
ols+0.026
Neg logit contributions
adies-0.011
ira-0.011
 dove-0.010
 sled-0.010
 palm-0.010
Token play
Token ID711
Feature activation+1.64e-01

Pos logit contributions
adies+0.042
ira+0.039
 sled+0.037
 dove+0.036
 palm+0.036
Neg logit contributions
arre-0.042
obe-0.042
 rivals-0.039
ols-0.037
anks-0.037
Token with
Token ID351
Feature activation+1.62e-02

Pos logit contributions
adies+0.004
 yes+0.003
 sled+0.003
 dove+0.003
Mom+0.003
Neg logit contributions
arre-0.005
obe-0.005
 rewarded-0.005
anks-0.005
osity-0.005
Token him
Token ID683
Feature activation+6.82e-01

Pos logit contributions
adies+0.000
ira+0.000
 sled+0.000
 dove+0.000
 palm+0.000
Neg logit contributions
arre-0.001
obe-0.000
 rivals-0.000
anks-0.000
iting-0.000
Token outside
Token ID2354
Feature activation+1.26e+00

Pos logit contributions
 sled+0.013
 yes+0.011
adies+0.011
ira+0.011
 dove+0.011
Neg logit contributions
arre-0.027
obe-0.026
ols-0.025
ulating-0.025
 rivals-0.025
Token.
Token ID13
Feature activation-1.48e-01

Pos logit contributions
adies+0.024
 sled+0.023
ira+0.023
 palm+0.021
Mom+0.019
Neg logit contributions
arre-0.050
obe-0.049
anks-0.045
ols-0.044
iting-0.044
Token But
Token ID887
Feature activation+9.61e-01

Pos logit contributions
arre+0.005
 rewarded+0.005
lling+0.005
obe+0.005
ils+0.005
Neg logit contributions
 sled-0.003
ira-0.003
Jen-0.003
Mom-0.003
Help-0.003
Token Wh
Token ID854
Feature activation-1.95e+00

Pos logit contributions
 dove+0.024
ira+0.024
 sled+0.024
adies+0.024
Mom+0.023
Neg logit contributions
arre-0.034
obe-0.032
anks-0.030
 rivals-0.030
igsaw-0.029
Tokenisk
Token ID1984
Feature activation-6.20e+00

Pos logit contributions
 rivals+0.021
stick+0.019
arre+0.019
 rewarded+0.018
obe+0.017
Neg logit contributions
adies-0.090
ira-0.088
Jen-0.082
ila-0.079
 sled-0.078
Tokeners
Token ID364
Feature activation-1.95e+00

Pos logit contributions
arre+0.141
obe+0.140
 rivals+0.133
anks+0.127
stick+0.122
Neg logit contributions
adies-0.226
ira-0.216
Ah-0.199
Jen-0.194
 dove-0.193
Token just
Token ID655
Feature activation+1.05e+00

Pos logit contributions
anks+0.070
obe+0.069
 rivals+0.067
igsaw+0.066
ols+0.066
Neg logit contributions
ira-0.043
 dove-0.043
adies-0.038
 palm-0.037
Help-0.034
Token wanted
Token ID2227
Feature activation+1.88e+00

Pos logit contributions
ira+0.025
 dove+0.024
adies+0.024
 palm+0.022
 sled+0.021
Neg logit contributions
arre-0.038
obe-0.037
anks-0.035
ols-0.034
 rivals-0.034
Token to
Token ID284
Feature activation-4.83e-01

Pos logit contributions
adies+0.048
ira+0.046
 sled+0.045
 dove+0.045
Ah+0.043
Neg logit contributions
arre-0.064
obe-0.059
ols-0.055
iting-0.055
anks-0.055
Token sleep
Token ID3993
Feature activation-3.35e+00

Pos logit contributions
arre+0.019
obe+0.019
 rivals+0.018
ols+0.017
anks+0.017
Neg logit contributions
ira-0.009
adies-0.009
 dove-0.008
 sled-0.008
 palm-0.008
Token the
Token ID262
Feature activation-5.95e-02

Pos logit contributions
arre+0.098
obe+0.095
 rivals+0.092
anks+0.090
stick+0.089
Neg logit contributions
ira-0.055
 sled-0.053
 palm-0.050
adies-0.047
 corn-0.046
Token tree
Token ID5509
Feature activation+5.09e-01

Pos logit contributions
obe+0.002
arre+0.002
 rivals+0.002
stick+0.002
anks+0.002
Neg logit contributions
adies-0.001
ira-0.001
Ah-0.001
 dove-0.001
 palm-0.001
Token to
Token ID284
Feature activation+3.43e-01

Pos logit contributions
 palm+0.012
 sled+0.012
ira+0.011
 dove+0.010
 key+0.010
Neg logit contributions
obe-0.017
arre-0.017
 rivals-0.016
anks-0.015
ols-0.015
Token its
Token ID663
Feature activation+6.40e-01

Pos logit contributions
ira+0.008
adies+0.008
 palm+0.008
 sled+0.007
 dove+0.007
Neg logit contributions
arre-0.012
obe-0.012
 rivals-0.011
anks-0.011
ols-0.010
Token once
Token ID1752
Feature activation-2.41e-01

Pos logit contributions
ira+0.015
 palm+0.015
 dove+0.014
 sled+0.014
adies+0.014
Neg logit contributions
arre-0.023
obe-0.022
ols-0.021
 rivals-0.020
anks-0.020
Token former
Token ID1966
Feature activation-6.15e+00

Pos logit contributions
obe+0.007
arre+0.007
 rivals+0.007
anks+0.006
stick+0.006
Neg logit contributions
ira-0.007
adies-0.007
 palm-0.006
 dove-0.006
Ah-0.006
Token beauty
Token ID8737
Feature activation-1.34e+00

Pos logit contributions
arre+0.173
obe+0.164
 rivals+0.158
stick+0.155
ols+0.151
Neg logit contributions
ira-0.183
adies-0.178
 palm-0.166
 sled-0.154
agg-0.151
Token.
Token ID13
Feature activation+1.78e-01

Pos logit contributions
arre+0.056
obe+0.056
anks+0.051
 rivals+0.051
 punished+0.050
Neg logit contributions
ira-0.023
 dove-0.021
 palm-0.020
adies-0.019
 sled-0.019
Token He
Token ID679
Feature activation+3.98e-02

Pos logit contributions
ira+0.005
adies+0.005
Ah+0.004
 palm+0.004
 sled+0.004
Neg logit contributions
obe-0.006
arre-0.006
 rivals-0.005
stick-0.005
ols-0.005
Token was
Token ID373
Feature activation+5.56e-01

Pos logit contributions
ira+0.001
 dove+0.001
 palm+0.001
Ah+0.001
adies+0.001
Neg logit contributions
obe-0.002
arre-0.001
anks-0.001
 rivals-0.001
ols-0.001
Token happy
Token ID3772
Feature activation+7.28e-02

Pos logit contributions
 palm+0.014
ira+0.014
 dove+0.014
Ah+0.013
adies+0.013
Neg logit contributions
obe-0.020
anks-0.018
arre-0.017
ols-0.017
 rivals-0.016
Token Lily
Token ID20037
Feature activation+2.43e-01

Pos logit contributions
obe+0.038
anks+0.037
stick+0.037
bank+0.033
arre+0.033
Neg logit contributions
Me-0.014
Mom-0.014
 other-0.013
 yes-0.013
 top-0.013
Token and
Token ID290
Feature activation-2.74e-01

Pos logit contributions
ira+0.004
 dove+0.004
 palm+0.003
osh+0.003
 rose+0.003
Neg logit contributions
igsaw-0.010
ols-0.010
anks-0.010
obe-0.010
ulating-0.009
Token Jack
Token ID3619
Feature activation-6.38e-01

Pos logit contributions
anks+0.008
 rewarded+0.008
stick+0.008
ables+0.008
arre+0.008
Neg logit contributions
ira-0.007
 palm-0.007
adies-0.007
 dove-0.007
Dad-0.007
Token never
Token ID1239
Feature activation+8.10e-01

Pos logit contributions
anks+0.026
igsaw+0.026
obe+0.026
ulating+0.024
cess+0.024
Neg logit contributions
 dove-0.011
ira-0.010
osh-0.010
 palm-0.009
 go-0.008
Token qu
Token ID627
Feature activation-3.21e+00

Pos logit contributions
 dove+0.019
 touch+0.019
 palm+0.017
Help+0.017
adies+0.016
Neg logit contributions
anks-0.026
ols-0.025
obe-0.025
arre-0.024
ables-0.024
Tokenarre
Token ID9624
Feature activation-6.12e+00

Pos logit contributions
obe+0.032
bank+0.028
 Ros+0.027
 rewarded+0.026
 Mickey+0.025
Neg logit contributions
adies-0.141
osh-0.133
ira-0.132
Jen-0.130
Ah-0.129
Tokenled
Token ID992
Feature activation-1.22e+00

Pos logit contributions
anks+0.199
 Ros+0.196
bank+0.194
ols+0.189
obe+0.188
Neg logit contributions
adies-0.133
osh-0.127
Ah-0.122
Help-0.113
ira-0.112
Token again
Token ID757
Feature activation+9.54e-01

Pos logit contributions
obe+0.044
ols+0.044
anks+0.043
arre+0.043
stick+0.043
Neg logit contributions
adies-0.024
 dove-0.022
 closer-0.021
ira-0.021
 yes-0.019
Token.
Token ID13
Feature activation-1.94e-01

Pos logit contributions
 palm+0.014
 touch+0.014
ira+0.014
 dove+0.013
 wonder+0.011
Neg logit contributions
stick-0.037
ols-0.036
penter-0.035
anks-0.035
 rivals-0.034
Token They
Token ID1119
Feature activation+1.62e-01

Pos logit contributions
obe+0.007
stick+0.006
 punished+0.006
arre+0.006
 rewarded+0.006
Neg logit contributions
ira-0.004
adies-0.004
Jen-0.004
Ah-0.004
 palm-0.004
Token learned
Token ID4499
Feature activation-2.88e-01

Pos logit contributions
 dove+0.003
ira+0.003
 palm+0.003
osh+0.003
 wonder+0.002
Neg logit contributions
anks-0.007
obe-0.007
arre-0.006
igsaw-0.006
ulating-0.006
Token.
Token ID13
Feature activation+1.76e-01

Pos logit contributions
obe+0.060
arre+0.058
 rivals+0.058
anks+0.057
iting+0.055
Neg logit contributions
ira-0.040
adies-0.038
 yes-0.036
 dove-0.036
 palm-0.034
Token
Token ID198
Feature activation+6.05e-01

Pos logit contributions
Mom+0.004
ira+0.004
Jen+0.004
Ah+0.004
Help+0.004
Neg logit contributions
arre-0.006
obe-0.006
 rivals-0.006
iting-0.006
ils-0.006
Token
Token ID198
Feature activation+5.35e-01

Pos logit contributions
ira+0.014
adies+0.014
Ah+0.012
Jen+0.012
 sled+0.012
Neg logit contributions
obe-0.021
arre-0.021
 rivals-0.020
stick-0.019
anks-0.019
TokenSo
Token ID2396
Feature activation+1.18e+00

Pos logit contributions
ira+0.011
adies+0.011
Ah+0.010
Mom+0.010
Jen+0.010
Neg logit contributions
obe-0.020
arre-0.020
 rivals-0.019
anks-0.019
stick-0.018
Token Wh
Token ID854
Feature activation-2.03e+00

