TOP ACTIVATIONS
MAX = 5.751

, leaving it to its former state .
the tree to its once former beauty . He was happy
to be restored to its former glory ."
the village back to its former glory !"
back the village to its former state . With the help
give them towels and p aj amas . They give them
We have different likes and disl ikes . We can be
. Rex sn arl s . He does not
and trees and cars and shops . They observe everything with
special . On Wed nes days she liked to count !
all fixed up and looked brand new ! "
see cars and trees and shops and people . They are
disappointment . M arl on 's mum hugged him
and bridges and parks and shops and schools and hospitals .
It was fixed and looked brand new ! Tim my was
famous ! And when his story is told , everyone who
to grow l and sn arl to try and scare her
and cozy in her p aj amas , even though she
Spot grow ls and sn arl s . He tries to
took their hats and bin ocular s and stuffed animals and

MIN ACTIVATIONS
MIN = -6.512

and he noticed something shiny wed ged between some branches .
so he asked the ch ame leon to play with him
Emma could hear a wh inn ying sound . She stepped
tried to catch the k ang aroo . It was not
and the picture was sm ud gy . Mom my said
house had a tall cane leaning against its front door .
forgive than to hold gr ud ges .
there 's a light up ahead . We just need to
her drawings would get sm ud ged because the paper wasn
, waiting for the k ang aroo to move .
he saw a big staff leaning against a tree .
there was a big th ud as the blocks started to
he saw a big ladder leaning against the fence . He
stick the mustache on her upper lip with some tape .
wanted to catch the k ang aro os and take them
is normal for old k ang aro os ."
The walls were terribly sm ud ged and she could not
It is the best tw ig in the world . It
's go catch the k ang aroo !" Ben says .
conversation and encouraged the k ang aroo to go ahead .

INTERVAL 2.685 - 5.751
CONTAINS 0.468%

help each other . <|endoftext|> Once upon a time there was
lake again soon ! <|endoftext|> Once upon a time , there
to the zoo . The zoo has many animals from different
The moral of the story was clear : never face
a great time ! <|endoftext|> Once upon a time there were

INTERVAL -0.380 - 2.685
CONTAINS 65.800%

! We need to rush and play together !"
the cr ay ons started to move around the paper !
you can build your nest here . But please don 't
down . They opened the jar together and shared the y
to fit on the top . The tower was not finished

INTERVAL -3.446 - -0.380
CONTAINS 33.671%

angry and said , " This coin belongs to me .
and tasty , so it was hard to decide . In
mine ! M andy quickly raced over and picked
if you want to be clever , you must write and
whenever she felt sad , she would remember the piano and

INTERVAL -6.512 - -3.446
CONTAINS 0.062%

to hold the f auc et up and support it .
sharing . She gave them each a hug and a kiss
can use it to spray each other !" The
my , " Can I let my wallet outside ?" Her
much that she ate it every single day . One day
Token,
Token ID11
Feature activation-9.92e-01

Pos logit contributions
inn+0.013
icky+0.011
ches+0.011
nie+0.011
 kernel+0.011
Neg logit contributions
 disl-0.014
 killed-0.012
bows-0.011
 Gig-0.011
 statues-0.011
Token leaving
Token ID4305
Feature activation+5.46e-01

Pos logit contributions
inn+0.023
ches+0.020
icky+0.020
 kernel+0.020
 aid+0.019
Neg logit contributions
 disl-0.031
 killed-0.024
 Sorry-0.024
 Gig-0.024
endant-0.024
Token it
Token ID340
Feature activation+2.52e-01

Pos logit contributions
 disl+0.017
 killed+0.014
 Gig+0.014
 statues+0.013
 Tri+0.013
Neg logit contributions
inn-0.013
ches-0.011
icky-0.011
nie-0.011
 kernel-0.011
Token to
Token ID284
Feature activation+3.37e-01

Pos logit contributions
 disl+0.008
 killed+0.006
endant+0.006
Thank+0.006
 Gig+0.006
Neg logit contributions
inn-0.006
ches-0.005
icky-0.005
 kernel-0.005
nie-0.005
Token its
Token ID663
Feature activation+1.45e-01

Pos logit contributions
 disl+0.010
 killed+0.008
endant+0.008
 Sorry+0.008
bows+0.008
Neg logit contributions
inn-0.008
ches-0.007
icky-0.007
 kernel-0.007
 aid-0.007
Token former
Token ID1966
Feature activation+5.75e+00

Pos logit contributions
 disl+0.004
 killed+0.003
 Sorry+0.003
Thank+0.003
 Gig+0.003
Neg logit contributions
inn-0.003
ches-0.003
icky-0.003
 kernel-0.003
 aid-0.003
Token state
Token ID1181
Feature activation+2.15e+00

Pos logit contributions
 disl+0.142
 Sorry+0.114
Thank+0.112
 Gig+0.110
 killed+0.109
Neg logit contributions
inn-0.164
ches-0.148
icky-0.147
 aid-0.146
nie-0.144
Token.
Token ID13
Feature activation-1.12e+00

Pos logit contributions
 disl+0.060
 killed+0.049
 statues+0.048
bows+0.048
 jewels+0.048
Neg logit contributions
inn-0.056
ches-0.049
icky-0.048
nie-0.047
 kernel-0.047
Token
Token ID220
Feature activation+6.58e-01

Pos logit contributions
inn+0.028
ches+0.025
 kernel+0.025
icky+0.024
nie+0.024
Neg logit contributions
 disl-0.033
 Gig-0.026
 Sorry-0.026
Thank-0.026
 killed-0.025
Token
Token ID198
Feature activation-7.88e-01

Pos logit contributions
 disl+0.019
 killed+0.015
 Gig+0.014
 Sorry+0.014
Thank+0.014
Neg logit contributions
inn-0.017
ches-0.015
 kernel-0.015
nie-0.015
icky-0.014
Token
Token ID198
Feature activation-2.08e-02

Pos logit contributions
inn+0.020
ches+0.018
 kernel+0.018
nie+0.018
icky+0.018
Neg logit contributions
 disl-0.022
Thank-0.017
 killed-0.017
 Gig-0.017
 Sorry-0.017
Token the
Token ID262
Feature activation+5.43e-01

Pos logit contributions
 disl+0.012
 Gig+0.010
 killed+0.010
 Tri+0.010
 statues+0.010
Neg logit contributions
inn-0.009
ches-0.008
icky-0.008
 aid-0.008
 kernel-0.008
Token tree
Token ID5509
Feature activation-1.80e-01

Pos logit contributions
 disl+0.017
 Sorry+0.013
 killed+0.013
 Gig+0.013
Thank+0.013
Neg logit contributions
inn-0.013
ches-0.011
icky-0.011
 kernel-0.011
 aid-0.011
Token to
Token ID284
Feature activation+4.35e-01

Pos logit contributions
inn+0.005
icky+0.004
ches+0.004
 kernel+0.004
ud+0.004
Neg logit contributions
 disl-0.005
bows-0.004
 killed-0.004
 jewels-0.004
 Tri-0.004
Token its
Token ID663
Feature activation+5.40e-01

Pos logit contributions
 disl+0.013
 killed+0.010
 Gig+0.010
Thank+0.010
 Sorry+0.010
Neg logit contributions
inn-0.011
ches-0.009
icky-0.009
 kernel-0.009
nie-0.009
Token once
Token ID1752
Feature activation+3.71e-01

Pos logit contributions
 disl+0.016
 killed+0.013
 Gig+0.012
Thank+0.012
endant+0.012
Neg logit contributions
inn-0.013
ches-0.012
icky-0.012
 kernel-0.011
nie-0.011
Token former
Token ID1966
Feature activation+5.71e+00

Pos logit contributions
 disl+0.011
 killed+0.009
Thank+0.009
 jewels+0.008
 lucky+0.008
Neg logit contributions
inn-0.010
icky-0.008
ches-0.008
 kernel-0.008
ud-0.008
Token beauty
Token ID8737
Feature activation+2.07e+00

Pos logit contributions
 disl+0.136
 Sorry+0.107
Thank+0.104
 killed+0.104
 Gig+0.101
Neg logit contributions
inn-0.168
ches-0.155
icky-0.152
nie-0.152
 aid-0.149
Token.
Token ID13
Feature activation-6.01e-01

Pos logit contributions
 disl+0.056
bows+0.046
 jewels+0.044
 statues+0.044
 Gig+0.044
Neg logit contributions
inn-0.055
icky-0.048
 kernel-0.047
 aid-0.047
ches-0.047
Token He
Token ID679
Feature activation-6.25e-01

Pos logit contributions
inn+0.016
ches+0.014
icky+0.014
 kernel+0.014
nie+0.013
Neg logit contributions
 disl-0.017
 killed-0.013
 Gig-0.013
 Sorry-0.013
Thank-0.013
Token was
Token ID373
Feature activation-5.16e-01

Pos logit contributions
inn+0.017
icky+0.015
ches+0.014
 kernel+0.014
 aid+0.014
Neg logit contributions
 disl-0.017
 killed-0.014
Thank-0.014
endant-0.013
 Gig-0.013
Token happy
Token ID3772
Feature activation+1.19e+00

Pos logit contributions
inn+0.016
ches+0.014
icky+0.014
 kernel+0.014
 aid+0.014
Neg logit contributions
 disl-0.012
 killed-0.009
Thank-0.009
 Gig-0.009
endant-0.009
Token to
Token ID284
Feature activation+4.92e-01

Pos logit contributions
inn+0.009
icky+0.007
ches+0.007
 kernel+0.007
 aid+0.007
Neg logit contributions
 disl-0.012
 killed-0.010
bows-0.010
 Gig-0.010
endant-0.010
Token be
Token ID307
Feature activation-1.76e-02

Pos logit contributions
 disl+0.013
 killed+0.010
 Gig+0.010
endant+0.010
Thank+0.010
Neg logit contributions
inn-0.013
ches-0.012
icky-0.012
 kernel-0.012
 aid-0.012
Token restored
Token ID15032
Feature activation-9.23e-01

Pos logit contributions
inn+0.000
ches+0.000
nie+0.000
 aid+0.000
'+0.000
Neg logit contributions
 disl-0.000
 Sorry-0.000
mm-0.000
 Gig-0.000
bows-0.000
Token to
Token ID284
Feature activation+3.51e-01

Pos logit contributions
inn+0.026
icky+0.022
 kernel+0.022
ches+0.022
 aid+0.022
Neg logit contributions
 disl-0.024
 Gig-0.019
 killed-0.019
bows-0.019
 jewels-0.019
Token its
Token ID663
Feature activation+3.97e-01

Pos logit contributions
 disl+0.010
endant+0.008
Thank+0.008
 Gig+0.008
 killed+0.008
Neg logit contributions
inn-0.008
icky-0.007
ches-0.007
 aid-0.007
nie-0.007
Token former
Token ID1966
Feature activation+5.53e+00

Pos logit contributions
 disl+0.012
 killed+0.009
endant+0.009
 Sorry+0.009
Thank+0.009
Neg logit contributions
inn-0.009
 aid-0.009
nie-0.008
icky-0.008
ches-0.008
Token glory
Token ID13476
Feature activation+4.00e-01

Pos logit contributions
 disl+0.134
 Sorry+0.105
Thank+0.104
 killed+0.103
 Gig+0.102
Neg logit contributions
inn-0.161
ches-0.147
icky-0.144
nie-0.143
 aid-0.143
Token."
Token ID526
Feature activation-4.16e-01

Pos logit contributions
 disl+0.010
 jewels+0.008
 statues+0.008
bows+0.008
endant+0.007
Neg logit contributions
inn-0.012
 kernel-0.010
ches-0.010
icky-0.010
 aid-0.010
Token
Token ID220
Feature activation+6.30e-01

Pos logit contributions
inn+0.011
ches+0.011
 kernel+0.011
nie+0.010
 aid+0.010
Neg logit contributions
 disl-0.011
 Gig-0.009
 Tri-0.008
 Sorry-0.008
Thank-0.008
Token
Token ID198
Feature activation-4.51e-01

Pos logit contributions
 disl+0.016
 Gig+0.012
 Tri+0.012
 killed+0.012
endant+0.012
Neg logit contributions
inn-0.017
 kernel-0.017
nie-0.016
ches-0.016
 strand-0.015
Token
Token ID198
Feature activation+4.08e-01

Pos logit contributions
inn+0.012
 kernel+0.012
ches+0.012
nie+0.012
 aid+0.011
Neg logit contributions
 disl-0.011
 Gig-0.009
Thank-0.008
 Tri-0.008
 Sorry-0.008
Token the
Token ID262
Feature activation-5.63e-02

Pos logit contributions
inn+0.007
icky+0.006
ches+0.006
 kernel+0.006
nie+0.006
Neg logit contributions
 disl-0.009
 killed-0.007
 Gig-0.007
 jewels-0.007
 Sorry-0.007
Token village
Token ID7404
Feature activation+5.00e-01

Pos logit contributions
inn+0.001
 aid+0.001
 kernel+0.001
'+0.001
icky+0.001
Neg logit contributions
 disl-0.002
 Sorry-0.001
 Tri-0.001
endant-0.001
 Gig-0.001
Token back
Token ID736
Feature activation-6.45e-01

Pos logit contributions
 disl+0.015
 killed+0.012
 Sorry+0.011
 Gig+0.011
endant+0.011
Neg logit contributions
inn-0.012
ches-0.011
icky-0.011
 kernel-0.011
nie-0.010
Token to
Token ID284
Feature activation+5.39e-01

Pos logit contributions
inn+0.014
ches+0.012
icky+0.012
 kernel+0.012
nie+0.011
Neg logit contributions
 disl-0.021
 killed-0.017
 Gig-0.017
endant-0.017
 Sorry-0.017
Token its
Token ID663
Feature activation+5.57e-01

Pos logit contributions
 disl+0.016
endant+0.013
 killed+0.013
bows+0.013
Thank+0.013
Neg logit contributions
inn-0.013
icky-0.011
ches-0.011
 kernel-0.011
 aid-0.011
Token former
Token ID1966
Feature activation+5.45e+00

Pos logit contributions
 disl+0.016
 killed+0.013
 Sorry+0.012
endant+0.012
Thank+0.012
Neg logit contributions
inn-0.014
ches-0.012
icky-0.012
 aid-0.012
 kernel-0.012
Token glory
Token ID13476
Feature activation+7.91e-01

Pos logit contributions
 disl+0.125
 killed+0.092
 Sorry+0.090
Thank+0.090
 Gig+0.089
Neg logit contributions
inn-0.169
ches-0.155
icky-0.153
 kernel-0.150
nie-0.150
Token!"
Token ID2474
Feature activation-1.17e+00

Pos logit contributions
 disl+0.020
 jewels+0.015
bows+0.015
 statues+0.015
endant+0.015
Neg logit contributions
inn-0.023
ches-0.020
icky-0.020
 kernel-0.020
ud-0.020
Token
Token ID220
Feature activation+3.51e-01

Pos logit contributions
inn+0.031
ches+0.027
icky+0.027
 kernel+0.027
nie+0.026
Neg logit contributions
 disl-0.033
Thank-0.026
 Gig-0.026
 Sorry-0.025
 killed-0.025
Token
Token ID198
Feature activation-8.56e-01

Pos logit contributions
 disl+0.009
 killed+0.007
 Gig+0.007
 Sorry+0.007
 Tri+0.007
Neg logit contributions
inn-0.009
 kernel-0.009
ches-0.009
nie-0.008
 strand-0.008
Token
Token ID198
Feature activation-1.47e-01

Pos logit contributions
inn+0.025
ches+0.023
 kernel+0.022
nie+0.022
ash+0.021
Neg logit contributions
 disl-0.021
Thank-0.017
 Gig-0.016
 killed-0.016
 Tri-0.016
Token back
Token ID736
Feature activation-9.67e-01

Pos logit contributions
inn+0.023
ches+0.021
icky+0.021
 kernel+0.020
 aid+0.020
Neg logit contributions
 disl-0.031
 Sorry-0.025
 killed-0.025
endant-0.025
Thank-0.024
Token the
Token ID262
Feature activation-1.75e-01

Pos logit contributions
inn+0.021
ches+0.018
icky+0.018
 kernel+0.017
nie+0.017
Neg logit contributions
 disl-0.032
 killed-0.026
 Sorry-0.026
endant-0.025
Thank-0.025
Token village
Token ID7404
Feature activation-2.75e-02

Pos logit contributions
 aid+0.004
inn+0.004
'+0.004
 kernel+0.003
 chair+0.003
Neg logit contributions
 disl-0.005
 Sorry-0.005
 Gig-0.004
bows-0.004
mm-0.004
Token to
Token ID284
Feature activation+1.21e-01

Pos logit contributions
inn+0.001
ches+0.001
icky+0.001
 kernel+0.001
nie+0.001
Neg logit contributions
 disl-0.001
 killed-0.001
endant-0.001
 Gig-0.001
Thank-0.001
Token its
Token ID663
Feature activation+2.80e-01

Pos logit contributions
 disl+0.004
 killed+0.003
 Gig+0.003
 Sorry+0.003
Thank+0.003
Neg logit contributions
inn-0.003
ches-0.002
icky-0.002
 kernel-0.002
nie-0.002
Token former
Token ID1966
Feature activation+5.33e+00

Pos logit contributions
 disl+0.008
 killed+0.006
 Sorry+0.006
endant+0.006
 Gig+0.006
Neg logit contributions
inn-0.007
ches-0.006
icky-0.006
 aid-0.006
 kernel-0.006
Token state
Token ID1181
Feature activation+1.61e+00

Pos logit contributions
 disl+0.121
 killed+0.089
 Sorry+0.088
Thank+0.087
 Gig+0.087
Neg logit contributions
inn-0.167
ches-0.152
icky-0.150
nie-0.148
 kernel-0.148
Token.
Token ID13
Feature activation-8.78e-01

Pos logit contributions
 disl+0.047
bows+0.038
 statues+0.038
 jewels+0.038
 killed+0.038
Neg logit contributions
inn-0.040
ches-0.035
icky-0.035
 kernel-0.034
nie-0.033
Token With
Token ID2080
Feature activation+4.21e-01

Pos logit contributions
inn+0.023
ches+0.021
 kernel+0.021
nie+0.020
icky+0.020
Neg logit contributions
 disl-0.024
 Gig-0.019
Thank-0.019
 Sorry-0.019
 Tri-0.019
Token the
Token ID262
Feature activation+2.11e-01

Pos logit contributions
 disl+0.013
 killed+0.010
 Gig+0.010
Thank+0.010
 Sorry+0.010
Neg logit contributions
inn-0.010
ches-0.009
icky-0.009
 kernel-0.009
nie-0.009
Token help
Token ID1037
Feature activation-1.53e+00

Pos logit contributions
 disl+0.006
 Sorry+0.005
endant+0.005
bows+0.005
 Gig+0.005
Neg logit contributions
inn-0.005
 kernel-0.005
'-0.005
 aid-0.005
ches-0.005
Token give
Token ID1577
Feature activation+6.12e-01

Pos logit contributions
 disl+0.039
endant+0.030
 Sorry+0.030
 Gig+0.030
 killed+0.029
Neg logit contributions
inn-0.041
ches-0.039
 kernel-0.038
 aid-0.037
icky-0.037
Token them
Token ID606
Feature activation+3.69e-01

Pos logit contributions
 disl+0.020
 Gig+0.017
 killed+0.017
Thank+0.017
 jewels+0.017
Neg logit contributions
inn-0.013
icky-0.011
ches-0.010
 kernel-0.010
nie-0.010
Token towels
Token ID38494
Feature activation+5.04e-01

Pos logit contributions
 disl+0.011
 killed+0.009
 Gig+0.009
Thank+0.009
 Sorry+0.009
Neg logit contributions
inn-0.009
ches-0.008
icky-0.008
 kernel-0.008
nie-0.008
Token and
Token ID290
Feature activation+1.03e+00

Pos logit contributions
 disl+0.017
 killed+0.014
 Gig+0.014
Thank+0.014
endant+0.014
Neg logit contributions
inn-0.010
icky-0.008
ches-0.008
 kernel-0.008
nie-0.008
Token p
Token ID279
Feature activation+2.89e+00

Pos logit contributions
 disl+0.029
 Gig+0.023
 killed+0.023
endant+0.023
 Sorry+0.023
Neg logit contributions
inn-0.025
ches-0.023
 kernel-0.023
icky-0.023
 aid-0.022
Tokenaj
Token ID1228
Feature activation+4.93e+00

Pos logit contributions
 disl+0.101
Thank+0.084
 Sorry+0.084
 killed+0.083
 Gig+0.082
Neg logit contributions
inn-0.058
ches-0.049
icky-0.048
 kernel-0.045
ash-0.044
Tokenamas
Token ID17485
Feature activation+1.66e+00

Pos logit contributions
 disl+0.194
 killed+0.164
 Gig+0.163
endant+0.160
Thank+0.159
Neg logit contributions
inn-0.075
icky-0.067
ches-0.065
nie-0.058
ide-0.057
Token.
Token ID13
Feature activation+1.25e+00

Pos logit contributions
 disl+0.057
 killed+0.046
 Gig+0.046
 Sorry+0.046
endant+0.046
Neg logit contributions
inn-0.033
ches-0.029
icky-0.028
 kernel-0.027
 aid-0.027
Token They
Token ID1119
Feature activation+1.57e+00

Pos logit contributions
 disl+0.036
 killed+0.030
endant+0.030
 jewels+0.029
bows+0.029
Neg logit contributions
inn-0.031
icky-0.028
 aid-0.027
ches-0.026
 kernel-0.026
Token give
Token ID1577
Feature activation+6.14e-01

Pos logit contributions
 disl+0.038
 Sorry+0.028
endant+0.028
 killed+0.028
 Gig+0.028
Neg logit contributions
inn-0.045
ches-0.043
 kernel-0.042
icky-0.041
 aid-0.041
Token them
Token ID606
Feature activation+3.77e-01

Pos logit contributions
 disl+0.021
 Gig+0.018
 killed+0.018
Thank+0.017
 jewels+0.017
Neg logit contributions
inn-0.012
icky-0.010
ches-0.010
 aid-0.010
 kernel-0.010
Token We
Token ID775
Feature activation-1.41e+00

Pos logit contributions
 disl+0.019
 killed+0.015
endant+0.015
 Gig+0.014
Thank+0.014
Neg logit contributions
inn-0.020
icky-0.018
ches-0.018
 aid-0.018
nie-0.018
Token have
Token ID423
Feature activation-6.66e-01

Pos logit contributions
inn+0.041
ches+0.039
icky+0.036
'+0.036
 kernel+0.036
Neg logit contributions
 disl-0.035
 Gig-0.027
endant-0.026
 Tri-0.025
Thank-0.025
Token different
Token ID1180
Feature activation+1.25e+00

Pos logit contributions
inn+0.014
ches+0.012
icky+0.012
 kernel+0.012
nie+0.012
Neg logit contributions
 disl-0.022
 killed-0.018
endant-0.018
 Gig-0.018
 Sorry-0.018
Token likes
Token ID7832
Feature activation+1.32e-01

Pos logit contributions
 disl+0.033
 Gig+0.027
Thank+0.027
 killed+0.027
 Sorry+0.027
Neg logit contributions
inn-0.032
ches-0.030
icky-0.029
nie-0.029
 aid-0.028
Token and
Token ID290
Feature activation+1.02e+00

Pos logit contributions
 disl+0.004
 killed+0.003
 jewels+0.003
 Gig+0.003
 statues+0.003
Neg logit contributions
inn-0.003
ches-0.003
icky-0.003
 kernel-0.003
nie-0.003
Token disl
Token ID19621
Feature activation+4.88e+00

Pos logit contributions
 disl+0.022
 Gig+0.022
mm+0.020
 Tri+0.020
Thank+0.020
Neg logit contributions
inn-0.024
ches-0.024
 mat-0.024
nie-0.024
 aid-0.023
Tokenikes
Token ID7938
Feature activation-2.83e-02

Pos logit contributions
 disl+0.103
bows+0.072
 Sorry+0.070
 killed+0.070
Thank+0.070
Neg logit contributions
inn-0.162
ches-0.149
 kernel-0.147
icky-0.146
 aid-0.145
Token.
Token ID13
Feature activation+6.54e-01

Pos logit contributions
inn+0.001
 aid+0.001
 kernel+0.001
icky+0.001
ches+0.001
Neg logit contributions
 disl-0.001
 killed-0.001
 Sorry-0.001
bows-0.001
Thank-0.001
Token We
Token ID775
Feature activation-1.27e+00

