TOP ACTIVATIONS
MAX = 0.083

" Can we go outside now ?" Anna and Ben
, " You are welcome , kids . But you still
" What are you doing , Tom and Lily ?" Mom
, " I love you , too , kids . Now
, " You are brave , Sara . You are okay
, " You 're welcome , Tom and Lily . We
" You are brave , Tim and Lily . You
. How about we go outside and you show us your
We are proud of you , Lily . You are a
kind . Can we be friends ?" The bug
, can we go back outside and look for Lily 's
" You are very sweet , Anna and Ben . Now
, " You are welcome , Lily and Tom . This
! Can we be fire men too ?" "
, " You are welcome , my loves . But next
, " You are brave , boys . You faced your
Can we be Rex 's friends ?" The man
why don 't we go inside and have some cookies and
I love you , too , kids . Now , let
, " I love you , Tom and Anna . I

MIN ACTIVATIONS
MIN = -0.101

still wanted to eat something scr um pt ious .
day Sue put on her m ama 's clean cloth .
Daisy was pushing her favourite t eddy bear in the swing
adventure . He took his t eddy bear with him and
a little bit and then scr abb led underneath some nearby
along the road with her t eddy bear and her favorite
made a funny face , scr unch ing up her nose
his bed and asked his t eddy bear , " T
so she put on her m ittens . Sarah looked at
moment , his little face scr unch ing up in concentration
curious . She asked her m ama , " What are
my , carried his favourite t eddy bear with him .
back home and asked his m ama if she could repair
day , she asked her m ama if she could go
day , she took some t edd ies from her bed
boy took his shovel and m op outside to the sandbox
She was wearing her favourite m ittens which were bright and
!" She got on her t ippy toes and stretched out
. She wore her favorite m itten every day . It
The family all grabbed their m ops and put on their

INTERVAL 0.037 - 0.083
CONTAINS 1.944%

'm sorry about your tower , but I 'm very grateful
. You were a good dog ." Tom my
, Sam , you can play with it first . But
think ?" his dad said . Ben looked again
was alone . The end . <|endoftext|> S ara loves spring

INTERVAL -0.009 - 0.037
CONTAINS 65.779%

, and even her toys . She talked when she ate
and see what was behind it . " Sam
. And remember , sometimes it 's good to enjoy the
loved each other very much . One day the
upon a time , there was a big dog named Spot

INTERVAL -0.055 - -0.009
CONTAINS 32.167%

He went over and picked an apple and he said ,
noise from down the street . He stopped to listen .
dad said , " Let 's tie a rope around the
help . He had a great idea - he climbed up
to the big pitch . He said that it was very

INTERVAL -0.101 - -0.055
CONTAINS 0.110%

funny with makeup on her furry face ! L
Lily showed her the torn t eddy bear and said ,
She stood on her t ippy toes and reached up to
Let 's sort the l oll ipop ." The
play with her dolls and t eddy bears . One day
Token
Token ID198
Feature activation-5.18e-03

Pos logit contributions
|+0.018
 thanks+0.016
ount+0.015
 difference+0.014
 Princess+0.014
Neg logit contributions
ittens-0.034
 knees-0.030
 powers-0.029
belt-0.029
 tools-0.029
Token"
Token ID1
Feature activation-1.50e-02

Pos logit contributions
ittens+0.009
belt+0.008
ths+0.008
ised+0.008
 possibly+0.008
Neg logit contributions
|-0.007
 thanks-0.007
 difference-0.006
ount-0.006
 Princess-0.006
TokenCan
Token ID6090
Feature activation-3.10e-02

Pos logit contributions
ittens+0.025
belt+0.024
 knees+0.024
 powers+0.023
ths+0.023
Neg logit contributions
|-0.020
 thanks-0.019
 difference-0.018
ount-0.017
 catches-0.017
Token we
Token ID356
Feature activation-6.83e-03

Pos logit contributions
ittens+0.059
 powers+0.058
iously+0.057
 possessions+0.057
 knees+0.056
Neg logit contributions
|-0.038
Anna-0.035
 thanks-0.033
 cheered-0.031
 Anna-0.031
Token go
Token ID467
Feature activation+2.61e-02

Pos logit contributions
ittens+0.013
 knees+0.012
 powers+0.012
belt+0.012
 possessions+0.012
Neg logit contributions
|-0.008
 thanks-0.007
Anna-0.007
 cheered-0.007
ount-0.007
Token outside
Token ID2354
Feature activation+8.18e-02

Pos logit contributions
|+0.033
 thanks+0.030
Anna+0.030
 cheered+0.029
ount+0.028
Neg logit contributions
 knees-0.045
ittens-0.044
belt-0.043
 powers-0.043
 possessions-0.041
Token now
Token ID783
Feature activation+2.62e-02

Pos logit contributions
|+0.124
ount+0.121
Queen+0.115
Joy+0.107
Pa+0.107
Neg logit contributions
 knees-0.114
belt-0.103
 powers-0.103
ately-0.102
iously-0.101
Token?"
Token ID1701
Feature activation+4.28e-02

Pos logit contributions
|+0.037
ount+0.032
 cheered+0.031
Anna+0.031
 thanks+0.031
Neg logit contributions
 knees-0.044
ittens-0.044
 powers-0.042
belt-0.041
iously-0.041
Token Anna
Token ID11735
Feature activation+4.58e-02

Pos logit contributions
|+0.048
ount+0.041
 difference+0.038
 thanks+0.037
 catches+0.034
Neg logit contributions
 knees-0.084
ittens-0.083
 cheeks-0.078
 powers-0.076
 possibly-0.076
Token and
Token ID290
Feature activation+1.98e-02

Pos logit contributions
|+0.082
 thanks+0.073
ount+0.072
 difference+0.071
Anna+0.070
Neg logit contributions
ittens-0.060
 knees-0.060
iously-0.056
 powers-0.056
belt-0.054
Token Ben
Token ID3932
Feature activation+3.57e-02

Pos logit contributions
|+0.010
 thanks+0.008
Anna+0.008
 cheered+0.006
 Anna+0.006
Neg logit contributions
ittens-0.051
 powers-0.051
 possessions-0.051
belt-0.050
iously-0.049
Token,
Token ID11
Feature activation+1.69e-02

Pos logit contributions
ittens+0.030
 knees+0.029
 powers+0.029
iously+0.028
 possessions+0.028
Neg logit contributions
|-0.021
Anna-0.017
 thanks-0.017
 cheered-0.016
ount-0.016
Token "
Token ID366
Feature activation+1.68e-02

Pos logit contributions
|+0.017
 thanks+0.016
Anna+0.016
 cheered+0.015
ount+0.014
Neg logit contributions
 powers-0.033
 possessions-0.033
ittens-0.033
 knees-0.033
iously-0.033
TokenYou
Token ID1639
Feature activation+3.43e-02

Pos logit contributions
|+0.022
 thanks+0.020
 difference+0.020
ount+0.019
 catches+0.018
Neg logit contributions
ittens-0.029
belt-0.027
bars-0.027
 possessions-0.026
ths-0.026
Token are
Token ID389
Feature activation+2.84e-02

Pos logit contributions
|+0.046
Anna+0.042
 difference+0.041
amp+0.039
ount+0.038
Neg logit contributions
 powers-0.055
 tools-0.054
 possessions-0.052
 possibly-0.051
ittens-0.050
Token welcome
Token ID7062
Feature activation+4.03e-02

Pos logit contributions
|+0.037
ack+0.031
oc+0.030
ount+0.029
 difference+0.029
Neg logit contributions
ittens-0.047
 tools-0.046
 powers-0.045
belt-0.043
 possessions-0.043
Token,
Token ID11
Feature activation+8.16e-02

Pos logit contributions
|+0.069
 cheered+0.057
ount+0.056
 difference+0.055
Anna+0.054
Neg logit contributions
ittens-0.063
 powers-0.055
iously-0.055
 knees-0.055
 cheeks-0.054
Token kids
Token ID3988
Feature activation+4.71e-02

Pos logit contributions
|+0.119
ount+0.087
 cheered+0.086
Queen+0.085
Joy+0.084
Neg logit contributions
ittens-0.152
 knees-0.141
iously-0.138
 cheeks-0.137
 possessions-0.137
Token.
Token ID13
Feature activation+3.47e-02

Pos logit contributions
|+0.096
Queen+0.084
ount+0.084
Nik+0.082
Joy+0.082
Neg logit contributions
ittens-0.047
 powers-0.044
belt-0.044
 knees-0.043
 possessions-0.042
Token But
Token ID887
Feature activation+2.25e-03

Pos logit contributions
|+0.047
ack+0.044
 cheered+0.044
 difference+0.043
ount+0.041
Neg logit contributions
ittens-0.054
belt-0.052
 powers-0.052
 possessions-0.052
 knees-0.051
Token you
Token ID345
Feature activation+2.61e-02

Pos logit contributions
 thanks+0.002
Anna+0.002
 welcome+0.002
 right+0.002
|+0.002
Neg logit contributions
ittens-0.005
iously-0.005
 powers-0.004
belt-0.004
 knees-0.004
Token still
Token ID991
Feature activation+1.44e-03

Pos logit contributions
Anna+0.028
joy+0.027
|+0.027
Kat+0.026
Cl+0.026
Neg logit contributions
 powers-0.043
 possibly-0.042
ittens-0.041
 tools-0.041
row-0.040
Token"
Token ID1
Feature activation-3.75e-03

Pos logit contributions
|+0.005
 thanks+0.004
Anna+0.004
 cheered+0.004
ount+0.004
Neg logit contributions
ittens-0.008
 knees-0.008
 possessions-0.007
 powers-0.007
belt-0.007
TokenWhat
Token ID2061
Feature activation+1.24e-02

Pos logit contributions
ittens+0.005
ths+0.005
 knees+0.005
 possessions+0.005
belt+0.005
Neg logit contributions
|-0.006
 thanks-0.005
 difference-0.005
ount-0.005
ack-0.005
Token are
Token ID389
Feature activation+1.21e-02

Pos logit contributions
|+0.013
ount+0.011
 thanks+0.011
Anna+0.011
 cheered+0.011
Neg logit contributions
ittens-0.024
 powers-0.024
 knees-0.024
 possessions-0.023
 tools-0.023
Token you
Token ID345
Feature activation+2.77e-02

Pos logit contributions
|+0.013
Anna+0.013
 thanks+0.012
 cheered+0.011
 Anna+0.011
Neg logit contributions
 powers-0.023
iously-0.023
ittens-0.023
 knees-0.022
belt-0.022
Token doing
Token ID1804
Feature activation+4.89e-02

Pos logit contributions
|+0.045
 thanks+0.041
Anna+0.041
 cheered+0.039
ount+0.038
Neg logit contributions
ittens-0.042
 knees-0.040
 powers-0.039
 possessions-0.038
iously-0.038
Token,
Token ID11
Feature activation+8.11e-02

Pos logit contributions
|+0.072
 thanks+0.059
ount+0.059
Anna+0.057
 cheered+0.057
Neg logit contributions
ittens-0.082
 powers-0.082
 knees-0.080
ths-0.078
belt-0.078
Token Tom
Token ID4186
Feature activation+5.19e-02

Pos logit contributions
|+0.137
Nik+0.101
ount+0.101
 cheered+0.101
Queen+0.098
Neg logit contributions
ittens-0.134
 knees-0.126
 tools-0.121
ths-0.121
 cheeks-0.118
Token and
Token ID290
Feature activation+3.09e-02

Pos logit contributions
|+0.079
ount+0.064
 Flor+0.061
Joy+0.058
 cheers+0.058
Neg logit contributions
ittens-0.090
row-0.084
 knees-0.083
 tools-0.081
 powers-0.081
Token Lily
Token ID20037
Feature activation+4.97e-02

Pos logit contributions
|+0.009
Anna+0.009
 thanks+0.008
 Anna+0.007
 catches+0.005
Neg logit contributions
 powers-0.086
iously-0.085
ittens-0.084
 possessions-0.084
belt-0.083
Token?"
Token ID1701
Feature activation+3.60e-02

Pos logit contributions
|+0.095
 Flor+0.082
ount+0.080
Joy+0.078
Cl+0.076
Neg logit contributions
ittens-0.059
 tools-0.057
row-0.056
 knees-0.053
 axe-0.053
Token Mom
Token ID11254
Feature activation+2.69e-02

Pos logit contributions
Anna+0.044
 thanks+0.042
|+0.042
 cheered+0.040
 Anna+0.039
Neg logit contributions
 powers-0.066
iously-0.066
ittens-0.065
 possessions-0.064
belt-0.064
Token,
Token ID11
Feature activation+1.94e-02

Pos logit contributions
ittens+0.005
 knees+0.004
 powers+0.004
iously+0.004
 possessions+0.004
Neg logit contributions
|-0.003
 thanks-0.002
Anna-0.002
ount-0.002
 cheered-0.002
Token "
Token ID366
Feature activation+1.94e-02

Pos logit contributions
|+0.026
 thanks+0.023
Anna+0.022
 cheered+0.021
ount+0.021
Neg logit contributions
ittens-0.035
 knees-0.033
 powers-0.033
belt-0.033
 possessions-0.032
TokenI
Token ID40
Feature activation+2.36e-02

Pos logit contributions
|+0.026
ount+0.023
 thanks+0.023
 difference+0.022
 cheered+0.021
Neg logit contributions
ittens-0.033
 powers-0.031
 possessions-0.031
 knees-0.031
belt-0.030
Token love
Token ID1842
Feature activation-6.41e-03

Pos logit contributions
|+0.037
ount+0.036
 Princess+0.032
amp+0.031
 thanks+0.031
Neg logit contributions
ittens-0.031
 powers-0.028
 tools-0.028
 possibly-0.028
 possessions-0.027
Token you
Token ID345
Feature activation+3.95e-02

Pos logit contributions
ittens+0.012
belt+0.012
 knees+0.012
 powers+0.012
 possessions+0.011
Neg logit contributions
|-0.008
 thanks-0.007
Anna-0.007
 cheered-0.007
 catches-0.006
Token,
Token ID11
Feature activation+8.09e-02

Pos logit contributions
|+0.066
ount+0.058
Anna+0.057
 cheered+0.055
 thanks+0.055
Neg logit contributions
ittens-0.061
 knees-0.057
 powers-0.056
iously-0.054
 cheeks-0.054
Token too
Token ID1165
Feature activation+1.73e-02

Pos logit contributions
|+0.100
ount+0.075
Queen+0.072
 cheered+0.072
vy+0.070
Neg logit contributions
ittens-0.167
 knees-0.156
 cheeks-0.150
ths-0.148
iously-0.148
Token,
Token ID11
Feature activation+7.89e-02

Pos logit contributions
|+0.021
Anna+0.018
 thanks+0.017
 cheered+0.017
ount+0.017
Neg logit contributions
ittens-0.034
 knees-0.032
 powers-0.032
iously-0.032
 possessions-0.031
Token kids
Token ID3988
Feature activation+4.68e-02

Pos logit contributions
|+0.103
ount+0.077
 cheered+0.076
Queen+0.074
vy+0.073
Neg logit contributions
ittens-0.157
 knees-0.148
ths-0.141
iously-0.141
 cheeks-0.140
Token.
Token ID13
Feature activation+3.64e-02

Pos logit contributions
|+0.087
ount+0.078
Queen+0.076
Kat+0.076
Nik+0.075
Neg logit contributions
ittens-0.055
 knees-0.051
 powers-0.051
 possessions-0.049
belt-0.048
Token Now
Token ID2735
Feature activation-5.11e-05

Pos logit contributions
|+0.047
 cheered+0.044
ount+0.043
ack+0.043
vy+0.041
Neg logit contributions
ittens-0.059
 powers-0.057
 knees-0.056
belt-0.056
 possessions-0.055
Token,
Token ID11
Feature activation+9.41e-03

Pos logit contributions
ittens+0.041
 knees+0.040
 powers+0.040
 possessions+0.040
iously+0.039
Neg logit contributions
|-0.022
 thanks-0.018
Anna-0.018
 cheered-0.017
ount-0.017
Token "
Token ID366
Feature activation+5.28e-03

Pos logit contributions
|+0.008
 thanks+0.008
Anna+0.008
 cheered+0.007
 Anna+0.007
Neg logit contributions
 powers-0.020
 possessions-0.020
iously-0.019
ittens-0.019
 knees-0.019
TokenYou
Token ID1639
Feature activation+2.80e-02

Pos logit contributions
|+0.007
 thanks+0.006
ount+0.006
 cheered+0.006
 difference+0.006
Neg logit contributions
ittens-0.009
 possessions-0.009
belt-0.009
 knees-0.009
 powers-0.009
Token are
Token ID389
Feature activation+2.56e-02

Pos logit contributions
|+0.026
 thanks+0.022
Anna+0.022
 cheered+0.020
ount+0.019
Neg logit contributions
ittens-0.061
 knees-0.059
 powers-0.059
 possessions-0.059
iously-0.058
Token brave
Token ID14802
Feature activation+2.77e-02

Pos logit contributions
|+0.035
ack+0.030
ount+0.030
 cheered+0.030
Anna+0.029
Neg logit contributions
ittens-0.044
 powers-0.043
 possessions-0.041
 tools-0.041
 knees-0.040
Token,
Token ID11
Feature activation+8.05e-02

Pos logit contributions
|+0.032
ount+0.026
Anna+0.024
Queen+0.023
Joy+0.022
Neg logit contributions
 powers-0.056
 knees-0.056
ittens-0.056
 possessions-0.055
iously-0.054
Token Sara
Token ID24799
Feature activation+3.47e-02

Pos logit contributions
|+0.090
 cheered+0.068
ount+0.066
Queen+0.062
ack+0.061
Neg logit contributions
ittens-0.177
 knees-0.168
iously-0.165
 cheeks-0.162
 possessions-0.156
Token.
Token ID13
Feature activation+2.79e-02

Pos logit contributions
|+0.066
ount+0.058
 blast+0.052
Col+0.051
Joy+0.050
Neg logit contributions
ittens-0.050
 knees-0.045
 powers-0.044
 possessions-0.044
 tools-0.044
Token You
Token ID921
Feature activation+3.33e-02

Pos logit contributions
|+0.033
 cheered+0.030
 thanks+0.028
Anna+0.028
ack+0.028
Neg logit contributions
ittens-0.052
 powers-0.050
 knees-0.050
 possessions-0.049
belt-0.049
Token are
Token ID389
Feature activation+2.72e-02

Pos logit contributions
|+0.032
Anna+0.028
 thanks+0.027
ount+0.025
 difference+0.025
Neg logit contributions
 powers-0.069
ittens-0.068
 knees-0.067
 possessions-0.067
iously-0.065
Token okay
Token ID8788
Feature activation+1.13e-02

Pos logit contributions
|+0.040
ack+0.035
ount+0.035
 cheered+0.033
Anna+0.033
Neg logit contributions
 powers-0.045
ittens-0.043
 possessions-0.042
 tools-0.042
 knees-0.041
Token,
Token ID11
Feature activation+1.64e-02

Pos logit contributions
ittens+0.008
 knees+0.008
 powers+0.008
iously+0.008
 cheeks+0.008
Neg logit contributions
|-0.006
 thanks-0.005
Anna-0.005
ount-0.005
 difference-0.005
Token "
Token ID366
Feature activation+1.53e-02

Pos logit contributions
|+0.026
Anna+0.022
 thanks+0.022
 difference+0.022
 cheered+0.021
Neg logit contributions
ittens-0.026
 knees-0.024
belt-0.024
iously-0.023
 powers-0.023
TokenYou
Token ID1639
Feature activation+3.25e-02

Pos logit contributions
|+0.019
 thanks+0.018
 difference+0.017
ount+0.017
 catches+0.016
Neg logit contributions
ittens-0.027
ths-0.025
 possessions-0.024
bars-0.024
belt-0.024
Token're
Token ID821
Feature activation+2.21e-02

Pos logit contributions
|+0.046
Anna+0.042
ount+0.040
Joy+0.039
 difference+0.038
Neg logit contributions
 powers-0.051
 tools-0.050
 possessions-0.048
ittens-0.047
 knees-0.047
Token welcome
Token ID7062
Feature activation+4.28e-02

Pos logit contributions
|+0.027
oc+0.022
 catches+0.022
ount+0.021
 cheered+0.021
Neg logit contributions
ittens-0.038
 tools-0.037
ble-0.036
 powers-0.035
ths-0.035
Token,
Token ID11
Feature activation+8.04e-02

Pos logit contributions
|+0.080
ount+0.065
 cheered+0.065
Queen+0.064
 difference+0.063
Neg logit contributions
ittens-0.059
 knees-0.052
iously-0.052
 cheeks-0.052
 powers-0.051
Token Tom
Token ID4186
Feature activation+4.92e-02

Pos logit contributions
|+0.131
ount+0.097
Queen+0.097
Nik+0.096
Joy+0.095
Neg logit contributions
ittens-0.134
 knees-0.127
ths-0.126
 cheeks-0.124
iously-0.122
Token and
Token ID290
Feature activation+2.79e-02

Pos logit contributions
|+0.092
ount+0.077
 blast+0.070
Joy+0.070
 Flor+0.069
Neg logit contributions
ittens-0.072
row-0.068
 knees-0.067
 powers-0.066
iously-0.065
Token Lily
Token ID20037
Feature activation+3.68e-02

Pos logit contributions
|+0.027
ount+0.021
 difference+0.020
Queen+0.020
 thanks+0.020
Neg logit contributions
ittens-0.059
 knees-0.059
 possessions-0.056
belt-0.055
 cheeks-0.055
Token.
Token ID13
Feature activation+4.07e-02

Pos logit contributions
|+0.078
ount+0.070
Joy+0.067
Kat+0.066
Queen+0.066
Neg logit contributions
 knees-0.035
 powers-0.035
 tools-0.033
 cheeks-0.032
 possessions-0.032
Token We
Token ID775
Feature activation+2.15e-02

Pos logit contributions
|+0.057
ack+0.054
 cheered+0.054
vy+0.052
Joy+0.051
Neg logit contributions
 possessions-0.056
 powers-0.056
 knees-0.055
ittens-0.055
belt-0.054
Token
Token ID198
Feature activation+5.63e-03

Pos logit contributions
|+0.017
 thanks+0.016
 difference+0.014
ount+0.014
 cheered+0.013
Neg logit contributions
ittens-0.046
 knees-0.041
 powers-0.041
 possessions-0.040
belt-0.040
Token"
Token ID1
Feature activation-5.98e-03

Pos logit contributions
|+0.007
 thanks+0.007
 difference+0.006
ount+0.006
 cheered+0.006
Neg logit contributions
ittens-0.010
 possessions-0.010
 knees-0.010
belt-0.010
 powers-0.009
TokenYou
Token ID1639
Feature activation+2.94e-02

Pos logit contributions
ittens+0.012
 knees+0.011
 powers+0.011
 possessions+0.011
iously+0.011
Neg logit contributions
|-0.007
 thanks-0.006
Anna-0.006
 cheered-0.006
ount-0.005
Token are
Token ID389
Feature activation+2.98e-02

Pos logit contributions
|+0.033
Anna+0.031
ount+0.028
 thanks+0.028
 difference+0.028
Neg logit contributions
 powers-0.054
ittens-0.054
 knees-0.053
 possessions-0.052
 tools-0.052
Token brave
Token ID14802
Feature activation+2.64e-02

Pos logit contributions
|+0.047
ack+0.043
ount+0.040
 difference+0.040
Anna+0.039
Neg logit contributions
ittens-0.041
 powers-0.041
 tools-0.041
ths-0.038
 possessions-0.037
Token,
Token ID11
Feature activation+8.03e-02

Pos logit contributions
|+0.032
ount+0.025
Anna+0.024
Queen+0.023
Joy+0.023
Neg logit contributions
 powers-0.052
 knees-0.052
ittens-0.052
iously-0.051
 possessions-0.051
Token Tim
Token ID5045
Feature activation+3.77e-02

Pos logit contributions
|+0.095
Anna+0.073
Nik+0.073
Queen+0.072
ount+0.072
Neg logit contributions
ittens-0.162
 knees-0.156
 cheeks-0.151
iously-0.151
 possessions-0.149
Token and
Token ID290
Feature activation+1.26e-02

Pos logit contributions
|+0.066
ount+0.059
 blast+0.054
Joy+0.053
Col+0.052
Neg logit contributions
ittens-0.054
 powers-0.051
 knees-0.051
row-0.051
 possessions-0.050
Token Lily
Token ID20037
Feature activation+2.93e-02