Pos logit contributions
ira+0.025
Mom+0.024
 sled+0.024
 dove+0.023
Jen+0.022
Neg logit contributions
arre-0.047
obe-0.044
 rivals-0.044
anks-0.040
iting-0.040
Tokenisk
Token ID1984
Feature activation-6.09e+00

Pos logit contributions
 rivals+0.025
arre+0.022
 rewarded+0.022
stick+0.021
obe+0.020
Neg logit contributions
ira-0.090
adies-0.088
Jen-0.082
ila-0.080
 sled-0.076
Tokeners
Token ID364
Feature activation-1.92e+00

Pos logit contributions
arre+0.141
obe+0.139
 rivals+0.131
anks+0.127
stick+0.120
Neg logit contributions
adies-0.220
ira-0.209
Ah-0.194
Jen-0.189
 dove-0.187
Token continued
Token ID3767
Feature activation-1.63e-01

Pos logit contributions
anks+0.070
obe+0.068
 rivals+0.065
arre+0.064
ols+0.064
Neg logit contributions
ira-0.043
 dove-0.041
adies-0.039
 palm-0.037
 yes-0.036
Token to
Token ID284
Feature activation+2.36e-01

Pos logit contributions
arre+0.006
ulating+0.006
obe+0.006
anks+0.006
cess+0.006
Neg logit contributions
 sled-0.003
 corn-0.003
ira-0.003
 dove-0.002
 rope-0.002
Token eat
Token ID4483
Feature activation-4.78e-01

Pos logit contributions
ira+0.005
 dove+0.004
 sled+0.004
adies+0.004
 palm+0.004
Neg logit contributions
arre-0.009
obe-0.009
anks-0.009
 rivals-0.009
ols-0.008
Token and
Token ID290
Feature activation-2.06e-01

Pos logit contributions
arre+0.018
 rivals+0.017
iting+0.017
obe+0.016
stick+0.016
Neg logit contributions
 sled-0.011
 palm-0.010
 corn-0.010
ira-0.010
 dove-0.010
Token Ch
Token ID609
Feature activation+2.09e-01

Pos logit contributions
ira+0.019
Ah+0.017
Mom+0.017
adies+0.017
Jen+0.016
Neg logit contributions
obe-0.034
arre-0.033
 rivals-0.032
iting-0.032
anks-0.032
Tokenir
Token ID343
Feature activation-7.93e-01

Pos logit contributions
ira+0.004
adies+0.004
 palm+0.003
Jen+0.003
Ah+0.003
Neg logit contributions
obe-0.008
arre-0.008
 rivals-0.008
stick-0.007
anks-0.007
Tokenpy
Token ID9078
Feature activation-2.01e+00

Pos logit contributions
obe+0.023
arre+0.023
 rivals+0.023
iting+0.021
ols+0.021
Neg logit contributions
ira-0.023
adies-0.023
 dove-0.020
Ah-0.019
 palm-0.019
Token and
Token ID290
Feature activation+1.48e-01

Pos logit contributions
obe+0.076
 rivals+0.074
anks+0.074
arre+0.073
igsaw+0.069
Neg logit contributions
ira-0.045
 dove-0.042
adies-0.038
 palm-0.035
osh-0.035
Token Wh
Token ID854
Feature activation-2.07e+00

Pos logit contributions
ira+0.004
 dove+0.003
Ah+0.003
 palm+0.003
 sled+0.003
Neg logit contributions
arre-0.006
obe-0.006
anks-0.005
 rivals-0.005
iting-0.005
Tokenisk
Token ID1984
Feature activation-6.09e+00

Pos logit contributions
 rivals+0.031
arre+0.031
obe+0.030
 rewarded+0.026
ulating+0.025
Neg logit contributions
ira-0.088
adies-0.087
Jen-0.080
 palm-0.078
Ah-0.077
Tokeners
Token ID364
Feature activation-1.72e+00

Pos logit contributions
arre+0.145
obe+0.142
 rivals+0.138
anks+0.128
ols+0.122
Neg logit contributions
adies-0.217
ira-0.210
Ah-0.193
Jen-0.189
 dove-0.184
Token knew
Token ID2993
Feature activation+7.28e-01

Pos logit contributions
obe+0.064
 rivals+0.062
anks+0.062
arre+0.061
igsaw+0.059
Neg logit contributions
ira-0.035
 dove-0.035
adies-0.033
 palm-0.031
Help-0.030
Token that
Token ID326
Feature activation-1.56e+00

Pos logit contributions
ira+0.022
adies+0.021
 dove+0.021
 sled+0.020
Jen+0.019
Neg logit contributions
arre-0.022
 rivals-0.021
obe-0.021
acking-0.018
anks-0.018
Token poison
Token ID8764
Feature activation-4.15e+00

Pos logit contributions
arre+0.056
 rivals+0.052
obe+0.052
anks+0.050
acking+0.049
Neg logit contributions
ira-0.037
 dove-0.034
adies-0.034
 sled-0.033
 palm-0.033
Token was
Token ID373
Feature activation+7.06e-01

Pos logit contributions
obe+0.169
arre+0.165
 rivals+0.163
anks+0.153
iting+0.151
Neg logit contributions
adies-0.072
 dove-0.072
ira-0.071
 palm-0.058
Help-0.056
Token bark
Token ID21405
Feature activation-2.86e-01

Pos logit contributions
arre+0.007
obe+0.007
anks+0.007
iting+0.007
igsaw+0.007
Neg logit contributions
 dove-0.003
ira-0.003
 sled-0.003
 run-0.002
 palm-0.002
Tokened
Token ID276
Feature activation+4.84e-01

Pos logit contributions
obe+0.010
arre+0.009
 rivals+0.009
ols+0.009
anks+0.009
Neg logit contributions
adies-0.007
ira-0.006
 dove-0.006
Ah-0.006
Help-0.005
Token,
Token ID11
Feature activation-2.91e-01

Pos logit contributions
 yes+0.008
 sled+0.008
 closer+0.008
 hello+0.007
adies+0.007
Neg logit contributions
arre-0.020
obe-0.019
anks-0.018
iting-0.018
ols-0.018
Token but
Token ID475
Feature activation+1.04e+00

Pos logit contributions
anks+0.011
obe+0.011
arre+0.011
igsaw+0.011
iting+0.010
Neg logit contributions
 dove-0.006
 palm-0.005
 sled-0.005
ira-0.005
 yes-0.005
Token Wh
Token ID854
Feature activation-1.88e+00

Pos logit contributions
 dove+0.024
ira+0.023
Mom+0.023
 sled+0.023
 yes+0.022
Neg logit contributions
obe-0.040
arre-0.038
anks-0.037
iting-0.035
acking-0.034
Tokenisk
Token ID1984
Feature activation-6.08e+00

Pos logit contributions
 rivals+0.018
arre+0.017
 rewarded+0.016
obe+0.015
stick+0.014
Neg logit contributions
ira-0.088
adies-0.087
Jen-0.080
 sled-0.078
 dove-0.076
Tokeners
Token ID364
Feature activation-2.29e+00

Pos logit contributions
arre+0.138
obe+0.136
 rivals+0.129
anks+0.125
stick+0.117
Neg logit contributions
adies-0.222
ira-0.213
Ah-0.196
Jen-0.193
 dove-0.189
Token did
Token ID750
Feature activation-8.05e-02

Pos logit contributions
anks+0.090
igsaw+0.089
obe+0.087
 rivals+0.084
ols+0.082
Neg logit contributions
 dove-0.046
ira-0.043
 palm-0.039
Help-0.037
 yes-0.036
Token not
Token ID407
Feature activation-1.07e+00

Pos logit contributions
arre+0.003
obe+0.003
anks+0.003
 rivals+0.003
iting+0.003
Neg logit contributions
ira-0.001
 sled-0.001
adies-0.001
 dove-0.001
 top-0.001
Token care
Token ID1337
Feature activation-3.05e-01

Pos logit contributions
arre+0.044
obe+0.041
anks+0.040
stick+0.040
 rivals+0.040
Neg logit contributions
adies-0.020
ira-0.018
 dove-0.018
 sled-0.016
Help-0.015
Token.
Token ID13
Feature activation-3.63e-01

Pos logit contributions
 rivals+0.011
obe+0.011
arre+0.011
stick+0.011
 rewarded+0.011
Neg logit contributions
ira-0.005
ila-0.005
adies-0.005
 sled-0.005
 palm-0.004
Tokeners
Token ID364
Feature activation-2.27e-01

Pos logit contributions
arre+0.104
obe+0.103
 rivals+0.095
anks+0.089
stick+0.088
Neg logit contributions
adies-0.193
ira-0.188
Ah-0.172
 dove-0.170
Jen-0.168
Token.
Token ID13
Feature activation-9.98e-02

Pos logit contributions
arre+0.010
 rivals+0.009
igsaw+0.009
anks+0.009
obe+0.009
Neg logit contributions
ira-0.003
Mom-0.003
 palm-0.003
adies-0.003
 dove-0.003
Token Lily
Token ID20037
Feature activation-4.76e-01

Pos logit contributions
obe+0.003
arre+0.003
 rivals+0.003
stick+0.003
anks+0.003
Neg logit contributions
adies-0.003
ira-0.003
Ah-0.003
 dove-0.002
 palm-0.002
Token and
Token ID290
Feature activation-4.98e-02

Pos logit contributions
arre+0.017
obe+0.016
anks+0.016
 rivals+0.015
ols+0.015
Neg logit contributions
ira-0.012
adies-0.011
 dove-0.010
 palm-0.010
Mom-0.010
Token Wh
Token ID854
Feature activation-2.17e+00

Pos logit contributions
arre+0.001
obe+0.001
 rivals+0.001
stick+0.001
anks+0.001
Neg logit contributions
adies-0.002
ira-0.002
Ah-0.002
 dove-0.002
 sled-0.002
Tokenisk
Token ID1984
Feature activation-6.07e+00

Pos logit contributions
 rivals+0.020
arre+0.019
 rewarded+0.017
obe+0.016
stick+0.016
Neg logit contributions
adies-0.103
ira-0.101
Jen-0.094
Mom-0.091
 sled-0.091
Tokeners
Token ID364
Feature activation-1.67e+00

Pos logit contributions
arre+0.135
obe+0.132
 rivals+0.125
anks+0.117
stick+0.113
Neg logit contributions
adies-0.224
ira-0.216
Ah-0.200
Jen-0.196
 dove-0.194
Token loved
Token ID6151
Feature activation+1.14e+00

Pos logit contributions
obe+0.050
arre+0.050
 rivals+0.047
stick+0.046
anks+0.046
Neg logit contributions
adies-0.046
ira-0.046
Ah-0.040
 dove-0.040
 palm-0.040
Token to
Token ID284
Feature activation+5.14e-01

Pos logit contributions
ira+0.023
 sled+0.023
 dove+0.022
 palm+0.022
 corn+0.022
Neg logit contributions
arre-0.044
ols-0.040
ulating-0.040
iting-0.039
 rewarded-0.039
Token play
Token ID711
Feature activation+5.77e-01

Pos logit contributions
adies+0.016
ira+0.015
Ah+0.014
 dove+0.014
 palm+0.014
Neg logit contributions
obe-0.014
arre-0.014
 rivals-0.013
stick-0.013
anks-0.013
Token with
Token ID351
Feature activation+9.50e-02

Pos logit contributions
adies+0.018
 dove+0.017
ira+0.017
Mom+0.016
 sled+0.016
Neg logit contributions
arre-0.014
 rewarded-0.014
 rivals-0.013
obe-0.013
anks-0.013
Token day
Token ID1110
Feature activation-1.15e+00