Pos logit contributions
 disl+0.017
 killed+0.014
endant+0.013
bows+0.013
 Gig+0.013
Neg logit contributions
inn-0.018
icky-0.016
ches-0.016
 aid-0.016
nie-0.015
Token can
Token ID460
Feature activation+3.06e-01

Pos logit contributions
inn+0.035
ches+0.034
'+0.032
 scrub+0.031
 kernel+0.031
Neg logit contributions
 disl-0.032
 Gig-0.026
endant-0.025
 statues-0.025
mm-0.025
Token be
Token ID307
Feature activation+3.01e-01

Pos logit contributions
 disl+0.008
 killed+0.007
 Sorry+0.006
 Gig+0.006
Thank+0.006
Neg logit contributions
inn-0.008
ches-0.007
icky-0.007
 kernel-0.007
nie-0.007
Token.
Token ID13
Feature activation+1.34e-01

Pos logit contributions
 disl+0.010
 killed+0.008
 Thank+0.008
 Gig+0.008
 Tri+0.007
Neg logit contributions
inn-0.013
nie-0.012
 kernel-0.012
ches-0.011
pron-0.011
Token
Token ID198
Feature activation-1.29e-01

Pos logit contributions
 disl+0.004
 killed+0.003
Thank+0.003
 Gig+0.003
 Sorry+0.003
Neg logit contributions
inn-0.003
ches-0.003
nie-0.003
 kernel-0.003
icky-0.003
Token
Token ID198
Feature activation+8.95e-01

Pos logit contributions
inn+0.003
ches+0.003
icky+0.003
 kernel+0.003
nie+0.003
Neg logit contributions
 disl-0.004
 killed-0.003
 Gig-0.003
 Sorry-0.003
Thank-0.003
TokenRex
Token ID47389
Feature activation+9.33e-01

Pos logit contributions
 disl+0.029
endant+0.024
bows+0.024
 jewels+0.024
 Gig+0.023
Neg logit contributions
inn-0.020
icky-0.017
ches-0.017
 aid-0.016
 kernel-0.016
Token sn
Token ID3013
Feature activation+8.07e-01

Pos logit contributions
 disl+0.026
 Gig+0.020
endant+0.020
 killed+0.020
 Sorry+0.020
Neg logit contributions
inn-0.024
ches-0.022
icky-0.021
 kernel-0.021
 aid-0.021
Tokenarl
Token ID7063
Feature activation+4.79e+00

Pos logit contributions
 disl+0.024
 killed+0.019
 jewels+0.019
 statues+0.019
 Gig+0.019
Neg logit contributions
inn-0.020
ches-0.018
icky-0.018
 kernel-0.017
 aid-0.017
Tokens
Token ID82
Feature activation+5.70e-02

Pos logit contributions
 disl+0.163
 killed+0.133
 Gig+0.131
endant+0.131
Thank+0.131
Neg logit contributions
inn-0.097
ches-0.084
icky-0.083
 kernel-0.080
 aid-0.079
Token.
Token ID13
Feature activation+1.36e+00

Pos logit contributions
 disl+0.002
 killed+0.001
Thank+0.001
 Gig+0.001
 jewels+0.001
Neg logit contributions
inn-0.001
icky-0.001
nie-0.001
ches-0.001
 kernel-0.001
Token He
Token ID679
Feature activation+4.41e-01

Pos logit contributions
 disl+0.043
endant+0.035
 killed+0.034
bows+0.034
 jewels+0.034
Neg logit contributions
inn-0.031
icky-0.027
ches-0.027
 aid-0.027
 kernel-0.026
Token does
Token ID857
Feature activation+3.01e-01

Pos logit contributions
 disl+0.012
 Gig+0.009
 Sorry+0.009
endant+0.009
Thank+0.009
Neg logit contributions
inn-0.012
ches-0.011
icky-0.010
 kernel-0.010
 aid-0.010
Token not
Token ID407
Feature activation+1.02e+00

Pos logit contributions
 disl+0.008
endant+0.006
 Gig+0.006
 Sorry+0.006
bows+0.006
Neg logit contributions
inn-0.008
ches-0.008
 aid-0.008
icky-0.007
 kernel-0.007
Token and
Token ID290
Feature activation+2.19e+00

Pos logit contributions
 disl+0.107
 Sorry+0.088
 Gig+0.086
 killed+0.086
endant+0.086
Neg logit contributions
inn-0.041
ches-0.036
 kernel-0.034
icky-0.034
 aid-0.034
Token trees
Token ID7150
Feature activation+2.60e+00

Pos logit contributions
 disl+0.064
 Sorry+0.050
endant+0.050
mm+0.049
 Gig+0.049
Neg logit contributions
nie-0.047
 chair-0.047
inn-0.047
 kernel-0.046
 aid-0.046
Token and
Token ID290
Feature activation+2.52e+00

Pos logit contributions
 disl+0.094
 killed+0.077
 Sorry+0.077
endant+0.076
Thank+0.076
Neg logit contributions
inn-0.048
ches-0.041
icky-0.040
 kernel-0.039
 aid-0.038
Token cars
Token ID5006
Feature activation+3.11e+00

Pos logit contributions
 disl+0.076
 Sorry+0.060
endant+0.060
mm+0.059
 Gig+0.058
Neg logit contributions
nie-0.052
 chair-0.052
 corner-0.052
 kernel-0.051
 aid-0.051
Token and
Token ID290
Feature activation+2.45e+00

Pos logit contributions
 disl+0.114
 Sorry+0.093
 Gig+0.092
 killed+0.092
endant+0.091
Neg logit contributions
inn-0.056
ches-0.048
icky-0.046
 kernel-0.046
 aid-0.045
Token shops
Token ID12437
Feature activation+4.78e+00

Pos logit contributions
 disl+0.075
 Sorry+0.060
endant+0.060
mm+0.059
 Gig+0.057
Neg logit contributions
 chair-0.050
nie-0.049
 corner-0.048
 aid-0.048
ches-0.048
Token.
Token ID13
Feature activation+1.52e+00

Pos logit contributions
 disl+0.191
 Sorry+0.157
 Gig+0.153
 killed+0.152
Thank+0.152
Neg logit contributions
inn-0.067
 aid-0.062
ches-0.059
 chair-0.059
'-0.059
Token They
Token ID1119
Feature activation+1.30e+00

Pos logit contributions
 disl+0.038
 Gig+0.029
Thank+0.028
 Sorry+0.028
 killed+0.028
Neg logit contributions
inn-0.045
ches-0.041
 kernel-0.040
nie-0.040
icky-0.039
Token observe
Token ID12414
Feature activation+1.63e+00

Pos logit contributions
 disl+0.034
 Gig+0.026
mm+0.025
endant+0.025
 Sorry+0.025
Neg logit contributions
inn-0.034
ches-0.033
 kernel-0.032
 aid-0.032
'-0.032
Token everything
Token ID2279
Feature activation+1.76e+00

Pos logit contributions
 disl+0.050
 killed+0.041
 statues+0.040
 Gig+0.040
bows+0.040
Neg logit contributions
inn-0.039
ches-0.033
icky-0.033
 kernel-0.032
nie-0.032
Token with
Token ID351
Feature activation+6.76e-01

Pos logit contributions
 disl+0.052
 statues+0.043
bows+0.043
 killed+0.043
 jewels+0.042
Neg logit contributions
inn-0.042
icky-0.036
ches-0.036
 aid-0.035
 kernel-0.035
Token special
Token ID2041
Feature activation-6.76e-01

Pos logit contributions
 disl+0.043
 killed+0.033
Thank+0.033
endant+0.033
 Sorry+0.033
Neg logit contributions
inn-0.042
ches-0.038
icky-0.038
nie-0.037
 kernel-0.037
Token.
Token ID13
Feature activation-1.68e-02

Pos logit contributions
inn+0.017
ches+0.015
icky+0.015
 kernel+0.014
 aid+0.014
Neg logit contributions
 disl-0.020
bows-0.016
 killed-0.016
Thank-0.016
 statues-0.015
Token On
Token ID1550
Feature activation-1.52e+00

Pos logit contributions
inn+0.001
 kernel+0.001
ler+0.001
ches+0.000
nie+0.000
Neg logit contributions
 disl-0.000
 Gig-0.000
Thank-0.000
 Thank-0.000
 Tri-0.000
Token Wed
Token ID3300
Feature activation+1.85e+00

Pos logit contributions
inn+0.043
ches+0.041
ud+0.039
ash+0.038
nie+0.038
Neg logit contributions
 disl-0.038
 Tri-0.029
Thank-0.029
 killed-0.028
 Gig-0.028
Tokennes
Token ID2516
Feature activation-3.44e-01

Pos logit contributions
 disl+0.070
Thank+0.059
 killed+0.059
bows+0.058
 Sorry+0.058
Neg logit contributions
inn-0.029
ches-0.024
icky-0.024
 kernel-0.024
 aid-0.023
Tokendays
Token ID12545
Feature activation+4.74e+00

Pos logit contributions
inn+0.009
 kernel+0.008
ches+0.008
icky+0.008
nie+0.008
Neg logit contributions
 disl-0.010
 killed-0.007
bows-0.007
 Tri-0.007
 Sorry-0.007
Token she
Token ID673
Feature activation-7.44e-02

Pos logit contributions
 disl+0.148
Thank+0.119
bows+0.119
 Sorry+0.119
 killed+0.119
Neg logit contributions
inn-0.108
ches-0.096
 kernel-0.093
icky-0.093
 aid-0.090
Token liked
Token ID8288
Feature activation+7.91e-01

Pos logit contributions
inn+0.002
icky+0.002
 kernel+0.002
ches+0.002
ide+0.002
Neg logit contributions
 disl-0.002
 killed-0.001
Thank-0.001
 Sorry-0.001
bows-0.001
Token to
Token ID284
Feature activation+4.78e-01

Pos logit contributions
 disl+0.028
 Gig+0.023
 killed+0.023
 statues+0.023
Thank+0.023
Neg logit contributions
inn-0.016
ches-0.013
icky-0.013
 kernel-0.012
 aid-0.012
Token count
Token ID954
Feature activation-6.18e-01

Pos logit contributions
 disl+0.012
 killed+0.009
 Sorry+0.009
Thank+0.009
bows+0.009
Neg logit contributions
inn-0.014
ches-0.013
icky-0.013
 kernel-0.012
nie-0.012
Token!
Token ID0
Feature activation-9.10e-01

Pos logit contributions
inn+0.014
ches+0.012
icky+0.012
 kernel+0.012
nie+0.012
Neg logit contributions
 disl-0.019
 killed-0.015
 Gig-0.015
 Sorry-0.015
endant-0.015
Token all
Token ID477
Feature activation-1.25e+00

Pos logit contributions
inn+0.030
ches+0.027
icky+0.026
 kernel+0.026
nie+0.025
Neg logit contributions
 disl-0.033
 killed-0.026
 Sorry-0.026
 Gig-0.026
Thank-0.026
Token fixed
Token ID5969
Feature activation-9.17e-02

Pos logit contributions
inn+0.034
ches+0.030
icky+0.030
 kernel+0.029
 aid+0.029
Neg logit contributions
 disl-0.035
 killed-0.027
Thank-0.026
endant-0.026
bows-0.026
Token up
Token ID510
Feature activation-1.65e+00

Pos logit contributions
inn+0.002
icky+0.002
 kernel+0.002
ches+0.002
 aid+0.002
Neg logit contributions
 disl-0.003
bows-0.002
 killed-0.002
 jewels-0.002
 statues-0.002
Token and
Token ID290
Feature activation+3.44e-02

Pos logit contributions
inn+0.036
ches+0.032
icky+0.031
 kernel+0.031
nie+0.030
Neg logit contributions
 disl-0.054
 killed-0.043
 Gig-0.043
 Sorry-0.042
Thank-0.042
Token looked
Token ID3114
Feature activation+1.23e+00

Pos logit contributions
 disl+0.001
endant+0.001
 killed+0.001
 Gig+0.001
 Sorry+0.001
Neg logit contributions
inn-0.001
ches-0.001
 kernel-0.001
nie-0.001
icky-0.001
Token brand
Token ID4508
Feature activation+4.74e+00

Pos logit contributions
 disl+0.039
mm+0.032
 Sorry+0.031
 Gig+0.030
 killed+0.030
Neg logit contributions
inn-0.028
ches-0.025
nie-0.025
 again-0.024
 kernel-0.023
Token new
Token ID649
Feature activation+5.30e-01

Pos logit contributions
 disl+0.137
 killed+0.107
 Sorry+0.105
Thank+0.105
endant+0.105
Neg logit contributions
inn-0.121
ches-0.108
icky-0.107
 kernel-0.105
 aid-0.104
Token!
Token ID0
Feature activation-1.05e+00

Pos logit contributions
 disl+0.019
 Sorry+0.015
Thank+0.015
 Gig+0.015
 killed+0.015
Neg logit contributions
inn-0.010
ches-0.009
icky-0.008
nie-0.008
 aid-0.008
Token
Token ID198
Feature activation-4.70e-01

Pos logit contributions
ches+0.030
inn+0.030
 kernel+0.028
ler+0.028
le+0.028
Neg logit contributions
 disl-0.024
 Thank-0.021
 Sorry-0.020
 Gig-0.020
Thank-0.019
Token
Token ID198
Feature activation+3.24e-01

Pos logit contributions
inn+0.015
ches+0.015
 kernel+0.015
ler+0.015
nie+0.015
Neg logit contributions
 disl-0.008
Thank-0.006
 lucky-0.006
 Thank-0.006
 Gig-0.006
Token"
Token ID1
Feature activation+1.73e+00

Pos logit contributions
 disl+0.008
Thank+0.008
 lucky+0.007
 Thank+0.006
 Sorry+0.006
Neg logit contributions
inn-0.008
ches-0.008
icky-0.008
ig-0.008
ash-0.008
Token see
Token ID766
Feature activation+1.13e+00

Pos logit contributions
 disl+0.034
mm+0.027
 Gig+0.027
endant+0.026
 Sorry+0.025
Neg logit contributions
 aid-0.033
'-0.032
ches-0.032
 chair-0.031
inn-0.031
Token cars
Token ID5006
Feature activation+2.34e+00

Pos logit contributions
 disl+0.036
 Sorry+0.029
Thank+0.029
endant+0.029
 killed+0.028
Neg logit contributions
inn-0.024
 kernel-0.022
icky-0.021
ches-0.021
 aid-0.021
Token and
Token ID290
Feature activation+1.67e+00

Pos logit contributions
 disl+0.085
 Gig+0.069
 Sorry+0.069
 killed+0.069
endant+0.069
Neg logit contributions
inn-0.042
ches-0.037
icky-0.036
 kernel-0.035
 aid-0.034
Token trees
Token ID7150
Feature activation+2.56e+00

Pos logit contributions
 disl+0.050
endant+0.042
mm+0.041
 Gig+0.041
 Sorry+0.041
Neg logit contributions
 chair-0.034
 mat-0.034
 kernel-0.033
inn-0.032
 aid-0.032
Token and
Token ID290
Feature activation+2.43e+00

Pos logit contributions
 disl+0.088
 killed+0.072
 Gig+0.071
Thank+0.071
endant+0.070
Neg logit contributions
inn-0.051
ches-0.044
icky-0.044
 kernel-0.042
nie-0.042
Token shops
Token ID12437
Feature activation+4.69e+00

Pos logit contributions
 disl+0.074
endant+0.061
mm+0.060
 Sorry+0.060
 Gig+0.058
Neg logit contributions
 chair-0.049
 corner-0.048
ches-0.047
 kernel-0.047
nie-0.047
Token and
Token ID290
Feature activation+2.29e+00

Pos logit contributions
 disl+0.185
 Sorry+0.152
 Gig+0.149
 killed+0.149
Thank+0.148
Neg logit contributions
inn-0.068
 aid-0.061
 kernel-0.059
ches-0.059
 chair-0.058
Token people
Token ID661
Feature activation+3.17e+00

Pos logit contributions
 disl+0.070
mm+0.059
endant+0.059
 Sorry+0.057
 Gig+0.056
Neg logit contributions
 corner-0.045
 chair-0.045
 aid-0.044
 kernel-0.043
 mat-0.043
Token.
Token ID13
Feature activation+2.10e+00

Pos logit contributions
 disl+0.111
 Sorry+0.090
 Gig+0.090
 killed+0.089
Thank+0.089
Neg logit contributions
inn-0.060
ches-0.053
icky-0.052
 kernel-0.051
 aid-0.051
Token They
Token ID1119
Feature activation+1.40e+00

Pos logit contributions
 disl+0.061
 killed+0.048
endant+0.048
 jewels+0.046
 Sorry+0.046
Neg logit contributions
inn-0.053
icky-0.048
 aid-0.047
ches-0.045
 kernel-0.045
Token are
Token ID389
Feature activation+1.76e+00

Pos logit contributions
 disl+0.037
mm+0.031
 Gig+0.031
endant+0.030
 Sorry+0.029
Neg logit contributions
 aid-0.033
'-0.033
 chair-0.033
inn-0.032
 scrub-0.032
Token disappointment
Token ID18641
Feature activation+1.67e+00

Pos logit contributions
inn+0.001
ches+0.001
icky+0.001
nie+0.001
 kernel+0.001
Neg logit contributions
 disl-0.001
 killed-0.001
Thank-0.001
 Gig-0.001
 Sorry-0.001
Token.
Token ID13
Feature activation-1.38e+00

Pos logit contributions
 disl+0.046
 killed+0.037
 jewels+0.036
 statues+0.036
Thank+0.036
Neg logit contributions
inn-0.043
icky-0.038
ches-0.037
 kernel-0.037
nie-0.036
Token
Token ID198
Feature activation-1.15e+00

Pos logit contributions
inn+0.036
ches+0.033
 kernel+0.032
icky+0.031
nie+0.031
Neg logit contributions
 disl-0.039
 Gig-0.031
 Sorry-0.030
Thank-0.030
 killed-0.030
Token
Token ID198
Feature activation-3.66e-01

Pos logit contributions
inn+0.029
 kernel+0.028
ches+0.027
nie+0.026
ler+0.026
Neg logit contributions
 disl-0.032
 Gig-0.025
Thank-0.025
 killed-0.024
 Tri-0.024
TokenM
Token ID44
Feature activation-7.01e-01

Pos logit contributions
inn+0.009
ches+0.009
 kernel+0.009
icky+0.008
nie+0.008
Neg logit contributions
 disl-0.010
Thank-0.008
 Gig-0.008
 Sorry-0.008
 killed-0.008
Tokenarl
Token ID7063
Feature activation+4.68e+00

Pos logit contributions
inn+0.014
ches+0.012
icky+0.011
 kernel+0.011
nie+0.011
Neg logit contributions
 disl-0.025
 killed-0.020
 Gig-0.020
 Sorry-0.020
endant-0.020
Tokenon
Token ID261
Feature activation-1.01e+00

Pos logit contributions
 disl+0.115
 killed+0.090
Thank+0.089
bows+0.088
 Gig+0.087
Neg logit contributions
inn-0.133
ches-0.121
icky-0.120
nie-0.119
 kernel-0.118
Token's
Token ID338
Feature activation-9.64e-01

Pos logit contributions
inn+0.028
ash+0.024
 mat+0.024
icky+0.024
ud+0.024
Neg logit contributions
 disl-0.025
 killed-0.021
endant-0.019
Thank-0.019
 jewels-0.019
Token mum
Token ID25682
Feature activation+7.23e-01

Pos logit contributions
inn+0.026
ches+0.023
icky+0.022
 kernel+0.022
ide+0.022
Neg logit contributions
 disl-0.026
 killed-0.021
 jewels-0.020
endant-0.020
 Gig-0.020
Token hugged
Token ID41130
Feature activation+9.05e-01

Pos logit contributions
 disl+0.017
 killed+0.014
Thank+0.013
 Gig+0.013
endant+0.013
Neg logit contributions
inn-0.022
icky-0.019
 kernel-0.019
ches-0.018
 mat-0.018
Token him
Token ID683
Feature activation-1.58e+00

Pos logit contributions
 disl+0.022
 Gig+0.019
Thank+0.018
 Tri+0.018
 Sorry+0.017
Neg logit contributions
inn-0.026
icky-0.023
ches-0.023
 kernel-0.023
 aid-0.022
Token and
Token ID290
Feature activation+2.45e+00

Pos logit contributions
 disl+0.046
 Gig+0.038
 Sorry+0.038
 killed+0.038
Thank+0.037
Neg logit contributions
inn-0.021
ches-0.018
icky-0.017
 kernel-0.017
 aid-0.017
Token bridges
Token ID19432
Feature activation+2.25e+00

Pos logit contributions
 disl+0.078
 Gig+0.066
 Sorry+0.064
mm+0.063
endant+0.063
Neg logit contributions
inn-0.044
 chair-0.044
 aid-0.043
 kernel-0.043
 scrub-0.042
Token and
Token ID290
Feature activation+3.26e+00

Pos logit contributions
 disl+0.085
 Gig+0.071
 Sorry+0.071
 killed+0.070
endant+0.069
Neg logit contributions
inn-0.037
ches-0.031
icky-0.031
 aid-0.030
 kernel-0.030
Token parks
Token ID14860
Feature activation+2.03e+00

Pos logit contributions
 disl+0.105
 Gig+0.087
 Sorry+0.085
mm+0.084
endant+0.084
Neg logit contributions
inn-0.059
 aid-0.059
 chair-0.058
 corner-0.058
 kernel-0.057
Token and
Token ID290
Feature activation+3.11e+00

Pos logit contributions
 disl+0.061
 statues+0.050
 killed+0.050
bows+0.049
 jewels+0.049
Neg logit contributions
inn-0.049
icky-0.043
ches-0.042
nie-0.042
 kernel-0.040
Token shops
Token ID12437
Feature activation+4.66e+00

Pos logit contributions
 disl+0.099
 Gig+0.081
mm+0.081
endant+0.079
 Sorry+0.078
Neg logit contributions
 corner-0.058
 aid-0.058
 chair-0.057
 again-0.056
inn-0.056
Token and
Token ID290
Feature activation+2.75e+00

Pos logit contributions
 disl+0.186
 Sorry+0.155
 Gig+0.152
mm+0.149
Thank+0.149
Neg logit contributions
inn-0.064
 aid-0.059
 again-0.057
 chair-0.057
ches-0.056
Token schools
Token ID4266
Feature activation+2.98e+00

Pos logit contributions
 disl+0.087
mm+0.073
 Gig+0.072
endant+0.072
 Sorry+0.072
Neg logit contributions
 aid-0.051
 corner-0.051
 chair-0.050
 again-0.050
 scrub-0.048
Token and
Token ID290
Feature activation+2.32e+00

Pos logit contributions
 disl+0.108
 Sorry+0.088
 Gig+0.088
 killed+0.087
endant+0.087
Neg logit contributions
inn-0.054
ches-0.047
icky-0.045
 aid-0.045
 kernel-0.045
Token hospitals
Token ID11301
Feature activation+1.90e+00

Pos logit contributions
 disl+0.072
mm+0.061
 Gig+0.061
 Sorry+0.059
endant+0.059
Neg logit contributions
 corner-0.043
 chair-0.042
 aid-0.042
 again-0.041
 scrub-0.040
Token.
Token ID13
Feature activation+1.29e+00

Pos logit contributions
 disl+0.062
 killed+0.050
 Sorry+0.050
 Gig+0.050
endant+0.050
Neg logit contributions
inn-0.040
ches-0.035
icky-0.035
 kernel-0.034
nie-0.033
Token It
Token ID632
Feature activation+9.21e-01

Pos logit contributions
 disl+0.006
 killed+0.005
endant+0.005
 Gig+0.005
bows+0.005
Neg logit contributions
inn-0.004
icky-0.004
ches-0.004
 aid-0.004
nie-0.004
Token was
Token ID373
Feature activation-3.80e-01

Pos logit contributions
 disl+0.030
 killed+0.025
Thank+0.024
endant+0.024
 Tri+0.024
Neg logit contributions
inn-0.020
icky-0.018
ches-0.017
 kernel-0.017
 aid-0.017
Token fixed
Token ID5969
Feature activation-2.34e-01

Pos logit contributions
inn+0.010
ches+0.008
icky+0.008
 kernel+0.008
nie+0.008
Neg logit contributions
 disl-0.011
 Sorry-0.009
bows-0.009
 killed-0.008
endant-0.008
Token and
Token ID290
Feature activation+3.80e-01