Pos logit contributions
|+0.007
 thanks+0.007
Anna+0.006
 Anna+0.005
 cheered+0.005
Neg logit contributions
ittens-0.031
 powers-0.031
iously-0.031
 knees-0.031
belt-0.030
Token.
Token ID13
Feature activation+2.57e-02

Pos logit contributions
|+0.048
ount+0.043
Anna+0.040
Joy+0.040
Col+0.039
Neg logit contributions
 powers-0.043
 possessions-0.041
 knees-0.041
ittens-0.040
 tools-0.039
Token You
Token ID921
Feature activation+3.90e-02

Pos logit contributions
|+0.031
 cheered+0.029
ack+0.026
Anna+0.026
 difference+0.026
Neg logit contributions
ittens-0.046
 powers-0.043
belt-0.043
 possessions-0.043
 knees-0.043
Token.
Token ID13
Feature activation+2.52e-02

Pos logit contributions
|+0.059
Anna+0.051
 thanks+0.051
ount+0.050
Queen+0.048
Neg logit contributions
ittens-0.078
 powers-0.078
 knees-0.077
belt-0.077
 possessions-0.075
Token How
Token ID1374
Feature activation-8.06e-05

Pos logit contributions
|+0.032
 cheered+0.028
Anna+0.027
ount+0.026
 thanks+0.026
Neg logit contributions
ittens-0.045
 powers-0.044
 knees-0.043
belt-0.043
 possessions-0.042
Token about
Token ID546
Feature activation+1.03e-03

Pos logit contributions
ittens+0.000
 powers+0.000
 knees+0.000
 possessions+0.000
belt+0.000
Neg logit contributions
|-0.000
 thanks-0.000
Anna-0.000
 cheered-0.000
ount-0.000
Token we
Token ID356
Feature activation+1.75e-02

Pos logit contributions
|+0.001
 thanks+0.001
Anna+0.001
 catches+0.001
 cheered+0.001
Neg logit contributions
ittens-0.002
belt-0.002
 possessions-0.002
iously-0.002
 knees-0.002
Token go
Token ID467
Feature activation+2.73e-02

Pos logit contributions
|+0.022
 thanks+0.020
Anna+0.020
 cheered+0.019
ount+0.018
Neg logit contributions
ittens-0.032
 knees-0.031
 powers-0.031
 possessions-0.031
iously-0.030
Token outside
Token ID2354
Feature activation+8.01e-02

Pos logit contributions
|+0.035
Anna+0.031
 thanks+0.031
 cheered+0.030
ount+0.029
Neg logit contributions
ittens-0.049
 knees-0.048
 powers-0.047
belt-0.047
 possessions-0.046
Token and
Token ID290
Feature activation-7.68e-03

Pos logit contributions
|+0.101
ount+0.094
Queen+0.087
Joy+0.086
Anna+0.083
Neg logit contributions
 knees-0.139
belt-0.133
 powers-0.132
ittens-0.131
 tools-0.127
Token you
Token ID345
Feature activation+3.41e-02

Pos logit contributions
ittens+0.017
iously+0.016
 powers+0.016
 possessions+0.016
belt+0.016
Neg logit contributions
|-0.007
 thanks-0.006
Anna-0.006
 cheered-0.006
 catches-0.005
Token show
Token ID905
Feature activation+1.38e-02

Pos logit contributions
|+0.038
 thanks+0.033
Anna+0.032
 cheered+0.031
ount+0.029
Neg logit contributions
ittens-0.068
 knees-0.066
 powers-0.066
 possessions-0.065
iously-0.065
Token us
Token ID514
Feature activation+1.78e-02

Pos logit contributions
|+0.017
 thanks+0.015
Anna+0.015
 cheered+0.014
ount+0.013
Neg logit contributions
ittens-0.026
 knees-0.025
 powers-0.025
 possessions-0.025
iously-0.025
Token your
Token ID534
Feature activation-2.93e-02

Pos logit contributions
|+0.022
 thanks+0.020
Anna+0.020
 cheered+0.019
ount+0.018
Neg logit contributions
ittens-0.032
 powers-0.032
 knees-0.032
 possessions-0.031
iously-0.031
TokenWe
Token ID1135
Feature activation+1.56e-02

Pos logit contributions
ittens+0.014
 knees+0.014
iously+0.014
 powers+0.014
 possessions+0.014
Neg logit contributions
|-0.007
Anna-0.006
 thanks-0.006
 cheered-0.006
Queen-0.005
Token are
Token ID389
Feature activation+2.60e-02

Pos logit contributions
|+0.021
Anna+0.019
ount+0.017
 difference+0.017
Nik+0.017
Neg logit contributions
 powers-0.026
ittens-0.025
 possessions-0.025
 knees-0.025
 tools-0.025
Token proud
Token ID6613
Feature activation+1.75e-02

Pos logit contributions
|+0.051
Anna+0.040
ack+0.039
Nik+0.037
 catches+0.037
Neg logit contributions
ittens-0.034
ble-0.032
 powers-0.031
 knees-0.030
bled-0.030
Token of
Token ID286
Feature activation+2.96e-02

Pos logit contributions
|+0.026
ount+0.021
Anna+0.021
Queen+0.020
 cheered+0.020
Neg logit contributions
 powers-0.029
ittens-0.029
 knees-0.029
 possessions-0.028
iously-0.027
Token you
Token ID345
Feature activation+4.71e-02

Pos logit contributions
|+0.038
 thanks+0.035
Anna+0.034
 cheered+0.033
 difference+0.031
Neg logit contributions
ittens-0.053
 knees-0.051
 powers-0.051
belt-0.051
 possessions-0.050
Token,
Token ID11
Feature activation+7.99e-02

Pos logit contributions
|+0.082
ount+0.072
Queen+0.069
Anna+0.069
Col+0.067
Neg logit contributions
ittens-0.072
 knees-0.070
iously-0.070
 cheeks-0.067
 powers-0.063
Token Lily
Token ID20037
Feature activation+4.13e-02

Pos logit contributions
|+0.117
ount+0.090
 cheered+0.086
Nik+0.085
vy+0.084
Neg logit contributions
ittens-0.144
 knees-0.141
 cheeks-0.134
 possessions-0.132
 tools-0.131
Token.
Token ID13
Feature activation+3.31e-02

Pos logit contributions
|+0.081
ount+0.074
 blast+0.067
Joy+0.067
Col+0.066
Neg logit contributions
ittens-0.051
 knees-0.050
 powers-0.048
 possessions-0.047
iously-0.047
Token You
Token ID921
Feature activation+3.95e-02

Pos logit contributions
|+0.044
 cheered+0.041
ack+0.041
Anna+0.040
 cal+0.040
Neg logit contributions
 powers-0.051
 knees-0.050
ittens-0.049
belt-0.048
 possessions-0.048
Token are
Token ID389
Feature activation+3.40e-02

Pos logit contributions
|+0.045
Anna+0.042
 difference+0.038
ount+0.037
ack+0.037
Neg logit contributions
 powers-0.074
 tools-0.070
 possessions-0.069
 knees-0.068
 cheeks-0.067
Token a
Token ID257
Feature activation+6.27e-02

Pos logit contributions
|+0.063
ack+0.057
ount+0.052
amp+0.050
 catches+0.049
Neg logit contributions
 powers-0.046
 tools-0.042
 possessions-0.041
nam-0.040
ths-0.038
Token kind
Token ID1611
Feature activation+7.42e-03

Pos logit contributions
ittens+0.005
iously+0.005
belt+0.005
 powers+0.005
 knees+0.005
Neg logit contributions
 thanks-0.002
|-0.002
Anna-0.002
 cheered-0.002
 welcome-0.002
Token.
Token ID13
Feature activation+2.55e-02

Pos logit contributions
|+0.008
Anna+0.007
 thanks+0.006
ount+0.006
 cheered+0.006
Neg logit contributions
 powers-0.015
ittens-0.015
 knees-0.015
 possessions-0.015
iously-0.015
Token Can
Token ID1680
Feature activation-2.94e-02

Pos logit contributions
|+0.031
 cheered+0.026
 thanks+0.026
Anna+0.025
ack+0.025
Neg logit contributions
ittens-0.046
 knees-0.045
 powers-0.045
belt-0.044
 possessions-0.043
Token we
Token ID356
Feature activation+7.85e-03

Pos logit contributions
 powers+0.061
ittens+0.060
iously+0.060
 possessions+0.060
belt+0.058
Neg logit contributions
|-0.030
Anna-0.028
 thanks-0.026
 Anna-0.026
 cheered-0.023
Token be
Token ID307
Feature activation+3.13e-02

Pos logit contributions
|+0.012
Anna+0.010
 cheered+0.010
 thanks+0.010
ount+0.010
Neg logit contributions
ittens-0.012
 knees-0.012
 powers-0.012
belt-0.011
 possessions-0.011
Token friends
Token ID2460
Feature activation+7.99e-02

Pos logit contributions
|+0.069
ount+0.060
amp+0.058
oke+0.056
Anna+0.055
Neg logit contributions
 powers-0.033
 knees-0.031
ittens-0.030
 possessions-0.030
 tools-0.029
Token?"
Token ID1701
Feature activation+3.69e-02

Pos logit contributions
|+0.122
ount+0.107
 thanks+0.095
Anna+0.093
Joy+0.093
Neg logit contributions
 powers-0.125
ittens-0.121
 knees-0.117
belt-0.116
 possessions-0.113
Token
Token ID198
Feature activation+2.02e-02

Pos logit contributions
|+0.039
ount+0.030
 difference+0.028
 thanks+0.027
 cheered+0.026
Neg logit contributions
ittens-0.080
 knees-0.078
 possibly-0.072
 powers-0.071
iously-0.070
Token
Token ID198
Feature activation-9.62e-03

Pos logit contributions
|+0.022
ount+0.018
 thanks+0.017
 difference+0.016
 cheered+0.015
Neg logit contributions
ittens-0.043
 knees-0.040
 powers-0.038
 tools-0.037
 possibly-0.036
TokenThe
Token ID464
Feature activation+1.98e-02

Pos logit contributions
ittens+0.018
 knees+0.017
ised+0.016
 possibly+0.016
 tools+0.016
Neg logit contributions
|-0.013
ount-0.011
 thanks-0.011
 difference-0.010
 Princess-0.009
Token bug
Token ID5434
Feature activation+1.97e-02

Pos logit contributions
|+0.029
Anna+0.027
 thanks+0.027
 cheered+0.025
 difference+0.024
Neg logit contributions
ittens-0.032
 powers-0.031
belt-0.031
 knees-0.031
iously-0.031
Token,
Token ID11
Feature activation+1.70e-02

Pos logit contributions
|+0.022
Anna+0.017
ount+0.017
Joy+0.017
Queen+0.016
Neg logit contributions
ittens-0.024
iously-0.023
 knees-0.023
 powers-0.023
 cheeks-0.022
Token can
Token ID460
Feature activation-2.98e-02

Pos logit contributions
|+0.025
Anna+0.022
 thanks+0.022
 cheered+0.022
ount+0.021
Neg logit contributions
ittens-0.027
 knees-0.027
 powers-0.026
 possessions-0.026
belt-0.026
Token we
Token ID356
Feature activation+3.28e-03

Pos logit contributions
 possessions+0.060
 powers+0.060
iously+0.060
belt+0.059
ittens+0.059
Neg logit contributions
|-0.032
Anna-0.030
 thanks-0.029
 Anna-0.028
 cheered-0.026
Token go
Token ID467
Feature activation+2.62e-02

Pos logit contributions
|+0.004
Anna+0.003
 thanks+0.003
 cheered+0.003
ount+0.003
Neg logit contributions
ittens-0.006
 knees-0.006
 powers-0.006
belt-0.006
 possessions-0.006
Token back
Token ID736
Feature activation+3.13e-02

Pos logit contributions
|+0.037
Anna+0.034
 thanks+0.034
 cheered+0.034
 difference+0.033
Neg logit contributions
 knees-0.040
ittens-0.040
belt-0.040
 powers-0.038
 possessions-0.036
Token outside
Token ID2354
Feature activation+7.98e-02

Pos logit contributions
|+0.048
ount+0.046
 cheered+0.045
 difference+0.044
 thanks+0.043
Neg logit contributions
 knees-0.044
ittens-0.042
 powers-0.042
belt-0.042
 tools-0.040
Token and
Token ID290
Feature activation-9.23e-03

Pos logit contributions
ount+0.116
|+0.114
Queen+0.104
Joy+0.099
Pa+0.098
Neg logit contributions
 knees-0.117
 powers-0.108
belt-0.106
ately-0.106
iously-0.105
Token look
Token ID804
Feature activation+4.59e-02

Pos logit contributions
ittens+0.018
 knees+0.017
 powers+0.017
 possessions+0.017
belt+0.017
Neg logit contributions
|-0.011
 thanks-0.009
Anna-0.009
 cheered-0.009
ount-0.008
Token for
Token ID329
Feature activation+2.42e-02

Pos logit contributions
|+0.079
Queen+0.067
ount+0.062
Joy+0.062
Anna+0.061
Neg logit contributions
 knees-0.068
ittens-0.065
 possessions-0.064
 powers-0.062
ised-0.062
Token Lily
Token ID20037
Feature activation+4.11e-02

Pos logit contributions
 thanks+0.027
|+0.025
Anna+0.025
 Anna+0.024
 Sara+0.023
Neg logit contributions
belt-0.047
ittens-0.045
 possessions-0.044
iously-0.044
bars-0.044
Token's
Token ID338
Feature activation-1.81e-02

Pos logit contributions
|+0.054
 cheered+0.047
ount+0.047
 thanks+0.046
 cheers+0.045
Neg logit contributions
ittens-0.072
belt-0.068
 powers-0.067
 knees-0.067
 possessions-0.064
Token "
Token ID366
Feature activation+7.61e-03

Pos logit contributions
|+0.017
 thanks+0.015
Anna+0.015
 cheered+0.014
ount+0.013
Neg logit contributions
ittens-0.026
 knees-0.025
 powers-0.025
 possessions-0.025
iously-0.024
TokenYou
Token ID1639
Feature activation+3.09e-02

Pos logit contributions
|+0.007
ount+0.007
 difference+0.006
 thanks+0.006
 catches+0.005
Neg logit contributions
bars-0.014
ittens-0.014
ths-0.014
belt-0.014
 possessions-0.014
Token are
Token ID389
Feature activation+2.64e-02

Pos logit contributions
|+0.035
Anna+0.029
ount+0.028
 difference+0.027
ack+0.026
Neg logit contributions
 powers-0.059
 tools-0.058
 possessions-0.057
 knees-0.056
ittens-0.055
Token very
Token ID845
Feature activation+1.18e-02

Pos logit contributions
|+0.040
ack+0.034
ount+0.032
 cheered+0.032
oc+0.031
Neg logit contributions
 tools-0.040
 powers-0.040
ittens-0.039
ths-0.038
 possessions-0.037
Token sweet
Token ID6029
Feature activation+1.31e-02

Pos logit contributions
|+0.017
 difference+0.014
 thanks+0.014
 cheered+0.014
ount+0.014
Neg logit contributions
ittens-0.020
 possessions-0.019
 powers-0.019
belt-0.018
 knees-0.017
Token,
Token ID11
Feature activation+7.97e-02

Pos logit contributions
|+0.019
ount+0.015
Joy+0.013
 catches+0.013
 cheered+0.013
Neg logit contributions
ittens-0.024
 knees-0.023
 powers-0.023
iously-0.023
 cheeks-0.022
Token Anna
Token ID11735
Feature activation+4.56e-02

Pos logit contributions
|+0.106
ount+0.083
 cheered+0.072
Queen+0.070
vy+0.066
Neg logit contributions
 knees-0.154
 cheeks-0.151
ittens-0.150
iously-0.148
 eyes-0.143
Token and
Token ID290
Feature activation+3.27e-02

Pos logit contributions
|+0.088
ount+0.079
Col+0.066
Joy+0.066
Goal+0.065
Neg logit contributions
 powers-0.060
ittens-0.058
 knees-0.056
 tools-0.056
 possessions-0.054
Token Ben
Token ID3932
Feature activation+3.12e-02

Pos logit contributions
|+0.020
 thanks+0.017
Anna+0.016
 cheered+0.014
ount+0.012
Neg logit contributions
ittens-0.080
 knees-0.079
 powers-0.079
 possessions-0.078
iously-0.077
Token.
Token ID13
Feature activation+3.08e-02

Pos logit contributions
|+0.059
ount+0.053
Joy+0.049
Kat+0.047
Queen+0.046
Neg logit contributions
 powers-0.040
 possessions-0.038
 tools-0.037
 knees-0.036
ittens-0.035
Token Now
Token ID2735
Feature activation-4.93e-03

Pos logit contributions
|+0.042
 cheered+0.039
ack+0.039
vy+0.038
 difference+0.037
Neg logit contributions
ittens-0.048
 powers-0.046
belt-0.045
 knees-0.045
 possessions-0.044
Token,
Token ID11
Feature activation+1.32e-02

Pos logit contributions
ittens+0.011
 knees+0.011
 powers+0.011
iously+0.011
 cheeks+0.010
Neg logit contributions
|-0.008
 thanks-0.007
Anna-0.007
ount-0.007
 cheered-0.006
Token "
Token ID366
Feature activation+1.15e-02

Pos logit contributions
|+0.018
 thanks+0.015
Anna+0.015
 cheered+0.015
ount+0.014
Neg logit contributions
ittens-0.023
 knees-0.023
 powers-0.022
belt-0.022
iously-0.022
TokenYou
Token ID1639
Feature activation+2.89e-02

Pos logit contributions
|+0.015
 thanks+0.014
ount+0.014
 difference+0.013
 catches+0.013
Neg logit contributions
ittens-0.020
 possessions-0.018
 powers-0.017
 knees-0.017
ths-0.017
Token are
Token ID389
Feature activation+2.31e-02

Pos logit contributions
|+0.041
Anna+0.035
 difference+0.035
ount+0.033
amp+0.033
Neg logit contributions
 powers-0.045
 tools-0.045
ittens-0.044
 possibly-0.043
 possessions-0.043
Token welcome
Token ID7062
Feature activation+3.57e-02

Pos logit contributions
|+0.029
ack+0.022
 cheered+0.021
ount+0.021
 difference+0.020
Neg logit contributions
ittens-0.043
 tools-0.040
 powers-0.040
 possessions-0.038
ble-0.038
Token,
Token ID11
Feature activation+7.96e-02

Pos logit contributions
|+0.060
 cheered+0.051
ount+0.048
Anna+0.047
 difference+0.046
Neg logit contributions
ittens-0.057
 knees-0.051
iously-0.051
 powers-0.050
 cheeks-0.050
Token Lily
Token ID20037
Feature activation+4.47e-02

Pos logit contributions
|+0.113
ount+0.084
vy+0.081
 cheered+0.080
Queen+0.080
Neg logit contributions
ittens-0.150
 knees-0.142
 cheeks-0.138
ths-0.136
iously-0.136
Token and
Token ID290
Feature activation+2.27e-02

Pos logit contributions
|+0.095
ount+0.086
Col+0.076
 blast+0.076
Joy+0.075
Neg logit contributions
ittens-0.050
 knees-0.048
 powers-0.046
row-0.046
 tools-0.045
Token Tom
Token ID4186
Feature activation+2.99e-02

Pos logit contributions
|+0.017
 thanks+0.016
Anna+0.015
 cheered+0.014
 catches+0.012
Neg logit contributions
ittens-0.053
 powers-0.052
 knees-0.051
 possessions-0.051
iously-0.051
Token.
Token ID13
Feature activation+2.94e-02

Pos logit contributions
|+0.057
ount+0.050
Kat+0.048
Queen+0.046
 blast+0.046
Neg logit contributions
 powers-0.037
 possessions-0.034
 knees-0.033
 tools-0.033
ittens-0.033
Token This
Token ID770
Feature activation+1.20e-02

Pos logit contributions
|+0.040
 cheered+0.037
ack+0.035
vy+0.034
ount+0.034
Neg logit contributions
ittens-0.047
 powers-0.045
 knees-0.045
 possessions-0.045
belt-0.044
Token!
Token ID0
Feature activation+1.52e-02

Pos logit contributions
|+0.008
Anna+0.006
ount+0.006
Queen+0.005
 difference+0.005
Neg logit contributions
ittens-0.018
iously-0.018
 knees-0.018
 powers-0.017
 possessions-0.017
Token Can
Token ID1680
Feature activation-3.47e-02

Pos logit contributions
|+0.022
Anna+0.019
 thanks+0.019
 difference+0.019
 cheered+0.019
Neg logit contributions
ittens-0.024
belt-0.023
 knees-0.023
 powers-0.023
bars-0.022
Token we
Token ID356
Feature activation-2.75e-03

Pos logit contributions
 powers+0.071
 possessions+0.070
ittens+0.069
iously+0.069
 knees+0.067
Neg logit contributions
|-0.038
Anna-0.033
 thanks-0.032
 Anna-0.030
 catches-0.029
Token be
Token ID307
Feature activation+2.27e-02

Pos logit contributions
ittens+0.004
 knees+0.004
 powers+0.004
belt+0.004
 possibly+0.004
Neg logit contributions
|-0.004
Anna-0.004
 cheered-0.004
 thanks-0.004
ount-0.003
Token fire
Token ID2046
Feature activation+4.53e-02

Pos logit contributions
|+0.043
Anna+0.039
 difference+0.037
ount+0.036
oke+0.036
Neg logit contributions
 powers-0.030
 knees-0.028
ittens-0.027
 tools-0.026
 possessions-0.026
Tokenmen
Token ID3653
Feature activation+7.95e-02

Pos logit contributions
|+0.067
Anna+0.059
 thanks+0.058
 cheered+0.056
Joy+0.053
Neg logit contributions
ittens-0.073
 powers-0.072
 knees-0.072
belt-0.071
iously-0.070
Token too
Token ID1165
Feature activation+1.15e-02

Pos logit contributions
|+0.124
 thanks+0.105
Anna+0.102
ount+0.101
Joy+0.100
Neg logit contributions
belt-0.116
ittens-0.115
ths-0.109
 knees-0.108
 powers-0.108
Token?"
Token ID1701
Feature activation+2.29e-02

Pos logit contributions
|+0.014
 thanks+0.012
Anna+0.012
 cheered+0.011
ount+0.011
Neg logit contributions
ittens-0.022
 knees-0.021
 powers-0.021
belt-0.021
 possessions-0.021
Token
Token ID198
Feature activation+6.56e-03

Pos logit contributions
|+0.022
ount+0.017
 thanks+0.017
 difference+0.017
Anna+0.017
Neg logit contributions
ittens-0.049
 knees-0.049
 powers-0.046
iously-0.046
belt-0.045
Token
Token ID198
Feature activation-1.93e-02

Pos logit contributions
|+0.008
 thanks+0.008
ount+0.007
 difference+0.007
 seeker+0.007
Neg logit contributions
ittens-0.012
 knees-0.010
ised-0.010
belt-0.010
row-0.010
Token"
Token ID1
Feature activation-2.22e-02

Pos logit contributions
ittens+0.030
belt+0.029
ths+0.028
ised+0.028
row+0.027
Neg logit contributions
|-0.030
 thanks-0.027
ount-0.026
 difference-0.026
 Flor-0.022
Token,
Token ID11
Feature activation+1.45e-02

Pos logit contributions
ittens+0.016
 knees+0.015
 powers+0.015
 possessions+0.015
belt+0.015
Neg logit contributions
|-0.012
 thanks-0.011
Anna-0.010
 cheered-0.010
ount-0.010
Token "
Token ID366
Feature activation+1.79e-02

Pos logit contributions
|+0.017
 thanks+0.015
Anna+0.015
 cheered+0.015
ount+0.014
Neg logit contributions
ittens-0.027
 powers-0.027
 knees-0.027
 possessions-0.027
iously-0.026
TokenYou
Token ID1639
Feature activation+3.71e-02

Pos logit contributions
|+0.023
 thanks+0.020
ount+0.020
 difference+0.020
 catches+0.019
Neg logit contributions
ittens-0.032
 possessions-0.029
belt-0.029
 powers-0.029
bars-0.029
Token are
Token ID389
Feature activation+3.54e-02