Pos logit contributions
adies+0.064
Ah+0.062
 reins+0.058
ira+0.057
Help+0.056
Neg logit contributions
 because-0.021
obe-0.021
arre-0.019
 rivals-0.017
 sharing-0.017
Token,
Token ID11
Feature activation-1.15e+00

Pos logit contributions
obe+0.022
arre+0.022
 rivals+0.020
stick+0.019
ols+0.019
Neg logit contributions
adies-0.044
ira-0.044
Ah-0.041
 palm-0.040
 dove-0.040
Token Lily
Token ID20037
Feature activation-4.47e-01

Pos logit contributions
obe+0.030
arre+0.030
 rivals+0.027
stick+0.027
anks+0.026
Neg logit contributions
adies-0.038
ira-0.038
Ah-0.034
 dove-0.034
 sled-0.034
Token and
Token ID290
Feature activation-2.28e-01

Pos logit contributions
obe+0.013
arre+0.013
 rivals+0.013
stick+0.012
anks+0.012
Neg logit contributions
adies-0.012
ira-0.012
Ah-0.011
 sled-0.011
 palm-0.011
Token Wh
Token ID854
Feature activation-2.29e+00

Pos logit contributions
arre+0.005
obe+0.005
 rivals+0.005
anks+0.004
stick+0.004
Neg logit contributions
ira-0.008
adies-0.008
 sled-0.008
 dove-0.007
Mom-0.007
Tokenisk
Token ID1984
Feature activation-6.07e+00

Pos logit contributions
 rivals+0.019
arre+0.019
obe+0.017
stick+0.016
 rewarded+0.015
Neg logit contributions
adies-0.111
ira-0.109
Jen-0.102
Mom-0.099
 dove-0.099
Tokeners
Token ID364
Feature activation-1.71e+00

Pos logit contributions
arre+0.120
obe+0.120
 rivals+0.111
stick+0.103
anks+0.103
Neg logit contributions
adies-0.235
ira-0.229
Ah-0.212
 dove-0.209
Jen-0.206
Token were
Token ID547
Feature activation+9.62e-02

Pos logit contributions
arre+0.048
obe+0.048
 rivals+0.045
stick+0.044
 punished+0.042
Neg logit contributions
ira-0.051
adies-0.050
Ah-0.047
 sled-0.044
Jen-0.043
Token playing
Token ID2712
Feature activation-7.21e-01

Pos logit contributions
adies+0.003
ira+0.003
 dove+0.003
 palm+0.003
 sled+0.003
Neg logit contributions
obe-0.002
arre-0.002
stick-0.002
 rivals-0.002
ols-0.002
Token with
Token ID351
Feature activation-1.19e-01

Pos logit contributions
obe+0.019
arre+0.019
 rewarded+0.019
anks+0.019
 rivals+0.019
Neg logit contributions
adies-0.021
 dove-0.020
ira-0.019
Help-0.019
 sled-0.019
Token their
Token ID511
Feature activation-1.46e+00

Pos logit contributions
obe+0.003
arre+0.003
 rivals+0.003
stick+0.003
ols+0.003
Neg logit contributions
adies-0.004
ira-0.003
Ah-0.003
 dove-0.003
 palm-0.003
Token
Token ID198
Feature activation+9.89e-02

Pos logit contributions
adies+0.002
ira+0.002
Ah+0.002
 dove+0.001
 palm+0.001
Neg logit contributions
obe-0.002
arre-0.002
 rivals-0.002
stick-0.002
anks-0.002
TokenL
Token ID43
Feature activation-1.13e+00

Pos logit contributions
adies+0.002
ira+0.002
Ah+0.002
Mom+0.002
 dove+0.002
Neg logit contributions
obe-0.004
arre-0.004
 rivals-0.003
anks-0.003
stick-0.003
Tokenily
Token ID813
Feature activation-3.12e-01

Pos logit contributions
obe+0.048
arre+0.047
 rivals+0.046
stick+0.046
anks+0.045
Neg logit contributions
adies-0.018
ira-0.017
Ah-0.014
 dove-0.013
 palm-0.013
Token and
Token ID290
Feature activation-3.57e-01

Pos logit contributions
anks+0.012
obe+0.012
arre+0.012
igsaw+0.012
ols+0.012
Neg logit contributions
ira-0.006
 dove-0.006
adies-0.005
 palm-0.005
Mom-0.005
Token Wh
Token ID854
Feature activation-2.27e+00

Pos logit contributions
arre+0.012
 rivals+0.010
ulating+0.010
iting+0.010
 rewarded+0.010
Neg logit contributions
ira-0.010
 dove-0.009
 sled-0.009
adies-0.009
Mom-0.009
Tokenisk
Token ID1984
Feature activation-6.06e+00

Pos logit contributions
 rivals+0.027
 rewarded+0.025
arre+0.022
stick+0.022
 practicing+0.021
Neg logit contributions
adies-0.101
ira-0.097
Jen-0.090
ila-0.087
Mom-0.085
Tokeners
Token ID364
Feature activation-1.61e+00

Pos logit contributions
arre+0.129
obe+0.128
 rivals+0.121
anks+0.113
stick+0.108
Neg logit contributions
adies-0.228
ira-0.221
Ah-0.206
Jen-0.199
 dove-0.199
Token were
Token ID547
Feature activation-1.10e-01

Pos logit contributions
obe+0.053
arre+0.052
 rivals+0.050
anks+0.048
stick+0.048
Neg logit contributions
adies-0.041
ira-0.040
 dove-0.036
 palm-0.035
Ah-0.035
Token both
Token ID1111
Feature activation+1.15e+00

Pos logit contributions
obe+0.004
anks+0.004
iting+0.004
igsaw+0.004
arre+0.004
Neg logit contributions
 dove-0.002
 palm-0.002
adies-0.002
ira-0.002
 sled-0.002
Token sad
Token ID6507
Feature activation-1.80e+00

Pos logit contributions
 palm+0.026
ira+0.025
 hand+0.024
 dove+0.024
adies+0.023
Neg logit contributions
obe-0.043
arre-0.041
ols-0.041
anks-0.039
isk-0.038
Token.
Token ID13
Feature activation-6.25e-01

Pos logit contributions
arre+0.065
stick+0.064
iting+0.063
isk+0.062
 rivals+0.062
Neg logit contributions
ira-0.039
 sled-0.035
adies-0.033
 dove-0.031
 palm-0.030
Token had
Token ID550
Feature activation-1.94e+00

Pos logit contributions
arre+0.004
obe+0.004
 rivals+0.004
anks+0.004
ols+0.003
Neg logit contributions
ira-0.003
adies-0.003
 dove-0.003
 palm-0.003
Mom-0.003
Token told
Token ID1297
Feature activation-1.87e-01

Pos logit contributions
arre+0.048
 rivals+0.046
obe+0.046
ols+0.044
stick+0.043
Neg logit contributions
adies-0.065
ira-0.064
 dove-0.060
 palm-0.058
Ah-0.057
Token her
Token ID607
Feature activation-9.91e-01

Pos logit contributions
obe+0.006
arre+0.006
 rivals+0.005
stick+0.005
anks+0.005
Neg logit contributions
adies-0.005
ira-0.005
Ah-0.005
 dove-0.004
 palm-0.004
Token.
Token ID13
Feature activation-7.50e-01

Pos logit contributions
arre+0.034
obe+0.034
 rivals+0.032
acking+0.031
occupied+0.030
Neg logit contributions
ira-0.025
adies-0.023
 palm-0.022
 dove-0.022
 sled-0.020
Token "
Token ID366
Feature activation-2.08e-01

Pos logit contributions
obe+0.030
 punished+0.028
 rewarded+0.028
 bothering+0.028
arre+0.027
Neg logit contributions
adies-0.013
ira-0.013
Mom-0.011
Ah-0.010
Dad-0.009
TokenIf
Token ID1532
Feature activation+2.37e+00

Pos logit contributions
arre+0.007
obe+0.007
stick+0.006
 rivals+0.006
 punished+0.006
Neg logit contributions
adies-0.005
ira-0.005
 sled-0.005
 palm-0.004
 dove-0.004
Token an
Token ID281
Feature activation-2.74e-01

Pos logit contributions
adies+0.071
ira+0.070
Ah+0.065
 sled+0.062
Jen+0.061
Neg logit contributions
obe-0.063
arre-0.060
 rivals-0.060
stick-0.058
ols-0.058
Token earthquake
Token ID16295
Feature activation-3.69e+00

Pos logit contributions
obe+0.005
arre+0.005
 rivals+0.004
stick+0.004
anks+0.004
Neg logit contributions
ira-0.011
adies-0.011
Ah-0.011
 dove-0.010
osh-0.010
Token happens
Token ID4325
Feature activation-1.89e+00

Pos logit contributions
obe+0.133
arre+0.130
 rivals+0.124
anks+0.120
ols+0.120
Neg logit contributions
ira-0.083
adies-0.082
 dove-0.074
 sled-0.069
osh-0.068
Token,
Token ID11
Feature activation-6.95e-01

Pos logit contributions
obe+0.066
arre+0.065
 rivals+0.061
isk+0.061
stick+0.061
Neg logit contributions
adies-0.042
ira-0.042
 sled-0.038
 dove-0.038
 palm-0.034
Token find
Token ID1064
Feature activation+6.01e-01

Pos logit contributions
obe+0.024
arre+0.024
 rivals+0.022
stick+0.022
anks+0.022
Neg logit contributions
adies-0.017
ira-0.016
Ah-0.014
 dove-0.014
 palm-0.014
Token you
Token ID345
Feature activation+1.36e+00

Pos logit contributions
adies+0.027
ira+0.027
Ah+0.023
 dove+0.023
 palm+0.023
Neg logit contributions
arre-0.035
obe-0.035
 rivals-0.033
stick-0.033
anks-0.032
Token and
Token ID290
Feature activation-3.13e-01

Pos logit contributions
adies+0.040
ira+0.038
 sled+0.034
 palm+0.033
 dove+0.033
Neg logit contributions
obe-0.041
arre-0.040
stick-0.037
 rivals-0.037
ols-0.037
Token be
Token ID307
Feature activation-7.59e-01

Pos logit contributions
arre+0.013
obe+0.012
stick+0.012
ols+0.012
anks+0.012
Neg logit contributions
ira-0.006
adies-0.005
 dove-0.005
 palm-0.005
 sled-0.005
Token polite
Token ID23507
Feature activation-4.29e-01

Pos logit contributions
storms+0.031
ols+0.031
obe+0.031
arre+0.030
anks+0.030
Neg logit contributions
Mom-0.013
adies-0.013
Ah-0.012
 hand-0.011
ira-0.011
Token,
Token ID11
Feature activation+4.70e-01

Pos logit contributions
obe+0.017
ols+0.017
arre+0.017
isk+0.016
igsaw+0.015
Neg logit contributions
adies-0.008
ira-0.007
 hand-0.006
 sled-0.006
Mom-0.006
Token OK
Token ID7477
Feature activation+2.83e+00

Pos logit contributions
ira+0.013
adies+0.012
 dove+0.012
 palm+0.012
 sled+0.011
Neg logit contributions
obe-0.015
arre-0.014
anks-0.014
ols-0.014
stick-0.014
Token?"
Token ID1701
Feature activation+4.52e-01

Pos logit contributions
Mom+0.055
ira+0.054
adies+0.051
 sled+0.049
Jen+0.044
Neg logit contributions
arre-0.108
 rivals-0.107
obe-0.107
ols-0.102
ulating-0.101
Token
Token ID198
Feature activation+9.04e-01