Pos logit contributions
inn+0.006
icky+0.005
 kernel+0.005
ches+0.005
 aid+0.005
Neg logit contributions
 disl-0.007
 killed-0.006
bows-0.005
 jewels-0.005
 statues-0.005
Token looked
Token ID3114
Feature activation+1.79e+00

Pos logit contributions
 disl+0.012
bows+0.009
 Sorry+0.009
endant+0.009
 Gig+0.009
Neg logit contributions
inn-0.009
ches-0.007
nie-0.007
 kernel-0.007
 chair-0.007
Token brand
Token ID4508
Feature activation+4.66e+00

Pos logit contributions
 disl+0.059
bows+0.047
 Sorry+0.047
 Gig+0.046
mm+0.046
Neg logit contributions
inn-0.040
 again-0.037
ches-0.037
nie-0.034
 scrub-0.032
Token new
Token ID649
Feature activation+6.97e-01

Pos logit contributions
 disl+0.138
 killed+0.109
 Gig+0.107
 Sorry+0.107
Thank+0.107
Neg logit contributions
inn-0.115
ches-0.102
icky-0.101
 kernel-0.098
nie-0.098
Token!
Token ID0
Feature activation-5.07e-01

Pos logit contributions
 disl+0.024
 killed+0.019
 Sorry+0.019
 Gig+0.019
Thank+0.019
Neg logit contributions
inn-0.014
ches-0.012
icky-0.012
 kernel-0.012
nie-0.012
Token Tim
Token ID5045
Feature activation-6.96e-01

Pos logit contributions
inn+0.012
icky+0.010
ches+0.010
nie+0.010
 aid+0.010
Neg logit contributions
 disl-0.016
 killed-0.013
endant-0.013
bows-0.013
 jewels-0.012
Tokenmy
Token ID1820
Feature activation-4.40e-01

Pos logit contributions
inn+0.018
 kernel+0.015
icky+0.015
ches+0.015
 aid+0.015
Neg logit contributions
 disl-0.020
 killed-0.016
Thank-0.016
endant-0.016
bows-0.015
Token was
Token ID373
Feature activation-8.56e-01

Pos logit contributions
inn+0.010
ches+0.009
icky+0.009
 kernel+0.008
nie+0.008
Neg logit contributions
 disl-0.014
 killed-0.011
 Gig-0.011
 Sorry-0.011
endant-0.011
Token famous
Token ID5863
Feature activation+2.88e-01

Pos logit contributions
 disl+0.024
 Sorry+0.019
bows+0.018
endant+0.018
 Gig+0.018
Neg logit contributions
inn-0.022
ches-0.019
icky-0.019
 kernel-0.019
 aid-0.019
Token!
Token ID0
Feature activation-1.20e+00

Pos logit contributions
 disl+0.009
 Sorry+0.008
 Gig+0.007
 killed+0.007
Thank+0.007
Neg logit contributions
inn-0.006
ches-0.005
icky-0.005
 aid-0.005
nie-0.005
Token And
Token ID843
Feature activation+8.94e-01

Pos logit contributions
inn+0.032
ches+0.029
 kernel+0.029
icky+0.028
nie+0.028
Neg logit contributions
 disl-0.033
 Gig-0.025
 Sorry-0.025
Thank-0.025
 killed-0.025
Token when
Token ID618
Feature activation-9.03e-02

Pos logit contributions
 disl+0.028
endant+0.023
 killed+0.023
bows+0.022
 Gig+0.022
Neg logit contributions
inn-0.019
nie-0.017
icky-0.017
 kernel-0.017
 Alex-0.017
Token his
Token ID465
Feature activation-3.42e-02

Pos logit contributions
inn+0.002
icky+0.002
 Alex+0.002
nie+0.002
 kernel+0.002
Neg logit contributions
 disl-0.003
endant-0.002
bows-0.002
Thank-0.002
 killed-0.002
Token story
Token ID1621
Feature activation+4.57e+00

Pos logit contributions
inn+0.001
 aid+0.001
icky+0.001
 kernel+0.001
ches+0.001
Neg logit contributions
 disl-0.001
Thank-0.001
 Gig-0.001
 killed-0.001
bows-0.001
Token is
Token ID318
Feature activation+5.97e-01

Pos logit contributions
 disl+0.140
 Gig+0.113
endant+0.111
 killed+0.108
 Tri+0.108
Neg logit contributions
inn-0.107
ches-0.097
icky-0.095
nie-0.091
 kernel-0.090
Token told
Token ID1297
Feature activation+1.70e+00

Pos logit contributions
 disl+0.016
 Sorry+0.012
 Gig+0.012
 killed+0.012
endant+0.012
Neg logit contributions
inn-0.017
ches-0.015
icky-0.015
nie-0.015
 kernel-0.014
Token,
Token ID11
Feature activation-5.70e-01

Pos logit contributions
 disl+0.055
endant+0.046
Thank+0.045
 killed+0.044
bows+0.044
Neg logit contributions
inn-0.036
ches-0.033
icky-0.032
nie-0.031
 aid-0.031
Token everyone
Token ID2506
Feature activation+1.04e+00

Pos logit contributions
inn+0.013
ches+0.011
icky+0.011
 kernel+0.011
nie+0.011
Neg logit contributions
 disl-0.018
endant-0.015
 killed-0.014
bows-0.014
Thank-0.014
Token who
Token ID508
Feature activation-8.09e-01

Pos logit contributions
 disl+0.030
 killed+0.024
 Sorry+0.023
 Gig+0.023
Thank+0.023
Neg logit contributions
inn-0.026
ches-0.023
icky-0.023
 kernel-0.022
 aid-0.022
Token to
Token ID284
Feature activation+5.74e-01

Pos logit contributions
inn+0.017
ches+0.015
nie+0.014
icky+0.014
 kernel+0.014
Neg logit contributions
 disl-0.031
 killed-0.026
 Gig-0.025
Thank-0.025
bows-0.024
Token grow
Token ID1663
Feature activation+1.10e+00

Pos logit contributions
 disl+0.015
endant+0.013
mm+0.012
 Sorry+0.012
 killed+0.012
Neg logit contributions
inn-0.014
ches-0.014
 aid-0.014
icky-0.013
 kernel-0.013
Tokenl
Token ID75
Feature activation+5.20e-01

Pos logit contributions
 disl+0.036
 killed+0.029
 Gig+0.029
Thank+0.028
endant+0.028
Neg logit contributions
inn-0.024
ches-0.021
icky-0.021
 kernel-0.020
nie-0.020
Token and
Token ID290
Feature activation+3.11e-01

Pos logit contributions
 disl+0.014
bows+0.013
 killed+0.012
endant+0.012
 statues+0.011
Neg logit contributions
inn-0.013
 kernel-0.011
nie-0.011
 strand-0.011
 aid-0.011
Token sn
Token ID3013
Feature activation+1.37e+00

Pos logit contributions
 disl+0.008
mm+0.007
endant+0.007
bows+0.006
Thank+0.006
Neg logit contributions
inn-0.008
ches-0.007
 aid-0.007
 kernel-0.007
icky-0.007
Tokenarl
Token ID7063
Feature activation+4.57e+00

Pos logit contributions
 disl+0.042
 statues+0.034
 jewels+0.034
 killed+0.033
 Sorry+0.032
Neg logit contributions
inn-0.034
ches-0.030
icky-0.028
ash-0.027
 kernel-0.027
Token to
Token ID284
Feature activation+8.50e-01

Pos logit contributions
 disl+0.151
 killed+0.124
 Gig+0.122
bows+0.122
 Sorry+0.121
Neg logit contributions
inn-0.095
ches-0.082
icky-0.081
 kernel-0.080
nie-0.079
Token try
Token ID1949
Feature activation-8.85e-01

Pos logit contributions
 disl+0.024
endant+0.020
 killed+0.019
 Sorry+0.019
mm+0.019
Neg logit contributions
inn-0.020
ches-0.019
 aid-0.019
icky-0.018
 kernel-0.018
Token and
Token ID290
Feature activation+6.03e-01

Pos logit contributions
inn+0.021
nie+0.018
 kernel+0.018
icky+0.017
ud+0.017
Neg logit contributions
 disl-0.028
 Gig-0.023
 statues-0.022
bows-0.022
 killed-0.022
Token scare
Token ID19437
Feature activation-2.20e-01

Pos logit contributions
 disl+0.017
endant+0.014
mm+0.014
bows+0.013
 Gig+0.013
Neg logit contributions
inn-0.014
 aid-0.014
ches-0.014
 kernel-0.013
icky-0.013
Token her
Token ID607
Feature activation+2.69e-01

Pos logit contributions
inn+0.005
ches+0.004
icky+0.004
 kernel+0.004
nie+0.004
Neg logit contributions
 disl-0.007
 killed-0.006
 Gig-0.006
 Sorry-0.006
Thank-0.006
Token and
Token ID290
Feature activation+6.49e-01

Pos logit contributions
 disl+0.045
 killed+0.036
 Sorry+0.036
 Gig+0.036
endant+0.036
Neg logit contributions
inn-0.028
ches-0.024
icky-0.024
 kernel-0.023
nie-0.023
Token cozy
Token ID37438
Feature activation+1.55e+00

Pos logit contributions
 disl+0.017
 statues+0.015
bows+0.015
endant+0.015
 Gig+0.014
Neg logit contributions
 scrub-0.015
's-0.014
ches-0.014
'-0.014
nie-0.014
Token in
Token ID287
Feature activation+1.53e+00

Pos logit contributions
 disl+0.051
 killed+0.041
 Sorry+0.041
 Gig+0.041
endant+0.041
Neg logit contributions
inn-0.033
ches-0.029
icky-0.028
 kernel-0.028
nie-0.027
Token her
Token ID607
Feature activation+1.05e+00

Pos logit contributions
 disl+0.050
 killed+0.040
endant+0.040
 Sorry+0.040
bows+0.039
Neg logit contributions
inn-0.034
ches-0.029
icky-0.029
 kernel-0.028
 aid-0.028
Token p
Token ID279
Feature activation+2.04e+00

Pos logit contributions
 disl+0.032
 killed+0.026
 Gig+0.025
 Sorry+0.025
Thank+0.025
Neg logit contributions
inn-0.025
ches-0.022
icky-0.021
 kernel-0.021
nie-0.021
Tokenaj
Token ID1228
Feature activation+4.56e+00

Pos logit contributions
 disl+0.057
Thank+0.047
 Gig+0.046
 killed+0.045
 Sorry+0.045
Neg logit contributions
inn-0.053
ches-0.048
icky-0.047
 aid-0.045
ash-0.045
Tokenamas
Token ID17485
Feature activation+1.87e+00

Pos logit contributions
 disl+0.171
 killed+0.143
 Gig+0.140
 Sorry+0.140
Thank+0.140
Neg logit contributions
inn-0.077
ches-0.065
icky-0.065
nie-0.061
 kernel-0.061
Token,
Token ID11
Feature activation-2.18e-01

Pos logit contributions
 disl+0.060
 killed+0.049
Thank+0.048
 Gig+0.048
 Sorry+0.048
Neg logit contributions
inn-0.041
ches-0.036
icky-0.035
 kernel-0.034
nie-0.034
Token even
Token ID772
Feature activation-3.63e-02

Pos logit contributions
inn+0.006
ches+0.005
icky+0.005
 kernel+0.005
nie+0.005
Neg logit contributions
 disl-0.006
 killed-0.004
 Gig-0.004
Thank-0.004
 Sorry-0.004
Token though
Token ID996
Feature activation-3.44e-01

Pos logit contributions
inn+0.001
icky+0.001
ches+0.001
 kernel+0.001
ud+0.001
Neg logit contributions
 disl-0.001
Thank-0.001
 killed-0.001
 jewels-0.001
 Gig-0.001
Token she
Token ID673
Feature activation+1.62e-02

Pos logit contributions
inn+0.011
ches+0.010
icky+0.009
nie+0.009
ash+0.009
Neg logit contributions
 disl-0.008
 Gig-0.006
 killed-0.006
 jewels-0.006
 statues-0.006
TokenSpot
Token ID32565
Feature activation+8.40e-01

Pos logit contributions
 disl+0.012
Thank+0.010
 killed+0.009
 Gig+0.009
 Sorry+0.009
Neg logit contributions
inn-0.013
icky-0.012
ches-0.012
 kernel-0.012
nie-0.012
Token grow
Token ID1663
Feature activation+2.23e+00

Pos logit contributions
 disl+0.021
 killed+0.016
Thank+0.015
 Sorry+0.015
bows+0.015
Neg logit contributions
inn-0.025
icky-0.022
ches-0.022
nie-0.022
 kernel-0.022
Tokenls
Token ID7278
Feature activation-4.11e-01

Pos logit contributions
 disl+0.051
 killed+0.043
 statues+0.041
 jewels+0.040
bows+0.039
Neg logit contributions
inn-0.066
 aid-0.060
nie-0.060
pron-0.060
 kernel-0.059
Token and
Token ID290
Feature activation+7.17e-01

Pos logit contributions
inn+0.009
nie+0.008
icky+0.008
 kernel+0.008
ches+0.008
Neg logit contributions
 disl-0.013
 killed-0.011
Thank-0.011
 Gig-0.011
 jewels-0.011
Token sn
Token ID3013
Feature activation+8.21e-01

Pos logit contributions
 disl+0.019
 killed+0.015
endant+0.015
 Gig+0.015
Thank+0.015
Neg logit contributions
inn-0.019
ches-0.018
icky-0.017
 kernel-0.017
 aid-0.017
Tokenarl
Token ID7063
Feature activation+4.55e+00

Pos logit contributions
 disl+0.025
 killed+0.020
Thank+0.020
 Sorry+0.020
 Gig+0.019
Neg logit contributions
inn-0.020
ches-0.018
icky-0.018
 kernel-0.017
nie-0.017
Tokens
Token ID82
Feature activation+2.93e-04

Pos logit contributions
 disl+0.148
 killed+0.122
 Sorry+0.120
 Gig+0.119
bows+0.119
Neg logit contributions
inn-0.096
ches-0.084
nie-0.082
icky-0.081
 kernel-0.081
Token.
Token ID13
Feature activation+1.01e+00

Pos logit contributions
 disl+0.000
 killed+0.000
Thank+0.000
 jewels+0.000
 Gig+0.000
Neg logit contributions
inn-0.000
nie-0.000
icky-0.000
ash-0.000
oby-0.000
Token He
Token ID679
Feature activation+1.87e-01

Pos logit contributions
 disl+0.025
 Gig+0.020
 killed+0.019
Thank+0.019
 Sorry+0.019
Neg logit contributions
inn-0.029
ches-0.027
nie-0.027
 kernel-0.026
icky-0.026
Token tries
Token ID8404
Feature activation-1.18e+00

Pos logit contributions
 disl+0.005
 killed+0.004
 Gig+0.004
 Sorry+0.004
Thank+0.004
Neg logit contributions
inn-0.005
ches-0.005
icky-0.005
 kernel-0.005
nie-0.005
Token to
Token ID284
Feature activation+4.17e-01

Pos logit contributions
inn+0.029
nie+0.027
 kernel+0.026
ler+0.026
ches+0.026
Neg logit contributions
 disl-0.034
 killed-0.029
 Gig-0.028
Thank-0.027
 Gold-0.027
Token took
Token ID1718
Feature activation-8.59e-01

Pos logit contributions
 disl+0.030
 Sorry+0.022
endant+0.021
bows+0.021
 statues+0.021
Neg logit contributions
inn-0.027
ches-0.025
nie-0.024
'-0.024
 kernel-0.024
Token their
Token ID511
Feature activation+1.02e+00

Pos logit contributions
inn+0.020
pron+0.017
nie+0.017
icky+0.017
 kernel+0.017
Neg logit contributions
 disl-0.025
 killed-0.021
 Gig-0.021
 Tri-0.021
 jewels-0.021
Token hats
Token ID23910
Feature activation+9.14e-01

Pos logit contributions
 disl+0.031
Thank+0.026
 Sorry+0.025
bows+0.025
mm+0.025
Neg logit contributions
inn-0.023
 aid-0.022
ches-0.022
 chair-0.021
 kernel-0.020
Token and
Token ID290
Feature activation+1.25e+00

Pos logit contributions
 disl+0.029
 killed+0.024
 Gig+0.024
bows+0.024
endant+0.024
Neg logit contributions
inn-0.019
icky-0.017
ches-0.016
nie-0.016
 kernel-0.016
Token bin
Token ID9874
Feature activation+2.57e+00

Pos logit contributions
 disl+0.038
 Sorry+0.031
bows+0.031
endant+0.030
mm+0.030
Neg logit contributions
inn-0.027
ches-0.026
 aid-0.025
 kernel-0.024
 chair-0.024
Tokenocular
Token ID37320
Feature activation+4.51e+00

Pos logit contributions
 disl+0.059
 Sorry+0.042
 killed+0.041
Thank+0.041
 Gig+0.040
Neg logit contributions
inn-0.082
ches-0.075
icky-0.073
 kernel-0.073
 aid-0.073
Tokens
Token ID82
Feature activation+7.04e-01

Pos logit contributions
 disl+0.176
Thank+0.144
 Sorry+0.144
 killed+0.143
 Gig+0.142
Neg logit contributions
inn-0.072
ches-0.066
icky-0.056
 kernel-0.056
nie-0.055
Token and
Token ID290
Feature activation+1.26e+00

Pos logit contributions
 disl+0.027
 Sorry+0.022
Thank+0.022
 killed+0.022
 Gig+0.022
Neg logit contributions
inn-0.011
ches-0.010
 aid-0.009
icky-0.009
 kernel-0.009
Token stuffed
Token ID22259
Feature activation+3.48e-01

Pos logit contributions
 disl+0.039
 Sorry+0.034
mm+0.033
endant+0.031
bows+0.031
Neg logit contributions
 aid-0.024
ches-0.024
 chair-0.024
inn-0.024
 scrub-0.024
Token animals
Token ID4695
Feature activation+1.74e+00

Pos logit contributions
 disl+0.011
 Sorry+0.009
endant+0.008
Thank+0.008
 killed+0.008
Neg logit contributions
inn-0.008
ches-0.008
icky-0.007
 kernel-0.007
nie-0.007
Token and
Token ID290
Feature activation+1.32e+00

Pos logit contributions
 disl+0.051
 killed+0.042
 jewels+0.041
endant+0.040
 Gig+0.040
Neg logit contributions
inn-0.043
icky-0.038
nie-0.037
ches-0.036
 kernel-0.036
Token and
Token ID290
Feature activation+7.23e-01

Pos logit contributions
inn+0.011
ches+0.010
ool+0.010
icky+0.009
nie+0.009
Neg logit contributions
 disl-0.008
 Gig-0.007
Thank-0.007
 statues-0.007
 jewels-0.007
Token he
Token ID339
Feature activation-6.41e-01

Pos logit contributions
 disl+0.021
endant+0.017
 killed+0.016
 Sorry+0.016
bows+0.016
Neg logit contributions
inn-0.018
ches-0.016
icky-0.016
 kernel-0.016
nie-0.016
Token noticed
Token ID6810
Feature activation+4.68e-01

Pos logit contributions
inn+0.020
icky+0.018
 kernel+0.017
ches+0.017
 aid+0.017
Neg logit contributions
 disl-0.014
 killed-0.012
Thank-0.011
 statues-0.010
 Gig-0.010
Token something
Token ID1223
Feature activation+1.13e+00

Pos logit contributions
 disl+0.012
 killed+0.009
 Gig+0.009
 statues+0.009
endant+0.009
Neg logit contributions
inn-0.014
ches-0.012
icky-0.012
nie-0.012
 kernel-0.012
Token shiny
Token ID22441
Feature activation-7.14e-01

Pos logit contributions
 disl+0.023
 killed+0.017
 statues+0.016
 jewels+0.016
 Tri+0.016
Neg logit contributions
inn-0.037
nie-0.035
icky-0.034
ud-0.034
ches-0.034
Token wed
Token ID29445
Feature activation-6.06e+00

Pos logit contributions
inn+0.015
icky+0.013
ches+0.013
 aid+0.013
nie+0.013
Neg logit contributions
 disl-0.023
 killed-0.019
endant-0.019
 jewels-0.019
bows-0.019
Tokenged
Token ID2004
Feature activation-3.41e+00

Pos logit contributions
 crib+0.164
 mat+0.162
 aid+0.162
icky+0.159
 chair+0.157
Neg logit contributions
 disl-0.125
 killed-0.110
 Gig-0.104
 Tri-0.102
 jewels-0.101
Token between
Token ID1022
Feature activation-2.88e+00

Pos logit contributions
inn+0.067
ches+0.059
 kernel+0.059
icky+0.059
 aid+0.058
Neg logit contributions
 disl-0.110
 killed-0.093
 jewels-0.093
 Gig-0.092
 Tri-0.092
Token some
Token ID617
Feature activation-3.97e-01

Pos logit contributions
inn+0.065
ches+0.061
nie+0.059
 kernel+0.057
pron+0.055
Neg logit contributions
 disl-0.086
 jewels-0.072
 Gig-0.072
 Tri-0.072
 killed-0.071
Token branches
Token ID13737
Feature activation-1.49e+00

Pos logit contributions
inn+0.011
ches+0.010
icky+0.010
nie+0.010
 kernel+0.010
Neg logit contributions
 disl-0.010
 killed-0.008
 jewels-0.008
 statues-0.008
endant-0.008
Token.
Token ID13
Feature activation-5.56e-01

Pos logit contributions
inn+0.039
nie+0.036
Alex+0.035
icky+0.034
 aid+0.034
Neg logit contributions
 disl-0.037
 killed-0.031
endant-0.030
bows-0.030
 Gig-0.029
Token so
Token ID523
Feature activation+9.88e-02

Pos logit contributions
inn+0.019
ches+0.017
icky+0.017
 kernel+0.016
nie+0.016
Neg logit contributions
 disl-0.022
 killed-0.018
Thank-0.017
 Gig-0.017
 Sorry-0.017
Token he
Token ID339
Feature activation-9.55e-01

Pos logit contributions
 disl+0.003
bows+0.003
endant+0.003
 Sorry+0.003
Thank+0.003
Neg logit contributions
inn-0.002
 kernel-0.002
icky-0.002
ches-0.002
 aid-0.002
Token asked
Token ID1965
Feature activation-1.42e-01

Pos logit contributions
inn+0.031
icky+0.029
ches+0.028
 kernel+0.028
 aid+0.027
Neg logit contributions
 disl-0.020
 killed-0.015
Thank-0.015
 Gig-0.015
 Sorry-0.014
Token the
Token ID262
Feature activation-3.99e-01

Pos logit contributions
inn+0.004
 kernel+0.003
ches+0.003
ud+0.003
icky+0.003
Neg logit contributions
 disl-0.004
 Gig-0.003
 jewels-0.003
 Tri-0.003
 statues-0.003
Token ch
Token ID442
Feature activation-6.12e-01

Pos logit contributions
inn+0.009
icky+0.008
 aid+0.008
ches+0.008
 kernel+0.008
Neg logit contributions
 disl-0.012
endant-0.010
 killed-0.010
 Sorry-0.010
 Gig-0.010
Tokename
Token ID480
Feature activation-5.71e+00

Pos logit contributions
inn+0.014
ches+0.013
 kernel+0.013
nie+0.012
 aid+0.012
Neg logit contributions
 disl-0.019
 killed-0.015
endant-0.015
 Tri-0.014
 Gig-0.014
Tokenleon
Token ID38970
Feature activation-1.84e+00

Pos logit contributions
inn+0.112
ud+0.101
 mat+0.095
ches+0.095
nie+0.094
Neg logit contributions
 disl-0.176
 Tri-0.151
 Gig-0.151
 lucky-0.146
 jewels-0.145
Token to
Token ID284
Feature activation-2.30e-01

Pos logit contributions
inn+0.040
ches+0.034
icky+0.033
 kernel+0.033
nie+0.033
Neg logit contributions
 disl-0.060
 killed-0.049
 Gig-0.049
endant-0.048
bows-0.048
Token play
Token ID711
Feature activation-2.71e-01

Pos logit contributions
inn+0.006
ches+0.006
 aid+0.006
 kernel+0.006
icky+0.006
Neg logit contributions
 disl-0.006
endant-0.005
 killed-0.004
bows-0.004
 Gig-0.004
Token with
Token ID351
Feature activation-8.00e-01

Pos logit contributions
inn+0.007
nie+0.007
ud+0.007
icky+0.007
ches+0.007
Neg logit contributions
 disl-0.007
Thank-0.006
 killed-0.005
 jewels-0.005
 statues-0.005
Token him
Token ID683
Feature activation-3.10e-01