Pos logit contributions
|+0.052
Anna+0.046
ount+0.044
 difference+0.044
ack+0.043
Neg logit contributions
 powers-0.060
 tools-0.059
ittens-0.058
 possessions-0.056
 knees-0.056
Token welcome
Token ID7062
Feature activation+4.27e-02

Pos logit contributions
|+0.048
ount+0.041
ack+0.040
 catches+0.037
 cheered+0.037
Neg logit contributions
ittens-0.059
 tools-0.058
 powers-0.058
 possessions-0.054
ths-0.054
Token,
Token ID11
Feature activation+7.93e-02

Pos logit contributions
|+0.075
 cheered+0.061
ount+0.061
Anna+0.058
ack+0.058
Neg logit contributions
ittens-0.067
 cheeks-0.059
 powers-0.059
iously-0.059
 knees-0.058
Token my
Token ID616
Feature activation+1.66e-03

Pos logit contributions
|+0.124
ount+0.093
 cheered+0.091
Queen+0.091
Joy+0.088
Neg logit contributions
ittens-0.140
 knees-0.132
 cheeks-0.127
 tools-0.126
ths-0.126
Token loves
Token ID10408
Feature activation+1.10e-02

Pos logit contributions
|+0.003
ount+0.002
Anna+0.002
Queen+0.002
Joy+0.002
Neg logit contributions
ittens-0.003
 powers-0.003
 knees-0.003
 possessions-0.003
 cheeks-0.003
Token.
Token ID13
Feature activation+3.24e-02

Pos logit contributions
|+0.011
 thanks+0.010
Anna+0.010
 cheered+0.009
ount+0.008
Neg logit contributions
ittens-0.023
 knees-0.022
 powers-0.022
 possessions-0.022
iously-0.022
Token But
Token ID887
Feature activation+4.89e-03

Pos logit contributions
|+0.041
 cheered+0.039
ack+0.037
ount+0.036
 difference+0.035
Neg logit contributions
ittens-0.055
 powers-0.053
belt-0.052
 possessions-0.052
 knees-0.051
Token next
Token ID1306
Feature activation-4.71e-03

Pos logit contributions
 thanks+0.005
|+0.005
Anna+0.005
 welcome+0.005
 right+0.005
Neg logit contributions
ittens-0.009
iously-0.009
belt-0.009
 knees-0.009
 powers-0.009
Token,
Token ID11
Feature activation+1.28e-02

Pos logit contributions
ittens+0.032
 knees+0.031
 powers+0.031
 possessions+0.030
iously+0.030
Neg logit contributions
|-0.023
 thanks-0.019
Anna-0.018
 cheered-0.018
 difference-0.017
Token "
Token ID366
Feature activation+8.01e-03

Pos logit contributions
|+0.014
 thanks+0.013
Anna+0.013
 cheered+0.012
ount+0.011
Neg logit contributions
ittens-0.025
 powers-0.024
 knees-0.024
 possessions-0.024
iously-0.024
TokenYou
Token ID1639
Feature activation+3.09e-02

Pos logit contributions
|+0.010
 thanks+0.009
 difference+0.009
ount+0.009
 catches+0.008
Neg logit contributions
ittens-0.014
belt-0.013
 possessions-0.013
ths-0.013
bars-0.013
Token are
Token ID389
Feature activation+2.88e-02

Pos logit contributions
|+0.037
Anna+0.032
ount+0.030
Nik+0.029
 difference+0.029
Neg logit contributions
 powers-0.057
 tools-0.055
 possessions-0.054
 knees-0.054
ittens-0.052
Token brave
Token ID14802
Feature activation+2.43e-02

Pos logit contributions
|+0.047
ack+0.040
oc+0.038
ount+0.038
 cheered+0.036
Neg logit contributions
 tools-0.041
 powers-0.041
ittens-0.040
ths-0.039
 possessions-0.039
Token,
Token ID11
Feature activation+7.91e-02

Pos logit contributions
|+0.032
ount+0.026
Anna+0.024
Queen+0.024
Joy+0.023
Neg logit contributions
 powers-0.046
 knees-0.046
iously-0.044
 possessions-0.044
ittens-0.044
Token boys
Token ID6510
Feature activation+4.32e-02

Pos logit contributions
|+0.109
ount+0.079
Queen+0.079
Anna+0.074
 cheered+0.074
Neg logit contributions
ittens-0.153
 knees-0.147
 cheeks-0.141
iously-0.141
ths-0.139
Token.
Token ID13
Feature activation+3.07e-02

Pos logit contributions
|+0.081
ount+0.070
Nik+0.069
Queen+0.069
Joy+0.068
Neg logit contributions
 powers-0.052
 possessions-0.049
ittens-0.048
 knees-0.047
 tools-0.047
Token You
Token ID921
Feature activation+3.53e-02

Pos logit contributions
|+0.039
 cheered+0.034
ack+0.033
 difference+0.033
 thanks+0.032
Neg logit contributions
ittens-0.053
 powers-0.052
 possessions-0.051
belt-0.051
 knees-0.051
Token faced
Token ID7452
Feature activation+2.40e-02

Pos logit contributions
|+0.042
Anna+0.039
ount+0.036
Nik+0.036
S+0.036
Neg logit contributions
 powers-0.064
 tools-0.061
 possessions-0.058
 knees-0.057
 possibly-0.057
Token your
Token ID534
Feature activation-3.25e-02

Pos logit contributions
|+0.027
 thanks+0.023
Anna+0.022
 cheered+0.022
ount+0.022
Neg logit contributions
 powers-0.046
ittens-0.045
 knees-0.045
 possessions-0.045
iously-0.044
Token Can
Token ID1680
Feature activation-3.08e-02

Pos logit contributions
|+0.032
Anna+0.027
 thanks+0.027
 cheered+0.026
ount+0.026
Neg logit contributions
ittens-0.056
 knees-0.056
 powers-0.055
belt-0.054
 possessions-0.054
Token we
Token ID356
Feature activation+7.99e-03

Pos logit contributions
ittens+0.061
 powers+0.061
 possessions+0.059
iously+0.059
 knees+0.058
Neg logit contributions
|-0.035
Anna-0.032
 thanks-0.031
 cheered-0.029
 Anna-0.028
Token be
Token ID307
Feature activation+2.97e-02

Pos logit contributions
|+0.012
Anna+0.011
ount+0.011
 cheered+0.011
 thanks+0.011
Neg logit contributions
ittens-0.012
 knees-0.011
 powers-0.011
 possibly-0.011
belt-0.011
Token Rex
Token ID17853
Feature activation+4.20e-02

Pos logit contributions
|+0.065
ount+0.058
 difference+0.054
amp+0.054
he+0.052
Neg logit contributions
 powers-0.029
ittens-0.029
 knees-0.028
 possessions-0.026
 tools-0.026
Token's
Token ID338
Feature activation+2.08e-02

Pos logit contributions
|+0.054
 cheered+0.046
Kat+0.046
ount+0.046
 thanks+0.045
Neg logit contributions
ittens-0.073
 powers-0.070
 knees-0.070
belt-0.070
 possessions-0.066
Token friends
Token ID2460
Feature activation+7.90e-02

Pos logit contributions
|+0.040
 cheered+0.036
ount+0.036
Anna+0.034
 thanks+0.033
Neg logit contributions
ittens-0.026
 knees-0.025
 possessions-0.024
 powers-0.024
 tools-0.023
Token?"
Token ID1701
Feature activation+4.39e-02

Pos logit contributions
|+0.130
ount+0.117
Joy+0.105
 cheered+0.103
 catches+0.102
Neg logit contributions
 powers-0.109
belt-0.108
ittens-0.106
 knees-0.102
ths-0.099
Token
Token ID198
Feature activation+1.79e-02

Pos logit contributions
|+0.057
ount+0.050
 difference+0.046
 thanks+0.044
 catches+0.041
Neg logit contributions
ittens-0.084
 knees-0.078
 possibly-0.074
 tools-0.069
 cheeks-0.069
Token
Token ID198
Feature activation-7.49e-03

Pos logit contributions
|+0.019
ount+0.017
 thanks+0.015
 difference+0.015
 Princess+0.013
Neg logit contributions
ittens-0.038
 knees-0.035
 powers-0.033
belt-0.033
 tools-0.032
TokenThe
Token ID464
Feature activation+3.07e-02

Pos logit contributions
ittens+0.014
 knees+0.014
belt+0.013
ths+0.013
 powers+0.013
Neg logit contributions
|-0.009
ount-0.008
 thanks-0.008
 difference-0.008
 Princess-0.007
Token man
Token ID582
Feature activation+3.32e-02

Pos logit contributions
|+0.035
 thanks+0.030
Anna+0.030
 cheered+0.029
ount+0.027
Neg logit contributions
ittens-0.061
 knees-0.059
 powers-0.059
 possessions-0.058
belt-0.058
Token why
Token ID1521
Feature activation+1.50e-02

Pos logit contributions
|+0.029
 thanks+0.026
Anna+0.026
 cheered+0.024
 difference+0.022
Neg logit contributions
ittens-0.057
 knees-0.055
 powers-0.055
iously-0.054
 possessions-0.054
Token don
Token ID836
Feature activation-2.51e-02

Pos logit contributions
|+0.021
Anna+0.019
 thanks+0.018
 cheered+0.018
ount+0.018
Neg logit contributions
ittens-0.025
 knees-0.024
 powers-0.024
 possessions-0.024
belt-0.024
Token't
Token ID470
Feature activation-1.27e-03

Pos logit contributions
ittens+0.041
 possessions+0.041
 knees+0.040
 powers+0.040
iously+0.040
Neg logit contributions
|-0.037
 thanks-0.034
Anna-0.033
 cheered-0.032
 catches-0.031
Token we
Token ID356
Feature activation+1.66e-02

Pos logit contributions
ittens+0.003
belt+0.002
 powers+0.002
 possessions+0.002
iously+0.002
Neg logit contributions
|-0.001
 thanks-0.001
Anna-0.001
 cheered-0.001
 difference-0.001
Token go
Token ID467
Feature activation+2.95e-02

Pos logit contributions
|+0.019
 thanks+0.017
Anna+0.017
 cheered+0.016
 difference+0.015
Neg logit contributions
ittens-0.032
iously-0.031
 knees-0.031
 powers-0.031
 possessions-0.031
Token inside
Token ID2641
Feature activation+7.89e-02

Pos logit contributions
|+0.040
Anna+0.038
 thanks+0.036
 cheered+0.035
ount+0.034
Neg logit contributions
ittens-0.049
 knees-0.049
 powers-0.049
belt-0.048
 possessions-0.048
Token and
Token ID290
Feature activation+1.21e-03

Pos logit contributions
|+0.094
ount+0.083
Joy+0.079
 cheered+0.079
Anna+0.075
Neg logit contributions
 powers-0.143
 knees-0.142
ittens-0.142
belt-0.141
 possessions-0.140
Token have
Token ID423
Feature activation+2.99e-02

Pos logit contributions
|+0.001
 thanks+0.001
Anna+0.001
 cheered+0.001
 welcome+0.001
Neg logit contributions
ittens-0.003
iously-0.003
 powers-0.003
 possessions-0.003
belt-0.003
Token some
Token ID617
Feature activation+1.39e-02

Pos logit contributions
|+0.032
 thanks+0.030
Anna+0.029
 cheered+0.028
 difference+0.026
Neg logit contributions
ittens-0.060
belt-0.057
iously-0.057
 knees-0.057
 possessions-0.056
Token cookies
Token ID14746
Feature activation+6.58e-02

Pos logit contributions
 thanks+0.016
 welcome+0.015
|+0.015
Anna+0.014
 like+0.014
Neg logit contributions
iously-0.027
belt-0.026
ittens-0.025
 knees-0.025
ths-0.025
Token and
Token ID290
Feature activation+6.94e-03

Pos logit contributions
|+0.079
 thanks+0.065
Anna+0.065
 cheered+0.063
 difference+0.062
Neg logit contributions
ittens-0.121
belt-0.121
 powers-0.118
 knees-0.117
 possessions-0.114
TokenI
Token ID40
Feature activation+2.36e-02

Pos logit contributions
|+0.026
ount+0.023
 thanks+0.023
 difference+0.022
 cheered+0.021
Neg logit contributions
ittens-0.033
 powers-0.031
 possessions-0.031
 knees-0.031
belt-0.030
Token love
Token ID1842
Feature activation-6.41e-03

Pos logit contributions
|+0.037
ount+0.036
 Princess+0.032
amp+0.031
 thanks+0.031
Neg logit contributions
ittens-0.031
 powers-0.028
 tools-0.028
 possibly-0.028
 possessions-0.027
Token you
Token ID345
Feature activation+3.95e-02

Pos logit contributions
ittens+0.012
belt+0.012
 knees+0.012
 powers+0.012
 possessions+0.011
Neg logit contributions
|-0.008
 thanks-0.007
Anna-0.007
 cheered-0.007
 catches-0.006
Token,
Token ID11
Feature activation+8.09e-02

Pos logit contributions
|+0.066
ount+0.058
Anna+0.057
 cheered+0.055
 thanks+0.055
Neg logit contributions
ittens-0.061
 knees-0.057
 powers-0.056
iously-0.054
 cheeks-0.054
Token too
Token ID1165
Feature activation+1.73e-02

Pos logit contributions
|+0.100
ount+0.075
Queen+0.072
 cheered+0.072
vy+0.070
Neg logit contributions
ittens-0.167
 knees-0.156
 cheeks-0.150
ths-0.148
iously-0.148
Token,
Token ID11
Feature activation+7.89e-02

Pos logit contributions
|+0.021
Anna+0.018
 thanks+0.017
 cheered+0.017
ount+0.017
Neg logit contributions
ittens-0.034
 knees-0.032
 powers-0.032
iously-0.032
 possessions-0.031
Token kids
Token ID3988
Feature activation+4.68e-02

Pos logit contributions
|+0.103
ount+0.077
 cheered+0.076
Queen+0.074
vy+0.073
Neg logit contributions
ittens-0.157
 knees-0.148
ths-0.141
iously-0.141
 cheeks-0.140
Token.
Token ID13
Feature activation+3.64e-02

Pos logit contributions
|+0.087
ount+0.078
Queen+0.076
Kat+0.076
Nik+0.075
Neg logit contributions
ittens-0.055
 knees-0.051
 powers-0.051
 possessions-0.049
belt-0.048
Token Now
Token ID2735
Feature activation-5.11e-05

Pos logit contributions
|+0.047
 cheered+0.044
ount+0.043
ack+0.043
vy+0.041
Neg logit contributions
ittens-0.059
 powers-0.057
 knees-0.056
belt-0.056
 possessions-0.055
Token,
Token ID11
Feature activation+2.26e-02

Pos logit contributions
 knees+0.000
ittens+0.000
 cheeks+0.000
 powers+0.000
iously+0.000
Neg logit contributions
|-0.000
ount-0.000
 cheered-0.000
Anna-0.000
Queen-0.000
Token let
Token ID1309
Feature activation+1.25e-02

Pos logit contributions
|+0.024
 thanks+0.021
Anna+0.021
 cheered+0.020
ount+0.019
Neg logit contributions
ittens-0.045
 knees-0.044
 powers-0.044
 possessions-0.044
belt-0.043
Token,
Token ID11
Feature activation+2.06e-02

Pos logit contributions
ittens+0.021
 powers+0.020
 knees+0.020
belt+0.020
 possessions+0.020
Neg logit contributions
|-0.010
 thanks-0.009
Anna-0.009
 cheered-0.009
 Anna-0.008
Token "
Token ID366
Feature activation+1.19e-02

Pos logit contributions
|+0.025
 thanks+0.022
Anna+0.022
 cheered+0.021
ount+0.020
Neg logit contributions
ittens-0.038
 knees-0.037
 powers-0.037
 possessions-0.037
iously-0.037
TokenI
Token ID40
Feature activation+2.50e-02

Pos logit contributions
|+0.016
 thanks+0.014
ount+0.014
 difference+0.013
 cheered+0.013
Neg logit contributions
ittens-0.021
 knees-0.019
belt-0.019
 powers-0.019
 possessions-0.019
Token love
Token ID1842
Feature activation-7.19e-03

Pos logit contributions
|+0.040
ount+0.038
amp+0.035
Joy+0.034
 thanks+0.034
Neg logit contributions
 tools-0.030
 powers-0.029
ittens-0.029
 possibly-0.028
 possessions-0.027
Token you
Token ID345
Feature activation+3.71e-02

Pos logit contributions
belt+0.014
ittens+0.014
 knees+0.014
iously+0.014
 powers+0.014
Neg logit contributions
|-0.008
 thanks-0.007
Anna-0.007
 Anna-0.007
 cheered-0.006
Token,
Token ID11
Feature activation+7.84e-02

Pos logit contributions
|+0.055
ount+0.047
Anna+0.046
 thanks+0.046
 cheered+0.045
Neg logit contributions
ittens-0.064
 knees-0.060
 powers-0.059
iously-0.058
 possessions-0.058
Token Tom
Token ID4186
Feature activation+4.68e-02

Pos logit contributions
|+0.107
ount+0.082
Queen+0.080
 cheered+0.078
Prin+0.077
Neg logit contributions
ittens-0.149
 knees-0.146
iously-0.137
 cheeks-0.137
ths-0.136
Token and
Token ID290
Feature activation+3.42e-02

Pos logit contributions
|+0.081
ount+0.071
 blast+0.064
Joy+0.060
Queen+0.059
Neg logit contributions
ittens-0.072
 powers-0.066
 knees-0.066
row-0.066
 tools-0.065
Token Anna
Token ID11735
Feature activation+3.82e-02

Pos logit contributions
|+0.019
 cheered+0.012
 thanks+0.011
ount+0.011
 difference+0.010
Neg logit contributions
ittens-0.087
 knees-0.086
belt-0.084
 powers-0.083
 possessions-0.083
Token.
Token ID13
Feature activation+3.59e-02

Pos logit contributions
|+0.077
ount+0.071
Queen+0.065
Nik+0.064
Kat+0.064
Neg logit contributions
 powers-0.041
 knees-0.040
ittens-0.039
 tools-0.038
 cheeks-0.037
Token I
Token ID314
Feature activation+2.55e-02

Pos logit contributions
|+0.048
 cheered+0.043
ount+0.043
ack+0.042
vy+0.040
Neg logit contributions
ittens-0.057
 powers-0.056
 knees-0.056
belt-0.055
 possessions-0.054
Token still
Token ID991
Feature activation-1.92e-02

Pos logit contributions
ittens+0.020
 knees+0.020
 powers+0.020
iously+0.019
 possessions+0.019
Neg logit contributions
|-0.013
 thanks-0.011
Anna-0.011
 cheered-0.011
 catches-0.010
Token wanted
Token ID2227
Feature activation-2.40e-02

Pos logit contributions
ittens+0.040
iously+0.037
 knees+0.037
ths+0.037
 powers+0.037
Neg logit contributions
|-0.021
 thanks-0.019
 cheered-0.018
Anna-0.018
 like-0.016
Token to
Token ID284
Feature activation-1.46e-02

Pos logit contributions
ittens+0.054
belt+0.052
iously+0.050
ised+0.049
ths+0.049
Neg logit contributions
 thanks-0.021
 like-0.019
 right-0.019
|-0.019
 Anna-0.019
Token eat
Token ID4483
Feature activation+1.44e-03

Pos logit contributions
ittens+0.031
belt+0.030
iously+0.030
 possessions+0.030
ths+0.029
Neg logit contributions
|-0.015
 thanks-0.013
 welcome-0.013
Anna-0.012
 like-0.012
Token something
Token ID1223
Feature activation-4.88e-03

Pos logit contributions
|+0.002
 thanks+0.002
Anna+0.002
 cheered+0.002
 like+0.002
Neg logit contributions
ittens-0.003
belt-0.003
iously-0.002
 knees-0.002
 possessions-0.002
Token scr
Token ID6040
Feature activation-1.01e-01

Pos logit contributions
ittens+0.010
belt+0.010
 knees+0.010
iously+0.010
 powers+0.009
Neg logit contributions
 thanks-0.005
|-0.005
Anna-0.004
 difference-0.004
 cheered-0.004
Tokenum
Token ID388
Feature activation+6.52e-04

Pos logit contributions
 powers+0.162
 knees+0.161
belt+0.159
 possessions+0.158
iously+0.151
Neg logit contributions
|-0.139
ack-0.139
ount-0.126
unts-0.122
S-0.122
Tokenpt
Token ID457
Feature activation-2.22e-02

Pos logit contributions
 thanks+0.001
|+0.001
 cheered+0.001
Anna+0.001
 difference+0.001
Neg logit contributions
ittens-0.001
 knees-0.001
belt-0.001
iously-0.001
 powers-0.001
Tokenious
Token ID699
Feature activation-6.68e-03

Pos logit contributions
ittens+0.046
 powers+0.045
 possessions+0.044
 knees+0.044
ths+0.043
Neg logit contributions
|-0.019
 thanks-0.019
 like-0.018
 cheered-0.017
Anna-0.017
Token.
Token ID13
Feature activation+2.34e-03

Pos logit contributions
ittens+0.014
 knees+0.013
belt+0.013
 powers+0.013
 possessions+0.013
Neg logit contributions
|-0.007
 thanks-0.006
Anna-0.006
 cheered-0.006
 difference-0.005
Token
Token ID220
Feature activation-4.72e-03

Pos logit contributions
|+0.003
 cheered+0.002
 thanks+0.002
Anna+0.002
ount+0.002
Neg logit contributions
ittens-0.005
 knees-0.004
belt-0.004
iously-0.004
bars-0.004
Token day
Token ID1110
Feature activation-2.72e-02

Pos logit contributions
 powers+0.041
iously+0.041
ittens+0.040
 knees+0.040
 possessions+0.040
Neg logit contributions
|-0.029
Anna-0.027
 thanks-0.027
 welcome-0.024
 cheered-0.024
Token Sue
Token ID26089
Feature activation-9.17e-03

Pos logit contributions
 powers+0.064
ittens+0.063
belt+0.063
 possessions+0.063
iously+0.061
Neg logit contributions
|-0.018
 thanks-0.017
Anna-0.016
 cheered-0.015
S-0.014
Token put
Token ID1234
Feature activation-6.99e-03

Pos logit contributions
 knees+0.015
ittens+0.015
 possessions+0.014
 powers+0.014
iously+0.014
Neg logit contributions
|-0.013
ount-0.012
 difference-0.011
 thanks-0.011
Anna-0.011
Token on
Token ID319
Feature activation-4.61e-04

Pos logit contributions
ittens+0.014
iously+0.014
 possessions+0.014
 powers+0.014
 knees+0.014
Neg logit contributions
|-0.007
Anna-0.006
 thanks-0.006
 Anna-0.005
 cheered-0.005
Token her
Token ID607
Feature activation-5.14e-02

Pos logit contributions
ittens+0.001
 powers+0.001
belt+0.001
 possessions+0.001
 knees+0.001
Neg logit contributions
|-0.001
 thanks-0.001
Anna-0.001
 cheered-0.001
 catches-0.001
Token m
Token ID285
Feature activation-1.00e-01

Pos logit contributions
ths+0.105
 weaknesses+0.105
 possessions+0.104
izing+0.104
ised+0.104
Neg logit contributions
 right-0.046
 thanks-0.044
 Anna-0.044
 welcome-0.042
 te-0.040
Tokenama
Token ID1689
Feature activation-3.67e-02

Pos logit contributions
ised+0.120
 possessions+0.115
izing+0.112
nam+0.109
ths+0.107
Neg logit contributions
ack-0.166
 And-0.163
Nik-0.158
S-0.156
amp-0.155
Token's
Token ID338
Feature activation-5.48e-02

Pos logit contributions
ittens+0.083
iously+0.081
 possessions+0.081
 powers+0.081
 knees+0.080
Neg logit contributions
|-0.028
 thanks-0.025
Anna-0.025
 cheered-0.023
 Anna-0.020
Token clean
Token ID3424
Feature activation-1.77e-02

Pos logit contributions
ths+0.103
ised+0.099
izing+0.096
 possessions+0.094
bars+0.094
Neg logit contributions
 right-0.064
 welcome-0.062
 te-0.059
 thanks-0.057
 seven-0.056
Token cloth
Token ID16270
Feature activation-2.91e-02

Pos logit contributions
 possibly+0.030
ths+0.029
ittens+0.029
iously+0.029
 possessions+0.029
Neg logit contributions
 thanks-0.022
 Anna-0.021
 and-0.020
 right-0.020
|-0.020
Token.
Token ID13
Feature activation-2.05e-02