Pos logit contributions
ira+0.011
adies+0.010
Ah+0.009
 dove+0.009
 palm+0.009
Neg logit contributions
obe-0.016
arre-0.016
 rivals-0.015
stick-0.015
anks-0.014
Token
Token ID198
Feature activation+7.22e-01

Pos logit contributions
adies+0.027
ira+0.025
 palm+0.023
 dove+0.023
 sled+0.023
Neg logit contributions
obe-0.026
arre-0.026
 rivals-0.024
stick-0.023
ols-0.023
TokenAnna
Token ID31160
Feature activation+2.46e-01

Pos logit contributions
adies+0.013
ira+0.012
 palm+0.010
 dove+0.010
 sled+0.010
Neg logit contributions
obe-0.029
arre-0.029
 rivals-0.028
stick-0.027
ols-0.027
Token smiled
Token ID13541
Feature activation+1.29e+00

Pos logit contributions
ira+0.005
adies+0.005
 dove+0.005
Ah+0.004
 palm+0.004
Neg logit contributions
obe-0.009
arre-0.009
anks-0.009
 rivals-0.009
ols-0.009
Token careful
Token ID8161
Feature activation+1.21e+00

Pos logit contributions
ira+0.007
adies+0.007
 dove+0.006
ila+0.005
 sled+0.005
Neg logit contributions
stick-0.012
arre-0.012
isk-0.012
obe-0.012
ols-0.012
Token and
Token ID290
Feature activation-8.27e-01

Pos logit contributions
adies+0.037
ira+0.036
 sled+0.032
 dove+0.032
 palm+0.032
Neg logit contributions
arre-0.034
obe-0.034
 rivals-0.031
stick-0.030
anks-0.030
Token check
Token ID2198
Feature activation-7.78e-01

Pos logit contributions
arre+0.025
obe+0.025
stick+0.023
anks+0.023
 rivals+0.023
Neg logit contributions
adies-0.023
ira-0.023
 dove-0.021
 palm-0.020
Ah-0.020
Token the
Token ID262
Feature activation+5.78e-01

Pos logit contributions
obe+0.021
arre+0.021
 rivals+0.020
stick+0.019
anks+0.019
Neg logit contributions
adies-0.024
ira-0.024
Ah-0.021
 dove-0.021
 sled-0.021
Token rope
Token ID17182
Feature activation+1.69e+00

Pos logit contributions
adies+0.017
ira+0.015
agg+0.014
Ah+0.014
Jen+0.013
Neg logit contributions
obe-0.018
arre-0.016
 rivals-0.016
anks-0.015
 punished-0.015
Token first
Token ID717
Feature activation+2.87e+00

Pos logit contributions
adies+0.043
ira+0.040
 sled+0.040
 dove+0.039
 palm+0.035
Neg logit contributions
arre-0.058
obe-0.057
 rivals-0.053
anks-0.049
ulating-0.048
Token."
Token ID526
Feature activation+7.19e-01

Pos logit contributions
adies+0.066
ira+0.065
 dove+0.058
 sled+0.055
 palm+0.052
Neg logit contributions
arre-0.106
obe-0.105
 rivals-0.096
stick-0.094
isk-0.091
Token
Token ID198
Feature activation+1.03e+00

Pos logit contributions
adies+0.022
ira+0.021
Ah+0.019
 dove+0.019
 palm+0.018
Neg logit contributions
obe-0.020
arre-0.020
 rivals-0.019
anks-0.019
ols-0.018
Token
Token ID198
Feature activation+9.32e-01

Pos logit contributions
adies+0.034
ira+0.030
Ah+0.029
 palm+0.028
Help+0.028
Neg logit contributions
obe-0.027
arre-0.026
 rivals-0.025
anks-0.024
ols-0.024
TokenThey
Token ID2990
Feature activation+6.56e-01

Pos logit contributions
adies+0.027
ira+0.025
 palm+0.023
Ah+0.023
 footh+0.022
Neg logit contributions
arre-0.028
obe-0.028
 rivals-0.026
ols-0.024
iting-0.023
Token held
Token ID2714
Feature activation+4.24e-01

Pos logit contributions
adies+0.018
ira+0.017
Ah+0.015
 palm+0.015
 sled+0.015
Neg logit contributions
obe-0.020
arre-0.020
 rivals-0.019
stick-0.019
ols-0.018
Token was
Token ID373
Feature activation+5.66e-01

Pos logit contributions
ira+0.006
adies+0.006
 dove+0.006
 palm+0.005
Ah+0.005
Neg logit contributions
arre-0.010
obe-0.010
 rivals-0.009
anks-0.009
ols-0.009
Token very
Token ID845
Feature activation-5.30e-01

Pos logit contributions
 palm+0.014
adies+0.014
 dove+0.013
ira+0.013
 sled+0.012
Neg logit contributions
arre-0.020
obe-0.020
ols-0.018
iting-0.018
anks-0.018
Token happy
Token ID3772
Feature activation-2.24e-01

Pos logit contributions
obe+0.016
arre+0.015
 rivals+0.014
stick+0.014
anks+0.014
Neg logit contributions
adies-0.015
ira-0.015
Ah-0.014
 dove-0.013
 palm-0.013
Token and
Token ID290
Feature activation-1.20e-01

Pos logit contributions
arre+0.011
ols+0.010
isk+0.009
obe+0.009
 punished+0.009
Neg logit contributions
 dove-0.003
 sled-0.003
ira-0.003
 palm-0.003
adies-0.003
Token he
Token ID339
Feature activation+6.42e-01

Pos logit contributions
arre+0.004
obe+0.004
ols+0.004
stick+0.004
 rivals+0.004
Neg logit contributions
 dove-0.003
ira-0.003
adies-0.003
 palm-0.003
Ah-0.003
Token promised
Token ID8072
Feature activation+2.88e+00

Pos logit contributions
 dove+0.016
ira+0.016
adies+0.014
Ah+0.014
 palm+0.014
Neg logit contributions
arre-0.023
obe-0.022
ols-0.021
anks-0.021
 rivals-0.021
Token to
Token ID284
Feature activation-9.87e-01

Pos logit contributions
adies+0.092
ira+0.091
Ah+0.082
 dove+0.082
 sled+0.081
Neg logit contributions
arre-0.077
obe-0.076
 rivals-0.070
stick-0.068
ols-0.068
Token always
Token ID1464
Feature activation-1.27e+00

Pos logit contributions
obe+0.034
arre+0.033
 rivals+0.032
stick+0.031
anks+0.031
Neg logit contributions
adies-0.024
ira-0.023
Ah-0.021
 dove-0.020
 palm-0.020
Token remember
Token ID3505
Feature activation+1.76e-01

Pos logit contributions
arre+0.047
obe+0.045
 rivals+0.044
stick+0.043
anks+0.042
Neg logit contributions
adies-0.028
ira-0.027
 dove-0.024
 palm-0.023
Ah-0.023
Token where
Token ID810
Feature activation+1.66e+00

Pos logit contributions
adies+0.005
ira+0.005
 sled+0.004
 palm+0.004
 dove+0.004
Neg logit contributions
arre-0.006
obe-0.006
 rivals-0.005
anks-0.005
ols-0.005
Token he
Token ID339
Feature activation-7.81e-01

Pos logit contributions
adies+0.050
ira+0.049
Ah+0.044
 sled+0.042
 dove+0.042
Neg logit contributions
obe-0.045
 rivals-0.043
arre-0.043
stick-0.042
anks-0.041
Token.
Token ID13
Feature activation-4.55e-02

Pos logit contributions
adies+0.017
ira+0.017
 dove+0.016
 sled+0.016
 palm+0.016
Neg logit contributions
arre-0.025
obe-0.025
anks-0.024
 rivals-0.023
ols-0.022
Token Everything
Token ID11391
Feature activation-7.90e-01

Pos logit contributions
obe+0.001
arre+0.001
stick+0.001
ols+0.001
iting+0.001
Neg logit contributions
adies-0.001
ira-0.001
Ah-0.001
 palm-0.001
Mom-0.001
Token looked
Token ID3114
Feature activation-1.06e-01

Pos logit contributions
obe+0.027
arre+0.026
anks+0.025
isk+0.024
 rivals+0.024
Neg logit contributions
ira-0.019
 dove-0.019
osh-0.019
adies-0.018
 sled-0.018
Token so
Token ID523
Feature activation+3.88e-01

Pos logit contributions
obe+0.004
arre+0.003
anks+0.003
stick+0.003
isk+0.003
Neg logit contributions
adies-0.003
 dove-0.003
 sled-0.003
 palm-0.003
ira-0.002
Token small
Token ID1402
Feature activation-1.00e+00

Pos logit contributions
adies+0.009
ira+0.009
Ah+0.008
 dove+0.008
 palm+0.008
Neg logit contributions
obe-0.014
arre-0.013
stick-0.013
anks-0.013
 rivals-0.013
Token down
Token ID866
Feature activation+2.37e+00

Pos logit contributions
arre+0.038
obe+0.037
isk+0.034
anks+0.034
 rivals+0.034
Neg logit contributions
adies-0.021
ira-0.020
 dove-0.019
 sled-0.019
 palm-0.017
Token below
Token ID2174
Feature activation+7.08e-01

Pos logit contributions
adies+0.065
ira+0.063
 palm+0.058
 sled+0.058
 dove+0.057
Neg logit contributions
obe-0.076
arre-0.074
 rivals-0.070
anks-0.067
stick-0.067
Token him
Token ID683
Feature activation+1.30e+00

Pos logit contributions
adies+0.018
ira+0.018
 dove+0.016
 palm+0.016
 sled+0.016
Neg logit contributions
obe-0.023
arre-0.023
 rivals-0.022
anks-0.021
stick-0.020
Token.
Token ID13
Feature activation-2.94e-02

Pos logit contributions
ira+0.030
 sled+0.029
 palm+0.029
 dove+0.029
adies+0.026
Neg logit contributions
arre-0.047
obe-0.047
 rivals-0.042
isk-0.041
anks-0.040
Token It
Token ID632
Feature activation-6.83e-02

Pos logit contributions
obe+0.001
stick+0.001
arre+0.001
iting+0.001
ols+0.001
Neg logit contributions
adies-0.001
ira-0.001
Ah-0.001
 palm-0.001
Mom-0.001
Token felt
Token ID2936
Feature activation-1.14e-01

Pos logit contributions
obe+0.003
arre+0.003
anks+0.003
 rivals+0.002
ols+0.002
Neg logit contributions
ira-0.001
 dove-0.001
adies-0.001
Ah-0.001
 palm-0.001
Tokens
Token ID82
Feature activation+5.98e-01

Pos logit contributions
adies+0.000
ira+0.000
Ah+0.000
 dove+0.000
 palm+0.000
Neg logit contributions
arre-0.000
obe-0.000
 rivals-0.000
stick-0.000
anks-0.000
Token how
Token ID703
Feature activation+9.76e-01

Pos logit contributions
ira+0.016
 palm+0.015
 corn+0.013
 sled+0.013
adies+0.013
Neg logit contributions
obe-0.021
arre-0.020
anks-0.018
 rivals-0.018
ulating-0.018
Token the
Token ID262
Feature activation+3.41e-01

Pos logit contributions
ira+0.027
adies+0.025
 dove+0.023
Ah+0.023
osh+0.022
Neg logit contributions
obe-0.033
arre-0.030
stick-0.030
anks-0.030
 rivals-0.029
Token black
Token ID2042
Feature activation+1.50e-01

Pos logit contributions
ira+0.007
adies+0.007
 palm+0.007
 dove+0.006
Ah+0.006
Neg logit contributions
obe-0.013
arre-0.012
stick-0.012
anks-0.012
 rivals-0.012
Token rake
Token ID47885
Feature activation-6.19e-01