Pos logit contributions
inn+0.018
ches+0.016
icky+0.016
 kernel+0.015
nie+0.015
Neg logit contributions
 disl-0.025
 killed-0.021
 Gig-0.020
Thank-0.020
 statues-0.020
Token Emma
Token ID18966
Feature activation-5.79e-02

Pos logit contributions
 disl+0.014
 killed+0.011
 Gig+0.011
 Sorry+0.011
Thank+0.011
Neg logit contributions
inn-0.010
ches-0.009
icky-0.008
 kernel-0.008
nie-0.008
Token could
Token ID714
Feature activation-1.06e+00

Pos logit contributions
inn+0.001
ches+0.001
 aid+0.001
icky+0.001
nie+0.001
Neg logit contributions
 disl-0.002
 Sorry-0.002
 Gig-0.001
 killed-0.001
endant-0.001
Token hear
Token ID3285
Feature activation+9.34e-01

Pos logit contributions
inn+0.034
 aid+0.032
ches+0.031
icky+0.031
 kernel+0.031
Neg logit contributions
 disl-0.023
 Gig-0.016
 Sorry-0.016
endant-0.016
mm-0.016
Token a
Token ID257
Feature activation+5.83e-02

Pos logit contributions
 disl+0.032
 Sorry+0.027
endant+0.026
mm+0.026
Thank+0.026
Neg logit contributions
inn-0.017
 aid-0.016
ches-0.016
icky-0.016
 Alex-0.015
Token wh
Token ID348
Feature activation+6.34e-01

Pos logit contributions
 disl+0.002
 killed+0.001
endant+0.001
 Gig+0.001
bows+0.001
Neg logit contributions
inn-0.002
ches-0.001
icky-0.001
 kernel-0.001
 aid-0.001
Tokeninn
Token ID3732
Feature activation-5.61e+00

Pos logit contributions
 disl+0.017
 killed+0.013
endant+0.013
mm+0.012
vell+0.012
Neg logit contributions
 chair-0.015
ches-0.014
 mat-0.014
 aid-0.014
 kernel-0.014
Tokenying
Token ID1112
Feature activation-2.06e+00

Pos logit contributions
inn+0.107
 crib+0.094
Alex+0.091
ud+0.088
 DVD+0.088
Neg logit contributions
 disl-0.166
bows-0.149
 statues-0.146
 Tri-0.140
 jewels-0.137
Token sound
Token ID2128
Feature activation-1.01e-01

Pos logit contributions
inn+0.055
icky+0.047
ches+0.045
ud+0.045
nie+0.045
Neg logit contributions
 disl-0.053
 statues-0.048
 jewels-0.047
bows-0.047
 Tri-0.046
Token.
Token ID13
Feature activation-6.47e-01

Pos logit contributions
inn+0.002
ches+0.002
icky+0.002
 kernel+0.002
nie+0.002
Neg logit contributions
 disl-0.003
 killed-0.003
Thank-0.003
bows-0.003
 Gig-0.003
Token She
Token ID1375
Feature activation+6.77e-02

Pos logit contributions
inn+0.020
ches+0.018
 kernel+0.018
icky+0.018
nie+0.017
Neg logit contributions
 disl-0.015
Thank-0.011
 Gig-0.011
 Sorry-0.011
 Thank-0.011
Token stepped
Token ID10764
Feature activation-6.18e-01

Pos logit contributions
 disl+0.002
 Gig+0.002
 Sorry+0.002
 killed+0.002
endant+0.002
Neg logit contributions
inn-0.002
ches-0.002
icky-0.001
nie-0.001
 kernel-0.001
Token tried
Token ID3088
Feature activation-2.36e+00

Pos logit contributions
 disl+0.005
 Gig+0.004
endant+0.004
 Sorry+0.004
 Tri+0.004
Neg logit contributions
inn-0.006
ches-0.005
icky-0.005
 kernel-0.005
nie-0.005
Token to
Token ID284
Feature activation+3.32e-01

Pos logit contributions
inn+0.057
 kernel+0.049
ches+0.046
nie+0.045
pron+0.045
Neg logit contributions
 disl-0.075
 killed-0.064
bows-0.058
 Gig-0.057
 Sorry-0.057
Token catch
Token ID4929
Feature activation-1.80e+00

Pos logit contributions
 disl+0.009
endant+0.008
 Gig+0.007
 statues+0.007
 Tri+0.007
Neg logit contributions
inn-0.008
 aid-0.008
ches-0.008
icky-0.007
 kernel-0.007
Token the
Token ID262
Feature activation-1.51e+00

Pos logit contributions
inn+0.062
pron+0.055
nie+0.054
 kernel+0.054
 aid+0.053
Neg logit contributions
 disl-0.038
 killed-0.029
 Gig-0.027
 Sorry-0.026
Thank-0.026
Token k
Token ID479
Feature activation-1.62e+00

Pos logit contributions
inn+0.045
icky+0.039
ches+0.038
 aid+0.037
nie+0.037
Neg logit contributions
 disl-0.037
 killed-0.032
Thank-0.031
 Gig-0.031
 lucky-0.030
Tokenang
Token ID648
Feature activation-5.39e+00

Pos logit contributions
inn+0.046
nie+0.045
 aid+0.045
icky+0.043
pron+0.043
Neg logit contributions
 disl-0.031
 killed-0.030
Thank-0.029
 Sorry-0.027
 tou-0.026
Tokenaroo
Token ID38049
Feature activation-2.14e+00

Pos logit contributions
inn+0.172
pron+0.167
oby+0.166
 aid+0.165
icky+0.165
Neg logit contributions
 disl-0.087
 killed-0.076
 Gig-0.074
 Sorry-0.068
 Tri-0.068
Token.
Token ID13
Feature activation+5.01e-01

Pos logit contributions
inn+0.066
icky+0.056
Alex+0.055
pron+0.055
 kernel+0.055
Neg logit contributions
 disl-0.050
 killed-0.040
 Gig-0.038
bows-0.037
 lucky-0.037
Token It
Token ID632
Feature activation+1.77e-01

Pos logit contributions
 disl+0.016
bows+0.013
endant+0.013
 statues+0.013
 killed+0.013
Neg logit contributions
inn-0.011
icky-0.010
 aid-0.009
ches-0.009
 Alex-0.009
Token was
Token ID373
Feature activation-3.61e-01

Pos logit contributions
 disl+0.006
 Gig+0.005
endant+0.005
 Sorry+0.005
Thank+0.005
Neg logit contributions
inn-0.004
ches-0.003
icky-0.003
nie-0.003
 kernel-0.003
Token not
Token ID407
Feature activation-8.05e-02

Pos logit contributions
inn+0.011
icky+0.010
ches+0.010
 kernel+0.010
 aid+0.009
Neg logit contributions
 disl-0.009
 killed-0.007
Thank-0.006
 Gig-0.006
endant-0.006
Token and
Token ID290
Feature activation+1.57e-01

Pos logit contributions
inn+0.008
ches+0.007
icky+0.007
 kernel+0.007
 aid+0.007
Neg logit contributions
 disl-0.013
 killed-0.011
 Gig-0.010
Thank-0.010
bows-0.010
Token the
Token ID262
Feature activation-1.14e-01

Pos logit contributions
 disl+0.004
 killed+0.003
 Sorry+0.003
Thank+0.003
 Gig+0.003
Neg logit contributions
inn-0.004
ches-0.004
icky-0.004
 aid-0.004
 kernel-0.004
Token picture
Token ID4286
Feature activation+1.29e+00

Pos logit contributions
inn+0.002
 aid+0.002
ches+0.002
 kernel+0.002
nie+0.002
Neg logit contributions
 disl-0.004
 Gig-0.003
 Sorry-0.003
endant-0.003
 killed-0.003
Token was
Token ID373
Feature activation-8.71e-01

Pos logit contributions
 disl+0.030
 killed+0.027
bows+0.025
Thank+0.024
 Sorry+0.024
Neg logit contributions
inn-0.038
icky-0.032
 aid-0.032
nie-0.032
 kernel-0.031
Token sm
Token ID895
Feature activation+1.57e-01

Pos logit contributions
inn+0.026
icky+0.024
ches+0.024
 aid+0.024
nie+0.024
Neg logit contributions
 disl-0.019
 killed-0.016
endant-0.015
 jewels-0.015
Thank-0.015
Tokenud
Token ID463
Feature activation-5.39e+00

Pos logit contributions
 disl+0.005
 killed+0.004
Thank+0.004
 Gig+0.004
endant+0.004
Neg logit contributions
inn-0.004
ches-0.003
icky-0.003
 kernel-0.003
 aid-0.003
Tokengy
Token ID1360
Feature activation+8.28e-02

Pos logit contributions
inn+0.124
 aid+0.115
Alex+0.107
icky+0.105
 kernel+0.104
Neg logit contributions
 disl-0.151
 killed-0.128
bows-0.126
 Gig-0.122
 jewels-0.119
Token.
Token ID13
Feature activation+5.51e-02

Pos logit contributions
 disl+0.003
Thank+0.002
 killed+0.002
 Sorry+0.002
 Gig+0.002
Neg logit contributions
inn-0.002
ches-0.002
icky-0.001
 kernel-0.001
nie-0.001
Token Mom
Token ID11254
Feature activation+8.78e-01

Pos logit contributions
 disl+0.002
 killed+0.001
endant+0.001
 Gig+0.001
bows+0.001
Neg logit contributions
inn-0.001
ches-0.001
icky-0.001
nie-0.001
 kernel-0.001
Tokenmy
Token ID1820
Feature activation+8.45e-02

Pos logit contributions
 disl+0.020
 killed+0.017
Thank+0.017
endant+0.016
 Gig+0.016
Neg logit contributions
inn-0.025
 aid-0.022
 kernel-0.022
icky-0.022
 mat-0.022
Token said
Token ID531
Feature activation+6.35e-01

Pos logit contributions
 disl+0.002
 killed+0.001
Thank+0.001
 Gig+0.001
endant+0.001
Neg logit contributions
inn-0.003
icky-0.003
 kernel-0.002
 aid-0.002
ches-0.002
Token house
Token ID2156
Feature activation+2.62e+00

Pos logit contributions
 disl+0.009
mm+0.008
endant+0.008
bows+0.008
 Sorry+0.008
Neg logit contributions
 corner-0.004
 crib-0.004
 chair-0.003
 aid-0.003
inn-0.003
Token had
Token ID550
Feature activation-2.85e-01

Pos logit contributions
 disl+0.076
 killed+0.066
 statues+0.063
Thank+0.062
endant+0.062
Neg logit contributions
inn-0.063
ches-0.055
icky-0.055
nie-0.053
 kernel-0.053
Token a
Token ID257
Feature activation+8.92e-02

Pos logit contributions
inn+0.007
icky+0.007
ches+0.007
 aid+0.007
 kernel+0.007
Neg logit contributions
 disl-0.008
 Sorry-0.006
mm-0.006
endant-0.006
 Gig-0.006
Token tall
Token ID7331
Feature activation-5.67e-01

Pos logit contributions
 disl+0.002
 killed+0.002
Thank+0.002
 Gig+0.002
bows+0.002
Neg logit contributions
inn-0.002
ches-0.002
icky-0.002
 kernel-0.002
 aid-0.002
Token cane
Token ID33009
Feature activation-7.22e-01

Pos logit contributions
inn+0.013
ches+0.012
icky+0.012
 kernel+0.011
nie+0.011
Neg logit contributions
 disl-0.017
 killed-0.014
 Gig-0.014
 Sorry-0.014
Thank-0.014
Token leaning
Token ID21804
Feature activation-5.35e+00

Pos logit contributions
inn+0.018
icky+0.015
ches+0.015
nie+0.015
 kernel+0.015
Neg logit contributions
 disl-0.021
 killed-0.018
endant-0.017
Thank-0.017
 jewels-0.017
Token against
Token ID1028
Feature activation-2.91e+00

Pos logit contributions
icky+0.116
oons+0.116
nie+0.112
inn+0.112
ud+0.111
Neg logit contributions
Thank-0.127
 Tri-0.127
ocular-0.125
hy-0.124
 disl-0.118
Token its
Token ID663
Feature activation-3.81e-01

Pos logit contributions
inn+0.079
ches+0.073
nie+0.069
pron+0.068
ash+0.068
Neg logit contributions
 disl-0.074
 Gig-0.067
 killed-0.064
 jewels-0.062
 statues-0.062
Token front
Token ID2166
Feature activation-3.89e-01

Pos logit contributions
inn+0.008
ches+0.007
icky+0.007
 kernel+0.007
nie+0.007
Neg logit contributions
 disl-0.013
 killed-0.010
 Gig-0.010
 Sorry-0.010
Thank-0.010
Token door
Token ID3420
Feature activation+5.03e-01

Pos logit contributions
inn+0.010
ches+0.009
icky+0.009
 kernel+0.008
nie+0.008
Neg logit contributions
 disl-0.011
 statues-0.009
endant-0.009
 killed-0.009
bows-0.009
Token.
Token ID13
Feature activation-1.63e-01

Pos logit contributions
 disl+0.016
 killed+0.013
endant+0.013
bows+0.012
 Gig+0.012
Neg logit contributions
inn-0.011
ches-0.010
icky-0.010
 kernel-0.010
nie-0.010
Token forgive
Token ID20927
Feature activation+3.78e-01

Pos logit contributions
 disl+0.010
endant+0.009
 statues+0.009
 killed+0.008
bows+0.008
Neg logit contributions
inn-0.010
ches-0.009
 aid-0.009
icky-0.009
nie-0.008
Token than
Token ID621
Feature activation+5.18e-01

Pos logit contributions
 disl+0.012
 killed+0.010
Thank+0.010
 Gig+0.010
 Sorry+0.010
Neg logit contributions
inn-0.008
ches-0.007
icky-0.007
 kernel-0.007
nie-0.007
Token to
Token ID284
Feature activation+1.40e+00

Pos logit contributions
 disl+0.017
endant+0.013
 Sorry+0.013
 Gig+0.013
mm+0.013
Neg logit contributions
inn-0.011
ches-0.010
icky-0.009
nie-0.009
 aid-0.009
Token hold
Token ID1745
Feature activation-2.85e+00

Pos logit contributions
 disl+0.037
endant+0.031
 killed+0.030
 Gig+0.029
 Tri+0.029
Neg logit contributions
inn-0.036
ches-0.033
icky-0.032
 aid-0.032
nie-0.032
Token gr
Token ID1036
Feature activation+1.53e+00

Pos logit contributions
inn+0.077
 kernel+0.068
icky+0.068
ches+0.067
 aid+0.066
Neg logit contributions
 disl-0.078
 killed-0.060
 Gig-0.059
 jewels-0.058
Thank-0.058
Tokenud
Token ID463
Feature activation-5.32e+00

Pos logit contributions
 disl+0.042
 killed+0.033
 Gig+0.032
 Sorry+0.032
Thank+0.032
Neg logit contributions
inn-0.041
ches-0.037
icky-0.037
nie-0.036
 kernel-0.036
Tokenges
Token ID3212
Feature activation-2.12e+00

Pos logit contributions
inn+0.123
 kernel+0.108
icky+0.104
 aid+0.104
 mat+0.103
Neg logit contributions
 disl-0.161
 Gig-0.125
 killed-0.125
 Tri-0.121
bows-0.118
Token.
Token ID13
Feature activation-9.48e-01

Pos logit contributions
inn+0.045
icky+0.038
ches+0.038
 kernel+0.038
nie+0.037
Neg logit contributions
 disl-0.070
 killed-0.057
Thank-0.056
 Gig-0.056
bows-0.056
Token
Token ID220
Feature activation+5.31e-01

Pos logit contributions
inn+0.021
icky+0.019
ches+0.018
 aid+0.018
nie+0.017
Neg logit contributions
 disl-0.030
 killed-0.025
 statues-0.024
endant-0.024
 jewels-0.024
Token
Token ID198
Feature activation-1.07e+00

Pos logit contributions
 disl+0.017
 killed+0.014
 jewels+0.014
 statues+0.013
endant+0.013
Neg logit contributions
inn-0.012
icky-0.011
ches-0.010
 aid-0.010
nie-0.010
Token
Token ID198
Feature activation-1.81e-01

Pos logit contributions
inn+0.026
ches+0.023
icky+0.023
 kernel+0.023
nie+0.022
Neg logit contributions
 disl-0.032
 killed-0.025
Thank-0.025
 Gig-0.025
 Sorry-0.024
Token there
Token ID612
Feature activation-1.62e+00

Pos logit contributions
inn+0.051
ches+0.043
icky+0.043
nie+0.041
ud+0.041
Neg logit contributions
 disl-0.052
 killed-0.041
 Sorry-0.040
 Gig-0.040
 statues-0.039
Token's
Token ID338
Feature activation-1.10e-02

Pos logit contributions
inn+0.040
ches+0.034
icky+0.034
 kernel+0.033
nie+0.033
Neg logit contributions
 disl-0.049
 killed-0.039
 Sorry-0.038
 Gig-0.038
Thank-0.038
Token a
Token ID257
Feature activation-8.39e-01

Pos logit contributions
inn+0.000
ches+0.000
icky+0.000
 aid+0.000
 kernel+0.000
Neg logit contributions
 disl-0.000
 Sorry-0.000
endant-0.000
bows-0.000
Thank-0.000
Token light
Token ID1657
Feature activation-1.57e+00

Pos logit contributions
inn+0.023
ches+0.021
icky+0.021
 kernel+0.021
 aid+0.020
Neg logit contributions
 disl-0.022
 killed-0.017
endant-0.016
Thank-0.016
 Gig-0.016
Token up
Token ID510
Feature activation-2.71e+00

Pos logit contributions
inn+0.043
icky+0.037
ches+0.035
ud+0.035
nie+0.035
Neg logit contributions
 disl-0.042
 killed-0.035
 Sorry-0.034
bows-0.034
 statues-0.033
Token ahead
Token ID4058
Feature activation-5.30e+00

Pos logit contributions
inn+0.071
icky+0.063
ches+0.063
 kernel+0.061
nie+0.059
Neg logit contributions
 disl-0.073
 killed-0.060
 Gig-0.059
Thank-0.058
 jewels-0.058
Token.
Token ID13
Feature activation-5.47e-01

Pos logit contributions
inn+0.167
 kernel+0.146
 aid+0.145
Alex+0.144
ches+0.143
Neg logit contributions
 disl-0.097
 Thank-0.080
 Gig-0.080
 killed-0.078
 Sorry-0.077
Token We
Token ID775
Feature activation-1.87e+00

Pos logit contributions
inn+0.014
ches+0.012
icky+0.012
 aid+0.012
nie+0.012
Neg logit contributions
 disl-0.016
 killed-0.012
endant-0.012
bows-0.012
 jewels-0.012
Token just
Token ID655
Feature activation-1.02e-02

Pos logit contributions
inn+0.046
ches+0.046
'+0.043
nie+0.041
 kernel+0.040
Neg logit contributions
 disl-0.053
mm-0.043
 statues-0.041
endant-0.041
 Gig-0.041
Token need
Token ID761
Feature activation-1.61e+00

Pos logit contributions
inn+0.000
ches+0.000
nie+0.000
 aid+0.000
'+0.000
Neg logit contributions
 disl-0.000
mm-0.000
bows-0.000
 Gig-0.000
endant-0.000
Token to
Token ID284
Feature activation+4.79e-01

Pos logit contributions
inn+0.031
ches+0.027
icky+0.027
 kernel+0.026
 aid+0.025
Neg logit contributions
 disl-0.056
 killed-0.045
 Sorry-0.045
Thank-0.045
endant-0.045
Token her
Token ID607
Feature activation+2.88e-01

Pos logit contributions
 disl+0.012
endant+0.009
Thank+0.009
 Gig+0.009
 killed+0.009
Neg logit contributions
inn-0.010
ches-0.009
icky-0.009
nie-0.009
 aid-0.009
Token drawings
Token ID23388
Feature activation+2.78e+00

Pos logit contributions
 disl+0.009
 Gig+0.007
 killed+0.007
 Sorry+0.007
Thank+0.007
Neg logit contributions
inn-0.007
ches-0.006
icky-0.006
 aid-0.006
nie-0.006
Token would
Token ID561
Feature activation+7.10e-01

Pos logit contributions
 disl+0.085
 Gig+0.074
 Sorry+0.068
Thank+0.067
mm+0.067
Neg logit contributions
ches-0.060
inn-0.060
ide-0.055
'-0.054
icky-0.053
Token get
Token ID651
Feature activation-2.67e-01

Pos logit contributions
 disl+0.021
 Gig+0.017
endant+0.017
 Sorry+0.017
 killed+0.017
Neg logit contributions
inn-0.016
ches-0.015
icky-0.014
 aid-0.014
 kernel-0.014
Token sm
Token ID895
Feature activation-4.68e-01

Pos logit contributions
inn+0.006
ches+0.006
icky+0.006
nie+0.005
 kernel+0.005
Neg logit contributions
 disl-0.008
mm-0.007
 Sorry-0.007
 Gig-0.006
Thank-0.006
Tokenud
Token ID463
Feature activation-5.27e+00

Pos logit contributions
inn+0.011
ches+0.010
icky+0.010
 kernel+0.010
nie+0.009
Neg logit contributions
 disl-0.014
 killed-0.011
Thank-0.011
 Gig-0.011
 Sorry-0.011
Tokenged
Token ID2004
Feature activation-2.30e+00

Pos logit contributions
inn+0.076
 aid+0.064
 kernel+0.059
Alex+0.055
 mat+0.053
Neg logit contributions
 disl-0.204
bows-0.179
 killed-0.169
 Gig-0.166
 jewels-0.166
Token because
Token ID780
Feature activation+4.09e-01

Pos logit contributions
inn+0.046
ches+0.040
icky+0.039
nie+0.038
 kernel+0.037
Neg logit contributions
 disl-0.079
 killed-0.064
 Sorry-0.064
Thank-0.063
 Gig-0.063
Token the
Token ID262
Feature activation-4.28e-01

Pos logit contributions
 disl+0.010
 killed+0.007
 statues+0.007
 jewels+0.007
 Sorry+0.007
Neg logit contributions
inn-0.012
ches-0.011
 aid-0.011
 kernel-0.011
nie-0.011
Token paper
Token ID3348
Feature activation+1.19e-01

Pos logit contributions
inn+0.010
ches+0.009
 kernel+0.009
 aid+0.009
nie+0.009
Neg logit contributions
 disl-0.012
 Gig-0.010
 killed-0.010
 Sorry-0.010
endant-0.009
Token wasn
Token ID2492
Feature activation-4.34e-01

Pos logit contributions
 disl+0.004
 Gig+0.003
 killed+0.003
Thank+0.003
 Sorry+0.003
Neg logit contributions
inn-0.002
ches-0.002
icky-0.002
 kernel-0.002
nie-0.002
Token,
Token ID11
Feature activation-1.88e+00

Pos logit contributions
 disl+0.008
bows+0.006
endant+0.006
 Gig+0.006
 jewels+0.006
Neg logit contributions
inn-0.007
ches-0.006
 kernel-0.006
icky-0.006
nie-0.006
Token waiting
Token ID4953
Feature activation-4.67e-01

Pos logit contributions
inn+0.046
ches+0.041
 kernel+0.040
icky+0.040
 aid+0.040
Neg logit contributions
 disl-0.055
 killed-0.044
 Sorry-0.043
endant-0.043
bows-0.043
Token for
Token ID329
Feature activation-3.98e-01

Pos logit contributions
inn+0.008
ches+0.007
icky+0.007
 kernel+0.007
nie+0.007
Neg logit contributions
 disl-0.017
 killed-0.014
 Gig-0.014
endant-0.014
Thank-0.014
Token the
Token ID262
Feature activation-1.20e+00

Pos logit contributions
inn+0.009
ches+0.008
icky+0.008
 kernel+0.008
 aid+0.008
Neg logit contributions
 disl-0.013
 killed-0.010
endant-0.010
 Sorry-0.010
bows-0.010
Token k
Token ID479
Feature activation-1.43e+00

Pos logit contributions
inn+0.029
ches+0.026
icky+0.026
 kernel+0.025
nie+0.025
Neg logit contributions
 disl-0.036
 killed-0.029
 Gig-0.028
Thank-0.028
 Sorry-0.028
Tokenang
Token ID648
Feature activation-5.10e+00

Pos logit contributions
inn+0.038
nie+0.037
 aid+0.036
icky+0.036
oby+0.035
Neg logit contributions
 disl-0.031
 killed-0.030
Thank-0.029
endant-0.028
 Gig-0.028
Tokenaroo
Token ID38049
Feature activation-1.95e+00