Pos logit contributions
ths+0.078
ittens+0.078
 powers+0.078
iously+0.077
 possessions+0.077
Neg logit contributions
 and-0.008
 right-0.005
 like-0.005
 thanks-0.005
|-0.004
Token Daisy
Token ID40355
Feature activation-1.25e-03

Pos logit contributions
|+0.000
 thanks+0.000
Anna+0.000
 cheered+0.000
ount+0.000
Neg logit contributions
ittens-0.001
 knees-0.001
 powers-0.001
iously-0.001
 possessions-0.001
Token was
Token ID373
Feature activation+1.20e-02

Pos logit contributions
 knees+0.002
ittens+0.002
 powers+0.002
 possessions+0.002
 cheeks+0.002
Neg logit contributions
|-0.002
ount-0.002
 difference-0.002
 thanks-0.002
Anna-0.002
Token pushing
Token ID7796
Feature activation-2.20e-02

Pos logit contributions
|+0.021
 difference+0.019
Anna+0.018
ount+0.018
oc+0.018
Neg logit contributions
 knees-0.016
belt-0.015
aging-0.015
ittens-0.015
 powers-0.014
Token her
Token ID607
Feature activation-6.25e-02

Pos logit contributions
 knees+0.036
ittens+0.035
 powers+0.034
 possessions+0.034
iously+0.034
Neg logit contributions
|-0.033
 thanks-0.029
Anna-0.029
ount-0.029
 difference-0.028
Token favourite
Token ID12507
Feature activation-6.10e-02

Pos logit contributions
ittens+0.080
 powers+0.074
iously+0.074
belt+0.073
 possessions+0.072
Neg logit contributions
 thanks-0.102
|-0.100
 cheered-0.100
 right-0.099
 catches-0.098
Token t
Token ID256
Feature activation-9.79e-02

Pos logit contributions
ittens+0.111
iously+0.108
belt+0.106
ths+0.106
ately+0.103
Neg logit contributions
|-0.072
Anna-0.069
 thanks-0.067
 cheered-0.064
 Anna-0.063
Tokeneddy
Token ID21874
Feature activation-3.90e-02

Pos logit contributions
 powers+0.214
iously+0.213
 possessions+0.207
 possibly+0.206
 weaknesses+0.205
Neg logit contributions
|-0.077
Anna-0.067
ack-0.063
amp-0.057
he-0.056
Token bear
Token ID6842
Feature activation-2.64e-02

Pos logit contributions
ittens+0.073
 powers+0.070
belt+0.070
 possessions+0.069
iously+0.069
Neg logit contributions
|-0.045
 thanks-0.043
Anna-0.041
 cheered-0.039
 difference-0.037
Token in
Token ID287
Feature activation+1.84e-02

Pos logit contributions
ittens+0.061
 possessions+0.060
 powers+0.059
belt+0.058
iously+0.058
Neg logit contributions
 thanks-0.017
|-0.017
 cheered-0.016
 like-0.015
 right-0.014
Token the
Token ID262
Feature activation+2.63e-02

Pos logit contributions
|+0.017
ount+0.014
Anna+0.013
 thanks+0.013
 cheered+0.013
Neg logit contributions
 knees-0.039
ittens-0.039
 powers-0.039
 possessions-0.038
iously-0.038
Token swing
Token ID9628
Feature activation-1.80e-03

Pos logit contributions
|+0.035
ount+0.033
 cheered+0.030
 thanks+0.030
oke+0.030
Neg logit contributions
ittens-0.042
 knees-0.042
belt-0.041
 tools-0.040
 trousers-0.040
Token adventure
Token ID8855
Feature activation-1.06e-02

Pos logit contributions
ittens+0.046
belt+0.044
 possessions+0.044
 cheeks+0.043
 powers+0.043
Neg logit contributions
 thanks-0.036
|-0.036
 right-0.032
 difference-0.032
 like-0.031
Token.
Token ID13
Feature activation-2.31e-02

Pos logit contributions
ittens+0.022
 knees+0.021
 possessions+0.021
 powers+0.021
iously+0.021
Neg logit contributions
|-0.011
 thanks-0.010
Anna-0.009
 cheered-0.009
 difference-0.008
Token He
Token ID679
Feature activation-2.12e-02

Pos logit contributions
ittens+0.053
ths+0.049
 possessions+0.048
 powers+0.048
belt+0.046
Neg logit contributions
|-0.021
 thanks-0.020
 And-0.019
-0.018
 Princess-0.018
Token took
Token ID1718
Feature activation-2.01e-02

Pos logit contributions
ittens+0.038
 powers+0.036
 possessions+0.036
iously+0.035
 knees+0.035
Neg logit contributions
|-0.029
 thanks-0.026
 cheered-0.025
Anna-0.025
 catches-0.023
Token his
Token ID465
Feature activation-5.45e-02

Pos logit contributions
ittens+0.039
belt+0.038
 knees+0.037
 possessions+0.037
iously+0.037
Neg logit contributions
|-0.023
 thanks-0.022
 cheered-0.020
Anna-0.020
 catches-0.019
Token t
Token ID256
Feature activation-9.76e-02

Pos logit contributions
izing+0.105
ittens+0.100
iously+0.100
anked+0.100
ths+0.099
Neg logit contributions
 thanks-0.059
 sees-0.054
 welcome-0.054
 blast-0.054
|-0.053
Tokeneddy
Token ID21874
Feature activation-3.40e-02

Pos logit contributions
iously+0.202
 powers+0.197
 possibly+0.197
 cheeks+0.194
chief+0.192
Neg logit contributions
|-0.086
ack-0.075
Anna-0.071
S-0.058
amp-0.057
Token bear
Token ID6842
Feature activation-1.96e-02

Pos logit contributions
ittens+0.058
 knees+0.057
 powers+0.057
 possessions+0.056
iously+0.055
Neg logit contributions
|-0.046
 thanks-0.042
Anna-0.042
 cheered-0.040
ount-0.039
Token with
Token ID351
Feature activation+2.06e-03

Pos logit contributions
ittens+0.043
 knees+0.042
 powers+0.041
 possessions+0.041
iously+0.041
Neg logit contributions
|-0.018
 thanks-0.015
Anna-0.015
 cheered-0.014
ount-0.013
Token him
Token ID683
Feature activation-1.18e-02

Pos logit contributions
 thanks+0.002
 cheered+0.002
 like+0.002
|+0.002
 welcome+0.002
Neg logit contributions
belt-0.004
ittens-0.004
iously-0.004
ths-0.004
bars-0.004
Token and
Token ID290
Feature activation-3.18e-02

Pos logit contributions
ittens+0.028
 knees+0.026
ths+0.026
iously+0.026
 powers+0.026
Neg logit contributions
|-0.008
 thanks-0.008
 cheered-0.007
 like-0.006
 right-0.006
Token a
Token ID257
Feature activation-1.80e-03

Pos logit contributions
|+0.013
 thanks+0.012
Anna+0.011
 cheered+0.011
 difference+0.010
Neg logit contributions
ittens-0.025
 knees-0.024
belt-0.024
 possessions-0.024
 powers-0.024
Token little
Token ID1310
Feature activation-1.48e-02

Pos logit contributions
ittens+0.003
 knees+0.003
 powers+0.003
 possessions+0.003
iously+0.003
Neg logit contributions
|-0.003
 thanks-0.003
Anna-0.003
 cheered-0.002
ount-0.002
Token bit
Token ID1643
Feature activation-2.36e-02

Pos logit contributions
ittens+0.024
 knees+0.023
 powers+0.023
 possessions+0.022
iously+0.022
Neg logit contributions
|-0.022
 thanks-0.020
Anna-0.020
 cheered-0.019
ount-0.019
Token and
Token ID290
Feature activation-1.90e-02

Pos logit contributions
ittens+0.047
 knees+0.046
 powers+0.046
iously+0.045
 possessions+0.045
Neg logit contributions
|-0.026
Anna-0.022
 thanks-0.022
 cheered-0.021
ount-0.020
Token then
Token ID788
Feature activation-3.07e-02

Pos logit contributions
ittens+0.034
 powers+0.032
 possessions+0.031
belt+0.031
 knees+0.031
Neg logit contributions
|-0.025
 thanks-0.024
 cheered-0.024
Anna-0.023
 catches-0.021
Token scr
Token ID6040
Feature activation-9.73e-02

Pos logit contributions
ittens+0.047
 knees+0.045
 powers+0.045
 possessions+0.044
iously+0.044
Neg logit contributions
|-0.047
 thanks-0.044
Anna-0.043
 cheered-0.042
ount-0.040
Tokenabb
Token ID6485
Feature activation-3.56e-02

Pos logit contributions
 powers+0.156
 possessions+0.154
belt+0.153
 knees+0.152
iously+0.142
Neg logit contributions
|-0.137
ack-0.134
 thanks-0.123
ount-0.122
Anna-0.122
Tokenled
Token ID992
Feature activation-2.28e-02

Pos logit contributions
ittens+0.049
belt+0.048
 knees+0.046
ths+0.044
 possessions+0.044
Neg logit contributions
|-0.058
 cheered-0.058
 thanks-0.054
ack-0.054
Anna-0.054
Token underneath
Token ID14638
Feature activation+5.79e-03

Pos logit contributions
 knees+0.040
 powers+0.039
iously+0.039
ittens+0.038
 possessions+0.037
Neg logit contributions
|-0.032
Anna-0.028
 thanks-0.026
ount-0.026
 difference-0.026
Token some
Token ID617
Feature activation-2.43e-02

Pos logit contributions
|+0.004
 thanks+0.004
 cheered+0.004
Anna+0.004
 Anna+0.003
Neg logit contributions
ittens-0.013
 possessions-0.013
iously-0.013
belt-0.013
 knees-0.013
Token nearby
Token ID6716
Feature activation-2.19e-02

Pos logit contributions
belt+0.049
ittens+0.049
 knees+0.047
iously+0.046
 possessions+0.045
Neg logit contributions
 thanks-0.026
 cheered-0.024
 difference-0.023
 cal-0.023
|-0.023
Token along
Token ID1863
Feature activation+6.66e-03

Pos logit contributions
 knees+0.015
ittens+0.014
 powers+0.014
 possessions+0.014
belt+0.014
Neg logit contributions
|-0.011
 thanks-0.010
Anna-0.010
ount-0.010
 difference-0.010
Token the
Token ID262
Feature activation-1.44e-02

Pos logit contributions
|+0.007
 thanks+0.006
Anna+0.006
ount+0.006
 cheered+0.006
Neg logit contributions
 knees-0.013
ittens-0.013
 powers-0.013
iously-0.013
 possessions-0.013
Token road
Token ID2975
Feature activation-2.58e-02

Pos logit contributions
 knees+0.022
ittens+0.022
 possessions+0.021
 powers+0.021
belt+0.021
Neg logit contributions
|-0.022
 thanks-0.020
 cheered-0.020
Anna-0.019
ount-0.019
Token with
Token ID351
Feature activation+4.19e-03

Pos logit contributions
ittens+0.051
 powers+0.049
 possessions+0.048
 knees+0.048
iously+0.048
Neg logit contributions
|-0.029
 thanks-0.026
Anna-0.025
 cheered-0.025
ount-0.023
Token her
Token ID607
Feature activation-4.29e-02

Pos logit contributions
 Anna+0.003
 thanks+0.003
 welcome+0.003
 Sara+0.003
Anna+0.003
Neg logit contributions
iously-0.010
belt-0.010
ittens-0.009
ths-0.009
 possessions-0.009
Token t
Token ID256
Feature activation-9.65e-02

Pos logit contributions
iously+0.095
 powers+0.088
row+0.087
bars+0.086
ered+0.086
Neg logit contributions
-0.032
 and-0.032
 thanks-0.030
 Anna-0.030
 And-0.029
Tokeneddy
Token ID21874
Feature activation-3.50e-02

Pos logit contributions
iously+0.217
 powers+0.217
 possibly+0.211
chief+0.209
 cheeks+0.206
Neg logit contributions
|-0.072
ack-0.060
Anna-0.059
amp-0.052
he-0.052
Token bear
Token ID6842
Feature activation-2.64e-02

Pos logit contributions
ittens+0.062
 knees+0.060
 powers+0.060
 possessions+0.059
iously+0.059
Neg logit contributions
|-0.046
 thanks-0.042
Anna-0.041
 cheered-0.040
ount-0.037
Token and
Token ID290
Feature activation-2.91e-02

Pos logit contributions
 powers+0.062
ittens+0.062
belt+0.061
iously+0.061
ths+0.061
Neg logit contributions
 thanks-0.015
 like-0.013
 and-0.013
|-0.013
 And-0.012
Token her
Token ID607
Feature activation-3.45e-02

Pos logit contributions
ittens+0.049
 powers+0.046
iously+0.045
 possessions+0.043
belt+0.043
Neg logit contributions
 cheered-0.042
 thanks-0.041
|-0.041
Anna-0.039
 like-0.038
Token favorite
Token ID4004
Feature activation-5.30e-02

Pos logit contributions
iously+0.064
ittens+0.063
ths+0.062
 powers+0.061
 possessions+0.061
Neg logit contributions
 thanks-0.038
|-0.038
Anna-0.033
 Princess-0.032
 Anna-0.032
Token made
Token ID925
Feature activation-5.86e-03

Pos logit contributions
ittens+0.007
 powers+0.007
 knees+0.007
 possessions+0.007
belt+0.007
Neg logit contributions
|-0.007
 thanks-0.006
Anna-0.006
 cheered-0.006
ount-0.006
Token a
Token ID257
Feature activation-1.37e-02

Pos logit contributions
ittens+0.011
 knees+0.011
 powers+0.011
belt+0.010
 possessions+0.010
Neg logit contributions
|-0.007
 thanks-0.006
Anna-0.006
 cheered-0.006
ount-0.006
Token funny
Token ID8258
Feature activation-4.08e-02

Pos logit contributions
 knees+0.021
ittens+0.021
 powers+0.020
 cheeks+0.019
 possessions+0.019
Neg logit contributions
|-0.022
ount-0.019
 thanks-0.019
Anna-0.019
 cheered-0.018
Token face
Token ID1986
Feature activation-9.59e-03

Pos logit contributions
ittens+0.054
 knees+0.054
 powers+0.053
 possessions+0.051
iously+0.051
Neg logit contributions
|-0.073
Anna-0.066
 thanks-0.065
ount-0.064
 cheered-0.063
Token,
Token ID11
Feature activation+5.70e-03

Pos logit contributions
ittens+0.022
 knees+0.021
 powers+0.021
iously+0.021
 possessions+0.021
Neg logit contributions
|-0.008
Anna-0.007
 thanks-0.006
 cheered-0.006
ount-0.006
Token scr
Token ID6040
Feature activation-9.60e-02

Pos logit contributions
|+0.007
Anna+0.005
 thanks+0.005
ount+0.005
 cheered+0.005
Neg logit contributions
ittens-0.011
 knees-0.011
 powers-0.011
iously-0.011
 possessions-0.011
Tokenunch
Token ID3316
Feature activation-3.28e-02

Pos logit contributions
 powers+0.136
 knees+0.135
 possessions+0.134
belt+0.133
ittens+0.130
Neg logit contributions
|-0.153
 thanks-0.141
Anna-0.140
ack-0.137
 cheered-0.136
Tokening
Token ID278
Feature activation-1.76e-02

Pos logit contributions
ittens+0.041
iously+0.039
 knees+0.039
 powers+0.039
 possessions+0.038
Neg logit contributions
|-0.061
Anna-0.054
 thanks-0.053
 cheered-0.052
ount-0.052
Token up
Token ID510
Feature activation-9.71e-03

Pos logit contributions
 knees+0.030
ittens+0.030
 powers+0.030
iously+0.030
 possessions+0.029
Neg logit contributions
|-0.024
Anna-0.021
 thanks-0.020
ount-0.020
Queen-0.019
Token her
Token ID607
Feature activation-4.08e-02

Pos logit contributions
 knees+0.019
iously+0.019
ittens+0.018
 powers+0.018
 cheeks+0.018
Neg logit contributions
|-0.012
Anna-0.010
Queen-0.009
ount-0.009
 difference-0.009
Token nose
Token ID9686
Feature activation-2.99e-02

Pos logit contributions
ittens+0.059
belt+0.058
ths+0.056
bars+0.055
 possessions+0.055
Neg logit contributions
 thanks-0.063
|-0.061
 like-0.057
 cheered-0.056
 right-0.056
Token his
Token ID465
Feature activation-3.12e-02

Pos logit contributions
ittens+0.035
belt+0.034
 possessions+0.033
 powers+0.033
iously+0.033
Neg logit contributions
|-0.011
 thanks-0.010
Anna-0.009
 Anna-0.009
 cheered-0.008
Token bed
Token ID3996
Feature activation-2.35e-02

Pos logit contributions
ittens+0.056
 powers+0.055
 possessions+0.055
iously+0.055
belt+0.055
Neg logit contributions
|-0.037
 thanks-0.036
Anna-0.033
 difference-0.031
 cheered-0.031
Token and
Token ID290
Feature activation-3.46e-02

Pos logit contributions
ittens+0.055
 possessions+0.055
 powers+0.055
 knees+0.054
iously+0.053
Neg logit contributions
|-0.015
 thanks-0.014
Anna-0.013
 cheered-0.012
 Anna-0.010
Token asked
Token ID1965
Feature activation-3.09e-02

Pos logit contributions
ittens+0.073
 powers+0.071
 possessions+0.070
iously+0.068
belt+0.067
Neg logit contributions
|-0.034
 cheered-0.032
Anna-0.030
 thanks-0.030
 like-0.028
Token his
Token ID465
Feature activation-4.46e-02

Pos logit contributions
ittens+0.056
 knees+0.053
 powers+0.053
belt+0.053
iously+0.053
Neg logit contributions
|-0.039
 thanks-0.037
Anna-0.036
 cheered-0.034
 welcome-0.033
Token t
Token ID256
Feature activation-9.60e-02

Pos logit contributions
ittens+0.085
iously+0.083
belt+0.082
 possessions+0.080
bars+0.080
Neg logit contributions
 thanks-0.052
Anna-0.047
 welcome-0.047
 difference-0.046
 Anna-0.046
Tokeneddy
Token ID21874
Feature activation-4.29e-02

Pos logit contributions
iously+0.201
 powers+0.194
 cheeks+0.194
 knees+0.192
 possessions+0.192
Neg logit contributions
Anna-0.091
|-0.089
ack-0.081
S-0.073
amp-0.070
Token bear
Token ID6842
Feature activation-3.61e-02

Pos logit contributions
ittens+0.072
 powers+0.071
 knees+0.070
 possessions+0.069
iously+0.068
Neg logit contributions
|-0.061
Anna-0.054
 thanks-0.052
 cheered-0.052
ount-0.052
Token,
Token ID11
Feature activation-3.75e-03

Pos logit contributions
ittens+0.074
 knees+0.072
 powers+0.072
 possessions+0.071
iously+0.070
Neg logit contributions
|-0.037
 thanks-0.033
Anna-0.032
 cheered-0.031
ount-0.029
Token "
Token ID366
Feature activation-1.53e-02

Pos logit contributions
ittens+0.008
 possessions+0.008
 powers+0.008
 knees+0.007
iously+0.007
Neg logit contributions
|-0.004
 thanks-0.003
Anna-0.003
 cheered-0.003
 Anna-0.003
TokenT
Token ID51
Feature activation-3.07e-02

Pos logit contributions
ittens+0.029
 powers+0.028
 knees+0.028
iously+0.027
 possessions+0.027
Neg logit contributions
|-0.019
Anna-0.018
 thanks-0.017
 cheered-0.016
Queen-0.015
Token so
Token ID523
Feature activation-4.96e-02

Pos logit contributions
ittens+0.022
 powers+0.022
 possessions+0.022
belt+0.021
iously+0.021
Neg logit contributions
 thanks-0.002
|-0.002
 cheered-0.002
 like-0.002
 right-0.001
Token she
Token ID673
Feature activation-1.25e-02

Pos logit contributions
 powers+0.075
iously+0.071
belt+0.069
 possessions+0.068
phones+0.068
Neg logit contributions
 thanks-0.077
Anna-0.077
|-0.076
 cheered-0.075
 Anna-0.074
Token put
Token ID1234
Feature activation-4.27e-03

Pos logit contributions
ittens+0.019
 powers+0.018
 knees+0.018
 possessions+0.018
iously+0.018
Neg logit contributions
|-0.019
 thanks-0.018
Anna-0.018
 cheered-0.017
ount-0.016
Token on
Token ID319
Feature activation+1.12e-03

Pos logit contributions
iously+0.009
ittens+0.009
 possessions+0.009
 knees+0.009
belt+0.009
Neg logit contributions
|-0.004
 thanks-0.003
 cheered-0.003
Anna-0.003
 Anna-0.003
Token her
Token ID607
Feature activation-4.54e-02

Pos logit contributions
|+0.001
 thanks+0.001
 Anna+0.001
Anna+0.001
 Mrs+0.001
Neg logit contributions
belt-0.002
 possessions-0.002
 powers-0.002
ittens-0.002
row-0.002
Token m
Token ID285
Feature activation-9.58e-02

Pos logit contributions
ths+0.084
iously+0.080
izing+0.080
bars+0.079
iked+0.078
Neg logit contributions
 thanks-0.053
|-0.050
 right-0.049
 like-0.047
 welcome-0.047
Tokenittens
Token ID34978
Feature activation-2.68e-02

Pos logit contributions
nam+0.086
 possessions+0.082
izing+0.081
ths+0.075
ised+0.074
Neg logit contributions
ack-0.199
|-0.181
 And-0.180
amp-0.180
S-0.178
Token.
Token ID13
Feature activation-1.30e-02

Pos logit contributions
 powers+0.062
ittens+0.062
 possessions+0.061
ths+0.060
iously+0.060
Neg logit contributions
|-0.016
 thanks-0.015
 cheered-0.013
 right-0.013
 like-0.013
Token Sarah
Token ID10490
Feature activation-4.67e-03

Pos logit contributions
ittens+0.026
 knees+0.025
 powers+0.025
 possessions+0.025
iously+0.025
Neg logit contributions
|-0.014
 thanks-0.012
Anna-0.012
 cheered-0.011
ount-0.011
Token looked
Token ID3114
Feature activation+1.36e-02

Pos logit contributions
ittens+0.008
 knees+0.007
 powers+0.007
 possessions+0.007
iously+0.007
Neg logit contributions
|-0.007
 thanks-0.006
Anna-0.006
ount-0.006
 cheered-0.006
Token at
Token ID379
Feature activation-2.18e-03

Pos logit contributions
|+0.021
Anna+0.019
Queen+0.018
ount+0.017
Nik+0.017
Neg logit contributions
 knees-0.021
ittens-0.021
 possessions-0.021
 powers-0.020
iously-0.020
Token moment
Token ID2589
Feature activation+3.02e-03

Pos logit contributions
ittens+0.013
 knees+0.012
 powers+0.012
 possessions+0.012
iously+0.012
Neg logit contributions
|-0.008
 thanks-0.008
Anna-0.008
 cheered-0.007
 difference-0.007
Token,
Token ID11
Feature activation+9.28e-03

Pos logit contributions
|+0.001
 thanks+0.001
Anna+0.001
 cheered+0.001
 difference+0.001
Neg logit contributions
ittens-0.008
 powers-0.008
 knees-0.008
 possessions-0.008
belt-0.008
Token his
Token ID465
Feature activation-3.77e-02

Pos logit contributions
|+0.013
 thanks+0.012
Anna+0.012
 cheered+0.012
 difference+0.011
Neg logit contributions
ittens-0.016
 powers-0.015
 knees-0.015
 possessions-0.015
belt-0.015
Token little
Token ID1310
Feature activation-2.55e-02

Pos logit contributions
ittens+0.066
 possessions+0.060
iously+0.060
 powers+0.060
belt+0.060
Neg logit contributions
 thanks-0.050
|-0.049
Anna-0.045
 difference-0.044
 cheered-0.044
Token face
Token ID1986
Feature activation-1.41e-02

Pos logit contributions
ittens+0.050
 powers+0.047
 possessions+0.047
belt+0.047
 knees+0.047
Neg logit contributions
|-0.028
 thanks-0.026
Anna-0.025
 cheered-0.025
 difference-0.024
Token scr
Token ID6040
Feature activation-9.55e-02