Pos logit contributions
ira+0.003
adies+0.003
 palm+0.003
 dove+0.003
 sled+0.003
Neg logit contributions
obe-0.006
arre-0.005
 rivals-0.005
 rewarded-0.005
anks-0.005
Token went
Token ID1816
Feature activation-5.45e-02

Pos logit contributions
obe+0.024
arre+0.023
 rivals+0.022
anks+0.022
ulating+0.021
Neg logit contributions
ira-0.012
 dove-0.012
 palm-0.011
osh-0.011
adies-0.011
Token on
Token ID319
Feature activation-5.47e-01

Pos logit contributions
arre+0.002
obe+0.002
 rivals+0.002
anks+0.002
cess+0.002
Neg logit contributions
adies-0.001
 dove-0.001
 sled-0.001
 palm-0.001
ira-0.001
Token its
Token ID663
Feature activation+1.62e-03

Pos logit contributions
arre+0.020
obe+0.020
 rivals+0.019
anks+0.019
iting+0.019
Neg logit contributions
ira-0.011
 sled-0.011
 palm-0.011
adies-0.011
 dove-0.010
Token big
Token ID1263
Feature activation-7.77e-01

Pos logit contributions
ira+0.000
adies+0.000
 palm+0.000
 sled+0.000
 dove+0.000
Neg logit contributions
arre-0.000
obe-0.000
ols-0.000
 rivals-0.000
anks-0.000
Token adventure
Token ID8855
Feature activation+4.59e-01

Pos logit contributions
arre+0.028
obe+0.027
anks+0.025
 rivals+0.025
ols+0.025
Neg logit contributions
ira-0.018
adies-0.018
 palm-0.017
 sled-0.017
 dove-0.016
Token!
Token ID0
Feature activation+8.16e-01

Pos logit contributions
ira+0.011
adies+0.010
 dove+0.010
 sled+0.009
 palm+0.009
Neg logit contributions
arre-0.016
obe-0.016
 rivals-0.015
anks-0.014
ols-0.014
Token you
Token ID345
Feature activation+2.05e+00

Pos logit contributions
ira+0.047
adies+0.046
 palm+0.043
 sled+0.043
 dove+0.042
Neg logit contributions
obe-0.036
ols-0.033
arre-0.032
 rivals-0.032
stick-0.032
Token so
Token ID523
Feature activation+1.13e+00

Pos logit contributions
adies+0.071
ira+0.068
 sled+0.062
Mom+0.062
 palm+0.062
Neg logit contributions
obe-0.052
arre-0.050
 rivals-0.046
stick-0.045
ols-0.044
Token much
Token ID881
Feature activation-9.66e-01

Pos logit contributions
adies+0.029
ira+0.029
 dove+0.026
Ah+0.026
 sled+0.025
Neg logit contributions
obe-0.035
arre-0.035
 rivals-0.034
ols-0.033
anks-0.033
Token!
Token ID0
Feature activation+3.41e-01

Pos logit contributions
arre+0.031
stick+0.028
obe+0.028
 rivals+0.028
ols+0.027
Neg logit contributions
ira-0.028
adies-0.028
 sled-0.024
 dove-0.024
ila-0.023
Token You
Token ID921
Feature activation+9.16e-01

Pos logit contributions
adies+0.009
ira+0.009
Ah+0.008
 dove+0.008
 palm+0.008
Neg logit contributions
obe-0.010
arre-0.010
 rivals-0.010
stick-0.010
anks-0.009
Token're
Token ID821
Feature activation-6.11e-01

Pos logit contributions
adies+0.014
 dove+0.012
ira+0.012
Help+0.011
Ah+0.011
Neg logit contributions
obe-0.040
anks-0.037
arre-0.037
 rivals-0.037
bank-0.037
Token very
Token ID845
Feature activation-1.39e+00

Pos logit contributions
arre+0.024
obe+0.024
ables+0.022
acking+0.022
iting+0.022
Neg logit contributions
adies-0.012
Mom-0.012
 palm-0.011
Ah-0.011
 no-0.011
Token kind
Token ID1611
Feature activation-9.64e-01

Pos logit contributions
arre+0.049
obe+0.049
stick+0.047
anks+0.045
 rivals+0.045
Neg logit contributions
adies-0.033
ira-0.032
Ah-0.028
 dove-0.028
 palm-0.028
Token."
Token ID526
Feature activation+2.52e-01

Pos logit contributions
obe+0.037
ols+0.036
arre+0.036
isk+0.034
itionally+0.033
Neg logit contributions
adies-0.019
ira-0.017
Mom-0.015
 dove-0.015
 hand-0.014
Token
Token ID220
Feature activation+1.96e+00

Pos logit contributions
ira+0.003
Mom+0.003
Jen+0.003
 palm+0.003
Ah+0.003
Neg logit contributions
obe-0.011
arre-0.011
 rivals-0.011
 bothering-0.010
ils-0.010
Token
Token ID198
Feature activation+5.60e-01

Pos logit contributions
ira+0.038
adies+0.037
Ah+0.032
Mom+0.032
Jen+0.031
Neg logit contributions
obe-0.076
arre-0.073
 rivals-0.072
stick-0.070
ols-0.068
Token and
Token ID290
Feature activation+3.67e-03

Pos logit contributions
ira+0.014
adies+0.013
 dove+0.013
 palm+0.012
Mom+0.011
Neg logit contributions
obe-0.015
arre-0.015
 rivals-0.015
anks-0.014
ols-0.014
Token the
Token ID262
Feature activation-6.63e-02

Pos logit contributions
adies+0.000
ira+0.000
 dove+0.000
 palm+0.000
Ah+0.000
Neg logit contributions
arre-0.000
obe-0.000
 rivals-0.000
stick-0.000
anks-0.000
Token bird
Token ID6512
Feature activation+4.46e-01

Pos logit contributions
obe+0.002
 Ros+0.002
arre+0.002
 sharing+0.002
stick+0.002
Neg logit contributions
adies-0.002
ira-0.002
Ah-0.002
 sled-0.002
 reins-0.002
Token wandered
Token ID36036
Feature activation-1.04e-01

Pos logit contributions
ira+0.013
 dove+0.012
adies+0.012
 palm+0.011
 sled+0.011
Neg logit contributions
obe-0.013
arre-0.013
 rivals-0.013
anks-0.012
stick-0.012
Token in
Token ID287
Feature activation+4.81e-01

Pos logit contributions
obe+0.003
arre+0.003
 rivals+0.003
stick+0.002
isk+0.002
Neg logit contributions
 dove-0.003
adies-0.003
ira-0.003
 sled-0.003
 palm-0.003
Token the
Token ID262
Feature activation-1.26e-01

Pos logit contributions
adies+0.015
ira+0.014
Ah+0.013
 dove+0.013
 palm+0.013
Neg logit contributions
obe-0.013
arre-0.013
 rivals-0.012
stick-0.012
ols-0.012
Token forest
Token ID8222
Feature activation+3.73e-01

Pos logit contributions
obe+0.003
arre+0.003
 rivals+0.003
stick+0.003
ols+0.003
Neg logit contributions
adies-0.004
ira-0.004
Ah-0.004
 sled-0.004
 dove-0.004
Token together
Token ID1978
Feature activation-9.94e-02

Pos logit contributions
ira+0.012
adies+0.012
 dove+0.011
 palm+0.011
 sled+0.011
Neg logit contributions
obe-0.009
arre-0.009
 rivals-0.009
anks-0.008
stick-0.008
Token and
Token ID290
Feature activation-5.77e-02

Pos logit contributions
arre+0.002
obe+0.002
 rivals+0.002
anks+0.002
stick+0.002
Neg logit contributions
adies-0.003
ira-0.003
 dove-0.003
 palm-0.003
 sled-0.003
Token listened
Token ID16399
Feature activation+8.20e-01

Pos logit contributions
obe+0.002
arre+0.002
 rivals+0.002
anks+0.002
stick+0.002
Neg logit contributions
ira-0.002
adies-0.002
 dove-0.002
Ah-0.001
 palm-0.001
Token to
Token ID284
Feature activation+3.09e-01

Pos logit contributions
adies+0.022
ira+0.020
 dove+0.019
 palm+0.017
Ah+0.017
Neg logit contributions
obe-0.027
arre-0.026
stick-0.024
 rivals-0.024
anks-0.024
Token envelop
Token ID16441
Feature activation-1.61e+00

Pos logit contributions
ira+0.004
 palm+0.004
 sled+0.004
 key+0.004
 dove+0.004
Neg logit contributions
arre-0.009
obe-0.009
iting-0.008
acking-0.008
ulating-0.008
Tokenes
Token ID274
Feature activation-1.20e+00

Pos logit contributions
obe+0.038
arre+0.038
 rivals+0.033
ulating+0.032
bank+0.031
Neg logit contributions
adies-0.058
ira-0.057
 dove-0.051
Mom-0.051
 sled-0.050
Token in
Token ID287
Feature activation+2.97e-01

Pos logit contributions
arre+0.062
obe+0.061
beh+0.058
igsaw+0.058
 rivals+0.057
Neg logit contributions
adies-0.010
 dove-0.008
 touch-0.008
 go-0.008
ira-0.008
Token the
Token ID262
Feature activation+2.35e-01

Pos logit contributions
adies+0.007
ira+0.007
Ah+0.006
 palm+0.006
 dove+0.006
Neg logit contributions
obe-0.010
arre-0.010
 rivals-0.009
stick-0.009
anks-0.009
Token box
Token ID3091
Feature activation+8.14e-01

Pos logit contributions
adies+0.006
ira+0.006
 palm+0.005
Ah+0.005
 dove+0.005
Neg logit contributions
obe-0.008
arre-0.008
 rivals-0.007
anks-0.007
stick-0.007
Token.
Token ID13
Feature activation-3.02e-01

Pos logit contributions
adies+0.014
ira+0.014
 palm+0.012
 dove+0.011
 key+0.011
Neg logit contributions
arre-0.036
obe-0.034
 rivals-0.032
occupied-0.030
 Oliver-0.030
Token
Token ID198
Feature activation-7.86e-01

Pos logit contributions
obe+0.007
arre+0.007
stick+0.007
 Ros+0.006
ols+0.006
Neg logit contributions
adies-0.010
ira-0.010
 dove-0.009
 palm-0.009
 sled-0.009
Token
Token ID198
Feature activation-7.21e-01

Pos logit contributions
obe+0.015
arre+0.014
ols+0.013
 about+0.013
 Ros+0.013
Neg logit contributions
adies-0.029
ira-0.027
 reins-0.026
 palm-0.026
 dove-0.025
TokenOne
Token ID3198
Feature activation+1.25e+00

Pos logit contributions
obe+0.022
arre+0.021
 Ellie+0.020
 about+0.020
 together+0.019
Neg logit contributions
ira-0.018
adies-0.017
 palm-0.017
 dove-0.016
 upper-0.016
Token day
Token ID1110
Feature activation-1.48e+00

Pos logit contributions
adies+0.046
Ah+0.044
ira+0.042
 reins+0.042
Help+0.041
Neg logit contributions
obe-0.023
 rivals-0.023
arre-0.022
 because-0.022
 videos-0.021
Token,
Token ID11
Feature activation-1.50e+00

Pos logit contributions
obe+0.024
arre+0.024
 rivals+0.021
stick+0.019
ols+0.019
Neg logit contributions
adies-0.059
ira-0.059
Ah-0.057
 palm-0.055
 dove-0.054
Token took
Token ID1718
Feature activation+2.57e-01