Pos logit contributions
inn+0.153
icky+0.151
oby+0.149
 studio+0.145
 aid+0.144
Neg logit contributions
 disl-0.093
 Gig-0.089
 killed-0.084
 tou-0.077
 Twe-0.074
Token to
Token ID284
Feature activation-7.51e-02

Pos logit contributions
inn+0.044
icky+0.037
ches+0.037
 kernel+0.036
nie+0.036
Neg logit contributions
 disl-0.062
 killed-0.050
 Gig-0.050
endant-0.049
 jewels-0.049
Token move
Token ID1445
Feature activation-2.52e+00

Pos logit contributions
inn+0.002
ches+0.002
 aid+0.002
 kernel+0.002
icky+0.002
Neg logit contributions
 disl-0.002
endant-0.001
bows-0.001
 Sorry-0.001
 killed-0.001
Token.
Token ID13
Feature activation-7.61e-01

Pos logit contributions
inn+0.063
pron+0.057
icky+0.056
 kernel+0.056
ches+0.056
Neg logit contributions
 disl-0.067
 Gig-0.056
 jewels-0.055
 killed-0.055
 Tri-0.054
Token
Token ID198
Feature activation-9.34e-01

Pos logit contributions
inn+0.019
ches+0.017
icky+0.016
 kernel+0.016
nie+0.016
Neg logit contributions
 disl-0.023
 killed-0.018
 Sorry-0.018
endant-0.018
 Gig-0.018
Token he
Token ID339
Feature activation-7.96e-01

Pos logit contributions
inn+0.029
ches+0.027
nie+0.026
 aid+0.026
ash+0.026
Neg logit contributions
 disl-0.023
 killed-0.018
 Gig-0.018
 Sorry-0.017
 Tri-0.017
Token saw
Token ID2497
Feature activation+5.85e-01

Pos logit contributions
inn+0.022
ches+0.020
icky+0.020
 kernel+0.019
 aid+0.019
Neg logit contributions
 disl-0.022
 Sorry-0.016
 killed-0.016
endant-0.016
 Gig-0.016
Token a
Token ID257
Feature activation-3.08e-01

Pos logit contributions
 disl+0.017
 killed+0.013
 Sorry+0.013
endant+0.013
Thank+0.013
Neg logit contributions
inn-0.015
ches-0.013
icky-0.013
 kernel-0.013
 aid-0.012
Token big
Token ID1263
Feature activation-1.59e-01

Pos logit contributions
inn+0.009
ches+0.008
icky+0.008
 kernel+0.008
nie+0.008
Neg logit contributions
 disl-0.008
 killed-0.006
 Gig-0.006
 Sorry-0.006
endant-0.006
Token staff
Token ID3085
Feature activation-2.05e-01

Pos logit contributions
inn+0.004
ches+0.004
icky+0.004
nie+0.004
 aid+0.004
Neg logit contributions
 disl-0.004
 Gig-0.003
 killed-0.003
 jewels-0.003
 Sorry-0.003
Token leaning
Token ID21804
Feature activation-5.09e+00

Pos logit contributions
inn+0.005
nie+0.005
icky+0.005
ches+0.005
 kernel+0.004
Neg logit contributions
 disl-0.005
 killed-0.005
 statues-0.005
endant-0.005
 Tri-0.004
Token against
Token ID1028
Feature activation-3.13e+00

Pos logit contributions
oons+0.128
nie+0.121
 mat+0.115
 panc+0.114
inn+0.112
Neg logit contributions
Thank-0.107
hy-0.105
 tou-0.101
 Tri-0.099
ocular-0.098
Token a
Token ID257
Feature activation-3.04e-01

Pos logit contributions
inn+0.095
pron+0.086
nie+0.086
ches+0.085
ash+0.084
Neg logit contributions
 disl-0.069
 Gig-0.060
 jewels-0.059
 Tri-0.058
 killed-0.057
Token tree
Token ID5509
Feature activation-6.47e-01

Pos logit contributions
inn+0.009
icky+0.008
ud+0.008
ash+0.008
nie+0.008
Neg logit contributions
 disl-0.007
 Gig-0.006
 statues-0.006
 jewels-0.006
 tou-0.006
Token.
Token ID13
Feature activation-5.77e-01

Pos logit contributions
inn+0.019
nie+0.017
Alex+0.017
icky+0.017
oby+0.016
Neg logit contributions
 disl-0.015
 killed-0.012
endant-0.012
bows-0.012
Thank-0.012
Token
Token ID220
Feature activation+6.24e-02

Pos logit contributions
inn+0.016
 kernel+0.015
nie+0.015
 aid+0.015
icky+0.015
Neg logit contributions
 disl-0.014
 Gig-0.011
Thank-0.011
 Tri-0.011
 Sorry-0.011
Token there
Token ID612
Feature activation+3.03e-01

Pos logit contributions
 disl+0.004
 Gig+0.003
Thank+0.003
 killed+0.003
 lucky+0.003
Neg logit contributions
inn-0.008
ches-0.007
nie-0.007
ash-0.007
ud-0.007
Token was
Token ID373
Feature activation-2.19e-01

Pos logit contributions
 disl+0.006
 killed+0.006
 statues+0.006
 Gig+0.006
Thank+0.006
Neg logit contributions
inn-0.009
nie-0.008
ash-0.008
ches-0.008
icky-0.008
Token a
Token ID257
Feature activation-4.57e-01

Pos logit contributions
inn+0.006
ches+0.005
icky+0.005
nie+0.005
 kernel+0.005
Neg logit contributions
 disl-0.006
 killed-0.005
 Gig-0.005
Thank-0.004
endant-0.004
Token big
Token ID1263
Feature activation-1.53e-01

Pos logit contributions
inn+0.014
ches+0.012
icky+0.012
nie+0.012
 kernel+0.012
Neg logit contributions
 disl-0.011
 killed-0.009
 Sorry-0.008
Thank-0.008
 Gig-0.008
Token th
Token ID294
Feature activation+3.32e-03

Pos logit contributions
inn+0.004
ches+0.004
icky+0.004
nie+0.004
ide+0.004
Neg logit contributions
 disl-0.004
 killed-0.003
 jewels-0.003
Thank-0.003
 statues-0.003
Tokenud
Token ID463
Feature activation-5.08e+00

Pos logit contributions
 disl+0.000
 killed+0.000
Thank+0.000
bows+0.000
endant+0.000
Neg logit contributions
inn-0.000
nie-0.000
ches-0.000
 aid-0.000
 kernel-0.000
Token as
Token ID355
Feature activation-3.59e+00

Pos logit contributions
inn+0.119
icky+0.111
 aid+0.110
 crib+0.109
rey+0.107
Neg logit contributions
 disl-0.126
 killed-0.110
drops-0.103
bows-0.102
 Gig-0.102
Token the
Token ID262
Feature activation-4.67e-01

Pos logit contributions
inn+0.095
ches+0.085
icky+0.084
 kernel+0.083
nie+0.082
Neg logit contributions
 disl-0.100
 killed-0.077
 Sorry-0.076
endant-0.076
 Gig-0.076
Token blocks
Token ID7021
Feature activation-2.28e-01

Pos logit contributions
inn+0.011
ches+0.010
icky+0.010
 kernel+0.010
nie+0.010
Neg logit contributions
 disl-0.014
 killed-0.011
 Gig-0.011
 Sorry-0.011
endant-0.011
Token started
Token ID2067
Feature activation-2.19e+00

Pos logit contributions
inn+0.006
icky+0.006
ches+0.006
nie+0.006
 kernel+0.005
Neg logit contributions
 disl-0.006
 killed-0.005
endant-0.004
Thank-0.004
bows-0.004
Token to
Token ID284
Feature activation+5.19e-02

Pos logit contributions
inn+0.044
ches+0.038
nie+0.038
 kernel+0.037
icky+0.036
Neg logit contributions
 disl-0.073
 killed-0.062
bows-0.060
 Gig-0.060
 Tri-0.059
Token he
Token ID339
Feature activation-1.07e+00

Pos logit contributions
 disl+0.028
 killed+0.021
 Gig+0.021
 Sorry+0.021
Thank+0.021
Neg logit contributions
inn-0.027
ches-0.024
icky-0.024
 kernel-0.024
nie-0.023
Token saw
Token ID2497
Feature activation+6.40e-01

Pos logit contributions
inn+0.028
ches+0.025
icky+0.025
 aid+0.024
 kernel+0.024
Neg logit contributions
 disl-0.031
bows-0.024
 Sorry-0.023
 Gig-0.023
 killed-0.023
Token a
Token ID257
Feature activation-4.37e-01

Pos logit contributions
 disl+0.019
 Sorry+0.015
 killed+0.015
Thank+0.015
endant+0.015
Neg logit contributions
inn-0.016
icky-0.014
ches-0.014
 kernel-0.014
 aid-0.013
Token big
Token ID1263
Feature activation-1.13e-01

Pos logit contributions
inn+0.013
ches+0.011
icky+0.011
nie+0.011
 kernel+0.011
Neg logit contributions
 disl-0.011
 killed-0.009
 Gig-0.009
 statues-0.009
endant-0.009
Token ladder
Token ID18002
Feature activation-1.01e+00

Pos logit contributions
inn+0.003
ches+0.003
icky+0.003
nie+0.003
ash+0.003
Neg logit contributions
 disl-0.003
 jewels-0.002
 statues-0.002
 killed-0.002
 Gig-0.002
Token leaning
Token ID21804
Feature activation-5.06e+00

Pos logit contributions
inn+0.029
icky+0.027
nie+0.026
ches+0.025
Alex+0.025
Neg logit contributions
 disl-0.023
 killed-0.020
Thank-0.020
hy-0.020
bows-0.019
Token against
Token ID1028
Feature activation-2.83e+00

Pos logit contributions
oons+0.116
icky+0.115
nie+0.113
ches+0.111
 mat+0.111
Neg logit contributions
Thank-0.118
hy-0.110
 Tri-0.109
ocular-0.108
 Twe-0.102
Token the
Token ID262
Feature activation-4.84e-01

Pos logit contributions
inn+0.076
ches+0.074
icky+0.071
nie+0.069
ash+0.067
Neg logit contributions
 disl-0.071
 Gig-0.062
 Tri-0.061
 jewels-0.060
 killed-0.060
Token fence
Token ID13990
Feature activation-5.37e-01

Pos logit contributions
inn+0.013
ches+0.011
icky+0.011
ash+0.011
 kernel+0.010
Neg logit contributions
 disl-0.013
 statues-0.011
 killed-0.011
 Gig-0.011
Thank-0.011
Token.
Token ID13
Feature activation-3.15e-01

Pos logit contributions
inn+0.017
nie+0.015
icky+0.015
ches+0.015
Alex+0.015
Neg logit contributions
 disl-0.011
ocular-0.009
 statues-0.009
bows-0.009
Thank-0.009
Token He
Token ID679
Feature activation-5.24e-01

Pos logit contributions
inn+0.008
ches+0.008
icky+0.008
 kernel+0.007
nie+0.007
Neg logit contributions
 disl-0.009
 killed-0.007
 Gig-0.007
Thank-0.007
 Sorry-0.006
Token stick
Token ID4859
Feature activation-7.99e-01

Pos logit contributions
 disl+0.001
 killed+0.001
 know+0.001
 Gig+0.001
bows+0.001
Neg logit contributions
inn-0.001
ud-0.001
 kernel-0.001
icky-0.001
nie-0.001
Token the
Token ID262
Feature activation-8.52e-01

Pos logit contributions
inn+0.019
nie+0.018
ud+0.017
icky+0.017
 kernel+0.017
Neg logit contributions
 disl-0.023
 jewels-0.019
 Gig-0.019
 killed-0.019
 Tri-0.018
Token mustache
Token ID49303
Feature activation+4.73e-01

Pos logit contributions
inn+0.022
icky+0.019
ches+0.018
ud+0.018
ide+0.017
Neg logit contributions
 disl-0.025
 jewels-0.021
 killed-0.020
endant-0.020
bows-0.020
Token on
Token ID319
Feature activation+9.02e-03

Pos logit contributions
 disl+0.014
bows+0.012
 killed+0.012
endant+0.011
Thank+0.011
Neg logit contributions
inn-0.011
icky-0.010
nie-0.009
ud-0.009
ches-0.009
Token her
Token ID607
Feature activation-6.48e-02

Pos logit contributions
 disl+0.000
 Gig+0.000
Thank+0.000
 Tri+0.000
 Gold+0.000
Neg logit contributions
inn-0.000
nie-0.000
 kernel-0.000
ches-0.000
ash-0.000
Token upper
Token ID6727
Feature activation-5.05e+00

Pos logit contributions
inn+0.002
ud+0.001
icky+0.001
ash+0.001
ches+0.001
Neg logit contributions
 disl-0.002
 jewels-0.002
endant-0.002
 killed-0.001
 statues-0.001
Token lip
Token ID10645
Feature activation+3.19e-01

Pos logit contributions
inn+0.124
ches+0.110
nie+0.104
 kernel+0.102
Alex+0.101
Neg logit contributions
 disl-0.152
endant-0.117
 Gig-0.117
mm-0.116
 killed-0.116
Token with
Token ID351
Feature activation+1.12e-02

Pos logit contributions
 disl+0.009
bows+0.008
 killed+0.008
endant+0.007
 jewels+0.007
Neg logit contributions
inn-0.008
icky-0.007
ches-0.007
 kernel-0.007
nie-0.007
Token some
Token ID617
Feature activation-5.78e-01

Pos logit contributions
 disl+0.000
bows+0.000
 killed+0.000
endant+0.000
 Sorry+0.000
Neg logit contributions
inn-0.000
icky-0.000
ches-0.000
 kernel-0.000
 aid-0.000
Token tape
Token ID9154
Feature activation-1.81e+00

Pos logit contributions
inn+0.016
ches+0.014
icky+0.014
 kernel+0.014
nie+0.014
Neg logit contributions
 disl-0.015
 killed-0.012
 Gig-0.011
 Sorry-0.011
Thank-0.011
Token.
Token ID13
Feature activation-4.07e-01

Pos logit contributions
inn+0.046
icky+0.040
nie+0.039
ches+0.038
 kernel+0.038
Neg logit contributions
 disl-0.052
bows-0.042
endant-0.041
 jewels-0.041
 killed-0.041
Token wanted
Token ID2227
Feature activation-7.07e-01

Pos logit contributions
 disl+0.027
 Gig+0.020
bows+0.020
endant+0.020
Thank+0.020
Neg logit contributions
inn-0.026
ches-0.024
icky-0.023
 kernel-0.023
nie-0.023
Token to
Token ID284
Feature activation+5.85e-01

Pos logit contributions
inn+0.013
ches+0.011
icky+0.011
 kernel+0.010
nie+0.010
Neg logit contributions
 disl-0.026
 killed-0.022
 Gig-0.021
Thank-0.021
 Sorry-0.021
Token catch
Token ID4929
Feature activation-1.17e+00

Pos logit contributions
 disl+0.018
endant+0.016
mm+0.015
bows+0.015
 statues+0.015
Neg logit contributions
 aid-0.012
ches-0.011
inn-0.011
mate-0.011
 scrub-0.011
Token the
Token ID262
Feature activation-8.01e-01

Pos logit contributions
inn+0.024
ches+0.021
icky+0.021
nie+0.020
 kernel+0.020
Neg logit contributions
 disl-0.039
 killed-0.032
 Gig-0.032
 Sorry-0.031
Thank-0.031
Token k
Token ID479
Feature activation-1.19e+00

Pos logit contributions
inn+0.019
 kernel+0.018
ches+0.018
 aid+0.017
icky+0.017
Neg logit contributions
 disl-0.024
endant-0.019
 Sorry-0.018
 Tri-0.018
mm-0.018
Tokenang
Token ID648
Feature activation-5.05e+00

Pos logit contributions
inn+0.030
nie+0.028
icky+0.027
 aid+0.026
ches+0.026
Neg logit contributions
 disl-0.032
 killed-0.029
 Sorry-0.027
Thank-0.027
 Tri-0.026
Tokenaro
Token ID12022
Feature activation-1.27e+00

Pos logit contributions
inn+0.143
pron+0.134
icky+0.134
nie+0.133
ches+0.132
Neg logit contributions
 disl-0.108
 killed-0.097
 Gig-0.092
 Sorry-0.090
 Tri-0.088
Tokenos
Token ID418
Feature activation-3.18e-01

Pos logit contributions
inn+0.028
 aid+0.025
 kernel+0.025
nie+0.024
icky+0.024
Neg logit contributions
 disl-0.039
 Gig-0.032
 Sorry-0.031
 killed-0.031
bows-0.031
Token and
Token ID290
Feature activation+4.30e-01

Pos logit contributions
inn+0.009
 aid+0.008
 kernel+0.008
ud+0.008
pron+0.008
Neg logit contributions
 disl-0.008
 killed-0.006
bows-0.006
 Gig-0.006
 Tri-0.006
Token take
Token ID1011
Feature activation-1.84e+00

Pos logit contributions
 disl+0.012
endant+0.011
mm+0.011
bows+0.010
Thank+0.010
Neg logit contributions
ches-0.009
 aid-0.009
 kernel-0.009
inn-0.009
 chair-0.009
Token them
Token ID606
Feature activation+4.26e-01

Pos logit contributions
inn+0.032
ches+0.027
icky+0.026
 kernel+0.025
 aid+0.025
Neg logit contributions
 disl-0.069
endant-0.058
Thank-0.057
bows-0.056
 Sorry-0.056
Token is
Token ID318
Feature activation-7.51e-01

Pos logit contributions
inn+0.005
icky+0.004
 kernel+0.004
ches+0.004
 aid+0.004
Neg logit contributions
 disl-0.005
 killed-0.004
Thank-0.004
 Sorry-0.004
bows-0.004
Token normal
Token ID3487
Feature activation-7.61e-01

Pos logit contributions
inn+0.021
ches+0.019
icky+0.019
 kernel+0.019
nie+0.019
Neg logit contributions
 disl-0.019
 killed-0.015
Thank-0.014
 Gig-0.014
endant-0.014
Token for
Token ID329
Feature activation-2.99e-01

Pos logit contributions
inn+0.018
ches+0.016
 kernel+0.015
icky+0.015
nie+0.015
Neg logit contributions
 disl-0.024
 killed-0.019
bows-0.019
 jewels-0.019
endant-0.018
Token old
Token ID1468
Feature activation-6.19e-01

Pos logit contributions
inn+0.007
ches+0.006
icky+0.006
 kernel+0.006
nie+0.006
Neg logit contributions
 disl-0.009
 killed-0.007
endant-0.007
Thank-0.007
 Sorry-0.007
Token k
Token ID479
Feature activation-1.82e+00

Pos logit contributions
inn+0.017
ches+0.015
icky+0.015
 kernel+0.014
nie+0.014
Neg logit contributions
 disl-0.018
 killed-0.013
bows-0.013
 statues-0.013
 Gig-0.013
Tokenang
Token ID648
Feature activation-5.04e+00

Pos logit contributions
inn+0.052
 aid+0.048
 kernel+0.048
nie+0.047
ches+0.046
Neg logit contributions
 disl-0.040
endant-0.035
 killed-0.035
bows-0.032
Thank-0.032
Tokenaro
Token ID12022
Feature activation-1.35e+00

Pos logit contributions
inn+0.127
 aid+0.115
 kernel+0.108
pron+0.107
icky+0.106
Neg logit contributions
 disl-0.137
 killed-0.114
 Gig-0.109
 Tri-0.106
 statues-0.105
Tokenos
Token ID418
Feature activation-2.51e-01

Pos logit contributions
inn+0.028
 kernel+0.024
 aid+0.024
icky+0.024
ches+0.024
Neg logit contributions
 disl-0.044
 killed-0.036
bows-0.036
endant-0.035
 Gig-0.035
Token."
Token ID526
Feature activation-6.44e-01

Pos logit contributions
inn+0.006
 kernel+0.005
icky+0.005
 aid+0.005
nie+0.005
Neg logit contributions
 disl-0.008
 killed-0.006
bows-0.006
 Sorry-0.006
 Gig-0.006
Token
Token ID198
Feature activation-1.21e+00

Pos logit contributions
inn+0.018
ches+0.017
 kernel+0.016
icky+0.016
nie+0.016
Neg logit contributions
 disl-0.017
 Gig-0.014
 Sorry-0.013
Thank-0.013
 Tri-0.013
Token
Token ID198
Feature activation-4.55e-01

Pos logit contributions
inn+0.036
 kernel+0.035
ches+0.034
nie+0.034
ler+0.033
Neg logit contributions
 disl-0.028
 Gig-0.022
Thank-0.021
 Tri-0.020
 killed-0.019
Token The
Token ID383
Feature activation+5.95e-01

Pos logit contributions
inn+0.007
icky+0.007
 aid+0.007
nie+0.006
ud+0.006
Neg logit contributions
 disl-0.010
 killed-0.008
 jewels-0.008
vell-0.008
endant-0.008
Token walls
Token ID7714
Feature activation+1.94e+00

Pos logit contributions
 disl+0.020
 Gig+0.016
endant+0.016
 killed+0.016
 Sorry+0.016
Neg logit contributions
inn-0.013
icky-0.011
 aid-0.011
 chair-0.011
 mat-0.011
Token were
Token ID547
Feature activation+9.74e-01

Pos logit contributions
 disl+0.045
 killed+0.038
bows+0.035
endant+0.035
Thank+0.034
Neg logit contributions
inn-0.057
icky-0.052
nie-0.051
 aid-0.051
ches-0.050
Token terribly
Token ID22121
Feature activation-6.16e-02

Pos logit contributions
 disl+0.025
 killed+0.019
Thank+0.019
endant+0.019
 Gig+0.018
Neg logit contributions
inn-0.028
ches-0.025
icky-0.025
 kernel-0.024
nie-0.024
Token sm
Token ID895
Feature activation+5.65e-01

Pos logit contributions
inn+0.002
ches+0.002
icky+0.002
 kernel+0.002
nie+0.002
Neg logit contributions
 disl-0.002
 Gig-0.001
 Sorry-0.001
 killed-0.001
Thank-0.001
Tokenud
Token ID463
Feature activation-5.03e+00

Pos logit contributions
 disl+0.018
 killed+0.014
 Sorry+0.014
 Gig+0.014
Thank+0.014
Neg logit contributions
inn-0.013
ches-0.011
icky-0.011
 kernel-0.011
nie-0.011
Tokenged
Token ID2004
Feature activation-2.01e+00

Pos logit contributions
inn+0.122
 aid+0.109
 kernel+0.106
icky+0.105
Alex+0.104
Neg logit contributions
 disl-0.139
 Gig-0.116
 killed-0.115
bows-0.114
 Tri-0.110
Token and
Token ID290
Feature activation-6.43e-02

Pos logit contributions
inn+0.040
ches+0.034
icky+0.034
nie+0.032
 kernel+0.032
Neg logit contributions
 disl-0.070
 Sorry-0.057
 killed-0.056
Thank-0.056
 Gig-0.056
Token she
Token ID673
Feature activation-5.32e-01

Pos logit contributions
inn+0.001
ches+0.001
 kernel+0.001
icky+0.001
nie+0.001
Neg logit contributions
 disl-0.002
 Sorry-0.002
endant-0.002
bows-0.002
Thank-0.002
Token could
Token ID714
Feature activation-7.86e-01

Pos logit contributions
inn+0.017
icky+0.015
 kernel+0.015
 aid+0.015
ash+0.015
Neg logit contributions
 disl-0.011
 killed-0.010
Thank-0.008
 wished-0.008
endant-0.008
Token not
Token ID407
Feature activation+1.22e+00

Pos logit contributions
inn+0.023
ches+0.021
icky+0.021
 aid+0.021
 kernel+0.021
Neg logit contributions
 disl-0.019
 Gig-0.014
endant-0.014
 killed-0.014
Thank-0.014
Token It
Token ID632
Feature activation+8.51e-02

Pos logit contributions
 disl+0.001
 Sorry+0.000
 killed+0.000
 Gig+0.000
Thank+0.000
Neg logit contributions
inn-0.001
ches-0.001
icky-0.001
 kernel-0.001
nie-0.001
Token is
Token ID318
Feature activation-4.83e-02

Pos logit contributions
 disl+0.003
 killed+0.002
 Sorry+0.002
endant+0.002
bows+0.002
Neg logit contributions
inn-0.002
icky-0.002
ches-0.002
 kernel-0.002
 aid-0.002
Token the
Token ID262
Feature activation-8.93e-01