Pos logit contributions
ittens+0.028
 possessions+0.027
 powers+0.025
 knees+0.025
iously+0.025
Neg logit contributions
 cheered-0.016
 thanks-0.015
 like-0.015
 and-0.014
|-0.013
Tokenunch
Token ID3316
Feature activation-3.03e-02

Pos logit contributions
 knees+0.144
 powers+0.143
 possessions+0.141
belt+0.138
iously+0.134
Neg logit contributions
|-0.145
ack-0.134
ount-0.130
Anna-0.130
 thanks-0.129
Tokening
Token ID278
Feature activation-2.04e-02

Pos logit contributions
ittens+0.043
 knees+0.042
 powers+0.041
 possessions+0.040
iously+0.040
Neg logit contributions
|-0.050
 thanks-0.047
Anna-0.046
 cheered-0.045
ount-0.043
Token up
Token ID510
Feature activation-8.56e-03

Pos logit contributions
ittens+0.043
 knees+0.041
 powers+0.041
 possessions+0.041
belt+0.040
Neg logit contributions
|-0.020
 thanks-0.018
Anna-0.017
 cheered-0.017
ount-0.015
Token in
Token ID287
Feature activation+1.26e-02

Pos logit contributions
 knees+0.018
ittens+0.017
iously+0.017
 powers+0.017
belt+0.017
Neg logit contributions
|-0.009
Anna-0.008
 thanks-0.007
 cheered-0.007
ount-0.007
Token concentration
Token ID10368
Feature activation-1.81e-02

Pos logit contributions
|+0.017
Anna+0.015
ount+0.015
Queen+0.014
 cheered+0.014
Neg logit contributions
 knees-0.021
 powers-0.021
 possessions-0.021
ittens-0.021
iously-0.020
Token curious
Token ID11040
Feature activation-2.48e-02

Pos logit contributions
|+0.013
 thanks+0.011
Anna+0.011
 cheered+0.011
ount+0.010
Neg logit contributions
ittens-0.023
 knees-0.023
 powers-0.023
 possessions-0.022
iously-0.022
Token.
Token ID13
Feature activation-2.44e-02

Pos logit contributions
ittens+0.065
belt+0.062
ths+0.060
 possessions+0.060
 powers+0.059
Neg logit contributions
 thanks-0.015
 like-0.012
 cheered-0.010
 and-0.010
 right-0.009
Token She
Token ID1375
Feature activation-1.76e-02

Pos logit contributions
ittens+0.052
 powers+0.051
 possessions+0.051
belt+0.050
iously+0.048
Neg logit contributions
|-0.023
Anna-0.021
 thanks-0.021
 cheered-0.020
 Anna-0.019
Token asked
Token ID1965
Feature activation-2.98e-02

Pos logit contributions
ittens+0.038
 possessions+0.036
iously+0.036
 powers+0.036
belt+0.035
Neg logit contributions
|-0.017
 cheered-0.016
Anna-0.016
 thanks-0.016
 sees-0.014
Token her
Token ID607
Feature activation-3.94e-02

Pos logit contributions
ittens+0.053
 powers+0.051
 knees+0.050
 possessions+0.050
belt+0.050
Neg logit contributions
|-0.039
 thanks-0.036
Anna-0.036
 cheered-0.034
ount-0.032
Token m
Token ID285
Feature activation-9.54e-02

Pos logit contributions
ittens+0.054
 knees+0.052
 powers+0.051
 possessions+0.051
iously+0.050
Neg logit contributions
|-0.069
 thanks-0.063
Anna-0.062
 cheered-0.061
ount-0.059
Tokenama
Token ID1689
Feature activation-3.50e-02

Pos logit contributions
 powers+0.135
 possessions+0.135
ised+0.126
 weaknesses+0.123
 knees+0.123
Neg logit contributions
ack-0.127
|-0.123
oc-0.118
 And-0.118
 thanks-0.117
Token,
Token ID11
Feature activation-5.77e-03

Pos logit contributions
ittens+0.069
 knees+0.067
 powers+0.067
 possessions+0.066
iously+0.065
Neg logit contributions
|-0.039
 thanks-0.034
Anna-0.034
 cheered-0.032
ount-0.030
Token "
Token ID366
Feature activation-2.27e-02

Pos logit contributions
ittens+0.010
 knees+0.010
 powers+0.009
iously+0.009
 possessions+0.009
Neg logit contributions
|-0.008
Anna-0.007
 thanks-0.007
 cheered-0.007
ount-0.007
TokenWhat
Token ID2061
Feature activation-1.43e-02

Pos logit contributions
ittens+0.040
 knees+0.039
 powers+0.039
 possessions+0.038
iously+0.038
Neg logit contributions
|-0.029
 thanks-0.026
Anna-0.026
 cheered-0.025
ount-0.024
Token are
Token ID389
Feature activation-1.22e-02

Pos logit contributions
ittens+0.031
 powers+0.031
 knees+0.031
 possessions+0.030
belt+0.030
Neg logit contributions
|-0.013
 thanks-0.011
Anna-0.010
 cheered-0.010
ount-0.009
Tokenmy
Token ID1820
Feature activation-5.01e-03

Pos logit contributions
ittens+0.006
 knees+0.006
row+0.006
iously+0.006
 powers+0.006
Neg logit contributions
|-0.004
ount-0.004
 difference-0.004
 Flor-0.003
Anna-0.003
Token,
Token ID11
Feature activation+2.13e-03

Pos logit contributions
 knees+0.009
ittens+0.008
 powers+0.008
iously+0.008
 possessions+0.008
Neg logit contributions
|-0.007
ount-0.006
 difference-0.006
Anna-0.006
Queen-0.005
Token carried
Token ID5281
Feature activation-1.40e-02

Pos logit contributions
|+0.004
 difference+0.003
ount+0.003
Anna+0.003
Queen+0.003
Neg logit contributions
 knees-0.003
ittens-0.003
 powers-0.003
 tools-0.002
iously-0.002
Token his
Token ID465
Feature activation-4.91e-02

Pos logit contributions
ittens+0.028
 knees+0.028
 powers+0.027
 possessions+0.027
iously+0.027
Neg logit contributions
|-0.015
 thanks-0.013
Anna-0.013
 cheered-0.012
ount-0.012
Token favourite
Token ID12507
Feature activation-4.95e-02

Pos logit contributions
ittens+0.083
 powers+0.078
iously+0.078
bars+0.078
ths+0.078
Neg logit contributions
|-0.067
 thanks-0.063
Anna-0.058
 welcome-0.057
 catches-0.056
Token t
Token ID256
Feature activation-9.51e-02

Pos logit contributions
ittens+0.086
iously+0.082
ths+0.081
belt+0.081
bars+0.079
Neg logit contributions
|-0.066
 thanks-0.062
Anna-0.060
 Anna-0.055
 catches-0.055
Tokeneddy
Token ID21874
Feature activation-3.41e-02

Pos logit contributions
iously+0.202
 powers+0.199
 possibly+0.196
 weaknesses+0.195
ths+0.195
Neg logit contributions
|-0.082
Anna-0.073
ack-0.061
S-0.058
he-0.055
Token bear
Token ID6842
Feature activation-2.27e-02

Pos logit contributions
ittens+0.055
 knees+0.055
 powers+0.054
 possessions+0.053
belt+0.052
Neg logit contributions
|-0.050
Anna-0.045
ount-0.044
 thanks-0.044
 cheered-0.044
Token with
Token ID351
Feature activation+5.69e-03

Pos logit contributions
ittens+0.049
 powers+0.048
 knees+0.047
 possessions+0.047
iously+0.047
Neg logit contributions
|-0.021
 thanks-0.018
Anna-0.017
 cheered-0.016
ount-0.015
Token him
Token ID683
Feature activation-1.58e-02

Pos logit contributions
 thanks+0.006
 cheered+0.005
 like+0.004
 Anna+0.004
 the+0.004
Neg logit contributions
belt-0.013
iously-0.013
ittens-0.012
ths-0.012
ately-0.012
Token.
Token ID13
Feature activation-6.47e-03

Pos logit contributions
ittens+0.035
ths+0.034
iously+0.034
 powers+0.034
 knees+0.034
Neg logit contributions
|-0.012
 thanks-0.012
 cheered-0.010
 like-0.009
Anna-0.009
Token back
Token ID736
Feature activation-2.91e-03

Pos logit contributions
 knees+0.003
iously+0.003
 powers+0.003
belt+0.003
 possessions+0.003
Neg logit contributions
|-0.004
 difference-0.004
Anna-0.004
ount-0.004
 thanks-0.004
Token home
Token ID1363
Feature activation+3.93e-03

Pos logit contributions
ittens+0.005
 powers+0.005
 knees+0.005
 possessions+0.005
belt+0.005
Neg logit contributions
|-0.004
 thanks-0.004
Anna-0.004
 cheered-0.003
ount-0.003
Token and
Token ID290
Feature activation-2.08e-02

Pos logit contributions
|+0.005
Anna+0.004
ount+0.004
 thanks+0.004
 difference+0.004
Neg logit contributions
 knees-0.007
ittens-0.007
iously-0.007
belt-0.007
 powers-0.007
Token asked
Token ID1965
Feature activation-3.92e-02

Pos logit contributions
ittens+0.043
 powers+0.039
iously+0.038
 possessions+0.038
bars+0.037
Neg logit contributions
 thanks-0.024
 cheered-0.024
|-0.023
 Anna-0.021
Anna-0.020
Token his
Token ID465
Feature activation-3.98e-02

Pos logit contributions
ittens+0.074
iously+0.071
 powers+0.071
belt+0.071
 knees+0.071
Neg logit contributions
 thanks-0.044
|-0.044
Anna-0.041
 cheered-0.040
 welcome-0.039
Token m
Token ID285
Feature activation-9.50e-02

Pos logit contributions
ittens+0.064
belt+0.063
bars+0.061
iously+0.061
 possessions+0.060
Neg logit contributions
 thanks-0.056
|-0.052
 difference-0.052
 welcome-0.051
Anna-0.051
Tokenama
Token ID1689
Feature activation-3.02e-02

Pos logit contributions
 powers+0.148
 possessions+0.146
 possibly+0.136
 weaknesses+0.135
ised+0.134
Neg logit contributions
ack-0.112
S-0.107
oc-0.103
Anna-0.102
 difference-0.101
Token if
Token ID611
Feature activation-5.33e-02

Pos logit contributions
ittens+0.055
 knees+0.054
 powers+0.054
 possessions+0.053
iously+0.052
Neg logit contributions
|-0.039
Anna-0.033
 thanks-0.032
 cheered-0.032
ount-0.030
Token she
Token ID673
Feature activation-1.44e-02

Pos logit contributions
ittens+0.078
 powers+0.072
iously+0.071
 knees+0.071
belt+0.070
Neg logit contributions
 thanks-0.086
|-0.084
Anna-0.083
 Anna-0.081
 cheered-0.079
Token could
Token ID714
Feature activation-2.06e-02

Pos logit contributions
ittens+0.028
iously+0.026
belt+0.025
 possessions+0.025
ths+0.025
Neg logit contributions
 thanks-0.018
 cheered-0.017
Anna-0.016
|-0.016
 like-0.016
Token repair
Token ID9185
Feature activation-3.96e-03

Pos logit contributions
iously+0.041
ittens+0.041
 possessions+0.040
ths+0.039
 powers+0.039
Neg logit contributions
 thanks-0.022
 have-0.022
 like-0.021
|-0.021
 welcome-0.021
Token day
Token ID1110
Feature activation-3.09e-02

Pos logit contributions
ittens+0.044
 powers+0.043
iously+0.043
 knees+0.042
 possessions+0.042
Neg logit contributions
|-0.035
 thanks-0.032
Anna-0.032
 cheered-0.029
 welcome-0.028
Token,
Token ID11
Feature activation-2.26e-02

Pos logit contributions
ittens+0.062
 knees+0.061
 powers+0.060
 possessions+0.059
iously+0.059
Neg logit contributions
|-0.033
 thanks-0.029
Anna-0.028
 cheered-0.027
 difference-0.026
Token she
Token ID673
Feature activation-1.40e-02

Pos logit contributions
ittens+0.033
 knees+0.032
iously+0.031
 powers+0.030
 possessions+0.030
Neg logit contributions
|-0.038
 thanks-0.034
Anna-0.033
 cheered-0.033
 difference-0.033
Token asked
Token ID1965
Feature activation-2.17e-02

Pos logit contributions
 knees+0.022
 possessions+0.020
 powers+0.020
ittens+0.019
 possibly+0.019
Neg logit contributions
|-0.020
 difference-0.019
 thanks-0.019
ount-0.019
Anna-0.018
Token her
Token ID607
Feature activation-3.41e-02

Pos logit contributions
 knees+0.028
ittens+0.027
 powers+0.026
iously+0.026
 possessions+0.025
Neg logit contributions
|-0.040
 cheered-0.035
 difference-0.035
 thanks-0.035
ount-0.035
Token m
Token ID285
Feature activation-9.49e-02

Pos logit contributions
ittens+0.046
 knees+0.044
 powers+0.044
 possessions+0.043
belt+0.041
Neg logit contributions
|-0.061
Anna-0.054
 thanks-0.054
 cheered-0.054
ount-0.052
Tokenama
Token ID1689
Feature activation-2.96e-02

Pos logit contributions
 possessions+0.133
 powers+0.131
 tools+0.119
iously+0.118
ised+0.118
Neg logit contributions
ack-0.135
S-0.131
Anna-0.130
|-0.130
amp-0.123
Token if
Token ID611
Feature activation-5.72e-02

Pos logit contributions
ittens+0.052
 powers+0.051
 knees+0.050
 possessions+0.050
iously+0.049
Neg logit contributions
|-0.041
Anna-0.034
 cheered-0.033
 thanks-0.032
ount-0.031
Token she
Token ID673
Feature activation-2.50e-02

Pos logit contributions
ittens+0.088
 powers+0.084
iously+0.083
 knees+0.082
belt+0.082
Neg logit contributions
 thanks-0.084
|-0.084
Anna-0.083
 Anna-0.080
 Princess-0.078
Token could
Token ID714
Feature activation-3.42e-02

Pos logit contributions
ittens+0.042
iously+0.038
belt+0.038
 possessions+0.037
 powers+0.037
Neg logit contributions
|-0.037
 thanks-0.035
 cheered-0.035
Anna-0.034
 like-0.031
Token go
Token ID467
Feature activation-2.34e-03

Pos logit contributions
ittens+0.070
iously+0.068
 possessions+0.068
 powers+0.067
 knees+0.067
Neg logit contributions
|-0.036
 thanks-0.033
Anna-0.030
 welcome-0.029
 cheered-0.029
Token day
Token ID1110
Feature activation-2.57e-02

Pos logit contributions
ittens+0.034
 powers+0.033
iously+0.033
 knees+0.033
belt+0.033
Neg logit contributions
|-0.026
 thanks-0.024
Anna-0.024
 cheered-0.022
 welcome-0.021
Token,
Token ID11
Feature activation-1.19e-02

Pos logit contributions
ittens+0.060
belt+0.059
 possessions+0.059
 powers+0.059
iously+0.058
Neg logit contributions
|-0.019
Anna-0.017
 thanks-0.017
 cheered-0.016
 Anna-0.015
Token she
Token ID673
Feature activation-7.59e-03

Pos logit contributions
ittens+0.029
 powers+0.029
 possessions+0.029
belt+0.028
iously+0.028
Neg logit contributions
Anna-0.007
|-0.007
 thanks-0.007
 Anna-0.007
 cheered-0.007
Token took
Token ID1718
Feature activation-1.51e-02

Pos logit contributions
 knees+0.012
ittens+0.012
 powers+0.011
 possessions+0.011
belt+0.011
Neg logit contributions
|-0.011
 thanks-0.010
 difference-0.010
ount-0.010
Anna-0.009
Token some
Token ID617
Feature activation-2.66e-02

Pos logit contributions
ittens+0.030
belt+0.029
 possessions+0.029
iously+0.029
 knees+0.029
Neg logit contributions
|-0.017
 thanks-0.015
Anna-0.015
 cheered-0.014
 Anna-0.014
Token t
Token ID256
Feature activation-9.45e-02

Pos logit contributions
iously+0.049
belt+0.048
ths+0.047
chief+0.044
bled+0.043
Neg logit contributions
 thanks-0.033
|-0.031
 like-0.031
Anna-0.030
 welcome-0.029
Tokenedd
Token ID6048
Feature activation-5.94e-02

Pos logit contributions
iously+0.194
 powers+0.191
 cheeks+0.187
 knees+0.187
belt+0.187
Neg logit contributions
|-0.084
Anna-0.081
ack-0.076
S-0.069
he-0.063
Tokenies
Token ID444
Feature activation-1.73e-04

Pos logit contributions
belt+0.090
iously+0.085
ths+0.083
ittens+0.083
 knees+0.080
Neg logit contributions
|-0.087
 thanks-0.084
Anna-0.083
 cheered-0.080
 like-0.079
Token from
Token ID422
Feature activation+7.97e-04

Pos logit contributions
ittens+0.000
 knees+0.000
 powers+0.000
 possessions+0.000
iously+0.000
Neg logit contributions
|-0.000
 thanks-0.000
Anna-0.000
 cheered-0.000
ount-0.000
Token her
Token ID607
Feature activation-2.60e-02

Pos logit contributions
|+0.001
 thanks+0.001
Anna+0.001
 cheered+0.001
ount+0.001
Neg logit contributions
ittens-0.001
 knees-0.001
 powers-0.001
 possessions-0.001
iously-0.001
Token bed
Token ID3996
Feature activation-1.54e-02

Pos logit contributions
ittens+0.044
 powers+0.042
iously+0.042
 knees+0.042
 possessions+0.042
Neg logit contributions
|-0.036
 thanks-0.033
Anna-0.033
 cheered-0.031
 difference-0.030
Token boy
Token ID2933
Feature activation-1.78e-02

Pos logit contributions
 powers+0.003
iously+0.003
 possessions+0.003
ittens+0.003
belt+0.003
Neg logit contributions
Anna-0.001
 thanks-0.001
|-0.001
 right-0.001
 difference-0.001
Token took
Token ID1718
Feature activation-1.40e-02

Pos logit contributions
ittens+0.031
 powers+0.030
 knees+0.030
 possessions+0.030
belt+0.030
Neg logit contributions
|-0.023
 thanks-0.021
Anna-0.021
 cheered-0.021
ount-0.019
Token his
Token ID465
Feature activation-4.99e-02

Pos logit contributions
ittens+0.030
 knees+0.029
 powers+0.029
 possessions+0.029
iously+0.029
Neg logit contributions
|-0.013
Anna-0.011
 thanks-0.011
 cheered-0.011
ount-0.010
Token shovel
Token ID33677
Feature activation-2.79e-02

Pos logit contributions
belt+0.087
bars+0.086
ths+0.085
iked+0.084
iously+0.084
Neg logit contributions
 right-0.055
 sees-0.053
 and-0.052
 welcome-0.049
 good-0.048
Token and
Token ID290
Feature activation-4.07e-02

Pos logit contributions
ittens+0.068
 powers+0.068
 possessions+0.066
belt+0.065
iously+0.065
Neg logit contributions
 thanks-0.014
|-0.013
 cheered-0.013
Anna-0.010
 right-0.010
Token m
Token ID285
Feature activation-9.45e-02

Pos logit contributions
ittens+0.075
iously+0.069
 powers+0.069
belt+0.069
 possessions+0.067
Neg logit contributions
 cheered-0.054
 thanks-0.049
 Anna-0.046
Anna-0.046
|-0.045
Tokenop
Token ID404
Feature activation-4.38e-02

Pos logit contributions
 powers+0.151
 possessions+0.142
stone+0.138
nam+0.137
 avail+0.131
Neg logit contributions
ack-0.125
ee-0.112
 And-0.110
S-0.108
he-0.108
Token outside
Token ID2354
Feature activation-4.74e-03

Pos logit contributions
ittens+0.095
belt+0.091
 powers+0.087
 possessions+0.086
iously+0.085
Neg logit contributions
 cheered-0.038
|-0.034
 thanks-0.033
 and-0.033
 catches-0.031
Token to
Token ID284
Feature activation-3.10e-03

Pos logit contributions
ittens+0.011
 possessions+0.010
belt+0.010
 powers+0.010
iously+0.010
Neg logit contributions
|-0.004
 thanks-0.004
 cheered-0.004
Anna-0.003
 like-0.003
Token the
Token ID262
Feature activation+2.48e-03

Pos logit contributions
ittens+0.007
belt+0.006
iously+0.006
 powers+0.006
 possessions+0.006
Neg logit contributions
|-0.003
 thanks-0.003
Anna-0.003
 cheered-0.003
 difference-0.003
Token sandbox
Token ID35204
Feature activation-2.83e-03

Pos logit contributions
|+0.004
 thanks+0.003
Anna+0.003
 cheered+0.003
ount+0.003
Neg logit contributions
ittens-0.004
 knees-0.004
 powers-0.004
 possessions-0.004
belt-0.004
Token She
Token ID1375
Feature activation-1.92e-02

Pos logit contributions
ittens+0.041
 powers+0.040
 possessions+0.039
iously+0.039
belt+0.038
Neg logit contributions
|-0.018
 thanks-0.016
Anna-0.015
 cheered-0.015
 Anna-0.013
Token was
Token ID373
Feature activation+5.25e-04

Pos logit contributions
ittens+0.037
 knees+0.037
 powers+0.036
 possessions+0.036
belt+0.036
Neg logit contributions
|-0.022
 thanks-0.019
Anna-0.019
 cheered-0.018
ount-0.017
Token wearing
Token ID5762
Feature activation-3.66e-03

Pos logit contributions
|+0.001
Anna+0.001
 thanks+0.001
 difference+0.001
ount+0.001
Neg logit contributions
 knees-0.001
ittens-0.001
 powers-0.001
belt-0.001
 possessions-0.001
Token her
Token ID607
Feature activation-4.11e-02

Pos logit contributions
iously+0.007
ittens+0.007
belt+0.007
 possessions+0.007
 knees+0.007
Neg logit contributions
|-0.004
Anna-0.004
 thanks-0.004
 Anna-0.003
 cheered-0.003
Token favourite
Token ID12507
Feature activation-5.54e-02

Pos logit contributions
iously+0.082
ths+0.078
bars+0.076
 possessions+0.073
ately+0.073
Neg logit contributions
|-0.045
Anna-0.043
 thanks-0.043
 right-0.042
 Anna-0.042
Token m
Token ID285
Feature activation-9.44e-02

Pos logit contributions
iously+0.127
ately+0.119
ths+0.119
ometers+0.117
bars+0.117
Neg logit contributions
|-0.048
Anna-0.048
 and-0.046
 te-0.045
 Anna-0.045
Tokenittens
Token ID34978
Feature activation-4.06e-02

Pos logit contributions
 possessions+0.089
 weaknesses+0.086
ths+0.084
ised+0.083
izing+0.081
Neg logit contributions
ack-0.184
|-0.182
amp-0.177
S-0.171
 And-0.170
Token which
Token ID543
Feature activation-2.69e-02

Pos logit contributions
 powers+0.102
ths+0.101
 possessions+0.101
iously+0.100
ittens+0.098
Neg logit contributions
 like-0.016
 and-0.016
 thanks-0.014
 right-0.014
|-0.013
Token were
Token ID547
Feature activation+2.27e-04

Pos logit contributions
iously+0.055
ths+0.052
ittens+0.052
 possessions+0.052
 powers+0.052
Neg logit contributions
|-0.030
Anna-0.027
 thanks-0.027
 cheered-0.026
 Anna-0.025
Token bright
Token ID6016
Feature activation-1.68e-02

Pos logit contributions
 like+0.000
Anna+0.000
 thanks+0.000
|+0.000
 Anna+0.000
Neg logit contributions
iously-0.000
 possessions-0.000
 powers-0.000
 knees-0.000
ately-0.000
Token and
Token ID290
Feature activation-1.60e-02

Pos logit contributions
ittens+0.041
 possessions+0.040
belt+0.040
iously+0.040
 powers+0.040
Neg logit contributions
 thanks-0.010
|-0.009
Anna-0.008
 cheered-0.008
 like-0.007
Token!"
Token ID2474
Feature activation-2.60e-03