Pos logit contributions
ira+0.016
adies+0.015
 palm+0.015
 dove+0.014
 sled+0.014
Neg logit contributions
arre-0.026
obe-0.024
 rivals-0.023
ulating-0.023
iting-0.023
Token turns
Token ID4962
Feature activation-1.46e-01

Pos logit contributions
ira+0.006
adies+0.006
Ah+0.006
 dove+0.006
 sled+0.006
Neg logit contributions
obe-0.009
arre-0.009
 rivals-0.008
anks-0.008
ols-0.008
Token covering
Token ID9505
Feature activation-1.21e+00

Pos logit contributions
obe+0.005
arre+0.005
isk+0.005
anks+0.005
cess+0.005
Neg logit contributions
 sled-0.003
 dove-0.003
 palm-0.003
ira-0.003
 rope-0.003
Token their
Token ID511
Feature activation+1.79e-01

Pos logit contributions
arre+0.044
obe+0.044
 rivals+0.040
anks+0.040
iting+0.039
Neg logit contributions
ira-0.027
adies-0.026
 palm-0.025
 sled-0.025
Ah-0.024
Token faces
Token ID6698
Feature activation+9.94e-02

Pos logit contributions
ira+0.004
 palm+0.004
adies+0.004
 sled+0.003
 dove+0.003
Neg logit contributions
obe-0.007
arre-0.007
ols-0.006
iting-0.006
 rivals-0.006
Token with
Token ID351
Feature activation-3.07e-01

Pos logit contributions
adies+0.002
ira+0.002
 sled+0.002
 dove+0.002
 yes+0.002
Neg logit contributions
obe-0.004
arre-0.003
isk-0.003
 rivals-0.003
ols-0.003
Token cream
Token ID8566
Feature activation-1.94e-01

Pos logit contributions
obe+0.012
arre+0.011
anks+0.011
iting+0.011
 rivals+0.010
Neg logit contributions
ira-0.006
 palm-0.006
adies-0.006
 sled-0.006
Ah-0.006
Token and
Token ID290
Feature activation+2.31e-01

Pos logit contributions
obe+0.007
arre+0.007
 rivals+0.007
ols+0.007
isk+0.007
Neg logit contributions
 sled-0.004
ira-0.004
 palm-0.003
 dove-0.003
 corn-0.003
Token then
Token ID788
Feature activation-3.22e-01

Pos logit contributions
ira+0.005
 dove+0.005
 palm+0.005
 sled+0.005
Ah+0.004
Neg logit contributions
arre-0.009
obe-0.008
iting-0.008
anks-0.008
 rivals-0.008
Token they
Token ID484
Feature activation+3.26e-01

Pos logit contributions
obe+0.013
arre+0.012
anks+0.011
isk+0.011
 rivals+0.011
Neg logit contributions
 dove-0.007
ira-0.007
 sled-0.006
 palm-0.006
adies-0.006
Token leaned
Token ID23831
Feature activation-1.14e-01

Pos logit contributions
ira+0.007
 dove+0.007
adies+0.007
osh+0.006
 palm+0.006
Neg logit contributions
obe-0.013
anks-0.011
arre-0.011
iting-0.011
 rivals-0.011
Token
Token ID198
Feature activation-2.91e-01

Pos logit contributions
obe+0.005
arre+0.005
 rivals+0.005
stick+0.005
anks+0.005
Neg logit contributions
adies-0.004
ira-0.004
Ah-0.003
 dove-0.003
 palm-0.003
Token
Token ID198
Feature activation-1.77e-01

Pos logit contributions
obe+0.007
arre+0.007
ols+0.006
 rivals+0.006
anks+0.006
Neg logit contributions
adies-0.010
ira-0.009
 dove-0.009
 palm-0.009
 reins-0.009
Token"
Token ID1
Feature activation-1.02e+00

Pos logit contributions
obe+0.006
arre+0.006
 rivals+0.006
stick+0.006
anks+0.006
Neg logit contributions
adies-0.004
ira-0.004
Ah-0.004
 dove-0.003
 palm-0.003
TokenHey
Token ID10814
Feature activation-1.23e-01

Pos logit contributions
obe+0.033
arre+0.032
 rivals+0.029
stick+0.029
 punished+0.029
Neg logit contributions
adies-0.027
ira-0.026
 sled-0.022
 palm-0.021
agg-0.020
Token,
Token ID11
Feature activation-8.41e-01

Pos logit contributions
obe+0.003
arre+0.003
 rivals+0.003
stick+0.003
anks+0.003
Neg logit contributions
adies-0.004
ira-0.004
Ah-0.004
 dove-0.004
 palm-0.004
Token cat
Token ID3797
Feature activation-1.60e+00

Pos logit contributions
obe+0.023
arre+0.022
 rivals+0.021
stick+0.021
ols+0.020
Neg logit contributions
adies-0.026
ira-0.026
Ah-0.023
 sled-0.022
 palm-0.022
Token!
Token ID0
Feature activation-3.81e-01

Pos logit contributions
arre+0.063
obe+0.055
 rivals+0.055
anks+0.055
 rewarded+0.051
Neg logit contributions
ira-0.037
adies-0.037
 dove-0.036
 sled-0.031
 palm-0.031
Token That
Token ID1320
Feature activation+3.26e-01

Pos logit contributions
arre+0.009
obe+0.009
 rivals+0.008
stick+0.008
anks+0.008
Neg logit contributions
adies-0.013
ira-0.013
Ah-0.012
 sled-0.012
 dove-0.012
Token is
Token ID318
Feature activation+4.58e-01

Pos logit contributions
adies+0.009
ira+0.009
Ah+0.008
 sled+0.008
 dove+0.008
Neg logit contributions
obe-0.010
arre-0.010
 rivals-0.009
stick-0.009
anks-0.009
Token not
Token ID407
Feature activation-3.86e-01

Pos logit contributions
adies+0.010
 dove+0.009
 palm+0.009
ira+0.009
Help+0.009
Neg logit contributions
arre-0.018
stick-0.016
obe-0.016
iting-0.016
anks-0.015
Token your
Token ID534
Feature activation-6.37e-01

Pos logit contributions
arre+0.015
stick+0.015
ols+0.015
obe+0.015
anks+0.014
Neg logit contributions
adies-0.007
 dove-0.007
ira-0.007
 corn-0.007
 palm-0.007
Token's
Token ID338
Feature activation+4.55e-01

Pos logit contributions
ira+0.013
adies+0.013
 dove+0.012
 palm+0.012
 sled+0.011
Neg logit contributions
obe-0.020
arre-0.019
anks-0.019
 rivals-0.019
isk-0.018
Token why
Token ID1521
Feature activation-2.43e-01

Pos logit contributions
ira+0.011
adies+0.010
 dove+0.010
Mom+0.010
 palm+0.010
Neg logit contributions
arre-0.015
stick-0.015
 rivals-0.015
anks-0.015
acking-0.015
Token we
Token ID356
Feature activation-4.00e-01

Pos logit contributions
obe+0.010
arre+0.009
stick+0.009
anks+0.009
 rivals+0.009
Neg logit contributions
ira-0.005
adies-0.005
 dove-0.004
 palm-0.004
 sled-0.004
Token have
Token ID423
Feature activation-3.21e+00

Pos logit contributions
obe+0.017
anks+0.016
 rivals+0.016
arre+0.015
igsaw+0.015
Neg logit contributions
 dove-0.006
adies-0.006
 palm-0.005
Help-0.005
ira-0.005
Token to
Token ID284
Feature activation-2.56e+00

Pos logit contributions
obe+0.113
arre+0.107
ols+0.106
isk+0.106
anks+0.104
Neg logit contributions
adies-0.070
 dove-0.068
ira-0.067
 palm-0.066
Help-0.064
Token test
Token ID1332
Feature activation-1.75e+00

Pos logit contributions
arre+0.099
obe+0.097
 rivals+0.094
anks+0.093
stick+0.091
Neg logit contributions
adies-0.047
ira-0.046
 dove-0.042
 palm-0.042
 sled-0.041
Token things
Token ID1243
Feature activation-5.48e-01

Pos logit contributions
obe+0.062
arre+0.059
isk+0.057
 rivals+0.056
stick+0.056
Neg logit contributions
adies-0.040
ira-0.039
 palm-0.035
 dove-0.034
 sled-0.033
Token to
Token ID284
Feature activation-1.44e+00

Pos logit contributions
obe+0.019
arre+0.018
 rivals+0.018
isk+0.018
stick+0.017
Neg logit contributions
adies-0.011
 dove-0.011
ira-0.011
 key-0.010
 touch-0.010
Token make
Token ID787
Feature activation+1.07e-01

Pos logit contributions
obe+0.045
arre+0.045
 rivals+0.042
stick+0.041
anks+0.041
Neg logit contributions
adies-0.039
ira-0.038
Ah-0.034
 dove-0.033
 sled-0.033
Token sure
Token ID1654
Feature activation+9.34e-01

Pos logit contributions
adies+0.002
ira+0.002
Ah+0.002
 palm+0.002
 dove+0.002
Neg logit contributions
obe-0.004
arre-0.004
 rivals-0.004
stick-0.004
isk-0.004
Token they
Token ID484
Feature activation-1.47e+00

Pos logit contributions
adies+0.017
ira+0.017
 dove+0.015
 palm+0.015
 sled+0.014
Neg logit contributions
obe-0.037
arre-0.036
stick-0.034
 rivals-0.034
isk-0.034
Token for
Token ID329
Feature activation-1.09e+00

Pos logit contributions
adies+0.002
 sled+0.002
ira+0.002
 palm+0.002
 key+0.002
Neg logit contributions
arre-0.003
 rivals-0.003
obe-0.003
stick-0.003
ols-0.003
Token his
Token ID465
Feature activation-9.24e-01

Pos logit contributions
arre+0.041
 rivals+0.037
obe+0.037
stick+0.037
iting+0.035
Neg logit contributions
adies-0.024
ira-0.023
 sled-0.021
 palm-0.021
Dad-0.021
Token play
Token ID711
Feature activation-2.00e-01

Pos logit contributions
obe+0.030
arre+0.029
 rivals+0.028
stick+0.028
anks+0.027
Neg logit contributions
adies-0.024
ira-0.023
Ah-0.021
 dove-0.020
Jen-0.019
Token room
Token ID2119
Feature activation-8.68e-01

Pos logit contributions
arre+0.006
obe+0.006
 rivals+0.006
anks+0.006
ols+0.006
Neg logit contributions
adies-0.005
ira-0.005
 sled-0.005
 dove-0.005
 palm-0.005
Token.
Token ID13
Feature activation+2.05e-02

Pos logit contributions
arre+0.038
obe+0.035
 rivals+0.034
ols+0.034
anks+0.032
Neg logit contributions
 yes-0.013
 sled-0.013
 key-0.012
ira-0.012
adies-0.012
Token Sammy
Token ID44067
Feature activation-1.45e+00

Pos logit contributions
ira+0.001
adies+0.001
Mom+0.000
 palm+0.000
Ah+0.000
Neg logit contributions
obe-0.001
arre-0.001
 rivals-0.001
stick-0.001
ols-0.001
Token just
Token ID655
Feature activation+7.67e-01

Pos logit contributions
anks+0.062
ols+0.059
obe+0.059
arre+0.058
 rivals+0.056
Neg logit contributions
ira-0.029
 dove-0.026
 palm-0.021
 sled-0.021
adies-0.020
Token had
Token ID550
Feature activation-1.56e+00