Pos logit contributions
inn+0.001
ches+0.001
icky+0.001
 kernel+0.001
 aid+0.001
Neg logit contributions
 disl-0.001
 killed-0.001
endant-0.001
 Gig-0.001
Thank-0.001
Token best
Token ID1266
Feature activation-1.93e+00

Pos logit contributions
inn+0.027
ches+0.024
icky+0.024
 kernel+0.023
nie+0.023
Neg logit contributions
 disl-0.021
 killed-0.016
Thank-0.016
 Gig-0.016
 jewels-0.016
Token tw
Token ID665
Feature activation-1.88e+00

Pos logit contributions
inn+0.051
ches+0.047
icky+0.045
 kernel+0.044
nie+0.043
Neg logit contributions
 disl-0.051
 jewels-0.044
bows-0.043
endant-0.042
 killed-0.041
Tokenig
Token ID328
Feature activation-5.02e+00

Pos logit contributions
inn+0.024
 aid+0.023
 kernel+0.023
 Alex+0.021
nie+0.021
Neg logit contributions
 disl-0.069
endant-0.063
 majesty-0.060
mm-0.060
bows-0.060
Token in
Token ID287
Feature activation+8.00e-02

Pos logit contributions
inn+0.127
ud+0.111
icky+0.108
 kernel+0.108
 aid+0.108
Neg logit contributions
 disl-0.142
bows-0.117
endant-0.114
 killed-0.112
 jewels-0.112
Token the
Token ID262
Feature activation+9.75e-01

Pos logit contributions
 disl+0.002
 killed+0.002
 jewels+0.002
 Sorry+0.002
Thank+0.002
Neg logit contributions
inn-0.002
ches-0.002
nie-0.002
ash-0.002
 kernel-0.002
Token world
Token ID995
Feature activation+1.18e+00

Pos logit contributions
 disl+0.028
Thank+0.022
 killed+0.022
 Gig+0.022
 jewels+0.022
Neg logit contributions
inn-0.025
ches-0.022
icky-0.022
 kernel-0.021
nie-0.021
Token.
Token ID13
Feature activation+1.02e-01

Pos logit contributions
 disl+0.032
 killed+0.025
bows+0.025
Thank+0.024
 Sorry+0.024
Neg logit contributions
inn-0.032
icky-0.028
ches-0.028
 kernel-0.028
 aid-0.027
Token It
Token ID632
Feature activation+2.37e-01

Pos logit contributions
 disl+0.003
 killed+0.002
endant+0.002
bows+0.002
 Gig+0.002
Neg logit contributions
inn-0.003
ches-0.003
icky-0.003
 aid-0.002
 kernel-0.002
Token's
Token ID338
Feature activation+3.20e-01

Pos logit contributions
inn+0.059
ud+0.043
icky+0.043
 kernel+0.042
pron+0.041
Neg logit contributions
 disl-0.101
 killed-0.087
 Gig-0.086
 Sorry-0.084
Thank-0.083
Token go
Token ID467
Feature activation-4.73e-01

Pos logit contributions
 disl+0.010
endant+0.008
bows+0.008
 killed+0.008
Thank+0.008
Neg logit contributions
inn-0.007
ches-0.007
 aid-0.007
 kernel-0.007
icky-0.007
Token catch
Token ID4929
Feature activation-1.52e+00

Pos logit contributions
inn+0.009
ches+0.008
icky+0.008
 kernel+0.008
nie+0.008
Neg logit contributions
 disl-0.017
 killed-0.013
 Sorry-0.013
endant-0.013
Thank-0.013
Token the
Token ID262
Feature activation-3.79e-01

Pos logit contributions
inn+0.041
nie+0.035
icky+0.034
 aid+0.034
 kernel+0.033
Neg logit contributions
 disl-0.044
 Gig-0.035
 killed-0.035
 statues-0.033
Thank-0.033
Token k
Token ID479
Feature activation-9.81e-01

Pos logit contributions
inn+0.009
ches+0.008
icky+0.008
 kernel+0.007
nie+0.007
Neg logit contributions
 disl-0.012
 killed-0.009
 Gig-0.009
 Sorry-0.009
Thank-0.009
Tokenang
Token ID648
Feature activation-4.98e+00

Pos logit contributions
inn+0.027
 aid+0.026
nie+0.025
icky+0.025
 kernel+0.024
Neg logit contributions
 disl-0.022
 killed-0.020
Thank-0.020
 Sorry-0.019
 Tri-0.019
Tokenaroo
Token ID38049
Feature activation-1.46e+00

Pos logit contributions
inn+0.157
icky+0.149
 aid+0.148
oby+0.146
ud+0.143
Neg logit contributions
 disl-0.088
 Gig-0.080
 Sorry-0.079
 killed-0.078
 Tri-0.075
Token!"
Token ID2474
Feature activation-1.48e-01

Pos logit contributions
inn+0.049
icky+0.043
 kernel+0.042
 aid+0.042
ches+0.042
Neg logit contributions
 disl-0.031
 Gig-0.023
 killed-0.023
bows-0.022
 Sorry-0.022
Token Ben
Token ID3932
Feature activation-8.44e-01

Pos logit contributions
inn+0.004
ches+0.003
ash+0.003
icky+0.003
mate+0.003
Neg logit contributions
 disl-0.004
 Gig-0.004
 Sorry-0.004
 killed-0.004
Thank-0.004
Token says
Token ID1139
Feature activation-7.00e-01

Pos logit contributions
inn+0.033
 kernel+0.032
pron+0.032
mate+0.031
icky+0.031
Neg logit contributions
 disl-0.012
 killed-0.006
bows-0.006
 Gig-0.006
 Tri-0.006
Token.
Token ID13
Feature activation-8.54e-01

Pos logit contributions
inn+0.021
 kernel+0.020
ud+0.020
nie+0.019
pron+0.019
Neg logit contributions
 disl-0.015
 killed-0.012
 Tri-0.012
bows-0.011
 Thank-0.011
Token conversation
Token ID5273
Feature activation+2.20e+00

Pos logit contributions
 disl+0.047
endant+0.037
 killed+0.037
Thank+0.037
 Sorry+0.037
Neg logit contributions
inn-0.037
ches-0.034
icky-0.033
 aid-0.033
nie-0.032
Token and
Token ID290
Feature activation-6.52e-01

Pos logit contributions
 disl+0.058
 statues+0.046
bows+0.046
 killed+0.046
Thank+0.046
Neg logit contributions
inn-0.058
icky-0.051
ches-0.051
nie-0.050
 kernel-0.050
Token encouraged
Token ID10085
Feature activation-9.15e-01

Pos logit contributions
inn+0.017
 kernel+0.016
ches+0.016
nie+0.016
 aid+0.015
Neg logit contributions
 disl-0.018
endant-0.014
bows-0.013
mm-0.013
 killed-0.013
Token the
Token ID262
Feature activation-9.52e-01

Pos logit contributions
inn+0.024
 kernel+0.022
icky+0.021
pron+0.021
 aid+0.021
Neg logit contributions
 disl-0.025
 Gig-0.021
 Tri-0.020
 killed-0.020
Thank-0.019
Token k
Token ID479
Feature activation-1.41e+00

Pos logit contributions
inn+0.019
nie+0.019
 kernel+0.018
 cable+0.018
 aid+0.018
Neg logit contributions
 disl-0.030
endant-0.025
mm-0.024
 Sorry-0.024
 killed-0.023
Tokenang
Token ID648
Feature activation-4.98e+00

Pos logit contributions
inn+0.032
ches+0.028
nie+0.028
icky+0.028
 kernel+0.028
Neg logit contributions
 disl-0.042
 killed-0.036
 Gig-0.035
endant-0.035
 Tri-0.035
Tokenaroo
Token ID38049
Feature activation-2.50e+00

Pos logit contributions
inn+0.145
icky+0.133
 mat+0.132
pron+0.131
ud+0.131
Neg logit contributions
 disl-0.110
 Gig-0.095
 Tri-0.094
 killed-0.092
 lucky-0.085
Token to
Token ID284
Feature activation+1.36e-01

Pos logit contributions
inn+0.055
icky+0.046
 kernel+0.046
ches+0.045
nie+0.044
Neg logit contributions
 disl-0.082
 killed-0.066
 Gig-0.066
 Tri-0.064
bows-0.064
Token go
Token ID467
Feature activation-5.78e-01

Pos logit contributions
 disl+0.004
endant+0.003
 killed+0.003
bows+0.003
 Sorry+0.003
Neg logit contributions
inn-0.003
ches-0.003
 aid-0.003
icky-0.003
 kernel-0.003
Token ahead
Token ID4058
Feature activation-3.47e+00

Pos logit contributions
inn+0.012
ches+0.010
icky+0.010
 kernel+0.010
nie+0.010
Neg logit contributions
 disl-0.020
 killed-0.016
 Sorry-0.016
 Gig-0.016
Thank-0.016
Token.
Token ID13
Feature activation-6.68e-01

Pos logit contributions
inn+0.106
ches+0.102
 kernel+0.101
nie+0.099
Alex+0.099
Neg logit contributions
 disl-0.053
 lucky-0.046
 Gig-0.046
 Thank-0.045
 Tri-0.045
Token help
Token ID1037
Feature activation-1.18e+00

Pos logit contributions
 disl+0.008
endant+0.006
 Gig+0.006
 killed+0.006
bows+0.006
Neg logit contributions
inn-0.008
ches-0.007
 kernel-0.007
 aid-0.007
nie-0.007
Token each
Token ID1123
Feature activation-2.19e+00

Pos logit contributions
inn+0.035
 kernel+0.030
icky+0.029
ud+0.029
 mat+0.028
Neg logit contributions
 disl-0.031
 killed-0.024
 Gig-0.023
 Sorry-0.023
 Tri-0.023
Token other
Token ID584
Feature activation+9.37e-01

Pos logit contributions
inn+0.072
icky+0.061
ches+0.060
ud+0.057
Alex+0.056
Neg logit contributions
 disl-0.049
 lucky-0.040
 killed-0.039
 Gig-0.038
Thank-0.037
Token.
Token ID13
Feature activation-8.25e-01

Pos logit contributions
 disl+0.027
bows+0.021
 killed+0.021
 lucky+0.021
 jewels+0.021
Neg logit contributions
inn-0.025
icky-0.020
ud-0.020
 kernel-0.020
ches-0.020
Token<|endoftext|>
Token ID50256
Feature activation+1.04e+00

Pos logit contributions
inn+0.024
ches+0.022
 kernel+0.021
nie+0.021
icky+0.020
Neg logit contributions
 disl-0.021
 Sorry-0.016
 Gig-0.016
Thank-0.016
 Thank-0.016
TokenOnce
Token ID7454
Feature activation+3.12e+00

Pos logit contributions
 disl+0.017
Thank+0.015
 Gig+0.014
 Tri+0.014
 killed+0.014
Neg logit contributions
inn-0.034
 kernel-0.032
nie-0.032
ches-0.032
ler-0.030
Token upon
Token ID2402
Feature activation-4.60e-01

Pos logit contributions
 disl+0.070
 lucky+0.059
endant+0.056
 Gig+0.055
 Sorry+0.053
Neg logit contributions
 kernel-0.086
inn-0.084
ches-0.083
 aid-0.082
nie-0.078
Token a
Token ID257
Feature activation-1.52e+00

Pos logit contributions
inn+0.014
ches+0.013
 kernel+0.012
icky+0.012
ash+0.012
Neg logit contributions
 disl-0.011
 killed-0.008
Thank-0.008
 Gig-0.008
 statues-0.008
Token time
Token ID640
Feature activation+3.16e-01

Pos logit contributions
inn+0.034
 kernel+0.033
ware+0.033
pan+0.032
mate+0.032
Neg logit contributions
 disl-0.041
 lucky-0.035
 dear-0.033
Thank-0.033
 fun-0.033
Token there
Token ID612
Feature activation+4.52e-01

Pos logit contributions
 disl+0.009
 killed+0.007
 Sorry+0.006
 Gig+0.006
endant+0.006
Neg logit contributions
inn-0.009
ches-0.008
 kernel-0.008
icky-0.008
nie-0.007
Token was
Token ID373
Feature activation-3.56e-02

Pos logit contributions
 disl+0.013
 killed+0.010
 Sorry+0.010
Thank+0.010
 Gig+0.010
Neg logit contributions
inn-0.012
ches-0.011
 kernel-0.010
nie-0.010
 aid-0.010
Token lake
Token ID13546
Feature activation-8.29e-01

Pos logit contributions
 disl+0.008
 killed+0.006
Thank+0.006
 Gig+0.006
 Sorry+0.006
Neg logit contributions
inn-0.007
ches-0.006
icky-0.006
 kernel-0.006
nie-0.006
Token again
Token ID757
Feature activation+6.38e-01

Pos logit contributions
inn+0.022
icky+0.019
ches+0.019
ud+0.018
Alex+0.018
Neg logit contributions
 disl-0.023
 Gig-0.018
Thank-0.018
 statues-0.018
 killed-0.018
Token soon
Token ID2582
Feature activation+7.99e-01

Pos logit contributions
 disl+0.019
 killed+0.015
Thank+0.015
 Gig+0.015
 Sorry+0.014
Neg logit contributions
inn-0.016
icky-0.014
ches-0.014
 kernel-0.014
nie-0.013
Token!
Token ID0
Feature activation-1.32e+00

Pos logit contributions
 disl+0.028
endant+0.022
 Sorry+0.022
 Gig+0.022
 killed+0.022
Neg logit contributions
inn-0.015
ches-0.014
 aid-0.013
icky-0.013
 kernel-0.013
Token<|endoftext|>
Token ID50256
Feature activation+1.16e+00

Pos logit contributions
inn+0.035
ches+0.033
 kernel+0.032
icky+0.032
nie+0.032
Neg logit contributions
 disl-0.035
 Gig-0.028
 Sorry-0.028
Thank-0.027
 Tri-0.027
TokenOnce
Token ID7454
Feature activation+3.24e+00

Pos logit contributions
 disl+0.025
Thank+0.020
 Gig+0.020
 killed+0.020
 Tri+0.019
Neg logit contributions
inn-0.035
 kernel-0.032
ches-0.032
nie-0.032
 aid-0.031
Token upon
Token ID2402
Feature activation-4.93e-02

Pos logit contributions
 disl+0.066
 lucky+0.059
endant+0.055
 Gig+0.054
 glad+0.052
Neg logit contributions
 kernel-0.093
ches-0.088
inn-0.088
 aid-0.087
 panc-0.086
Token a
Token ID257
Feature activation-1.36e+00

Pos logit contributions
inn+0.001
ches+0.001
icky+0.001
 kernel+0.001
nie+0.001
Neg logit contributions
 disl-0.001
 killed-0.001
Thank-0.001
 Gig-0.001
endant-0.001
Token time
Token ID640
Feature activation+5.82e-01

Pos logit contributions
inn+0.028
 kernel+0.026
ware+0.025
ches+0.025
pan+0.025
Neg logit contributions
 disl-0.040
 lucky-0.034
Thank-0.034
 dear-0.033
 Gig-0.033
Token,
Token ID11
Feature activation+1.17e+00

Pos logit contributions
 disl+0.017
 killed+0.014
Thank+0.013
endant+0.013
 Sorry+0.013
Neg logit contributions
inn-0.015
icky-0.013
ches-0.013
nie-0.012
 kernel-0.012
Token there
Token ID612
Feature activation+7.88e-02

Pos logit contributions
 disl+0.017
 lucky+0.016
Thank+0.015
 Gig+0.015
 killed+0.014
Neg logit contributions
ches-0.038
 kernel-0.037
inn-0.037
ash-0.037
 aid-0.037
Token to
Token ID284
Feature activation+8.36e-01

Pos logit contributions
 disl+0.003
 killed+0.003
 Sorry+0.003
Thank+0.003
endant+0.003
Neg logit contributions
inn-0.002
ches-0.001
icky-0.001
 kernel-0.001
 aid-0.001
Token the
Token ID262
Feature activation+5.92e-01

Pos logit contributions
 disl+0.028
 killed+0.022
Thank+0.022
 Sorry+0.022
endant+0.022
Neg logit contributions
inn-0.018
ches-0.015
icky-0.015
 kernel-0.015
 aid-0.015
Token zoo
Token ID26626
Feature activation+1.68e+00

Pos logit contributions
 disl+0.018
endant+0.014
bows+0.014
 killed+0.014
mm+0.014
Neg logit contributions
 aid-0.012
inn-0.012
 corner-0.012
 chair-0.012
 kernel-0.012
Token.
Token ID13
Feature activation+6.04e-01

Pos logit contributions
 disl+0.049
 killed+0.040
 statues+0.039
bows+0.039
 Gig+0.039
Neg logit contributions
inn-0.042
icky-0.036
ches-0.036
 kernel-0.035
nie-0.034
Token The
Token ID383
Feature activation+2.75e-01

Pos logit contributions
 disl+0.018
 killed+0.015
endant+0.014
 jewels+0.014
bows+0.014
Neg logit contributions
inn-0.014
 aid-0.013
ches-0.013
icky-0.012
nie-0.012
Token zoo
Token ID26626
Feature activation+2.88e+00

Pos logit contributions
 disl+0.010
endant+0.009
 bleed+0.009
 killed+0.008
uts+0.008
Neg logit contributions
 cable-0.004
 corner-0.004
 rug-0.004
 tray-0.004
 player-0.004
Token has
Token ID468
Feature activation-1.22e-01

Pos logit contributions
 disl+0.096
 Gig+0.077
Thank+0.077
 killed+0.075
endant+0.075
Neg logit contributions
inn-0.056
ches-0.054
icky-0.051
nie-0.050
 kernel-0.050
Token many
Token ID867
Feature activation+1.83e+00

Pos logit contributions
inn+0.003
ches+0.003
 aid+0.003
icky+0.002
 kernel+0.002
Neg logit contributions
 disl-0.004
 Sorry-0.003
mm-0.003
Thank-0.003
endant-0.003
Token animals
Token ID4695
Feature activation+1.49e+00

Pos logit contributions
 disl+0.054
 Sorry+0.049
Thank+0.047
mm+0.043
 Gig+0.042
Neg logit contributions
 corner-0.036
ches-0.035
ide-0.035
 chair-0.034
nie-0.034
Token from
Token ID422
Feature activation+9.45e-01

Pos logit contributions
 disl+0.054
 Sorry+0.045
Thank+0.045
mm+0.044
 Gig+0.044
Neg logit contributions
inn-0.025
ches-0.024
'-0.023
icky-0.022
 aid-0.021
Token different
Token ID1180
Feature activation+1.55e+00

Pos logit contributions
 disl+0.031
 killed+0.025
 Sorry+0.024
endant+0.024
Thank+0.024
Neg logit contributions
inn-0.020
ches-0.018
icky-0.018
 kernel-0.017
nie-0.017
Token
Token ID198
Feature activation-5.12e-02

Pos logit contributions
inn+0.021
nie+0.020
 kernel+0.020
ches+0.019
ler+0.019
Neg logit contributions
 disl-0.019
 Gig-0.015
Thank-0.015
 killed-0.014
 Tri-0.014
TokenThe
Token ID464
Feature activation+1.56e-01

Pos logit contributions
inn+0.001
icky+0.001
nie+0.001
ash+0.001
 kernel+0.001
Neg logit contributions
 disl-0.001
Thank-0.001
 killed-0.001
 Gig-0.001
 lucky-0.001
Token moral
Token ID6573
Feature activation+1.48e+00

Pos logit contributions
 disl+0.005
endant+0.004
bows+0.004
 Gig+0.004
 Sorry+0.004
Neg logit contributions
inn-0.004
ches-0.003
icky-0.003
 aid-0.003
 kernel-0.003
Token of
Token ID286
Feature activation-1.05e+00

Pos logit contributions
 disl+0.049
 killed+0.043
Thank+0.042
 Gig+0.042
 Tri+0.041
Neg logit contributions
inn-0.029
ches-0.024
 kernel-0.024
icky-0.024
nie-0.023
Token the
Token ID262
Feature activation-3.60e-01

Pos logit contributions
inn+0.034
about+0.031
ud+0.031
 aid+0.030
ash+0.030
Neg logit contributions
 disl-0.021
 Gig-0.017
 lucky-0.016
 Tri-0.015
 glad-0.014
Token story
Token ID1621
Feature activation+2.77e+00

Pos logit contributions
inn+0.007
ches+0.006
icky+0.006
 kernel+0.006
nie+0.006
Neg logit contributions
 disl-0.013
 killed-0.010
 Gig-0.010
Thank-0.010
 Sorry-0.010
Token was
Token ID373
Feature activation+5.57e-01

Pos logit contributions
 disl+0.072
 Sorry+0.057
bows+0.056
 killed+0.055
 Thank+0.054
Neg logit contributions
inn-0.079
 kernel-0.071
ches-0.069
nie-0.067
icky-0.067
Token clear
Token ID1598
Feature activation-8.49e-01

Pos logit contributions
 disl+0.014
 killed+0.011
 Gig+0.010
Thank+0.010
 Sorry+0.010
Neg logit contributions
inn-0.017
ches-0.015
 kernel-0.015
icky-0.015
 aid-0.015
Token:
Token ID25
Feature activation-7.98e-02

Pos logit contributions
inn+0.023
 kernel+0.020
icky+0.020
nie+0.019
 aid+0.019
Neg logit contributions
 disl-0.024
 killed-0.018
bows-0.018
 Sorry-0.017
 Thank-0.017
Token never
Token ID1239
Feature activation+1.37e+00

Pos logit contributions
inn+0.002
ches+0.002
icky+0.002
 kernel+0.002
nie+0.002
Neg logit contributions
 disl-0.002
 killed-0.002
Thank-0.002
 Gig-0.002
 Sorry-0.002
Token face
Token ID1986
Feature activation-8.51e-02

Pos logit contributions
 disl+0.036
endant+0.029
mm+0.029
 Sorry+0.028
 Gig+0.028
Neg logit contributions
inn-0.035
ches-0.033
nie-0.033
 aid-0.032
icky-0.032
Token a
Token ID257
Feature activation+1.10e+00

Pos logit contributions
 disl+0.027
 Sorry+0.021
endant+0.021
 killed+0.021
 Gig+0.020
Neg logit contributions
inn-0.027
ches-0.024
icky-0.024
nie-0.023
 kernel-0.023
Token great
Token ID1049
Feature activation+1.26e+00

Pos logit contributions
 disl+0.024
 killed+0.017
endant+0.017
 Gig+0.017
 Sorry+0.016
Neg logit contributions
inn-0.036
ches-0.033
icky-0.033
 kernel-0.032
nie-0.032
Token time
Token ID640
Feature activation-7.47e-01

Pos logit contributions
 disl+0.042
bows+0.035
Thank+0.035
 lucky+0.034
 Gig+0.034
Neg logit contributions
inn-0.025
ches-0.023
icky-0.022
 kernel-0.022
nie-0.021
Token!
Token ID0
Feature activation-6.68e-01

Pos logit contributions
inn+0.017
ches+0.015
icky+0.014
 kernel+0.014
nie+0.014
Neg logit contributions
 disl-0.024
 killed-0.019
 Gig-0.019
Thank-0.019
 Sorry-0.019
Token<|endoftext|>
Token ID50256
Feature activation+1.32e+00

Pos logit contributions
inn+0.016
icky+0.015
ches+0.014
 aid+0.014
nie+0.014
Neg logit contributions
 disl-0.020
 killed-0.016
endant-0.016
 Sorry-0.015
 jewels-0.015
TokenOnce
Token ID7454
Feature activation+3.31e+00

Pos logit contributions
 disl+0.027
Thank+0.021
 Gig+0.021
 killed+0.020
 Tri+0.020
Neg logit contributions
inn-0.041
 kernel-0.039
ches-0.039
nie-0.039
 aid-0.037
Token upon
Token ID2402
Feature activation-1.21e-01

Pos logit contributions
 disl+0.077
 lucky+0.065
endant+0.062
 Gig+0.062
 Tri+0.059
Neg logit contributions
 kernel-0.088
inn-0.087
ches-0.086
 aid-0.082
nie-0.081
Token a
Token ID257
Feature activation-1.29e+00

Pos logit contributions
inn+0.004
ches+0.003
 kernel+0.003
icky+0.003
nie+0.003
Neg logit contributions
 disl-0.003
 killed-0.002
Thank-0.002
 Gig-0.002
 statues-0.002
Token time
Token ID640
Feature activation+4.00e-01