Pos logit contributions
 powers+0.021
 knees+0.021
ittens+0.021
 possessions+0.020
iously+0.020
Neg logit contributions
|-0.012
 thanks-0.010
Anna-0.010
 cheered-0.009
ount-0.009
Token She
Token ID1375
Feature activation-1.29e-02

Pos logit contributions
ittens+0.006
 knees+0.006
 powers+0.006
 possessions+0.006
iously+0.006
Neg logit contributions
|-0.002
 thanks-0.001
Anna-0.001
 cheered-0.001
ount-0.001
Token got
Token ID1392
Feature activation-2.35e-02

Pos logit contributions
ittens+0.022
 possessions+0.021
iously+0.021
 powers+0.021
belt+0.021
Neg logit contributions
|-0.017
 cheered-0.017
Anna-0.017
 thanks-0.016
ack-0.015
Token on
Token ID319
Feature activation-2.06e-03

Pos logit contributions
ittens+0.052
belt+0.050
iously+0.050
 powers+0.049
 possessions+0.049
Neg logit contributions
|-0.021
 thanks-0.019
 cheered-0.019
Anna-0.017
 right-0.017
Token her
Token ID607
Feature activation-4.79e-02

Pos logit contributions
ittens+0.004
 powers+0.004
belt+0.004
 possessions+0.004
 knees+0.004
Neg logit contributions
|-0.002
 thanks-0.002
Anna-0.002
 cheered-0.002
 difference-0.002
Token t
Token ID256
Feature activation-9.44e-02

Pos logit contributions
row+0.091
iked+0.086
arded+0.086
 possessions+0.086
izing+0.085
Neg logit contributions
|-0.050
 thanks-0.050
 Anna-0.049
 right-0.049
 and-0.048
Tokenippy
Token ID41214
Feature activation-7.06e-02

Pos logit contributions
iously+0.197
 powers+0.197
 possessions+0.193
 possibly+0.190
 cheeks+0.190
Neg logit contributions
|-0.085
Anna-0.073
ack-0.072
he-0.060
amp-0.060
Token toes
Token ID23932
Feature activation-2.08e-02

Pos logit contributions
ths+0.115
belt+0.113
ittens+0.112
 possessions+0.110
izing+0.104
Neg logit contributions
|-0.090
 and-0.087
 cheered-0.086
 And-0.084
 thanks-0.082
Token and
Token ID290
Feature activation-4.11e-02

Pos logit contributions
ittens+0.062
 possessions+0.062
 powers+0.060
ths+0.059
 weaknesses+0.057
Neg logit contributions
 cheered-0.002
 like-0.002
 and-0.002
 thanks-0.001
 right-0.001
Token stretched
Token ID19110
Feature activation-2.98e-02

Pos logit contributions
ittens+0.079
iously+0.074
 possessions+0.072
 powers+0.070
izing+0.069
Neg logit contributions
 cheered-0.055
 Anna-0.049
 thanks-0.048
Anna-0.047
 sees-0.044
Token out
Token ID503
Feature activation-1.41e-02

Pos logit contributions
ittens+0.052
 knees+0.050
 powers+0.050
 possessions+0.049
iously+0.049
Neg logit contributions
|-0.040
 thanks-0.036
Anna-0.036
 cheered-0.035
ount-0.033
Token.
Token ID13
Feature activation-1.28e-02

Pos logit contributions
|+0.010
 catches+0.009
ount+0.009
 thanks+0.009
 cheers+0.008
Neg logit contributions
ittens-0.009
 knees-0.008
 possessions-0.008
 powers-0.008
row-0.007
Token She
Token ID1375
Feature activation-1.11e-02

Pos logit contributions
ittens+0.022
 knees+0.022
 powers+0.022
iously+0.021
belt+0.021
Neg logit contributions
|-0.016
 thanks-0.015
Anna-0.014
 cheered-0.014
 catches-0.014
Token wore
Token ID12408
Feature activation-1.75e-02

Pos logit contributions
ittens+0.020
 knees+0.020
 powers+0.020
 possessions+0.019
belt+0.019
Neg logit contributions
|-0.014
 thanks-0.013
Anna-0.012
 cheered-0.012
ount-0.012
Token her
Token ID607
Feature activation-3.94e-02

Pos logit contributions
iously+0.042
belt+0.040
ately+0.040
ittens+0.040
bars+0.040
Neg logit contributions
|-0.012
 thanks-0.012
Anna-0.012
 Anna-0.012
 like-0.011
Token favorite
Token ID4004
Feature activation-5.27e-02

Pos logit contributions
iously+0.086
ths+0.082
bars+0.080
iked+0.078
ately+0.077
Neg logit contributions
 thanks-0.037
|-0.035
 right-0.034
 Anna-0.034
 Princess-0.033
Token m
Token ID285
Feature activation-9.39e-02

Pos logit contributions
iously+0.128
ths+0.120
ately+0.119
ometers+0.115
bars+0.114
Neg logit contributions
|-0.040
 Princess-0.039
 te-0.038
 and-0.037
Anna-0.037
Tokenitten
Token ID2621
Feature activation-4.71e-02

Pos logit contributions
 possessions+0.083
ths+0.079
iously+0.079
ised+0.079
 weaknesses+0.078
Neg logit contributions
|-0.183
ack-0.181
 And-0.175
S-0.171
amp-0.170
Token every
Token ID790
Feature activation-3.93e-02

Pos logit contributions
ths+0.126
iously+0.123
acies+0.122
 avail+0.119
 weaknesses+0.118
Neg logit contributions
 and-0.024
 named-0.021
 like-0.019
|-0.015
 And-0.014
Token day
Token ID1110
Feature activation-1.94e-02

Pos logit contributions
iously+0.094
ths+0.093
ittens+0.093
 possessions+0.092
drivers+0.091
Neg logit contributions
|-0.031
 thanks-0.026
Anna-0.026
 welcome-0.024
 Anna-0.023
Token.
Token ID13
Feature activation-1.31e-02

Pos logit contributions
iously+0.044
ths+0.044
 powers+0.043
ittens+0.043
 possessions+0.043
Neg logit contributions
|-0.013
 thanks-0.012
 like-0.012
 cheered-0.011
Anna-0.010
Token It
Token ID632
Feature activation-2.04e-02

Pos logit contributions
ittens+0.023
 knees+0.022
 powers+0.022
 possessions+0.021
iously+0.021
Neg logit contributions
|-0.018
 thanks-0.016
Anna-0.016
 cheered-0.016
ount-0.015
Token The
Token ID383
Feature activation-1.27e-02

Pos logit contributions
ittens+0.014
 possessions+0.014
 powers+0.013
belt+0.013
 knees+0.013
Neg logit contributions
|-0.004
 thanks-0.003
Anna-0.003
 cheered-0.003
 Anna-0.003
Token family
Token ID1641
Feature activation-1.94e-02

Pos logit contributions
 powers+0.024
ittens+0.024
iously+0.024
belt+0.023
 possessions+0.023
Neg logit contributions
 thanks-0.014
|-0.013
Anna-0.013
 difference-0.013
 cheered-0.012
Token all
Token ID477
Feature activation+4.11e-03

Pos logit contributions
ittens+0.031
 knees+0.030
 powers+0.030
 possessions+0.029
belt+0.029
Neg logit contributions
|-0.029
 thanks-0.026
Anna-0.026
 cheered-0.024
ount-0.024
Token grabbed
Token ID13176
Feature activation-5.90e-03

Pos logit contributions
|+0.006
 thanks+0.006
Anna+0.006
 cheered+0.005
ount+0.005
Neg logit contributions
ittens-0.007
 knees-0.006
 powers-0.006
 possessions-0.006
iously-0.006
Token their
Token ID511
Feature activation-3.71e-02

Pos logit contributions
ittens+0.012
 powers+0.012
 knees+0.012
 possessions+0.012
belt+0.012
Neg logit contributions
|-0.006
 thanks-0.005
Anna-0.005
 cheered-0.005
ount-0.005
Token m
Token ID285
Feature activation-9.38e-02

Pos logit contributions
iously+0.053
ittens+0.053
belt+0.052
bars+0.051
ths+0.051
Neg logit contributions
|-0.051
 thanks-0.051
 sees-0.049
 right-0.048
 difference-0.048
Tokenops
Token ID2840
Feature activation-2.69e-02

Pos logit contributions
 powers+0.107
 avail+0.098
nam+0.096
 possessions+0.096
stone+0.095
Neg logit contributions
ack-0.154
ount-0.143
amp-0.142
|-0.139
 And-0.137
Token and
Token ID290
Feature activation-2.46e-02

Pos logit contributions
ittens+0.072
 powers+0.072
 possessions+0.071
iously+0.071
ths+0.071
Neg logit contributions
|-0.007
 thanks-0.006
 cheered-0.004
Anna-0.003
 right-0.002
Token put
Token ID1234
Feature activation+9.59e-04

Pos logit contributions
ittens+0.048
iously+0.047
 powers+0.046
 possessions+0.045
belt+0.045
Neg logit contributions
 cheered-0.029
 thanks-0.027
|-0.025
 Anna-0.024
 catches-0.023
Token on
Token ID319
Feature activation+7.89e-03

Pos logit contributions
|+0.001
 thanks+0.001
Anna+0.001
 cheered+0.001
ount+0.001
Neg logit contributions
ittens-0.002
 knees-0.002
 powers-0.002
 possessions-0.002
iously-0.002
Token their
Token ID511
Feature activation-3.37e-02

Pos logit contributions
|+0.007
Anna+0.005
 thanks+0.005
 cheered+0.005
ount+0.005
Neg logit contributions
ittens-0.018
 knees-0.018
 powers-0.017
 possessions-0.017
iously-0.017
Token'm
Token ID1101
Feature activation-5.26e-03

Pos logit contributions
 powers+0.004
 possibly+0.004
 possessions+0.004
belt+0.004
ittens+0.004
Neg logit contributions
 thanks-0.003
|-0.003
Nik-0.003
Kat-0.003
 Princess-0.003
Token sorry
Token ID7926
Feature activation-7.94e-03

Pos logit contributions
ittens+0.008
 powers+0.008
 knees+0.008
belt+0.007
iously+0.007
Neg logit contributions
|-0.008
Anna-0.007
 difference-0.007
 thanks-0.007
 cheered-0.007
Token about
Token ID546
Feature activation+1.38e-02

Pos logit contributions
ittens+0.015
 knees+0.014
 powers+0.014
 possessions+0.014
iously+0.014
Neg logit contributions
|-0.010
 thanks-0.009
Anna-0.009
 cheered-0.008
ount-0.008
Token your
Token ID534
Feature activation-2.59e-02

Pos logit contributions
|+0.016
 thanks+0.015
Anna+0.015
 cheered+0.014
 difference+0.013
Neg logit contributions
ittens-0.026
 knees-0.025
 powers-0.025
belt-0.025
 possessions-0.025
Token tower
Token ID10580
Feature activation+3.46e-02

Pos logit contributions
ittens+0.043
 knees+0.041
 powers+0.041
iously+0.040
 possessions+0.040
Neg logit contributions
|-0.037
 thanks-0.034
Anna-0.033
 cheered-0.032
 difference-0.031
Token,
Token ID11
Feature activation+3.84e-02

Pos logit contributions
|+0.037
 thanks+0.032
Anna+0.031
 cheered+0.030
ount+0.028
Neg logit contributions
ittens-0.069
 knees-0.068
 powers-0.068
 possessions-0.067
iously-0.066
Token but
Token ID475
Feature activation-3.60e-03

Pos logit contributions
|+0.063
Queen+0.051
 cheered+0.049
Anna+0.047
Joy+0.047
Neg logit contributions
ittens-0.061
 knees-0.059
belt-0.055
 powers-0.053
 possibly-0.053
Token I
Token ID314
Feature activation+7.68e-03

Pos logit contributions
ittens+0.007
iously+0.007
 powers+0.007
belt+0.007
 possessions+0.007
Neg logit contributions
 thanks-0.004
Anna-0.004
|-0.004
 Anna-0.004
 cheered-0.004
Token'm
Token ID1101
Feature activation-3.55e-03

Pos logit contributions
|+0.012
Anna+0.011
 Princess+0.011
Queen+0.011
Nik+0.011
Neg logit contributions
 powers-0.010
 possibly-0.009
 knees-0.009
 possessions-0.009
ittens-0.009
Token very
Token ID845
Feature activation-5.20e-03

Pos logit contributions
ittens+0.006
 powers+0.005
 knees+0.005
belt+0.005
ths+0.005
Neg logit contributions
|-0.005
Anna-0.005
 difference-0.005
Queen-0.005
ack-0.004
Token grateful
Token ID14066
Feature activation+2.03e-03

Pos logit contributions
ittens+0.009
 possessions+0.008
 knees+0.008
 powers+0.008
belt+0.008
Neg logit contributions
|-0.008
 thanks-0.006
Anna-0.006
Queen-0.006
ount-0.006
Token.
Token ID13
Feature activation+2.73e-02

Pos logit contributions
|+0.033
Anna+0.029
ount+0.028
 cheered+0.027
 thanks+0.026
Neg logit contributions
ittens-0.059
 powers-0.057
 knees-0.057
iously-0.056
 possessions-0.055
Token You
Token ID921
Feature activation+3.66e-02

Pos logit contributions
|+0.033
 cheered+0.031
ount+0.030
Anna+0.030
ack+0.029
Neg logit contributions
ittens-0.047
 powers-0.046
 knees-0.046
belt-0.045
 possessions-0.044
Token were
Token ID547
Feature activation+3.07e-02

Pos logit contributions
|+0.040
Anna+0.038
ount+0.035
Nik+0.034
S+0.033
Neg logit contributions
 powers-0.072
 knees-0.067
 tools-0.066
 possessions-0.066
ittens-0.065
Token a
Token ID257
Feature activation+6.64e-02

Pos logit contributions
|+0.050
ount+0.047
ack+0.046
Anna+0.044
oke+0.043
Neg logit contributions
 powers-0.047
 tools-0.043
 possessions-0.042
 knees-0.039
 needles-0.039
Token good
Token ID922
Feature activation+1.47e-02

Pos logit contributions
ount+0.130
|+0.124
amp+0.105
oke+0.100
ill+0.097
Neg logit contributions
 powers-0.080
 tools-0.079
 axe-0.079
 razor-0.073
 possessions-0.071
Token dog
Token ID3290
Feature activation+5.61e-02

Pos logit contributions
|+0.025
ount+0.022
 cheered+0.021
Anna+0.020
 thanks+0.019
Neg logit contributions
 knees-0.023
 powers-0.022
ittens-0.022
 possessions-0.021
 tools-0.021
Token."
Token ID526
Feature activation+3.04e-02

Pos logit contributions
|+0.087
ount+0.081
Col+0.078
Kat+0.077
 difference+0.074
Neg logit contributions
ittens-0.080
 powers-0.080
belt-0.077
iously-0.073
row-0.073
Token
Token ID198
Feature activation+1.78e-02

Pos logit contributions
|+0.033
ount+0.031
vy+0.029
 difference+0.029
 thanks+0.029
Neg logit contributions
ittens-0.062
 knees-0.058
 cheeks-0.056
iously-0.055
belt-0.053
Token
Token ID198
Feature activation-5.75e-03

Pos logit contributions
ount+0.017
|+0.017
 thanks+0.017
 difference+0.016
 catches+0.015
Neg logit contributions
ittens-0.038
 knees-0.033
 powers-0.031
 possessions-0.031
belt-0.031
TokenTom
Token ID13787
Feature activation+2.15e-02

Pos logit contributions
ittens+0.011
belt+0.010
ths+0.009
 possessions+0.009
 knees+0.009
Neg logit contributions
|-0.007
 thanks-0.007
ount-0.007
 difference-0.007
 cheered-0.006
Tokenmy
Token ID1820
Feature activation+1.72e-02

Pos logit contributions
ount+0.030
|+0.030
 difference+0.028
Queen+0.025
Kat+0.025
Neg logit contributions
 knees-0.036
row-0.034
iously-0.033
ittens-0.033
 cheeks-0.032
Token,
Token ID11
Feature activation+3.37e-02

Pos logit contributions
ittens+0.022
belt+0.021
 knees+0.021
iously+0.021
 powers+0.021
Neg logit contributions
|-0.009
 thanks-0.009
Anna-0.009
 cheered-0.008
 catches-0.008
Token Sam
Token ID3409
Feature activation+2.53e-02

Pos logit contributions
|+0.046
Anna+0.038
 thanks+0.038
 cheered+0.037
ount+0.037
Neg logit contributions
ittens-0.059
 knees-0.058
 powers-0.058
 possessions-0.057
belt-0.056
Token,
Token ID11
Feature activation+3.37e-02

Pos logit contributions
|+0.039
ount+0.033
 difference+0.031
Queen+0.031
Kat+0.031
Neg logit contributions
 powers-0.040
ittens-0.039
 knees-0.039
 possessions-0.038
iously-0.037
Token you
Token ID345
Feature activation+2.09e-02

Pos logit contributions
|+0.049
Anna+0.041
 thanks+0.041
 cheered+0.040
ount+0.040
Neg logit contributions
ittens-0.055
 knees-0.055
 powers-0.054
belt-0.052
 possessions-0.052
Token can
Token ID460
Feature activation-2.28e-02

Pos logit contributions
|+0.032
Anna+0.028
ount+0.028
Nik+0.028
Kat+0.027
Neg logit contributions
 powers-0.031
 tools-0.029
 knees-0.029
ittens-0.028
 possessions-0.028
Token play
Token ID711
Feature activation+4.65e-02

Pos logit contributions
ittens+0.043
 knees+0.043
 powers+0.042
belt+0.041
 possessions+0.041
Neg logit contributions
|-0.027
 thanks-0.023
Anna-0.023
 cheered-0.022
ount-0.022
Token with
Token ID351
Feature activation+3.29e-02

Pos logit contributions
|+0.062
Nik+0.058
ount+0.057
 thanks+0.055
Kat+0.052
Neg logit contributions
 powers-0.077
 knees-0.074
belt-0.074
 tools-0.071
ittens-0.071
Token it
Token ID340
Feature activation+2.94e-02

Pos logit contributions
|+0.029
Anna+0.028
 thanks+0.028
 Anna+0.026
 cheered+0.025
Neg logit contributions
ittens-0.070
iously-0.070
belt-0.068
 knees-0.067
 powers-0.067
Token first
Token ID717
Feature activation+1.23e-02

Pos logit contributions
|+0.035
 thanks+0.029
Anna+0.029
 cheered+0.028
ount+0.028
Neg logit contributions
ittens-0.055
 knees-0.054
 powers-0.054
iously-0.053
belt-0.053
Token.
Token ID13
Feature activation+1.95e-02

Pos logit contributions
|+0.013
 thanks+0.011
Anna+0.011
 cheered+0.011
ount+0.011
Neg logit contributions
ittens-0.024
 powers-0.024
 knees-0.024
 possessions-0.023
iously-0.023
Token But
Token ID887
Feature activation+1.87e-03

Pos logit contributions
|+0.026
 cheered+0.022
Anna+0.022
 difference+0.021
 thanks+0.021
Neg logit contributions
ittens-0.033
 powers-0.032
 knees-0.032
belt-0.031
iously-0.030
Token think
Token ID892
Feature activation+2.82e-03

Pos logit contributions
|+0.015
 thanks+0.013
Anna+0.013
 cheered+0.013
ount+0.012
Neg logit contributions
ittens-0.032
 knees-0.031
 powers-0.031
 possessions-0.030
iously-0.030
Token?"
Token ID1701
Feature activation+3.77e-02

Pos logit contributions
|+0.004
 thanks+0.003
Anna+0.003
 cheered+0.003
ount+0.003
Neg logit contributions
ittens-0.005
 knees-0.005
 powers-0.005
 possessions-0.005
iously-0.005
Token his
Token ID465
Feature activation-2.36e-02

Pos logit contributions
|+0.065
ount+0.059
 thanks+0.056
 cheered+0.054
 difference+0.054
Neg logit contributions
ittens-0.052
 knees-0.051
 powers-0.048
 possessions-0.047
belt-0.046
Token dad
Token ID9955
Feature activation+2.01e-02

Pos logit contributions
ittens+0.033
 knees+0.032
 powers+0.032
 possessions+0.031
belt+0.031
Neg logit contributions
|-0.040
 thanks-0.037
Anna-0.036
 cheered-0.035
ount-0.034
Token said
Token ID531
Feature activation-2.96e-03

Pos logit contributions
 cheered+0.023
|+0.022
 thanks+0.021
Anna+0.020
 Anna+0.018
Neg logit contributions
 possessions-0.039
ittens-0.039
 powers-0.039
belt-0.038
 knees-0.037
Token.
Token ID13
Feature activation+3.80e-02

Pos logit contributions
ittens+0.006
 powers+0.006
 possessions+0.006
belt+0.006
 knees+0.006
Neg logit contributions
|-0.003
 thanks-0.002
 cheered-0.002
Anna-0.002
 difference-0.002
Token
Token ID198
Feature activation+2.49e-02

Pos logit contributions
|+0.038
ount+0.030
 difference+0.029
 thanks+0.028
ack+0.025
Neg logit contributions
ittens-0.079
 knees-0.076
 powers-0.075
 possibly-0.073
belt-0.073
Token
Token ID198
Feature activation-3.91e-03

Pos logit contributions
|+0.030
ount+0.028
 thanks+0.024
 Princess+0.024
 difference+0.024
Neg logit contributions
ittens-0.047
 knees-0.041
ised-0.039
 tools-0.039
 possibly-0.039
TokenBen
Token ID11696
Feature activation+3.40e-02

Pos logit contributions
ittens+0.007
 possessions+0.006
belt+0.006
 knees+0.006
 possibly+0.006
Neg logit contributions
|-0.006
ount-0.005
 difference-0.005
 thanks-0.005
 celebrate-0.004
Token looked
Token ID3114
Feature activation+2.31e-02

Pos logit contributions
|+0.051
ount+0.044
 difference+0.043
Anna+0.041
 thanks+0.041
Neg logit contributions
 knees-0.056
iously-0.053
 powers-0.053
 cheeks-0.052
ittens-0.052
Token again
Token ID757
Feature activation+1.65e-03

Pos logit contributions
|+0.041
Anna+0.034
Queen+0.034
Joy+0.031
ount+0.031
Neg logit contributions
 knees-0.036
iously-0.033
 possessions-0.033
 powers-0.032
ised-0.032
Token was
Token ID373
Feature activation+1.64e-02

Pos logit contributions
|+0.043
 thanks+0.040
Anna+0.039
 cheered+0.038
 catches+0.035
Neg logit contributions
ittens-0.052
 powers-0.050
 possessions-0.050
 knees-0.050
iously-0.050
Token alone
Token ID3436
Feature activation+2.53e-02

Pos logit contributions
|+0.023
Anna+0.020
 cheered+0.020
ount+0.019
 thanks+0.019
Neg logit contributions
ittens-0.027
 powers-0.026
 knees-0.026
 possessions-0.026
belt-0.026
Token.
Token ID13
Feature activation+3.88e-02

Pos logit contributions
|+0.039
ount+0.034
Anna+0.034
Queen+0.033
Nik+0.032
Neg logit contributions
 knees-0.038
 powers-0.038
ittens-0.038
belt-0.037
iously-0.036
Token The
Token ID383
Feature activation+2.83e-02

Pos logit contributions
|+0.037
 thanks+0.032
Anna+0.031
 cheered+0.030
ount+0.028
Neg logit contributions
ittens-0.082
 knees-0.080
 powers-0.080
 possessions-0.079
iously-0.079
Token end
Token ID886
Feature activation+1.54e-02

Pos logit contributions
|+0.030
 thanks+0.026
Anna+0.026
 cheered+0.025
ount+0.023
Neg logit contributions
ittens-0.058
 knees-0.056
 powers-0.056
 possessions-0.055
iously-0.055
Token.
Token ID13
Feature activation+3.96e-02

Pos logit contributions
|+0.014
Anna+0.013
 thanks+0.012
 cheered+0.012
 Anna+0.010
Neg logit contributions
ittens-0.034
iously-0.034
 knees-0.033
 possessions-0.033
belt-0.033
Token<|endoftext|>
Token ID50256
Feature activation+2.59e-02

Pos logit contributions
|+0.029
 thanks+0.025
 cheered+0.025
 difference+0.023
ount+0.023
Neg logit contributions
ittens-0.089
 knees-0.084
 powers-0.084
 possessions-0.082
belt-0.082
TokenS
Token ID50
Feature activation+2.79e-02