Pos logit contributions
ira+0.018
adies+0.017
 dove+0.016
 palm+0.015
 sled+0.015
Neg logit contributions
arre-0.028
obe-0.027
anks-0.026
ols-0.026
 rivals-0.026
Token to
Token ID284
Feature activation-1.53e+00

Pos logit contributions
obe+0.058
arre+0.058
anks+0.054
ols+0.054
 rivals+0.054
Neg logit contributions
ira-0.034
adies-0.034
 dove-0.030
Ah-0.030
 palm-0.029
Token rest
Token ID1334
Feature activation-8.02e-01

Pos logit contributions
obe+0.056
arre+0.055
 rivals+0.053
stick+0.052
anks+0.051
Neg logit contributions
adies-0.033
ira-0.033
Ah-0.028
 dove-0.027
 palm-0.027
Token in
Token ID287
Feature activation-4.68e-01

Pos logit contributions
arre+0.027
obe+0.027
 rivals+0.026
ols+0.026
anks+0.025
Neg logit contributions
ira-0.020
 sled-0.019
adies-0.019
 palm-0.018
Mom-0.017
Token Another
Token ID6023
Feature activation+8.60e-01

Pos logit contributions
obe+0.010
arre+0.009
stick+0.009
 rivals+0.009
anks+0.009
Neg logit contributions
adies-0.006
ira-0.006
Ah-0.005
 palm-0.005
 dove-0.005
Token family
Token ID1641
Feature activation-1.08e+00

Pos logit contributions
ira+0.019
adies+0.018
 dove+0.016
 palm+0.015
Ah+0.015
Neg logit contributions
obe-0.033
arre-0.032
stick-0.030
anks-0.030
 rivals-0.030
Token was
Token ID373
Feature activation-4.40e-01

Pos logit contributions
obe+0.041
anks+0.039
arre+0.039
 rivals+0.037
ols+0.037
Neg logit contributions
ira-0.023
adies-0.022
 dove-0.022
 palm-0.020
Ah-0.019
Token struggling
Token ID9648
Feature activation-8.79e-01

Pos logit contributions
obe+0.015
anks+0.014
arre+0.014
ols+0.013
 rivals+0.013
Neg logit contributions
ira-0.011
adies-0.011
 dove-0.011
 palm-0.010
 sled-0.009
Token with
Token ID351
Feature activation-5.51e-01

Pos logit contributions
arre+0.034
obe+0.033
ols+0.032
anks+0.032
isk+0.030
Neg logit contributions
ira-0.016
 palm-0.016
 dove-0.016
adies-0.016
 sled-0.016
Token their
Token ID511
Feature activation-2.05e+00

Pos logit contributions
obe+0.020
arre+0.020
anks+0.018
 rivals+0.018
iting+0.018
Neg logit contributions
ira-0.012
adies-0.012
 palm-0.011
 dove-0.011
 sled-0.011
Token own
Token ID898
Feature activation-2.43e-01

Pos logit contributions
obe+0.070
arre+0.070
stick+0.065
 rivals+0.064
anks+0.064
Neg logit contributions
ira-0.049
adies-0.048
 palm-0.044
 dove-0.044
 sled-0.044
Token enormous
Token ID9812
Feature activation-6.99e-01

Pos logit contributions
obe+0.009
arre+0.009
 rivals+0.008
anks+0.008
ols+0.008
Neg logit contributions
ira-0.006
adies-0.005
 palm-0.005
 sled-0.005
 dove-0.005
Token luggage
Token ID31488
Feature activation-4.59e-01

Pos logit contributions
obe+0.024
arre+0.024
 rivals+0.023
stick+0.023
anks+0.022
Neg logit contributions
adies-0.016
ira-0.016
Ah-0.014
 dove-0.013
Jen-0.013
Token.
Token ID13
Feature activation-7.70e-02

Pos logit contributions
arre+0.018
obe+0.017
 rivals+0.016
anks+0.015
 cooperating+0.015
Neg logit contributions
adies-0.008
ira-0.008
 dove-0.008
 sled-0.008
 key-0.008
Token And
Token ID843
Feature activation-6.93e-01

Pos logit contributions
obe+0.003
iting+0.003
arre+0.003
stick+0.003
anks+0.003
Neg logit contributions
adies-0.002
ira-0.002
Ah-0.002
Mom-0.001
Jen-0.001
Token stories
Token ID3923
Feature activation-1.39e+00

Pos logit contributions
ira+0.025
adies+0.025
 palm+0.023
Mom+0.022
 dove+0.022
Neg logit contributions
arre-0.035
obe-0.033
iting-0.032
isk-0.031
 rivals-0.031
Token.
Token ID13
Feature activation-2.91e-01

Pos logit contributions
arre+0.063
obe+0.058
 rivals+0.057
isk+0.056
 punished+0.056
Neg logit contributions
adies-0.021
ira-0.020
 yes-0.018
 key-0.017
 go-0.015
Token
Token ID198
Feature activation-4.71e-01

Pos logit contributions
obe+0.008
arre+0.008
stick+0.007
ols+0.007
 Ros+0.007
Neg logit contributions
adies-0.009
ira-0.008
 dove-0.008
Ah-0.008
 palm-0.008
Token
Token ID198
Feature activation-3.99e-01

Pos logit contributions
obe+0.009
arre+0.009
 Ros+0.008
ols+0.008
 around+0.008
Neg logit contributions
adies-0.018
ira-0.016
 palm-0.016
 dove-0.016
Ah-0.015
TokenOne
Token ID3198
Feature activation+1.33e+00

Pos logit contributions
obe+0.015
arre+0.014
ols+0.013
stick+0.013
iting+0.013
Neg logit contributions
adies-0.008
 palm-0.007
ira-0.007
Ah-0.007
 dove-0.007
Token day
Token ID1110
Feature activation-1.57e+00

Pos logit contributions
adies+0.052
Ah+0.048
ira+0.047
 reins+0.047
 sled+0.046
Neg logit contributions
obe-0.023
arre-0.023
 rivals-0.022
 videos-0.021
 because-0.020
Token,
Token ID11
Feature activation-1.42e+00

Pos logit contributions
obe+0.037
arre+0.037
 rivals+0.035
stick+0.034
anks+0.033
Neg logit contributions
adies-0.054
ira-0.054
Ah-0.049
 dove-0.048
 sled-0.048
Token Chloe
Token ID29476
Feature activation-6.09e-01

Pos logit contributions
obe+0.037
arre+0.037
 rivals+0.035
stick+0.034
ols+0.033
Neg logit contributions
adies-0.045
ira-0.044
Ah-0.040
 palm-0.039
 dove-0.039
Token was
Token ID373
Feature activation+1.94e-01

Pos logit contributions
obe+0.021
arre+0.021
anks+0.020
 rivals+0.020
ols+0.020
Neg logit contributions
adies-0.014
ira-0.014
 dove-0.012
 palm-0.012
Ah-0.012
Token playing
Token ID2712
Feature activation-8.94e-01

Pos logit contributions
adies+0.006
ira+0.005
 dove+0.005
 palm+0.005
Help+0.005
Neg logit contributions
obe-0.006
ols-0.005
arre-0.005
anks-0.005
manship-0.005
Token.
Token ID13
Feature activation-6.31e-01

Pos logit contributions
anks+0.029
arre+0.028
 rewarded+0.028
obe+0.027
ols+0.027
Neg logit contributions
adies-0.021
 dove-0.020
 top-0.019
Help-0.019
Mom-0.019
Token Tom
Token ID4186
Feature activation+2.33e-01

Pos logit contributions
adies+0.004
ira+0.004
 sled+0.003
 dove+0.003
 palm+0.003
Neg logit contributions
obe-0.005
arre-0.005
 rivals-0.004
ols-0.004
stick-0.004
Token and
Token ID290
Feature activation+2.23e-01

Pos logit contributions
ira+0.005
 dove+0.005
adies+0.005
 sled+0.005
 palm+0.004
Neg logit contributions
obe-0.008
arre-0.008
anks-0.008
stick-0.008
ols-0.008
Token Mia
Token ID32189
Feature activation-2.29e-01

Pos logit contributions
adies+0.005
ira+0.005
Ah+0.005
 dove+0.005
 palm+0.005
Neg logit contributions
obe-0.007
arre-0.007
 rivals-0.007
stick-0.007
anks-0.007
Token stop
Token ID2245
Feature activation+5.54e-01

Pos logit contributions
obe+0.009
arre+0.009
 rivals+0.009
stick+0.008
anks+0.008
Neg logit contributions
adies-0.004
ira-0.004
 dove-0.004
 palm-0.004
 sled-0.003
Token qu
Token ID627
Feature activation-2.20e+00

Pos logit contributions
adies+0.017
ira+0.016
 sled+0.015
 dove+0.015
 palm+0.015
Neg logit contributions
arre-0.015
obe-0.015
 rivals-0.014
stick-0.014
anks-0.014
Tokenarre
Token ID9624
Feature activation-5.33e+00

Pos logit contributions
obe+0.062
stick+0.060
 rivals+0.059
 Ros+0.057
 rewarded+0.057
Neg logit contributions
adies-0.061
ira-0.059
 palm-0.054
Jen-0.053
Mom-0.053
Tokenling
Token ID1359
Feature activation-1.42e+00

Pos logit contributions
 Ros+0.130
obe+0.126
 rivals+0.125
anks+0.124
stick+0.124
Neg logit contributions
adies-0.173
ira-0.166
 dove-0.147
Ah-0.147
osh-0.146
Token.
Token ID13
Feature activation-7.39e-01

Pos logit contributions
arre+0.049
obe+0.048
 rivals+0.045
anks+0.045
iting+0.044
Neg logit contributions
adies-0.034
ira-0.032
 sled-0.030
 palm-0.030
 dove-0.030
Token They
Token ID1119
Feature activation+3.68e-01

Pos logit contributions
obe+0.022
arre+0.022
stick+0.020
 rivals+0.020
iting+0.020
Neg logit contributions
ira-0.022
adies-0.021
Ah-0.020
Jen-0.019
 palm-0.019
Token see
Token ID766
Feature activation+1.48e+00

Pos logit contributions
adies+0.006
ira+0.006
 dove+0.006
 palm+0.006
 sled+0.005
Neg logit contributions
obe-0.015
arre-0.015
anks-0.014
 rivals-0.014
stick-0.014
Token the
Token ID262
Feature activation+1.25e-02

Pos logit contributions
adies+0.042
ira+0.041
Ah+0.037
 dove+0.036
 sled+0.036
Neg logit contributions
obe-0.044
arre-0.044
 rivals-0.042
stick-0.041
ols-0.040
Token much
Token ID881
Feature activation-3.77e+00

Pos logit contributions
obe+0.067
arre+0.067
 rivals+0.063
stick+0.062
anks+0.061
Neg logit contributions
adies-0.055
ira-0.054
Ah-0.048
 dove-0.047
 palm-0.047
Token pasta
Token ID26296
Feature activation-2.54e+00

Pos logit contributions
arre+0.109
stick+0.107
obe+0.107
 rivals+0.103
ols+0.100
Neg logit contributions
adies-0.111
ira-0.107
 dove-0.096
 palm-0.096
 sled-0.095
Token you
Token ID345
Feature activation-3.95e-01

Pos logit contributions
obe+0.089
arre+0.089
 rivals+0.084
stick+0.083
ols+0.082
Neg logit contributions
adies-0.054
 yes-0.053
ira-0.052
 corn-0.049
 dove-0.047
Token won
Token ID1839
Feature activation+1.80e-01