Pos logit contributions
inn+0.027
 kernel+0.025
ches+0.024
ware+0.024
pan+0.024
Neg logit contributions
 disl-0.039
 lucky-0.032
Thank-0.032
 Gig-0.031
 dear-0.031
Token there
Token ID612
Feature activation+6.11e-01

Pos logit contributions
 disl+0.011
 killed+0.008
 Gig+0.008
 Sorry+0.008
 Tri+0.008
Neg logit contributions
inn-0.011
ches-0.010
 kernel-0.010
nie-0.010
icky-0.010
Token were
Token ID547
Feature activation+1.51e+00

Pos logit contributions
 disl+0.016
 killed+0.013
Thank+0.013
 Sorry+0.013
 Gig+0.013
Neg logit contributions
inn-0.016
ches-0.015
 kernel-0.014
nie-0.014
 aid-0.014
Token!
Token ID0
Feature activation-1.31e+00

Pos logit contributions
inn+0.041
icky+0.035
 kernel+0.034
ches+0.034
 aid+0.033
Neg logit contributions
 disl-0.051
 killed-0.041
 Gig-0.040
bows-0.040
Thank-0.039
Token We
Token ID775
Feature activation-1.49e+00

Pos logit contributions
inn+0.036
ches+0.032
icky+0.032
nie+0.031
 aid+0.031
Neg logit contributions
 disl-0.035
 killed-0.027
endant-0.027
 Gig-0.026
Thank-0.026
Token need
Token ID761
Feature activation-9.38e-01

Pos logit contributions
inn+0.038
ches+0.037
'+0.035
nie+0.034
 kernel+0.033
Neg logit contributions
 disl-0.044
mm-0.034
endant-0.034
 statues-0.033
bows-0.032
Token to
Token ID284
Feature activation+7.06e-01

Pos logit contributions
inn+0.016
ches+0.014
icky+0.014
 kernel+0.013
nie+0.013
Neg logit contributions
 disl-0.035
 killed-0.029
 Gig-0.028
 Sorry-0.028
Thank-0.028
Token rush
Token ID10484
Feature activation-7.95e-01

Pos logit contributions
 disl+0.021
endant+0.017
bows+0.017
Thank+0.016
 Sorry+0.016
Neg logit contributions
inn-0.016
 aid-0.016
ches-0.015
icky-0.015
 kernel-0.015
Token and
Token ID290
Feature activation+4.99e-01

Pos logit contributions
inn+0.015
ches+0.013
icky+0.013
 kernel+0.013
 aid+0.012
Neg logit contributions
 disl-0.028
 killed-0.023
 Gig-0.023
Thank-0.023
 Sorry-0.023
Token play
Token ID711
Feature activation+5.61e-01

Pos logit contributions
 disl+0.014
endant+0.011
bows+0.011
 killed+0.011
 Gig+0.011
Neg logit contributions
inn-0.012
ches-0.011
 aid-0.011
 kernel-0.011
icky-0.011
Token together
Token ID1978
Feature activation-2.36e-01

Pos logit contributions
 disl+0.014
 killed+0.011
Thank+0.011
 Sorry+0.011
 Gig+0.011
Neg logit contributions
inn-0.016
icky-0.014
 kernel-0.014
nie-0.014
ches-0.014
Token!"
Token ID2474
Feature activation-8.15e-01

Pos logit contributions
inn+0.008
 kernel+0.008
ches+0.007
 aid+0.007
icky+0.007
Neg logit contributions
 disl-0.004
bows-0.003
Thank-0.003
 killed-0.003
 Gig-0.003
Token
Token ID220
Feature activation+3.40e-01

Pos logit contributions
inn+0.011
ches+0.011
'+0.011
ide+0.010
 again+0.010
Neg logit contributions
 disl-0.030
endant-0.027
 majesty-0.026
 killed-0.026
 statues-0.025
Token
Token ID198
Feature activation-9.30e-01

Pos logit contributions
 disl+0.009
 killed+0.006
 Gig+0.006
 Sorry+0.006
 Tri+0.006
Neg logit contributions
inn-0.009
 kernel-0.009
nie-0.009
ches-0.008
 strand-0.008
Token the
Token ID262
Feature activation+1.54e+00

Pos logit contributions
 disl+0.000
 killed+0.000
 Gig+0.000
 Tri+0.000
 jewels+0.000
Neg logit contributions
inn-0.000
ches-0.000
 kernel-0.000
icky-0.000
nie-0.000
Token cr
Token ID1067
Feature activation+8.01e-01

Pos logit contributions
 disl+0.053
 Gig+0.046
 Sorry+0.044
 Thank+0.041
endant+0.041
Neg logit contributions
nie-0.028
inn-0.027
icky-0.027
 chair-0.027
 sheet-0.027
Tokenay
Token ID323
Feature activation+5.51e-01

Pos logit contributions
 disl+0.028
 Gig+0.023
 Sorry+0.022
 killed+0.022
Thank+0.022
Neg logit contributions
inn-0.017
icky-0.015
ches-0.015
ud-0.013
ide-0.013
Tokenons
Token ID684
Feature activation+7.08e-01

Pos logit contributions
 disl+0.017
 Gig+0.014
 Sorry+0.014
Thank+0.014
 killed+0.014
Neg logit contributions
inn-0.013
icky-0.011
ches-0.011
 kernel-0.011
nie-0.010
Token started
Token ID2067
Feature activation-1.44e+00

Pos logit contributions
 disl+0.020
 Gig+0.015
 Sorry+0.015
Thank+0.015
mm+0.015
Neg logit contributions
inn-0.019
ches-0.018
 kernel-0.017
icky-0.017
 aid-0.016
Token to
Token ID284
Feature activation+5.27e-02

Pos logit contributions
inn+0.026
icky+0.022
ches+0.022
 kernel+0.021
 aid+0.020
Neg logit contributions
 disl-0.052
 Sorry-0.043
Thank-0.043
 Gig-0.043
 killed-0.043
Token move
Token ID1445
Feature activation-1.89e+00

Pos logit contributions
 disl+0.002
endant+0.001
 Gig+0.001
mm+0.001
 Sorry+0.001
Neg logit contributions
inn-0.001
ches-0.001
icky-0.001
 aid-0.001
 kernel-0.001
Token around
Token ID1088
Feature activation-9.26e-01

Pos logit contributions
inn+0.042
 kernel+0.036
icky+0.036
ches+0.036
nie+0.035
Neg logit contributions
 disl-0.059
 killed-0.049
bows-0.048
 statues-0.048
 Tri-0.048
Token the
Token ID262
Feature activation+6.95e-01

Pos logit contributions
inn+0.023
ches+0.020
 kernel+0.019
icky+0.019
nie+0.019
Neg logit contributions
 disl-0.028
 killed-0.022
Thank-0.022
 statues-0.022
 Gig-0.022
Token paper
Token ID3348
Feature activation-6.84e-01

Pos logit contributions
 disl+0.028
 Gig+0.024
 killed+0.023
 Sorry+0.023
endant+0.023
Neg logit contributions
inn-0.010
icky-0.008
 aid-0.008
nie-0.008
ches-0.008
Token!
Token ID0
Feature activation-8.23e-01

Pos logit contributions
inn+0.016
ches+0.014
icky+0.014
nie+0.013
 kernel+0.013
Neg logit contributions
 disl-0.021
 killed-0.017
bows-0.017
endant-0.017
 statues-0.017
Token you
Token ID345
Feature activation-4.58e-01

Pos logit contributions
ches+0.004
inn+0.004
nie+0.004
icky+0.004
 chair+0.004
Neg logit contributions
 disl-0.006
bows-0.005
endant-0.005
 killed-0.005
vell-0.005
Token can
Token ID460
Feature activation-2.69e-01

Pos logit contributions
inn+0.011
ches+0.011
icky+0.010
nie+0.010
 kernel+0.010
Neg logit contributions
 disl-0.014
Thank-0.011
 Gig-0.011
bows-0.010
 statues-0.010
Token build
Token ID1382
Feature activation-8.58e-01

Pos logit contributions
inn+0.007
ches+0.006
icky+0.006
 kernel+0.006
 aid+0.006
Neg logit contributions
 disl-0.008
 killed-0.006
 Gig-0.006
endant-0.006
Thank-0.006
Token your
Token ID534
Feature activation+2.96e-01

Pos logit contributions
inn+0.017
icky+0.016
ches+0.016
 aid+0.015
 kernel+0.014
Neg logit contributions
 disl-0.028
Thank-0.024
 Sorry-0.023
bows-0.023
 Gig-0.022
Token nest
Token ID16343
Feature activation+1.70e-01

Pos logit contributions
 disl+0.010
 Sorry+0.008
Thank+0.008
bows+0.008
 killed+0.008
Neg logit contributions
inn-0.006
 aid-0.005
ches-0.005
icky-0.005
 kernel-0.005
Token here
Token ID994
Feature activation+1.12e-01

Pos logit contributions
 disl+0.005
bows+0.004
 killed+0.004
endant+0.004
 jewels+0.004
Neg logit contributions
inn-0.004
icky-0.004
ches-0.004
 kernel-0.004
 aid-0.003
Token.
Token ID13
Feature activation-3.04e-01

Pos logit contributions
 disl+0.003
 killed+0.002
bows+0.002
 jewels+0.002
 Gig+0.002
Neg logit contributions
inn-0.003
ches-0.003
icky-0.003
 kernel-0.003
nie-0.003
Token But
Token ID887
Feature activation-1.12e+00

Pos logit contributions
inn+0.008
ches+0.007
icky+0.007
 aid+0.007
nie+0.007
Neg logit contributions
 disl-0.009
 killed-0.007
endant-0.007
bows-0.007
 statues-0.007
Token please
Token ID3387
Feature activation+1.09e+00

Pos logit contributions
inn+0.032
ches+0.029
icky+0.029
 kernel+0.028
nie+0.028
Neg logit contributions
 disl-0.029
 killed-0.022
endant-0.021
 Gig-0.021
Thank-0.021
Token don
Token ID836
Feature activation-9.42e-02

Pos logit contributions
 disl+0.032
endant+0.026
 statues+0.026
 Gig+0.025
Thank+0.025
Neg logit contributions
inn-0.024
ches-0.024
 aid-0.022
'-0.022
nie-0.022
Token't
Token ID470
Feature activation+4.64e-01

Pos logit contributions
inn+0.003
nie+0.003
 kernel+0.003
ches+0.002
 aid+0.002
Neg logit contributions
 disl-0.002
 killed-0.002
 Sorry-0.002
 Gig-0.002
Thank-0.002
Token down
Token ID866
Feature activation-1.78e+00

Pos logit contributions
inn+0.011
 kernel+0.009
ches+0.009
icky+0.009
nie+0.009
Neg logit contributions
 disl-0.016
 killed-0.014
 Gig-0.013
endant-0.013
 jewels-0.013
Token.
Token ID13
Feature activation+3.55e-01

Pos logit contributions
inn+0.045
ches+0.043
nie+0.041
 kernel+0.041
icky+0.040
Neg logit contributions
 disl-0.047
 killed-0.039
 Gig-0.038
 jewels-0.038
 Tri-0.038
Token They
Token ID1119
Feature activation+9.11e-01

Pos logit contributions
 disl+0.011
bows+0.009
 killed+0.009
 statues+0.009
endant+0.009
Neg logit contributions
inn-0.008
icky-0.007
 aid-0.007
 chair-0.006
ches-0.006
Token opened
Token ID4721
Feature activation+6.60e-01

Pos logit contributions
 disl+0.024
 Sorry+0.018
bows+0.018
 killed+0.018
endant+0.018
Neg logit contributions
inn-0.026
ches-0.023
 kernel-0.023
icky-0.023
nie-0.022
Token the
Token ID262
Feature activation+4.23e-01

Pos logit contributions
 disl+0.018
 Gig+0.015
 jewels+0.015
 statues+0.015
 killed+0.015
Neg logit contributions
inn-0.017
ches-0.015
nie-0.015
icky-0.015
ash-0.014
Token jar
Token ID17379
Feature activation-7.19e-03

Pos logit contributions
 disl+0.012
 jewels+0.011
endant+0.011
 killed+0.011
 statues+0.010
Neg logit contributions
inn-0.010
ide-0.009
nie-0.008
ches-0.008
icky-0.008
Token together
Token ID1978
Feature activation+1.96e-01

Pos logit contributions
inn+0.000
nie+0.000
 kernel+0.000
ches+0.000
icky+0.000
Neg logit contributions
 disl-0.000
ocular-0.000
endant-0.000
bows-0.000
 jewels-0.000
Token and
Token ID290
Feature activation+7.78e-01

Pos logit contributions
 disl+0.004
 statues+0.003
 jewels+0.003
endant+0.003
 lucky+0.003
Neg logit contributions
inn-0.006
nie-0.006
ches-0.006
icky-0.005
pron-0.005
Token shared
Token ID4888
Feature activation+7.24e-01

Pos logit contributions
 disl+0.021
 killed+0.016
endant+0.015
 Sorry+0.015
 Gig+0.015
Neg logit contributions
inn-0.022
ches-0.020
icky-0.019
 kernel-0.019
nie-0.019
Token the
Token ID262
Feature activation-8.55e-02

Pos logit contributions
 disl+0.027
 killed+0.022
 Sorry+0.022
Thank+0.022
bows+0.022
Neg logit contributions
inn-0.013
icky-0.011
 kernel-0.010
ches-0.010
 aid-0.010
Token y
Token ID331
Feature activation+6.06e-01

Pos logit contributions
inn+0.002
ches+0.002
icky+0.002
 kernel+0.002
nie+0.002
Neg logit contributions
 disl-0.003
 killed-0.002
 Sorry-0.002
 Gig-0.002
Thank-0.002
Token to
Token ID284
Feature activation+9.81e-01

Pos logit contributions
 disl+0.032
 Gig+0.026
 Sorry+0.026
Thank+0.025
endant+0.025
Neg logit contributions
inn-0.019
ches-0.016
icky-0.016
 kernel-0.015
 aid-0.015
Token fit
Token ID4197
Feature activation-1.91e+00

Pos logit contributions
 disl+0.027
 killed+0.021
 Sorry+0.020
Thank+0.020
bows+0.020
Neg logit contributions
inn-0.026
ches-0.024
icky-0.024
 kernel-0.023
nie-0.023
Token on
Token ID319
Feature activation-9.03e-01

Pos logit contributions
inn+0.041
ches+0.037
 kernel+0.036
 aid+0.036
icky+0.036
Neg logit contributions
 disl-0.060
 killed-0.049
 jewels-0.049
 statues-0.049
bows-0.049
Token the
Token ID262
Feature activation+3.46e-01

Pos logit contributions
inn+0.023
ches+0.021
nie+0.020
 kernel+0.019
ash+0.019
Neg logit contributions
 disl-0.026
 statues-0.022
 jewels-0.021
 killed-0.020
 Gig-0.020
Token top
Token ID1353
Feature activation-1.78e+00

Pos logit contributions
 disl+0.011
 statues+0.009
 jewels+0.009
endant+0.009
 killed+0.009
Neg logit contributions
inn-0.008
ches-0.007
icky-0.007
 kernel-0.006
ud-0.006
Token.
Token ID13
Feature activation+9.47e-01

Pos logit contributions
inn+0.044
ches+0.041
Alex+0.040
nie+0.040
 kernel+0.039
Neg logit contributions
 disl-0.039
bows-0.037
 statues-0.037
ocular-0.036
endant-0.035
Token The
Token ID383
Feature activation+6.55e-01

Pos logit contributions
 disl+0.027
 killed+0.021
endant+0.021
 Gig+0.021
bows+0.020
Neg logit contributions
inn-0.025
icky-0.022
ches-0.021
 aid-0.021
 kernel-0.021
Token tower
Token ID10580
Feature activation+1.75e+00

Pos logit contributions
 disl+0.021
 killed+0.017
Thank+0.017
 statues+0.017
endant+0.017
Neg logit contributions
inn-0.015
ches-0.013
icky-0.013
 kernel-0.012
nie-0.012
Token was
Token ID373
Feature activation-4.35e-01

Pos logit contributions
 disl+0.046
 killed+0.042
endant+0.038
 statues+0.038
Thank+0.038
Neg logit contributions
inn-0.046
icky-0.041
nie-0.040
ches-0.040
 aid-0.039
Token not
Token ID407
Feature activation-1.65e-01

Pos logit contributions
inn+0.012
ches+0.012
icky+0.011
 aid+0.011
nie+0.011
Neg logit contributions
 disl-0.010
 killed-0.009
 jewels-0.008
endant-0.008
Thank-0.008
Token finished
Token ID5201
Feature activation+2.73e-01

Pos logit contributions
inn+0.005
ches+0.004
icky+0.004
 kernel+0.004
nie+0.004
Neg logit contributions
 disl-0.004
 killed-0.003
 Sorry-0.003
 Gig-0.003
Thank-0.003
Token angry
Token ID7954
Feature activation+1.66e+00

Pos logit contributions
 disl+0.046
bows+0.042
mm+0.040
Thank+0.038
 killed+0.038
Neg logit contributions
inn-0.048
icky-0.042
nie-0.040
ches-0.040
 nervously-0.039
Token and
Token ID290
Feature activation+5.29e-02

Pos logit contributions
 disl+0.057
 killed+0.047
 Gig+0.046
Thank+0.046
 Sorry+0.046
Neg logit contributions
inn-0.033
ches-0.029
icky-0.028
 kernel-0.027
nie-0.027
Token said
Token ID531
Feature activation+1.19e+00

Pos logit contributions
 disl+0.001
endant+0.001
bows+0.001
mm+0.001
 Gig+0.001
Neg logit contributions
inn-0.001
ches-0.001
nie-0.001
 kernel-0.001
 Alex-0.001
Token,
Token ID11
Feature activation-1.42e+00

Pos logit contributions
 disl+0.031
 Gig+0.024
 killed+0.024
 Sorry+0.023
 Tri+0.023
Neg logit contributions
inn-0.034
ches-0.031
 kernel-0.030
nie-0.030
icky-0.030
Token "
Token ID366
Feature activation+4.41e-01

Pos logit contributions
inn+0.031
ches+0.027
icky+0.027
 kernel+0.026
nie+0.025
Neg logit contributions
 disl-0.046
 Gig-0.038
Thank-0.038
 killed-0.037
 Sorry-0.037
TokenThis
Token ID1212
Feature activation-1.71e+00

Pos logit contributions
 disl+0.012
 killed+0.009
Thank+0.009
 Gig+0.009
 Sorry+0.009
Neg logit contributions
inn-0.012
ches-0.011
icky-0.011
 kernel-0.011
nie-0.011
Token coin
Token ID10752
Feature activation-4.11e-01

Pos logit contributions
inn+0.039
ches+0.035
icky+0.034
 kernel+0.034
nie+0.033
Neg logit contributions
 disl-0.054
 killed-0.043
 Gig-0.042
 Sorry-0.042
Thank-0.042
Token belongs
Token ID14448
Feature activation-7.68e-01

Pos logit contributions
inn+0.010
ches+0.009
icky+0.009
 kernel+0.008
nie+0.008
Neg logit contributions
 disl-0.012
 killed-0.010
 Gig-0.010
Thank-0.010
 Sorry-0.010
Token to
Token ID284
Feature activation+1.73e-01

Pos logit contributions
inn+0.015
icky+0.012
 kernel+0.012
ches+0.012
 aid+0.011
Neg logit contributions
 disl-0.027
 killed-0.023
endant-0.022
 Gig-0.022
 jewels-0.022
Token me
Token ID502
Feature activation-5.75e-01

Pos logit contributions
 disl+0.005
endant+0.004
bows+0.004
 killed+0.004
Thank+0.004
Neg logit contributions
inn-0.004
ches-0.003
icky-0.003
 aid-0.003
 kernel-0.003
Token.
Token ID13
Feature activation-9.22e-01

Pos logit contributions
inn+0.016
ches+0.014
icky+0.014
 kernel+0.014
nie+0.013
Neg logit contributions
 disl-0.015
 killed-0.012
 Gig-0.012
 Sorry-0.012
endant-0.011
Token and
Token ID290
Feature activation+7.66e-01

Pos logit contributions
 disl+0.009
 Sorry+0.008
 killed+0.008
endant+0.007
 Tri+0.007
Neg logit contributions
inn-0.004
ches-0.003
 kernel-0.003
icky-0.003
nie-0.003
Token tasty
Token ID25103
Feature activation-3.23e-02

Pos logit contributions
 disl+0.020
 killed+0.015
endant+0.015
bows+0.014
 majesty+0.014
Neg logit contributions
inn-0.021
nie-0.020
 kernel-0.019
ches-0.019
 chair-0.019
Token,
Token ID11
Feature activation-1.18e-01

Pos logit contributions
inn+0.001
ches+0.001
icky+0.001
 kernel+0.001
nie+0.001
Neg logit contributions
 disl-0.001
 killed-0.001
 Sorry-0.001
endant-0.001
Thank-0.001
Token so
Token ID523
Feature activation+4.49e-01

Pos logit contributions
inn+0.002
 kernel+0.002
 chair+0.002
nie+0.002
 mat+0.001
Neg logit contributions
 disl-0.004
 Sorry-0.004
endant-0.004
 killed-0.004
 majesty-0.003
Token it
Token ID340
Feature activation-4.15e-01

Pos logit contributions
 disl+0.016
 killed+0.013
 majesty+0.013
endant+0.013
 bleed+0.012
Neg logit contributions
inn-0.007
 again-0.007
 particular-0.006
 of-0.006
 one-0.006
Token was
Token ID373
Feature activation-4.25e-01

Pos logit contributions
inn+0.012
icky+0.011
ches+0.011
 aid+0.011
 kernel+0.010
Neg logit contributions
 disl-0.010
 killed-0.008
Thank-0.008
 Gig-0.008
 Sorry-0.008
Token hard
Token ID1327
Feature activation-1.82e+00

Pos logit contributions
inn+0.012
ches+0.011
icky+0.010
 kernel+0.010
nie+0.010
Neg logit contributions
 disl-0.011
 killed-0.009
 Sorry-0.009
endant-0.009
 Gig-0.008
Token to
Token ID284
Feature activation+4.75e-01

Pos logit contributions
inn+0.032
ches+0.027
icky+0.027
nie+0.026
 kernel+0.026
Neg logit contributions
 disl-0.067
 Sorry-0.056
 Gig-0.055
 killed-0.055
Thank-0.055
Token decide
Token ID5409
Feature activation+8.09e-01

Pos logit contributions
 disl+0.014
endant+0.011
 Sorry+0.011
bows+0.011
 killed+0.011
Neg logit contributions
inn-0.012
ches-0.011
 kernel-0.011
 aid-0.010
icky-0.010
Token.
Token ID13
Feature activation-6.23e-01

Pos logit contributions
 disl+0.025
 killed+0.020
 Gig+0.020
endant+0.020
Thank+0.020
Neg logit contributions
inn-0.019
ches-0.016
icky-0.016
 kernel-0.016
nie-0.016
Token In
Token ID554
Feature activation+2.20e-02

Pos logit contributions
inn+0.009
 corner+0.007
 aid+0.007
'+0.007
ide+0.007
Neg logit contributions
 disl-0.025
 killed-0.021
 jewels-0.020
 majesty-0.020
vell-0.019
Token mine
Token ID6164
Feature activation+4.04e-01

Pos logit contributions
inn+0.008
ches+0.007
icky+0.007
 kernel+0.007
nie+0.007
Neg logit contributions
 disl-0.007
 killed-0.006
 Gig-0.006
 Sorry-0.006
endant-0.006
Token!
Token ID0
Feature activation-1.07e+00

Pos logit contributions
 disl+0.010
 killed+0.008
endant+0.008
 statues+0.008
 jewels+0.007
Neg logit contributions
inn-0.012
ches-0.011
icky-0.010
nie-0.010
 kernel-0.010
Token
Token ID198
Feature activation-8.38e-01

Pos logit contributions
inn+0.028
ches+0.027
nie+0.027
 kernel+0.026
ide+0.025
Neg logit contributions
 disl-0.028
 Gig-0.022
 Tri-0.022
 Sorry-0.022
 Thank-0.021
Token
Token ID198
Feature activation+2.76e-01

Pos logit contributions
nie+0.025
inn+0.025
 kernel+0.025
ches+0.024
ler+0.024
Neg logit contributions
 disl-0.018
 Gig-0.013
 Tri-0.013
Thank-0.012
 killed-0.012
TokenM
Token ID44
Feature activation-5.92e-01