Pos logit contributions
 difference+0.029
ount+0.029
 thanks+0.028
|+0.028
Nik+0.027
Neg logit contributions
 powers-0.041
ittens-0.040
 tools-0.038
 knees-0.037
row-0.037
Tokenara
Token ID3301
Feature activation+3.69e-02

Pos logit contributions
|+0.039
 cheered+0.036
 thanks+0.033
ount+0.032
 difference+0.032
Neg logit contributions
ittens-0.048
ths-0.041
bars-0.041
 knees-0.041
chief-0.040
Token loves
Token ID10408
Feature activation-2.97e-02

Pos logit contributions
|+0.047
 difference+0.046
ount+0.045
Joy+0.041
 Ms+0.038
Neg logit contributions
 knees-0.064
 powers-0.059
 tools-0.058
 possessions-0.057
belt-0.057
Token spring
Token ID6076
Feature activation-1.57e-02

Pos logit contributions
belt+0.063
iously+0.061
ittens+0.058
 powers+0.058
 possessions+0.057
Neg logit contributions
 thanks-0.030
 Anna-0.027
|-0.026
 Sara-0.026
 Mr-0.026
Token,
Token ID11
Feature activation+2.28e-02

Pos logit contributions
|+0.004
Anna+0.003
 thanks+0.003
 cheered+0.003
ount+0.003
Neg logit contributions
ittens-0.005
 knees-0.005
iously-0.005
 powers-0.005
 possessions-0.005
Token and
Token ID290
Feature activation-2.08e-02

Pos logit contributions
|+0.026
Anna+0.021
ount+0.020
ack+0.019
 difference+0.019
Neg logit contributions
ittens-0.045
 knees-0.044
 powers-0.043
 tools-0.042
 possessions-0.042
Token even
Token ID772
Feature activation-2.01e-02

Pos logit contributions
ittens+0.039
iously+0.038
 powers+0.037
belt+0.037
 possessions+0.036
Neg logit contributions
 thanks-0.025
|-0.024
 cheered-0.024
Anna-0.023
 Anna-0.022
Token her
Token ID607
Feature activation-2.97e-02

Pos logit contributions
ittens+0.043
iously+0.041
belt+0.041
 knees+0.041
 powers+0.040
Neg logit contributions
 thanks-0.019
|-0.019
Anna-0.018
 cheered-0.017
 Anna-0.017
Token toys
Token ID14958
Feature activation+9.55e-03

Pos logit contributions
ittens+0.049
 knees+0.047
iously+0.047
 powers+0.047
belt+0.046
Neg logit contributions
|-0.042
 thanks-0.039
Anna-0.038
 cheered-0.037
 difference-0.036
Token.
Token ID13
Feature activation-3.48e-03

Pos logit contributions
|+0.009
 thanks+0.009
Anna+0.008
 cheered+0.008
ount+0.007
Neg logit contributions
ittens-0.020
 knees-0.019
 powers-0.019
 possessions-0.019
iously-0.019
Token She
Token ID1375
Feature activation-4.00e-03

Pos logit contributions
ittens+0.005
 knees+0.005
 powers+0.005
iously+0.005
belt+0.005
Neg logit contributions
|-0.005
 thanks-0.005
 cheered-0.004
Anna-0.004
ount-0.004
Token talked
Token ID6619
Feature activation+1.57e-03

Pos logit contributions
 knees+0.005
ittens+0.005
 powers+0.005
 cheeks+0.005
ths+0.005
Neg logit contributions
|-0.007
ount-0.006
 difference-0.006
 welcome-0.006
 thanks-0.006
Token when
Token ID618
Feature activation-2.45e-02

Pos logit contributions
|+0.002
Anna+0.002
ount+0.002
 thanks+0.002
 difference+0.002
Neg logit contributions
ittens-0.003
 powers-0.003
 knees-0.003
 possessions-0.003
belt-0.003
Token she
Token ID673
Feature activation-1.33e-02

Pos logit contributions
ittens+0.040
iously+0.040
 powers+0.040
 possessions+0.038
belt+0.038
Neg logit contributions
Anna-0.034
 thanks-0.033
|-0.033
 Anna-0.033
 cheered-0.031
Token ate
Token ID15063
Feature activation+2.55e-03

Pos logit contributions
 knees+0.021
ittens+0.021
 powers+0.020
ths+0.020
iously+0.020
Neg logit contributions
|-0.019
 difference-0.017
ount-0.016
 thanks-0.016
Anna-0.016
Token and
Token ID290
Feature activation-1.71e-02

Pos logit contributions
|+0.011
 thanks+0.009
Anna+0.009
 cheered+0.009
ount+0.008
Neg logit contributions
ittens-0.020
 knees-0.019
 powers-0.019
 possessions-0.019
iously-0.019
Token see
Token ID766
Feature activation+1.49e-02

Pos logit contributions
ittens+0.038
 powers+0.036
 possessions+0.036
iously+0.036
belt+0.035
Neg logit contributions
|-0.016
 thanks-0.014
 cheered-0.013
Anna-0.013
 catches-0.012
Token what
Token ID644
Feature activation-9.77e-03

Pos logit contributions
|+0.021
Anna+0.018
 thanks+0.017
 cheered+0.017
ount+0.017
Neg logit contributions
 knees-0.025
ittens-0.025
 powers-0.025
 possessions-0.025
iously-0.024
Token was
Token ID373
Feature activation+2.33e-02

Pos logit contributions
ittens+0.019
iously+0.018
belt+0.017
 knees+0.017
 possessions+0.017
Neg logit contributions
|-0.012
Anna-0.012
 thanks-0.011
 cheered-0.011
 Anna-0.010
Token behind
Token ID2157
Feature activation+2.65e-02

Pos logit contributions
|+0.031
Anna+0.026
 thanks+0.026
 cheered+0.025
 difference+0.024
Neg logit contributions
 powers-0.041
ittens-0.041
 knees-0.041
 possessions-0.041
belt-0.040
Token it
Token ID340
Feature activation+8.13e-03

Pos logit contributions
|+0.033
 thanks+0.031
Anna+0.030
 cheered+0.029
 catches+0.027
Neg logit contributions
ittens-0.048
 powers-0.046
 knees-0.046
 possessions-0.046
iously-0.045
Token.
Token ID13
Feature activation+2.26e-02

Pos logit contributions
 thanks+0.006
|+0.005
Anna+0.005
 cheered+0.005
 like+0.004
Neg logit contributions
ittens-0.019
belt-0.019
 possessions-0.019
 knees-0.019
 powers-0.019
Token
Token ID198
Feature activation+1.27e-02

Pos logit contributions
|+0.024
 thanks+0.021
Anna+0.020
 cheered+0.019
ount+0.018
Neg logit contributions
ittens-0.046
 knees-0.045
 powers-0.045
belt-0.044
 possessions-0.044
Token
Token ID198
Feature activation-1.46e-02

Pos logit contributions
|+0.011
 thanks+0.010
ount+0.009
 difference+0.009
 Princess+0.009
Neg logit contributions
ittens-0.028
 knees-0.026
belt-0.025
 powers-0.025
 possessions-0.025
Token"
Token ID1
Feature activation-2.66e-02

Pos logit contributions
ittens+0.027
belt+0.026
 knees+0.026
 possessions+0.025
 powers+0.025
Neg logit contributions
|-0.018
 thanks-0.017
 difference-0.015
ount-0.015
 cheered-0.015
TokenSam
Token ID16305
Feature activation+2.28e-02

Pos logit contributions
ittens+0.052
 knees+0.051
 powers+0.051
 possessions+0.050
belt+0.050
Neg logit contributions
|-0.030
 thanks-0.027
Anna-0.026
 cheered-0.025
ount-0.024
Token.
Token ID13
Feature activation+1.73e-03

Pos logit contributions
|+0.007
Anna+0.006
 thanks+0.006
 cheered+0.006
ount+0.006
Neg logit contributions
 knees-0.011
 powers-0.011
ittens-0.011
 possessions-0.011
iously-0.011
Token And
Token ID843
Feature activation-7.87e-03

Pos logit contributions
|+0.002
 cheered+0.002
 thanks+0.002
Anna+0.002
ount+0.002
Neg logit contributions
ittens-0.003
 knees-0.003
 powers-0.003
belt-0.003
iously-0.003
Token remember
Token ID3505
Feature activation-1.60e-02

Pos logit contributions
ittens+0.015
 powers+0.014
 knees+0.014
belt+0.014
iously+0.014
Neg logit contributions
|-0.009
 thanks-0.009
Anna-0.009
 cheered-0.008
 difference-0.008
Token,
Token ID11
Feature activation+2.91e-02

Pos logit contributions
ittens+0.033
 knees+0.031
belt+0.031
 possessions+0.031
 powers+0.031
Neg logit contributions
|-0.016
 thanks-0.016
Anna-0.015
 cheered-0.013
 difference-0.013
Token sometimes
Token ID3360
Feature activation-2.55e-02

Pos logit contributions
|+0.042
Anna+0.035
 cheered+0.035
ount+0.035
 thanks+0.033
Neg logit contributions
 knees-0.048
ittens-0.048
 powers-0.047
 possessions-0.047
iously-0.046
Token it
Token ID340
Feature activation-2.48e-04

Pos logit contributions
ittens+0.051
belt+0.048
iously+0.047
 powers+0.047
 knees+0.046
Neg logit contributions
 thanks-0.028
|-0.027
Anna-0.025
 difference-0.025
 cheered-0.024
Token's
Token ID338
Feature activation-1.15e-02

Pos logit contributions
ittens+0.001
 knees+0.001
 powers+0.001
 possessions+0.001
iously+0.001
Neg logit contributions
|-0.000
 thanks-0.000
Anna-0.000
 cheered-0.000
ount-0.000
Token good
Token ID922
Feature activation-2.43e-02

Pos logit contributions
ittens+0.021
 knees+0.021
 powers+0.020
iously+0.020
 possessions+0.020
Neg logit contributions
|-0.014
 thanks-0.013
Anna-0.013
 cheered-0.012
 difference-0.012
Token to
Token ID284
Feature activation-9.04e-04

Pos logit contributions
ittens+0.049
belt+0.046
iously+0.044
 knees+0.044
bars+0.043
Neg logit contributions
 thanks-0.027
|-0.025
 difference-0.024
Anna-0.023
 like-0.023
Token enjoy
Token ID2883
Feature activation+1.86e-02

Pos logit contributions
ittens+0.002
 knees+0.002
 powers+0.002
belt+0.002
 possessions+0.002
Neg logit contributions
|-0.001
 thanks-0.001
Anna-0.001
 cheered-0.001
 difference-0.001
Token the
Token ID262
Feature activation+5.49e-03

Pos logit contributions
|+0.021
 thanks+0.018
Anna+0.018
 cheered+0.018
ount+0.017
Neg logit contributions
ittens-0.036
 knees-0.035
 powers-0.035
 possessions-0.035
iously-0.034
Token loved
Token ID6151
Feature activation-2.46e-02

Pos logit contributions
|+0.011
 difference+0.010
Anna+0.009
ount+0.009
 thanks+0.009
Neg logit contributions
 possessions-0.010
ittens-0.010
 powers-0.010
 knees-0.010
belt-0.010
Token each
Token ID1123
Feature activation+5.05e-03

Pos logit contributions
ittens+0.047
belt+0.047
iously+0.046
 powers+0.045
 knees+0.044
Neg logit contributions
|-0.028
 thanks-0.027
Anna-0.024
 Anna-0.023
 cheered-0.023
Token other
Token ID584
Feature activation-4.49e-03

Pos logit contributions
|+0.007
ount+0.006
 cheered+0.006
 thanks+0.006
Anna+0.006
Neg logit contributions
ittens-0.008
 knees-0.008
 possessions-0.008
 powers-0.008
 tools-0.008
Token very
Token ID845
Feature activation-2.49e-02

Pos logit contributions
 knees+0.008
 possessions+0.008
 powers+0.008
ittens+0.008
iously+0.007
Neg logit contributions
|-0.006
Anna-0.005
ount-0.005
 thanks-0.005
 catches-0.005
Token much
Token ID881
Feature activation-5.69e-03

Pos logit contributions
ittens+0.049
 knees+0.047
 possessions+0.047
 powers+0.046
belt+0.046
Neg logit contributions
|-0.028
 thanks-0.025
Anna-0.024
 cheered-0.023
ount-0.023
Token.
Token ID13
Feature activation+5.61e-03

Pos logit contributions
ittens+0.010
 powers+0.010
 knees+0.010
 possessions+0.010
iously+0.010
Neg logit contributions
|-0.008
Anna-0.006
ount-0.006
 thanks-0.006
 cheered-0.006
Token
Token ID198
Feature activation+1.23e-02

Pos logit contributions
|+0.007
 cal+0.007
 cheered+0.007
 thanks+0.007
 victorious+0.006
Neg logit contributions
ittens-0.010
 knees-0.009
 cheeks-0.009
bars-0.008
belt-0.008
Token
Token ID198
Feature activation-2.25e-02

Pos logit contributions
 thanks+0.012
|+0.011
 cal+0.011
ount+0.011
 difference+0.011
Neg logit contributions
ittens-0.025
 knees-0.023
 powers-0.022
belt-0.022
 possibly-0.021
TokenOne
Token ID3198
Feature activation-1.80e-02

Pos logit contributions
ittens+0.022
ths+0.016
belt+0.016
ised+0.016
 possibly+0.016
Neg logit contributions
 thanks-0.047
 difference-0.046
 catches-0.044
|-0.044
 cal-0.043
Token day
Token ID1110
Feature activation-2.74e-02

Pos logit contributions
ittens+0.027
 knees+0.026
 powers+0.025
 possessions+0.025
belt+0.025
Neg logit contributions
|-0.029
 thanks-0.026
 cheered-0.026
Anna-0.026
ount-0.025
Token the
Token ID262
Feature activation-8.86e-03

Pos logit contributions
ittens+0.058
 powers+0.057
 knees+0.057
 possessions+0.056
iously+0.056
Neg logit contributions
|-0.026
 thanks-0.022
Anna-0.022
 cheered-0.021
ount-0.019
Token upon
Token ID2402
Feature activation+2.69e-02

Pos logit contributions
|+0.001
 thanks+0.001
Anna+0.001
 cheered+0.000
ount+0.000
Neg logit contributions
ittens-0.001
 knees-0.001
 powers-0.001
 possessions-0.001
belt-0.001
Token a
Token ID257
Feature activation+2.25e-02

Pos logit contributions
|+0.028
Anna+0.025
 thanks+0.025
 cheered+0.023
Queen+0.021
Neg logit contributions
ittens-0.055
 knees-0.054
 possessions-0.053
 powers-0.053
iously-0.053
Token time
Token ID640
Feature activation-9.98e-03

Pos logit contributions
|+0.031
ount+0.031
 cheered+0.030
 cheers+0.028
 thanks+0.028
Neg logit contributions
ittens-0.041
 knees-0.035
 powers-0.033
iously-0.032
ths-0.032
Token,
Token ID11
Feature activation+1.16e-02

Pos logit contributions
ittens+0.020
 knees+0.019
 powers+0.018
iously+0.018
 possessions+0.018
Neg logit contributions
|-0.011
 thanks-0.010
Anna-0.010
 cheered-0.010
 difference-0.009
Token there
Token ID612
Feature activation+4.51e-03

Pos logit contributions
|+0.017
 thanks+0.016
 cheered+0.015
 difference+0.015
Anna+0.015
Neg logit contributions
ittens-0.019
 knees-0.018
belt-0.018
 powers-0.017
 possessions-0.017
Token was
Token ID373
Feature activation+5.49e-03

Pos logit contributions
|+0.007
 thanks+0.006
Anna+0.006
ount+0.006
 cheered+0.006
Neg logit contributions
ittens-0.007
 knees-0.007
 powers-0.007
 possessions-0.007
belt-0.007
Token a
Token ID257
Feature activation+3.44e-02

Pos logit contributions
|+0.008
 difference+0.007
 thanks+0.007
ount+0.007
 cheered+0.007
Neg logit contributions
ittens-0.009
 knees-0.009
 powers-0.008
 possessions-0.008
iously-0.008
Token big
Token ID1263
Feature activation+2.55e-02

Pos logit contributions
|+0.070
ount+0.066
 cheered+0.059
 thanks+0.058
rs+0.058
Neg logit contributions
ittens-0.044
 knees-0.038
 axe-0.035
 tools-0.034
belt-0.033
Token dog
Token ID3290
Feature activation+2.53e-02

Pos logit contributions
|+0.046
ount+0.044
 cheered+0.040
Kat+0.039
Cl+0.039
Neg logit contributions
ittens-0.036
 knees-0.035
 axe-0.035
 powers-0.032
 cheeks-0.032
Token named
Token ID3706
Feature activation+8.98e-03

Pos logit contributions
|+0.026
ount+0.024
 difference+0.023
 thanks+0.023
 catches+0.022
Neg logit contributions
ittens-0.052
 knees-0.049
 powers-0.048
belt-0.047
 possessions-0.046
Token Spot
Token ID15899
Feature activation+1.53e-02

Pos logit contributions
|+0.009
 thanks+0.008
Anna+0.008
 cheered+0.007
ount+0.007
Neg logit contributions
ittens-0.019
 knees-0.018
 powers-0.018
 possessions-0.018
iously-0.018
Token He
Token ID679
Feature activation-1.87e-02

Pos logit contributions
ittens+0.019
 knees+0.019
iously+0.018
 powers+0.018
belt+0.018
Neg logit contributions
|-0.019
 thanks-0.017
Anna-0.017
 difference-0.016
 cheered-0.016
Token went
Token ID1816
Feature activation-2.92e-03

Pos logit contributions
ittens+0.036
 possessions+0.034
belt+0.034
 powers+0.033
bars+0.032
Neg logit contributions
 cheered-0.022
Anna-0.020
 thanks-0.020
|-0.020
 catches-0.018
Token over
Token ID625
Feature activation+1.54e-02

Pos logit contributions
ittens+0.005
 knees+0.005
 powers+0.005
belt+0.005
 possessions+0.005
Neg logit contributions
|-0.004
Anna-0.003
 thanks-0.003
 cheered-0.003
 difference-0.003
Token and
Token ID290
Feature activation-2.53e-02

Pos logit contributions
|+0.021
 thanks+0.019
Anna+0.019
 cheered+0.018
ount+0.017
Neg logit contributions
ittens-0.026
 knees-0.026
 powers-0.026
 possessions-0.025
iously-0.025
Token picked
Token ID6497
Feature activation-7.12e-03

Pos logit contributions
ittens+0.046
 powers+0.044
 possessions+0.043
 knees+0.043
iously+0.042
Neg logit contributions
|-0.033
 thanks-0.030
 cheered-0.030
Anna-0.029
 catches-0.027
Token an
Token ID281
Feature activation-2.36e-02

Pos logit contributions
 knees+0.010
 powers+0.010
iously+0.009
 possessions+0.009
ittens+0.009
Neg logit contributions
|-0.013
Anna-0.011
ount-0.011
 cheered-0.011
 thanks-0.010
Token apple
Token ID17180
Feature activation-2.19e-02

Pos logit contributions
ittens+0.039
belt+0.039
 possessions+0.037
 powers+0.037
 knees+0.037
Neg logit contributions
 thanks-0.031
 welcome-0.029
 difference-0.029
 like-0.029
 right-0.029
Token and
Token ID290
Feature activation-2.43e-02

Pos logit contributions
ittens+0.049
 powers+0.047
 possessions+0.047
 knees+0.047
belt+0.046
Neg logit contributions
|-0.017
 thanks-0.016
Anna-0.015
 cheered-0.015
 difference-0.013
Token he
Token ID339
Feature activation-2.64e-02

Pos logit contributions
ittens+0.046
belt+0.043
 powers+0.043
 possessions+0.042
iously+0.041
Neg logit contributions
 cheered-0.029
 thanks-0.029
|-0.026
Anna-0.026
 catches-0.026
Token said
Token ID531
Feature activation-2.79e-02

Pos logit contributions
ittens+0.049
 possessions+0.047
 powers+0.046
iously+0.046
belt+0.045
Neg logit contributions
 cheered-0.031
|-0.029
 thanks-0.029
Anna-0.029
 catches-0.026
Token,
Token ID11
Feature activation-5.53e-03

Pos logit contributions
ittens+0.057
 knees+0.055
 powers+0.054
 possessions+0.054
belt+0.054
Neg logit contributions
|-0.028
 thanks-0.027
 cheered-0.026
Anna-0.025
 catches-0.023
Token noise
Token ID7838
Feature activation-1.41e-02

Pos logit contributions
ittens+0.040
 powers+0.039
iously+0.039
 knees+0.039
belt+0.039
Neg logit contributions
|-0.030
Anna-0.027
 thanks-0.027
 cheered-0.027
 difference-0.026
Token from
Token ID422
Feature activation-3.61e-03

Pos logit contributions
ittens+0.032
 possessions+0.031
belt+0.031
iously+0.030
 knees+0.030
Neg logit contributions
|-0.012
 thanks-0.012
 cheered-0.011
 like-0.011
Anna-0.010
Token down
Token ID866
Feature activation+2.73e-03

Pos logit contributions
ittens+0.009
iously+0.008
 possessions+0.008
 powers+0.008
belt+0.008
Neg logit contributions
|-0.003
 thanks-0.003
Anna-0.002
 cheered-0.002
 Anna-0.002
Token the
Token ID262
Feature activation+1.46e-02

Pos logit contributions
|+0.003
Anna+0.002
 thanks+0.002
 cheered+0.002
 difference+0.002
Neg logit contributions
ittens-0.005
 powers-0.005
 knees-0.005
iously-0.005
belt-0.005
Token street
Token ID4675
Feature activation-6.99e-03

Pos logit contributions
|+0.025
 thanks+0.024
 cheered+0.024
ount+0.023
Anna+0.022
Neg logit contributions
 knees-0.019
belt-0.018
 tools-0.018
 needles-0.017
 powers-0.017
Token.
Token ID13
Feature activation-1.95e-02

Pos logit contributions
ittens+0.014
 powers+0.014
 knees+0.014
 possessions+0.013
iously+0.013
Neg logit contributions
|-0.008
 thanks-0.007
Anna-0.007
 cheered-0.006
ount-0.006
Token He
Token ID679
Feature activation-2.44e-02

Pos logit contributions
ittens+0.039
 possessions+0.038
 powers+0.037
iously+0.037
ths+0.037
Neg logit contributions
|-0.022
 thanks-0.020
Anna-0.019
 cheered-0.019
 Anna-0.017
Token stopped
Token ID5025
Feature activation-2.74e-02

Pos logit contributions
ittens+0.051
 possessions+0.047
belt+0.047
 powers+0.046
iously+0.045
Neg logit contributions
|-0.029
 cheered-0.027
Anna-0.027
 thanks-0.025
 sees-0.023
Token to
Token ID284
Feature activation-1.91e-03

Pos logit contributions
ittens+0.064
 powers+0.062
 knees+0.062
belt+0.062
 possessions+0.062
Neg logit contributions
|-0.021
 thanks-0.018
Anna-0.017
 cheered-0.016
ount-0.014
Token listen
Token ID6004
Feature activation-1.94e-02

Pos logit contributions
 knees+0.004
 powers+0.003
iously+0.003
 possessions+0.003
 tools+0.003
Neg logit contributions
|-0.002
ount-0.002
Anna-0.002
ack-0.002
 cheered-0.002
Token.
Token ID13
Feature activation-1.47e-02

Pos logit contributions
ittens+0.043
 possessions+0.041
 powers+0.041
belt+0.040
 knees+0.040
Neg logit contributions
|-0.017
 thanks-0.016
Anna-0.015
 cheered-0.015
 like-0.013
Token dad
Token ID9955
Feature activation-4.96e-03

Pos logit contributions
ittens+0.111
iously+0.104
 powers+0.102
row+0.100
 knees+0.100
Neg logit contributions
 thanks-0.065
 Anna-0.064
 Mrs-0.063
Anna-0.062
 Sara-0.060
Token said
Token ID531
Feature activation-1.82e-02

Pos logit contributions
 knees+0.009
ittens+0.009
 powers+0.008
iously+0.008
 possessions+0.008
Neg logit contributions
|-0.007
Anna-0.006
 thanks-0.006
Queen-0.005
ount-0.005
Token,
Token ID11
Feature activation+2.05e-03