Pos logit contributions
obe+0.016
stick+0.015
arre+0.015
 rivals+0.015
ols+0.014
Neg logit contributions
adies-0.007
ira-0.007
 dove-0.007
 palm-0.006
 sled-0.006
Token't
Token ID470
Feature activation-1.60e+00

Pos logit contributions
adies+0.003
Mom+0.003
ira+0.003
 top+0.003
 palm+0.003
Neg logit contributions
obe-0.007
 rivals-0.007
arre-0.006
iting-0.006
 rewarded-0.006
Token grow
Token ID1663
Feature activation-4.47e+00

Pos logit contributions
stick+0.067
ols+0.064
arre+0.063
 rivals+0.063
anks+0.062
Neg logit contributions
 touch-0.024
 palm-0.021
 dare-0.021
 go-0.020
 dove-0.020
Token fit
Token ID4197
Feature activation-2.83e+00

Pos logit contributions
obe+0.152
stick+0.142
arre+0.139
 rivals+0.138
iting+0.132
Neg logit contributions
adies-0.117
ira-0.104
 palm-0.096
 corn-0.096
 dove-0.093
Token like
Token ID588
Feature activation+2.78e-01

Pos logit contributions
obe+0.094
arre+0.092
stick+0.088
isk+0.088
ols+0.085
Neg logit contributions
adies-0.069
ira-0.059
 palm-0.057
 corn-0.056
Mom-0.056
Token me
Token ID502
Feature activation+8.16e-01

Pos logit contributions
adies+0.006
ira+0.006
 palm+0.006
 dove+0.006
 corn+0.006
Neg logit contributions
arre-0.010
obe-0.010
stick-0.009
iting-0.009
anks-0.009
Token!"
Token ID2474
Feature activation+8.74e-01

Pos logit contributions
adies+0.019
ira+0.019
 palm+0.018
 dove+0.017
 sled+0.017
Neg logit contributions
obe-0.028
arre-0.027
 rivals-0.026
stick-0.026
ols-0.026
Token
Token ID220
Feature activation+1.39e+00

Pos logit contributions
ira+0.021
adies+0.020
Ah+0.018
 dove+0.018
 palm+0.018
Neg logit contributions
arre-0.030
obe-0.030
 rivals-0.029
stick-0.027
anks-0.027
Token they
Token ID484
Feature activation-1.64e+00

Pos logit contributions
ira+0.000
 dove+0.000
 palm+0.000
adies+0.000
 sled+0.000
Neg logit contributions
obe-0.000
arre-0.000
anks-0.000
stick-0.000
 rivals-0.000
Token just
Token ID655
Feature activation-3.16e-02

Pos logit contributions
obe+0.064
anks+0.061
arre+0.058
 rivals+0.057
ols+0.057
Neg logit contributions
 dove-0.035
ira-0.032
 palm-0.031
osh-0.029
 sled-0.029
Token kept
Token ID4030
Feature activation-1.37e-01

Pos logit contributions
obe+0.001
arre+0.001
 rivals+0.001
anks+0.001
stick+0.001
Neg logit contributions
adies-0.001
ira-0.001
 dove-0.001
 palm-0.001
Ah-0.001
Token on
Token ID319
Feature activation-1.34e+00

Pos logit contributions
obe+0.004
anks+0.004
arre+0.004
isk+0.004
stick+0.004
Neg logit contributions
 sled-0.004
 palm-0.004
 dove-0.004
ira-0.003
Help-0.003
Token qu
Token ID627
Feature activation-2.25e+00

Pos logit contributions
obe+0.033
arre+0.032
anks+0.032
isk+0.032
ols+0.031
Neg logit contributions
 palm-0.040
 sled-0.040
ira-0.038
 dove-0.037
adies-0.037
Tokenarre
Token ID9624
Feature activation-5.42e+00

Pos logit contributions
obe+0.035
 Ros+0.034
stick+0.033
 rivals+0.031
 Mickey+0.029
Neg logit contributions
adies-0.087
ira-0.084
Jen-0.080
osh-0.078
 palm-0.078
Tokenling
Token ID1359
Feature activation-1.34e+00

Pos logit contributions
 Ros+0.164
isk+0.153
anks+0.153
stick+0.145
obe+0.144
Neg logit contributions
adies-0.135
ira-0.131
osh-0.128
Ah-0.121
 lever-0.114
Token!
Token ID0
Feature activation+3.07e-01

Pos logit contributions
obe+0.049
arre+0.048
anks+0.044
iting+0.044
 rivals+0.044
Neg logit contributions
 palm-0.027
ira-0.025
adies-0.025
 sled-0.025
 dove-0.024
Token
Token ID220
Feature activation+1.50e+00

Pos logit contributions
ira+0.007
Ah+0.006
adies+0.006
Mom+0.006
Jen+0.006
Neg logit contributions
obe-0.012
arre-0.011
 rivals-0.010
stick-0.010
iting-0.010
Token
Token ID198
Feature activation+1.38e-01

Pos logit contributions
ira+0.030
adies+0.029
Ah+0.025
 sled+0.024
Jen+0.024
Neg logit contributions
obe-0.057
arre-0.054
 rivals-0.054
stick-0.054
ols-0.051
Token
Token ID198
Feature activation+8.27e-02

Pos logit contributions
adies+0.003
ira+0.003
Ah+0.003
 dove+0.003
 palm+0.003
Neg logit contributions
obe-0.005
arre-0.005
 rivals-0.004
stick-0.004
anks-0.004
Token promised
Token ID8072
Feature activation+2.85e+00

Pos logit contributions
obe+0.013
arre+0.013
anks+0.012
 rivals+0.012
ols+0.012
Neg logit contributions
ira-0.010
adies-0.009
 dove-0.009
 palm-0.009
Ah-0.009
Token herself
Token ID5223
Feature activation+1.32e-01

Pos logit contributions
ira+0.083
adies+0.083
 dove+0.074
 palm+0.073
 sled+0.073
Neg logit contributions
arre-0.083
obe-0.081
 rivals-0.078
ols-0.074
stick-0.074
Token to
Token ID284
Feature activation-1.02e+00

Pos logit contributions
ira+0.004
adies+0.004
 dove+0.004
 palm+0.004
 corn+0.004
Neg logit contributions
obe-0.004
arre-0.004
 rivals-0.003
ols-0.003
anks-0.003
Token think
Token ID892
Feature activation+1.23e+00

Pos logit contributions
arre+0.033
obe+0.033
 rivals+0.031
stick+0.030
anks+0.030
Neg logit contributions
adies-0.026
ira-0.026
 dove-0.023
 palm-0.023
Ah-0.022
Token before
Token ID878
Feature activation-1.83e-02

Pos logit contributions
adies+0.037
ira+0.037
Ah+0.032
 dove+0.032
 palm+0.032
Neg logit contributions
obe-0.036
arre-0.035
 rivals-0.033
stick-0.032
anks-0.032
Token acting
Token ID7205
Feature activation-4.78e+00

Pos logit contributions
arre+0.001
obe+0.001
 rivals+0.001
stick+0.001
anks+0.000
Neg logit contributions
ira-0.001
adies-0.000
 dove-0.000
 palm-0.000
 sled-0.000
Token,
Token ID11
Feature activation-6.20e-01

Pos logit contributions
obe+0.179
isk+0.167
arre+0.163
stick+0.158
 rivals+0.158
Neg logit contributions
adies-0.101
 dove-0.092
 yes-0.092
ira-0.090
 wonder-0.086
Token so
Token ID523
Feature activation+1.20e+00

Pos logit contributions
obe+0.018
arre+0.017
 rivals+0.017
anks+0.016
ols+0.016
Neg logit contributions
adies-0.018
ira-0.018
 palm-0.016
 dove-0.016
 sled-0.016
Token that
Token ID326
Feature activation-3.05e-01

Pos logit contributions
ira+0.025
adies+0.021
 dove+0.020
 palm+0.020
Mom+0.019
Neg logit contributions
arre-0.048
obe-0.048
 rivals-0.046
anks-0.044
stick-0.043
Token she
Token ID673
Feature activation-2.73e-01

Pos logit contributions
obe+0.011
arre+0.011
 rivals+0.011
anks+0.010
stick+0.010
Neg logit contributions
ira-0.007
adies-0.007
 palm-0.006
 dove-0.006
Ah-0.006
Token could
Token ID714
Feature activation+1.19e+00

Pos logit contributions
obe+0.010
arre+0.010
 rivals+0.009
anks+0.009
ols+0.009
Neg logit contributions
ira-0.006
adies-0.006
 dove-0.006
Ah-0.005
 palm-0.005
Token that
Token ID326
Feature activation-1.56e+00

Pos logit contributions
ira+0.010
adies+0.010
 palm+0.009
Ah+0.009
 dove+0.009
Neg logit contributions
arre-0.017
obe-0.017
 rivals-0.016
anks-0.016
iting-0.015
Token her
Token ID607
Feature activation+3.87e-01

Pos logit contributions
obe+0.056
arre+0.056
anks+0.054
 rivals+0.053
ols+0.053
Neg logit contributions
ira-0.035
adies-0.034
 palm-0.032
 dove-0.032
 sled-0.031
Token mom
Token ID1995
Feature activation-7.69e-01

Pos logit contributions
ira+0.005
 palm+0.004
 dove+0.004
 sled+0.004
adies+0.003
Neg logit contributions
obe-0.018
arre-0.018
ols-0.018
iting-0.017
stick-0.017
Token had
Token ID550
Feature activation-2.19e+00

Pos logit contributions
 rivals+0.029
arre+0.029
anks+0.028
obe+0.028
ols+0.026
Neg logit contributions
ira-0.016
adies-0.014
 dove-0.014
Mom-0.013
 palm-0.013
Token sp
Token ID599
Feature activation-2.63e+00

Pos logit contributions
obe+0.069
arre+0.069
 rivals+0.066
ols+0.064
anks+0.063
Neg logit contributions
adies-0.058
ira-0.057
Ah-0.051
 dove-0.051
 palm-0.050
Tokenilt
Token ID2326
Feature activation-4.50e+00

Pos logit contributions
obe+0.077
arre+0.076
 rivals+0.071
stick+0.070
anks+0.069
Neg logit contributions
adies-0.076
ira-0.075
Ah-0.068
 dove-0.067
 palm-0.066
Token milk
Token ID7545
Feature activation-1.22e+00

Pos logit contributions
obe+0.157
arre+0.156
 rivals+0.153
iting+0.146
ols+0.145
Neg logit contributions
adies-0.102
ira-0.101
 palm-0.097
 dove-0.093
 corn-0.088
Token on
Token ID319
Feature activation+3.68e-01

Pos logit contributions
 rivals+0.046
arre+0.046
obe+0.045
ols+0.044
cess+0.043
Neg logit contributions
 sled-0.023
 palm-0.022
 dove-0.021
 eggs-0.021
 key-0.021
Token the
Token ID262
Feature activation-1.86e-01

Pos logit contributions
ira+0.008
adies+0.007
 palm+0.007
Mom+0.007
 sled+0.006
Neg logit contributions
arre-0.014
obe-0.014
 rivals-0.013
iting-0.013
anks-0.013
Token floor
Token ID4314
Feature activation-5.37e-01

Pos logit contributions
arre+0.006
obe+0.006
 rivals+0.005
stick+0.005
ols+0.005
Neg logit contributions
adies-0.005
ira-0.005
 palm-0.004
Ah-0.004
 dove-0.004
Token.
Token ID13
Feature activation-4.12e-01

Pos logit contributions
arre+0.021
obe+0.021
 rivals+0.020
ols+0.019
anks+0.019
Neg logit contributions
adies-0.010
ira-0.010
 palm-0.009
 sled-0.008
 key-0.007