Pos logit contributions
 disl+0.008
Thank+0.007
 killed+0.006
 Tri+0.006
 Sorry+0.006
Neg logit contributions
inn-0.006
ches-0.006
nie-0.006
 kernel-0.006
 crib-0.006
Tokenandy
Token ID10757
Feature activation-1.47e+00

Pos logit contributions
inn+0.008
icky+0.006
ud+0.005
ches+0.005
ash+0.004
Neg logit contributions
 disl-0.026
Thank-0.023
bows-0.022
 killed-0.022
 Sorry-0.022
Token quickly
Token ID2952
Feature activation+1.05e+00

Pos logit contributions
inn+0.036
icky+0.031
 kernel+0.031
ches+0.030
nie+0.029
Neg logit contributions
 disl-0.043
 killed-0.035
endant-0.034
 Gig-0.034
Thank-0.034
Token raced
Token ID32897
Feature activation-2.53e-01

Pos logit contributions
 disl+0.033
 Sorry+0.028
mm+0.028
bows+0.027
Thank+0.025
Neg logit contributions
inn-0.024
ches-0.023
 aid-0.021
'-0.021
 kernel-0.020
Token over
Token ID625
Feature activation+9.61e-02

Pos logit contributions
inn+0.005
icky+0.005
ches+0.005
 kernel+0.004
ud+0.004
Neg logit contributions
 disl-0.008
 Gig-0.007
 Tri-0.007
Thank-0.007
 killed-0.007
Token and
Token ID290
Feature activation-2.56e-01

Pos logit contributions
 disl+0.003
 Gig+0.002
 statues+0.002
 jewels+0.002
 Tri+0.002
Neg logit contributions
inn-0.002
nie-0.002
ches-0.002
 kernel-0.002
pron-0.002
Token picked
Token ID6497
Feature activation+4.15e-01

Pos logit contributions
inn+0.006
ches+0.006
 kernel+0.005
nie+0.005
icky+0.005
Neg logit contributions
 disl-0.008
bows-0.006
mm-0.006
endant-0.006
 Sorry-0.006
Token if
Token ID611
Feature activation-4.98e-01

Pos logit contributions
inn+0.046
ches+0.040
ash+0.038
 kernel+0.037
icky+0.037
Neg logit contributions
 disl-0.037
Thank-0.029
 Sorry-0.028
 killed-0.028
 lucky-0.028
Token you
Token ID345
Feature activation+6.87e-01

Pos logit contributions
inn+0.016
ches+0.015
icky+0.015
 kernel+0.015
nie+0.015
Neg logit contributions
 disl-0.011
 killed-0.008
endant-0.007
 Gig-0.007
Thank-0.007
Token want
Token ID765
Feature activation-6.72e-01

Pos logit contributions
 disl+0.017
 Gig+0.013
 killed+0.013
endant+0.012
 Sorry+0.012
Neg logit contributions
inn-0.020
ches-0.019
icky-0.018
 kernel-0.018
nie-0.018
Token to
Token ID284
Feature activation+1.19e+00

Pos logit contributions
inn+0.015
ches+0.012
icky+0.012
 kernel+0.012
nie+0.012
Neg logit contributions
 disl-0.022
 killed-0.018
Thank-0.018
 Sorry-0.018
 Gig-0.018
Token be
Token ID307
Feature activation+4.11e-01

Pos logit contributions
 disl+0.031
 killed+0.023
endant+0.023
 Gig+0.023
 Sorry+0.023
Neg logit contributions
inn-0.034
ches-0.030
icky-0.030
 kernel-0.030
 aid-0.029
Token clever
Token ID14169
Feature activation-1.21e+00

Pos logit contributions
 disl+0.010
 killed+0.008
 Sorry+0.007
endant+0.007
 Gig+0.007
Neg logit contributions
inn-0.012
ches-0.011
icky-0.011
 kernel-0.011
nie-0.011
Token,
Token ID11
Feature activation-5.24e-01

Pos logit contributions
inn+0.031
 kernel+0.027
ches+0.027
icky+0.027
 aid+0.025
Neg logit contributions
 disl-0.034
 killed-0.027
 jewels-0.027
Thank-0.027
bows-0.026
Token you
Token ID345
Feature activation+5.55e-02

Pos logit contributions
inn+0.017
ches+0.015
icky+0.015
 kernel+0.015
nie+0.015
Neg logit contributions
 disl-0.012
 killed-0.009
 Gig-0.009
Thank-0.009
 Sorry-0.009
Token must
Token ID1276
Feature activation+1.09e+00

Pos logit contributions
 disl+0.001
 killed+0.001
 Gig+0.001
endant+0.001
Thank+0.001
Neg logit contributions
inn-0.002
ches-0.001
icky-0.001
 kernel-0.001
nie-0.001
Token write
Token ID3551
Feature activation+3.28e-01

Pos logit contributions
 disl+0.027
 killed+0.020
Thank+0.020
 Gig+0.020
 Sorry+0.020
Neg logit contributions
inn-0.032
ches-0.029
icky-0.029
 kernel-0.029
nie-0.028
Token and
Token ID290
Feature activation+8.08e-01

Pos logit contributions
 disl+0.010
 killed+0.008
 Gig+0.008
endant+0.008
 Sorry+0.008
Neg logit contributions
inn-0.008
ches-0.007
icky-0.007
nie-0.007
 kernel-0.007
Token whenever
Token ID8797
Feature activation+1.03e+00

Pos logit contributions
inn+0.002
ches+0.002
icky+0.002
 kernel+0.002
nie+0.002
Neg logit contributions
 disl-0.003
 killed-0.002
 Gig-0.002
Thank-0.002
 Sorry-0.002
Token she
Token ID673
Feature activation+8.96e-02

Pos logit contributions
 disl+0.033
endant+0.027
 killed+0.026
bows+0.026
Thank+0.025
Neg logit contributions
inn-0.022
icky-0.019
nie-0.019
 aid-0.019
 kernel-0.019
Token felt
Token ID2936
Feature activation+9.63e-01

Pos logit contributions
 disl+0.002
 Gig+0.002
 Sorry+0.002
endant+0.002
 killed+0.002
Neg logit contributions
inn-0.002
ches-0.002
icky-0.002
nie-0.002
 aid-0.002
Token sad
Token ID6507
Feature activation+2.65e+00

Pos logit contributions
 disl+0.022
 killed+0.016
 Gig+0.015
Thank+0.015
 Sorry+0.015
Neg logit contributions
inn-0.030
ches-0.028
icky-0.028
 kernel-0.027
nie-0.027
Token,
Token ID11
Feature activation-4.64e-01

Pos logit contributions
 disl+0.082
 killed+0.065
endant+0.065
 Gig+0.064
Thank+0.064
Neg logit contributions
inn-0.061
ches-0.054
icky-0.053
 aid-0.052
nie-0.052
Token she
Token ID673
Feature activation-4.83e-01

Pos logit contributions
inn+0.013
ches+0.012
icky+0.012
 kernel+0.012
 aid+0.011
Neg logit contributions
 disl-0.012
endant-0.009
 killed-0.009
 Sorry-0.009
Thank-0.009
Token would
Token ID561
Feature activation-1.21e-01

Pos logit contributions
inn+0.011
ches+0.010
icky+0.010
 kernel+0.009
nie+0.009
Neg logit contributions
 disl-0.015
 killed-0.012
 Gig-0.012
 Sorry-0.012
endant-0.012
Token remember
Token ID3505
Feature activation+4.45e-01

Pos logit contributions
inn+0.003
ches+0.003
icky+0.003
 kernel+0.003
nie+0.003
Neg logit contributions
 disl-0.003
 killed-0.003
 Gig-0.002
 Sorry-0.002
Thank-0.002
Token the
Token ID262
Feature activation-1.36e-01

Pos logit contributions
 disl+0.013
 killed+0.010
 Gig+0.010
Thank+0.010
 statues+0.010
Neg logit contributions
inn-0.012
icky-0.010
ches-0.010
 kernel-0.010
nie-0.010
Token piano
Token ID19132
Feature activation+6.71e-01

Pos logit contributions
inn+0.004
icky+0.004
ches+0.004
ud+0.003
ide+0.003
Neg logit contributions
 disl-0.004
Thank-0.003
 lucky-0.003
bows-0.003
 killed-0.003
Token and
Token ID290
Feature activation+2.50e-02

Pos logit contributions
 disl+0.021
 killed+0.016
bows+0.016
Thank+0.016
 Sorry+0.016
Neg logit contributions
inn-0.016
icky-0.014
ches-0.014
 kernel-0.013
nie-0.013
Token to
Token ID284
Feature activation-6.82e-02

Pos logit contributions
inn+0.043
nie+0.038
ches+0.037
icky+0.037
 kernel+0.036
Neg logit contributions
 disl-0.062
 killed-0.050
endant-0.050
 jewels-0.050
bows-0.050
Token hold
Token ID1745
Feature activation-3.43e+00

Pos logit contributions
inn+0.002
icky+0.002
ches+0.002
nie+0.002
 kernel+0.002
Neg logit contributions
 disl-0.002
 killed-0.001
 Gig-0.001
Thank-0.001
 Tri-0.001
Token the
Token ID262
Feature activation-7.58e-01

Pos logit contributions
 aid+0.087
ide+0.087
nie+0.086
inn+0.083
ches+0.083
Neg logit contributions
 disl-0.079
 jewels-0.071
 Tri-0.071
 Gig-0.069
 gold-0.068
Token f
Token ID277
Feature activation-1.33e+00

Pos logit contributions
inn+0.018
 kernel+0.016
icky+0.016
 aid+0.016
ches+0.016
Neg logit contributions
 disl-0.023
 Gig-0.018
 Sorry-0.018
bows-0.018
endant-0.018
Tokenauc
Token ID14272
Feature activation-1.66e+00

Pos logit contributions
inn+0.022
ches+0.019
icky+0.019
 kernel+0.018
nie+0.018
Neg logit contributions
 disl-0.050
 killed-0.041
endant-0.041
 Sorry-0.041
 Gig-0.041
Tokenet
Token ID316
Feature activation-3.58e+00

Pos logit contributions
inn+0.027
icky+0.023
 aid+0.022
 kernel+0.022
ches+0.022
Neg logit contributions
 disl-0.063
 killed-0.052
bows-0.051
Thank-0.051
 Gig-0.051
Token up
Token ID510
Feature activation-3.11e+00

Pos logit contributions
inn+0.087
nie+0.081
ud+0.079
Alex+0.079
 aid+0.079
Neg logit contributions
 disl-0.094
 Tri-0.079
ocular-0.078
 Gig-0.076
bows-0.075
Token and
Token ID290
Feature activation-4.65e-01

Pos logit contributions
inn+0.069
ches+0.067
nie+0.065
icky+0.064
 kernel+0.063
Neg logit contributions
 disl-0.085
 jewels-0.075
 Tri-0.073
 killed-0.073
 Gig-0.072
Token support
Token ID1104
Feature activation-6.14e-01

Pos logit contributions
inn+0.012
icky+0.010
ches+0.010
nie+0.010
 kernel+0.010
Neg logit contributions
 disl-0.014
 killed-0.011
Thank-0.011
 Sorry-0.011
 Gig-0.011
Token it
Token ID340
Feature activation-4.03e-01

Pos logit contributions
inn+0.016
ches+0.014
icky+0.013
nie+0.013
 aid+0.013
Neg logit contributions
 disl-0.017
 killed-0.014
 jewels-0.013
 Tri-0.013
Thank-0.013
Token.
Token ID13
Feature activation-8.02e-01

Pos logit contributions
inn+0.009
ches+0.008
icky+0.008
 kernel+0.007
nie+0.007
Neg logit contributions
 disl-0.013
 killed-0.011
Thank-0.010
 Sorry-0.010
 Gig-0.010
Token sharing
Token ID7373
Feature activation+9.88e-01

Pos logit contributions
 disl+0.011
 Gig+0.009
endant+0.009
bows+0.009
 statues+0.009
Neg logit contributions
inn-0.010
 player-0.009
nie-0.009
 scrub-0.009
pron-0.009
Token.
Token ID13
Feature activation+5.71e-01

Pos logit contributions
 disl+0.032
 killed+0.025
Thank+0.025
bows+0.025
 Sorry+0.025
Neg logit contributions
inn-0.023
ches-0.020
icky-0.019
 kernel-0.019
nie-0.019
Token She
Token ID1375
Feature activation+9.28e-01

Pos logit contributions
 disl+0.019
vell+0.017
 killed+0.017
 jewels+0.016
endant+0.016
Neg logit contributions
inn-0.011
 aid-0.009
icky-0.009
 Alex-0.009
 corner-0.009
Token gave
Token ID2921
Feature activation+3.62e-01

Pos logit contributions
 disl+0.025
 Sorry+0.019
 Gig+0.019
bows+0.019
 Tri+0.018
Neg logit contributions
inn-0.025
ches-0.023
nie-0.022
 kernel-0.022
 aid-0.022
Token them
Token ID606
Feature activation-5.56e-02

Pos logit contributions
 disl+0.014
 killed+0.012
 Sorry+0.011
endant+0.011
Thank+0.011
Neg logit contributions
inn-0.006
ches-0.005
icky-0.005
 kernel-0.005
nie-0.005
Token each
Token ID1123
Feature activation-3.86e+00

Pos logit contributions
inn+0.001
ches+0.001
icky+0.001
 kernel+0.001
nie+0.001
Neg logit contributions
 disl-0.002
 killed-0.001
 Gig-0.001
 Sorry-0.001
Thank-0.001
Token a
Token ID257
Feature activation-4.24e-01

Pos logit contributions
inn+0.119
icky+0.106
ches+0.106
ide+0.105
 aid+0.104
Neg logit contributions
 disl-0.083
 Gig-0.068
Thank-0.068
 jewels-0.065
 killed-0.065
Token hug
Token ID16225
Feature activation-5.90e-01

Pos logit contributions
inn+0.011
ches+0.010
icky+0.010
nie+0.010
 kernel+0.010
Neg logit contributions
 disl-0.011
 killed-0.009
endant-0.009
Thank-0.009
 Sorry-0.009
Token and
Token ID290
Feature activation-9.73e-02

Pos logit contributions
inn+0.014
icky+0.012
ches+0.012
 kernel+0.011
nie+0.011
Neg logit contributions
 disl-0.018
bows-0.015
Thank-0.015
 killed-0.015
 Gig-0.015
Token a
Token ID257
Feature activation-1.37e-01

Pos logit contributions
inn+0.002
 kernel+0.002
ches+0.002
 aid+0.002
 scrub+0.002
Neg logit contributions
 disl-0.003
endant-0.002
 Sorry-0.002
 Gig-0.002
 Tri-0.002
Token kiss
Token ID9245
Feature activation-2.07e-01

Pos logit contributions
inn+0.004
ches+0.003
icky+0.003
 kernel+0.003
 aid+0.003
Neg logit contributions
 disl-0.004
 killed-0.003
 Gig-0.003
 Sorry-0.003
endant-0.003
Token can
Token ID460
Feature activation-7.05e-01

Pos logit contributions
inn+0.054
ches+0.051
'+0.047
nie+0.047
icky+0.046
Neg logit contributions
 disl-0.060
 Gig-0.047
mm-0.047
endant-0.045
 statues-0.045
Token use
Token ID779
Feature activation-2.03e+00

Pos logit contributions
inn+0.018
ches+0.017
icky+0.016
 kernel+0.016
 aid+0.016
Neg logit contributions
 disl-0.020
 killed-0.015
 Gig-0.015
endant-0.015
Thank-0.015
Token it
Token ID340
Feature activation-1.14e+00

Pos logit contributions
inn+0.052
icky+0.045
nie+0.045
 kernel+0.044
ches+0.044
Neg logit contributions
 disl-0.059
 killed-0.047
 jewels-0.047
endant-0.045
 Tri-0.045
Token to
Token ID284
Feature activation+2.72e-01

Pos logit contributions
inn+0.021
ches+0.018
icky+0.018
nie+0.017
 kernel+0.016
Neg logit contributions
 disl-0.041
 killed-0.034
 Sorry-0.034
Thank-0.034
 Gig-0.033
Token spray
Token ID11662
Feature activation-9.82e-01

Pos logit contributions
 disl+0.008
 killed+0.006
 Gig+0.006
 Sorry+0.006
endant+0.006
Neg logit contributions
inn-0.007
ches-0.006
icky-0.006
 kernel-0.006
 aid-0.006
Token each
Token ID1123
Feature activation-3.72e+00

Pos logit contributions
inn+0.025
nie+0.022
icky+0.022
 aid+0.021
 kernel+0.021
Neg logit contributions
 disl-0.029
 killed-0.022
 Gig-0.022
 jewels-0.022
 Sorry-0.022
Token other
Token ID584
Feature activation-4.57e-02

Pos logit contributions
inn+0.114
 aid+0.099
pron+0.097
icky+0.096
nie+0.096
Neg logit contributions
 disl-0.082
 killed-0.065
 lucky-0.064
Thank-0.062
 love-0.059
Token!"
Token ID2474
Feature activation-1.12e+00

Pos logit contributions
inn+0.001
ud+0.001
 kernel+0.001
icky+0.001
ches+0.001
Neg logit contributions
 disl-0.001
bows-0.001
 jewels-0.001
 statues-0.001
 killed-0.001
Token
Token ID198
Feature activation-8.59e-01

Pos logit contributions
inn+0.030
ches+0.027
icky+0.026
 kernel+0.026
nie+0.026
Neg logit contributions
 disl-0.031
 Gig-0.024
Thank-0.024
 killed-0.024
 Sorry-0.023
Token
Token ID198
Feature activation-1.03e-01

Pos logit contributions
inn+0.023
nie+0.021
 kernel+0.021
ches+0.020
ash+0.020
Neg logit contributions
 disl-0.023
 Gig-0.018
Thank-0.018
 killed-0.018
 Tri-0.017
TokenThe
Token ID464
Feature activation-2.26e-01

Pos logit contributions
inn+0.003
ches+0.002
icky+0.002
nie+0.002
 kernel+0.002
Neg logit contributions
 disl-0.003
Thank-0.002
 killed-0.002
 Sorry-0.002
 Gig-0.002
Tokenmy
Token ID1820
Feature activation+1.45e-01

Pos logit contributions
 disl+0.036
 Gig+0.029
Thank+0.029
bows+0.029
 Tri+0.028
Neg logit contributions
inn-0.032
ches-0.028
 kernel-0.028
icky-0.027
 aid-0.027
Token,
Token ID11
Feature activation-2.18e+00

Pos logit contributions
 disl+0.004
 Gig+0.003
 jewels+0.003
 statues+0.003
bows+0.003
Neg logit contributions
inn-0.004
 kernel-0.004
ches-0.004
ud-0.004
icky-0.003
Token "
Token ID366
Feature activation+5.60e-01

Pos logit contributions
inn+0.059
ches+0.057
ud+0.054
ler+0.053
 kernel+0.053
Neg logit contributions
 disl-0.057
 Gig-0.049
Thank-0.048
 Tri-0.047
 lucky-0.047
TokenCan
Token ID6090
Feature activation-1.56e-01

Pos logit contributions
 disl+0.014
Thank+0.012
 Gig+0.011
 Sorry+0.011
 killed+0.011
Neg logit contributions
inn-0.016
ches-0.014
icky-0.014
 kernel-0.013
nie-0.013
Token I
Token ID314
Feature activation-1.57e+00

Pos logit contributions
inn+0.005
ches+0.005
icky+0.005
 kernel+0.005
nie+0.005
Neg logit contributions
 disl-0.003
 killed-0.002
 Sorry-0.002
Thank-0.002
 Gig-0.002
Token let
Token ID1309
Feature activation-3.53e+00

Pos logit contributions
inn+0.039
'+0.035
ches+0.034
 aid+0.033
 kernel+0.032
Neg logit contributions
 disl-0.048
bows-0.038
 statues-0.036
 killed-0.036
endant-0.036
Token my
Token ID616
Feature activation+6.29e-01

Pos logit contributions
inn+0.116
ud+0.099
 kernel+0.099
icky+0.098
 aid+0.098
Neg logit contributions
 disl-0.082
 Sorry-0.062
 Gig-0.061
 killed-0.061
 Tri-0.059
Token wallet
Token ID13008
Feature activation+1.09e+00

Pos logit contributions
 disl+0.023
bows+0.019
 killed+0.018
Thank+0.017
vell+0.017
Neg logit contributions
 chair-0.011
 aid-0.011
 hand-0.011
 plate-0.011
'-0.011
Token outside
Token ID2354
Feature activation-1.29e+00

Pos logit contributions
 disl+0.038
 Gig+0.030
Thank+0.029
 killed+0.029
endant+0.029
Neg logit contributions
inn-0.021
ches-0.019
icky-0.018
 kernel-0.018
 aid-0.018
Token?"
Token ID1701
Feature activation-7.10e-01

Pos logit contributions
inn+0.041
ches+0.036
icky+0.035
ud+0.035
 kernel+0.034
Neg logit contributions
 disl-0.030
 Sorry-0.024
 killed-0.022
Thank-0.022
 Gig-0.022
Token Her
Token ID2332
Feature activation-2.76e-01

Pos logit contributions
inn+0.024
 kernel+0.022
ches+0.022
nie+0.021
ud+0.021
Neg logit contributions
 disl-0.015
 Sorry-0.012
 Tri-0.011
Thank-0.011
 Gig-0.011
Token much
Token ID881
Feature activation+7.98e-01

Pos logit contributions
 disl+0.003
 killed+0.002
 Sorry+0.002
endant+0.002
Thank+0.002
Neg logit contributions
inn-0.004
icky-0.004
ches-0.004
 kernel-0.003
nie-0.003
Token that
Token ID326
Feature activation-9.65e-01

Pos logit contributions
 disl+0.026
 Sorry+0.021
 killed+0.020
endant+0.020
Thank+0.020
Neg logit contributions
inn-0.018
ches-0.016
icky-0.016
 kernel-0.015
 aid-0.015
Token she
Token ID673
Feature activation-1.95e-01

Pos logit contributions
inn+0.029
icky+0.026
ches+0.026
 kernel+0.026
nie+0.026
Neg logit contributions
 disl-0.024
 killed-0.017
endant-0.017
bows-0.017
 Sorry-0.017
Token ate
Token ID15063
Feature activation+6.75e-01

Pos logit contributions
inn+0.007
icky+0.006
 aid+0.006
ches+0.006
 kernel+0.006
Neg logit contributions
 disl-0.004
 killed-0.003
Thank-0.003
 Gig-0.003
 Sorry-0.003
Token it
Token ID340
Feature activation-3.14e-01

Pos logit contributions
 disl+0.019
 Gig+0.016
 jewels+0.016
Thank+0.016
 statues+0.016
Neg logit contributions
inn-0.017
ches-0.015
 aid-0.015
nie-0.015
icky-0.014
Token every
Token ID790
Feature activation-3.85e+00

Pos logit contributions
inn+0.008
 aid+0.007
icky+0.007
ches+0.007
 kernel+0.007
Neg logit contributions
 disl-0.009
bows-0.007
Thank-0.007
 Gig-0.007
 jewels-0.007
Token single
Token ID2060
Feature activation-1.42e+00

Pos logit contributions
inn+0.111
ches+0.108
uart+0.105
icky+0.101
ide+0.101
Neg logit contributions
 disl-0.073
Thank-0.070
 lucky-0.069
 Sorry-0.066
 Gig-0.063
Token day
Token ID1110
Feature activation-1.90e+00

Pos logit contributions
inn+0.035
ches+0.034
icky+0.032
uart+0.031
ide+0.030
Neg logit contributions
 disl-0.038
Thank-0.032
 killed-0.031
 jewels-0.031
 Thank-0.030
Token.
Token ID13
Feature activation+3.09e-01

Pos logit contributions
inn+0.052
ches+0.047
icky+0.047
Alex+0.046
nie+0.045
Neg logit contributions
 disl-0.045
 Gig-0.039
Thank-0.038
bows-0.037
 statues-0.037
Token One
Token ID1881
Feature activation-6.82e-01

Pos logit contributions
 disl+0.008
 Gig+0.007
Thank+0.006
bows+0.006
 Sorry+0.006
Neg logit contributions
inn-0.008
ches-0.008
 kernel-0.008
icky-0.007
nie-0.007
Token day
Token ID1110
Feature activation-1.52e-01

Pos logit contributions
ches+0.020
inn+0.019
pan+0.018
uart+0.018
Alex+0.018
Neg logit contributions
 disl-0.015
 lucky-0.014
Thank-0.013
 Gig-0.013
 dear-0.012