Pos logit contributions
ittens+0.033
 knees+0.033
 powers+0.032
 possessions+0.032
iously+0.032
Neg logit contributions
|-0.023
 thanks-0.020
Anna-0.020
 cheered-0.019
ount-0.018
Token "
Token ID366
Feature activation-2.69e-02

Pos logit contributions
|+0.003
Anna+0.003
 thanks+0.003
 difference+0.003
Queen+0.003
Neg logit contributions
 knees-0.003
ittens-0.003
iously-0.003
belt-0.003
 powers-0.003
TokenLet
Token ID5756
Feature activation-1.54e-02

Pos logit contributions
ittens+0.049
 knees+0.048
 powers+0.048
 possessions+0.047
iously+0.047
Neg logit contributions
|-0.034
Anna-0.030
 thanks-0.030
 cheered-0.029
ount-0.027
Token's
Token ID338
Feature activation-2.96e-02

Pos logit contributions
 knees+0.031
ittens+0.030
 powers+0.030
 possessions+0.030
iously+0.029
Neg logit contributions
|-0.017
ount-0.013
 thanks-0.013
Anna-0.013
 cheered-0.012
Token tie
Token ID9839
Feature activation+7.81e-03

Pos logit contributions
ittens+0.059
iously+0.056
 possessions+0.056
 powers+0.055
belt+0.055
Neg logit contributions
|-0.033
 thanks-0.030
Anna-0.029
 cheered-0.028
 difference-0.027
Token a
Token ID257
Feature activation+8.08e-04

Pos logit contributions
|+0.008
 thanks+0.008
Anna+0.007
 cheered+0.007
 catches+0.007
Neg logit contributions
ittens-0.016
 knees-0.015
iously-0.015
 powers-0.015
 possessions-0.015
Token rope
Token ID17182
Feature activation+1.22e-02

Pos logit contributions
|+0.001
Anna+0.001
 thanks+0.001
 cheered+0.001
 difference+0.001
Neg logit contributions
ittens-0.001
iously-0.001
 knees-0.001
 powers-0.001
 possessions-0.001
Token around
Token ID1088
Feature activation+2.86e-02

Pos logit contributions
|+0.013
Anna+0.011
 thanks+0.011
 cheered+0.010
 difference+0.010
Neg logit contributions
ittens-0.024
 powers-0.024
 knees-0.024
belt-0.024
 possessions-0.023
Token the
Token ID262
Feature activation+2.89e-02

Pos logit contributions
|+0.032
ount+0.027
 thanks+0.026
Anna+0.026
 cheered+0.025
Neg logit contributions
 knees-0.056
 powers-0.056
ittens-0.054
 possessions-0.054
belt-0.053
Token help
Token ID1037
Feature activation-8.02e-03

Pos logit contributions
|+0.022
Anna+0.020
ount+0.019
 cheered+0.019
 thanks+0.018
Neg logit contributions
 knees-0.028
 powers-0.027
 tools-0.026
iously-0.026
 possessions-0.026
Token.
Token ID13
Feature activation-4.62e-03

Pos logit contributions
ittens+0.015
 knees+0.015
 powers+0.015
 possessions+0.014
iously+0.014
Neg logit contributions
|-0.010
Anna-0.009
 thanks-0.008
 cheered-0.008
ount-0.008
Token He
Token ID679
Feature activation-2.76e-03

Pos logit contributions
ittens+0.009
 knees+0.008
 powers+0.008
 possessions+0.008
belt+0.008
Neg logit contributions
|-0.006
 thanks-0.005
Anna-0.005
 cheered-0.005
ount-0.004
Token had
Token ID550
Feature activation+6.07e-04

Pos logit contributions
ittens+0.005
 knees+0.004
 powers+0.004
 possessions+0.004
iously+0.004
Neg logit contributions
|-0.004
 thanks-0.003
Anna-0.003
 cheered-0.003
ount-0.003
Token a
Token ID257
Feature activation+1.28e-02

Pos logit contributions
|+0.001
 thanks+0.001
 cheered+0.001
 catches+0.001
Anna+0.001
Neg logit contributions
ittens-0.001
belt-0.001
 knees-0.001
iously-0.001
 possessions-0.001
Token great
Token ID1049
Feature activation-1.58e-02

Pos logit contributions
|+0.019
ount+0.017
Anna+0.017
 thanks+0.016
 cheered+0.016
Neg logit contributions
ittens-0.021
 powers-0.020
 knees-0.020
 possessions-0.020
belt-0.019
Token idea
Token ID2126
Feature activation+2.39e-02

Pos logit contributions
ittens+0.023
 knees+0.022
 powers+0.022
 possessions+0.021
belt+0.021
Neg logit contributions
|-0.026
Anna-0.024
 thanks-0.024
ount-0.023
 cheered-0.023
Token -
Token ID532
Feature activation-3.06e-03

Pos logit contributions
|+0.026
 thanks+0.022
Anna+0.022
 cheered+0.021
ount+0.020
Neg logit contributions
ittens-0.048
 knees-0.047
 powers-0.047
 possessions-0.046
iously-0.046
Token he
Token ID339
Feature activation-3.85e-03

Pos logit contributions
ittens+0.005
 knees+0.005
iously+0.005
belt+0.005
 possessions+0.005
Neg logit contributions
 thanks-0.004
 cheered-0.004
Anna-0.004
|-0.004
 like-0.004
Token climbed
Token ID19952
Feature activation-4.36e-03

Pos logit contributions
ittens+0.006
 knees+0.006
 powers+0.006
 possessions+0.006
iously+0.006
Neg logit contributions
|-0.006
 thanks-0.005
Anna-0.005
 cheered-0.005
 catches-0.005
Token up
Token ID510
Feature activation+1.39e-02

Pos logit contributions
iously+0.007
 knees+0.007
 powers+0.007
ittens+0.007
 tools+0.007
Neg logit contributions
|-0.006
Anna-0.006
 difference-0.005
 cheered-0.005
ount-0.005
Token to
Token ID284
Feature activation+2.05e-02

Pos logit contributions
|+0.005
Anna+0.004
 thanks+0.004
 cheered+0.004
ount+0.004
Neg logit contributions
ittens-0.008
 knees-0.007
 powers-0.007
 possessions-0.007
belt-0.007
Token the
Token ID262
Feature activation+1.79e-02

Pos logit contributions
|+0.022
 cheered+0.020
ount+0.019
Anna+0.019
ack+0.018
Neg logit contributions
 knees-0.040
 powers-0.040
ittens-0.040
 possessions-0.038
 tools-0.037
Token big
Token ID1263
Feature activation+2.44e-02

Pos logit contributions
|+0.022
 cheered+0.020
 thanks+0.019
Anna+0.018
ount+0.018
Neg logit contributions
ittens-0.032
 knees-0.031
 powers-0.031
belt-0.031
 possessions-0.031
Token pitch
Token ID7078
Feature activation+1.02e-02

Pos logit contributions
|+0.041
ount+0.036
 cheered+0.035
Anna+0.035
And+0.034
Neg logit contributions
 knees-0.035
 tools-0.034
 powers-0.034
ths-0.033
 axe-0.033
Token.
Token ID13
Feature activation-4.57e-03

Pos logit contributions
|+0.014
Anna+0.013
ount+0.013
 thanks+0.012
 cheered+0.012
Neg logit contributions
 knees-0.017
 powers-0.016
belt-0.016
ittens-0.016
 possessions-0.015
Token He
Token ID679
Feature activation-1.33e-02

Pos logit contributions
ittens+0.009
 knees+0.009
 powers+0.009
iously+0.009
 possessions+0.009
Neg logit contributions
|-0.005
 thanks-0.004
Anna-0.004
 cheered-0.004
ount-0.004
Token said
Token ID531
Feature activation-2.97e-02

Pos logit contributions
ittens+0.021
 knees+0.021
 powers+0.021
 possessions+0.020
iously+0.020
Neg logit contributions
|-0.020
 thanks-0.018
Anna-0.018
 cheered-0.017
ount-0.016
Token that
Token ID326
Feature activation-2.75e-02

Pos logit contributions
ittens+0.061
 possessions+0.059
 powers+0.059
 knees+0.059
belt+0.058
Neg logit contributions
|-0.028
 thanks-0.027
Anna-0.026
 cheered-0.026
 catches-0.024
Token it
Token ID340
Feature activation-1.70e-02

Pos logit contributions
ittens+0.047
iously+0.046
 knees+0.046
 powers+0.046
belt+0.045
Neg logit contributions
|-0.037
 thanks-0.035
Anna-0.034
 cheered-0.033
 difference-0.031
Token was
Token ID373
Feature activation-3.37e-03

Pos logit contributions
ittens+0.038
iously+0.035
 possessions+0.034
 knees+0.034
 powers+0.034
Neg logit contributions
|-0.017
 thanks-0.015
 cheered-0.015
Anna-0.014
 catches-0.013
Token very
Token ID845
Feature activation-3.00e-02

Pos logit contributions
ittens+0.007
 knees+0.007
iously+0.007
 powers+0.007
 possessions+0.007
Neg logit contributions
|-0.003
 thanks-0.003
Anna-0.003
 welcome-0.003
 cheered-0.003
Token funny
Token ID8258
Feature activation-1.90e-02

Pos logit contributions
ittens+0.036
 knees+0.035
 powers+0.034
 possessions+0.034
iously+0.033
Neg logit contributions
|-0.029
 thanks-0.025
Anna-0.025
 cheered-0.024
ount-0.024
Token with
Token ID351
Feature activation+1.39e-02

Pos logit contributions
ittens+0.040
 knees+0.039
 powers+0.039
 possessions+0.039
belt+0.039
Neg logit contributions
|-0.018
 thanks-0.016
Anna-0.016
 cheered-0.015
ount-0.014
Token makeup
Token ID16029
Feature activation-5.47e-03

Pos logit contributions
 thanks+0.014
|+0.013
 cheered+0.012
 Anna+0.012
Anna+0.012
Neg logit contributions
ittens-0.030
belt-0.030
iously-0.028
 powers-0.028
 possessions-0.028
Token on
Token ID319
Feature activation-1.01e-03

Pos logit contributions
ittens+0.012
 possessions+0.012
 knees+0.012
 powers+0.012
iously+0.012
Neg logit contributions
 thanks-0.004
|-0.004
 cheered-0.004
Anna-0.003
 like-0.003
Token her
Token ID607
Feature activation-4.81e-02

Pos logit contributions
ittens+0.002
 powers+0.002
 possessions+0.002
belt+0.002
iously+0.002
Neg logit contributions
|-0.001
 thanks-0.001
Anna-0.001
 cheered-0.001
 Anna-0.001
Token furry
Token ID40857
Feature activation-5.91e-02

Pos logit contributions
ths+0.083
iously+0.080
ised+0.079
bars+0.077
iked+0.076
Neg logit contributions
 thanks-0.058
 Anna-0.057
|-0.056
 right-0.055
 Princess-0.054
Token face
Token ID1986
Feature activation-1.37e-02

Pos logit contributions
ths+0.110
bars+0.107
iously+0.105
ised+0.100
belt+0.099
Neg logit contributions
|-0.066
 welcome-0.065
 thanks-0.064
 Princess-0.063
 and-0.062
Token!
Token ID0
Feature activation+1.60e-03

Pos logit contributions
ittens+0.033
 possessions+0.033
 powers+0.032
belt+0.032
 knees+0.032
Neg logit contributions
 thanks-0.008
 like-0.007
 cheered-0.007
Anna-0.006
 Anna-0.006
Token
Token ID198
Feature activation+2.29e-02

Pos logit contributions
|+0.001
 thanks+0.001
Anna+0.001
 cheered+0.001
 difference+0.001
Neg logit contributions
ittens-0.004
 knees-0.004
 powers-0.004
 possessions-0.004
belt-0.004
Token
Token ID198
Feature activation-2.00e-02

Pos logit contributions
|+0.019
 thanks+0.019
ount+0.018
 difference+0.017
 catches+0.016
Neg logit contributions
ittens-0.050
 knees-0.046
 powers-0.045
 possessions-0.044
 possibly-0.043
TokenL
Token ID43
Feature activation+7.71e-03

Pos logit contributions
ittens+0.040
 knees+0.038
 possessions+0.037
belt+0.037
 powers+0.037
Neg logit contributions
|-0.022
 thanks-0.021
 difference-0.019
 cheered-0.019
ount-0.018
Token Lily
Token ID20037
Feature activation+6.21e-04

Pos logit contributions
ittens+0.009
 possessions+0.009
 powers+0.009
belt+0.009
 knees+0.009
Neg logit contributions
|-0.003
Anna-0.003
 thanks-0.003
 cheered-0.003
 Anna-0.002
Token showed
Token ID3751
Feature activation-3.22e-02

Pos logit contributions
|+0.001
Anna+0.001
 thanks+0.001
ount+0.001
 cheered+0.001
Neg logit contributions
ittens-0.001
 knees-0.001
 powers-0.001
iously-0.001
 possessions-0.001
Token her
Token ID607
Feature activation-4.13e-02

Pos logit contributions
ittens+0.059
belt+0.058
 possessions+0.056
iously+0.055
 knees+0.055
Neg logit contributions
|-0.041
 thanks-0.039
Anna-0.038
 cheered-0.036
 Anna-0.035
Token the
Token ID262
Feature activation-2.26e-02

Pos logit contributions
ittens+0.080
iously+0.079
belt+0.079
ths+0.076
 powers+0.075
Neg logit contributions
 thanks-0.047
|-0.044
Anna-0.040
 Anna-0.040
 cheered-0.039
Token torn
Token ID12445
Feature activation-4.47e-02

Pos logit contributions
ths+0.046
iked+0.046
ittens+0.046
iously+0.045
ised+0.044
Neg logit contributions
 right-0.025
 thanks-0.022
 difference-0.021
Anna-0.020
 sees-0.020
Token t
Token ID256
Feature activation-7.79e-02

Pos logit contributions
ths+0.091
iously+0.084
ittens+0.084
 possessions+0.082
 possibly+0.082
Neg logit contributions
 and-0.049
 right-0.043
 thanks-0.042
Anna-0.042
 like-0.042
Tokeneddy
Token ID21874
Feature activation-3.38e-02

Pos logit contributions
 powers+0.168
iously+0.168
 knees+0.163
ths+0.163
 possessions+0.162
Neg logit contributions
|-0.059
Anna-0.059
he-0.048
ack-0.046
 thanks-0.044
Token bear
Token ID6842
Feature activation-1.86e-02

Pos logit contributions
ittens+0.068
iously+0.066
belt+0.065
 powers+0.065
ths+0.065
Neg logit contributions
|-0.035
 thanks-0.034
Anna-0.030
 cheered-0.029
 Princess-0.027
Token and
Token ID290
Feature activation-2.74e-02

Pos logit contributions
ittens+0.052
belt+0.050
 powers+0.049
 possessions+0.049
 knees+0.048
Neg logit contributions
 thanks-0.007
|-0.006
 right-0.004
 cheered-0.004
 and-0.004
Token said
Token ID531
Feature activation-3.80e-02

Pos logit contributions
ittens+0.062
belt+0.061
iously+0.056
 powers+0.055
bars+0.055
Neg logit contributions
 cheered-0.027
 thanks-0.027
 Anna-0.023
 Mrs-0.022
 Princess-0.021
Token,
Token ID11
Feature activation-5.22e-03

Pos logit contributions
ittens+0.087
 knees+0.085
belt+0.085
 possessions+0.085
 powers+0.084
Neg logit contributions
|-0.026
 thanks-0.025
 cheered-0.024
Anna-0.023
 Anna-0.020
Token She
Token ID1375
Feature activation-9.25e-03

Pos logit contributions
ittens+0.027
 powers+0.026
 possessions+0.026
 knees+0.026
belt+0.026
Neg logit contributions
|-0.014
 thanks-0.013
Anna-0.012
 cheered-0.012
 Princess-0.011
Token stood
Token ID6204
Feature activation-1.68e-02

Pos logit contributions
ittens+0.018
 possessions+0.017
iously+0.017
 powers+0.016
belt+0.016
Neg logit contributions
|-0.011
 cheered-0.011
Anna-0.010
 thanks-0.010
 catches-0.009
Token on
Token ID319
Feature activation+1.06e-02

Pos logit contributions
ittens+0.030
 knees+0.030
belt+0.029
 powers+0.029
ths+0.028
Neg logit contributions
|-0.023
 thanks-0.019
Anna-0.019
 cheered-0.019
ount-0.019
Token her
Token ID607
Feature activation-2.75e-02

Pos logit contributions
|+0.010
 thanks+0.009
Anna+0.008
 cheered+0.008
ount+0.008
Neg logit contributions
ittens-0.023
 knees-0.022
 powers-0.022
 possessions-0.022
iously-0.022
Token t
Token ID256
Feature activation-7.71e-02

Pos logit contributions
ittens+0.047
 powers+0.046
 possessions+0.045
iously+0.045
ths+0.044
Neg logit contributions
|-0.037
 thanks-0.034
Anna-0.033
 cheered-0.031
 difference-0.030
Tokenippy
Token ID41214
Feature activation-6.16e-02

Pos logit contributions
 powers+0.134
iously+0.132
 possessions+0.131
 knees+0.126
 cheeks+0.126
Neg logit contributions
|-0.102
Anna-0.098
ack-0.087
amp-0.082
S-0.080
Token toes
Token ID23932
Feature activation-1.78e-02

Pos logit contributions
ittens+0.116
ths+0.114
 possessions+0.114
 powers+0.112
iously+0.111
Neg logit contributions
|-0.067
Anna-0.061
 thanks-0.058
 cheered-0.055
 Anna-0.055
Token and
Token ID290
Feature activation-3.11e-02

Pos logit contributions
ittens+0.051
 possessions+0.051
 powers+0.050
ths+0.049
iously+0.048
Neg logit contributions
 thanks-0.002
 cheered-0.002
|-0.002
 like-0.001
Anna-0.001
Token reached
Token ID4251
Feature activation-1.59e-02

Pos logit contributions
ittens+0.061
 powers+0.055
iously+0.054
 possessions+0.054
belt+0.052
Neg logit contributions
 cheered-0.040
 thanks-0.036
Anna-0.035
 Anna-0.035
|-0.034
Token up
Token ID510
Feature activation-3.96e-03

Pos logit contributions
 knees+0.033
ittens+0.033
 powers+0.033
iously+0.032
 possessions+0.032
Neg logit contributions
|-0.016
Anna-0.013
 thanks-0.013
 cheered-0.013
ount-0.012
Token to
Token ID284
Feature activation-1.33e-03

Pos logit contributions
 knees+0.006
iously+0.005
 powers+0.005
ittens+0.005
 tools+0.005
Neg logit contributions
|-0.007
Anna-0.006
 difference-0.006
Queen-0.006
ount-0.006
TokenLet
Token ID5756
Feature activation-1.03e-02

Pos logit contributions
ittens+0.015
 powers+0.015
 possessions+0.015
 knees+0.015
belt+0.015
Neg logit contributions
|-0.011
 thanks-0.010
Anna-0.009
 difference-0.009
 cheered-0.009
Token's
Token ID338
Feature activation-2.12e-02

Pos logit contributions
 knees+0.019
ittens+0.019
 powers+0.019
 possessions+0.019
iously+0.019
Neg logit contributions
|-0.012
ount-0.010
Anna-0.010
 thanks-0.010
 cheered-0.009
Token sort
Token ID3297
Feature activation+7.65e-03

Pos logit contributions
ittens+0.039
 knees+0.038
 powers+0.038
 possessions+0.038
iously+0.038
Neg logit contributions
|-0.026
 thanks-0.023
Anna-0.023
 cheered-0.022
ount-0.021
Token the
Token ID262
Feature activation-3.76e-03

Pos logit contributions
|+0.009
 thanks+0.008
 cheered+0.008
Anna+0.008
ount+0.007
Neg logit contributions
ittens-0.014
 powers-0.014
 knees-0.014
 possessions-0.014
iously-0.013
Token l
Token ID300
Feature activation-3.03e-02

Pos logit contributions
ittens+0.007
 knees+0.007
belt+0.007
 powers+0.007
iously+0.007
Neg logit contributions
|-0.004
 thanks-0.004
Anna-0.004
 cheered-0.004
 difference-0.004
Tokenoll
Token ID692
Feature activation-5.66e-02

Pos logit contributions
ittens+0.039
 knees+0.038
 powers+0.038
 possessions+0.037
iously+0.037
Neg logit contributions
|-0.054
 thanks-0.050
Anna-0.049
 cheered-0.048
ount-0.046
Tokenipop
Token ID42800
Feature activation-1.49e-02

Pos logit contributions
 knees+0.076
ths+0.075
ised+0.074
 powers+0.072
iously+0.071
Neg logit contributions
Anna-0.086
 catches-0.083
 Sara-0.082
!"-0.082
 thanks-0.081
Token."
Token ID526
Feature activation+7.31e-03

Pos logit contributions
ittens+0.030
 knees+0.029
 powers+0.029
 possessions+0.029
iously+0.029
Neg logit contributions
|-0.016
 thanks-0.014
Anna-0.013
 cheered-0.013
ount-0.012
Token
Token ID198
Feature activation+7.29e-03

Pos logit contributions
|+0.008
Anna+0.007
 thanks+0.007
ount+0.007
 difference+0.007
Neg logit contributions
 knees-0.014
ittens-0.014
 cheeks-0.013
iously-0.013
 powers-0.013
Token
Token ID198
Feature activation-2.33e-02

Pos logit contributions
 thanks+0.009
ount+0.009
 difference+0.009
|+0.008
 cal+0.008
Neg logit contributions
ittens-0.014
 knees-0.012
ised-0.012
 possibly-0.011
 tools-0.011
TokenThe
Token ID464
Feature activation+4.07e-03

Pos logit contributions
ittens+0.042
 knees+0.040
 possessions+0.039
ths+0.038
 powers+0.038
Neg logit contributions
|-0.031
 thanks-0.028
ount-0.027
 difference-0.026
 catches-0.025
Token play
Token ID711
Feature activation+2.32e-02

Pos logit contributions
iously+0.052
belt+0.051
 possessions+0.051
ths+0.051
ised+0.049
Neg logit contributions
|-0.016
 celebrate-0.016
 thanks-0.016
 have-0.015
 blast-0.015
Token with
Token ID351
Feature activation+9.45e-04

Pos logit contributions
|+0.028
 thanks+0.025
Anna+0.023
 cheered+0.023
ount+0.023
Neg logit contributions
ittens-0.045
 knees-0.043
 powers-0.043
 possessions-0.041
belt-0.041
Token her
Token ID607
Feature activation-3.94e-02

Pos logit contributions
 Anna+0.001
Anna+0.001
 thanks+0.001
 Sara+0.001
|+0.001
Neg logit contributions
iously-0.002
belt-0.002
ately-0.002
 possibly-0.002
row-0.002
Token dolls
Token ID36062
Feature activation+7.91e-03

Pos logit contributions
iously+0.072
bars+0.065
belt+0.064
ths+0.064
 powers+0.063
Neg logit contributions
Anna-0.049
|-0.048
 thanks-0.046
 Anna-0.046
 and-0.043
Token and
Token ID290
Feature activation-2.01e-02

Pos logit contributions
|+0.005
 thanks+0.004
Anna+0.004
 cheered+0.004
ount+0.003
Neg logit contributions
ittens-0.019
 powers-0.019
iously-0.019
 knees-0.019
 possessions-0.019
Token t
Token ID256
Feature activation-8.42e-02

Pos logit contributions
ittens+0.037
iously+0.037
 powers+0.037
belt+0.036
 possessions+0.035
Neg logit contributions
|-0.024
 thanks-0.023
Anna-0.022
 cheered-0.021
 Anna-0.020
Tokeneddy
Token ID21874
Feature activation-1.50e-02

Pos logit contributions
 powers+0.178
iously+0.176
 knees+0.164
 flexibility+0.163
chief+0.163
Neg logit contributions
|-0.090
Anna-0.077
ack-0.074
ount-0.068
S-0.067
Token bears
Token ID13062
Feature activation+3.01e-03

Pos logit contributions
ittens+0.024
 knees+0.024
 powers+0.023
 possessions+0.023
iously+0.022
Neg logit contributions
|-0.023
Anna-0.020
 thanks-0.020
ount-0.020
 cheered-0.020
Token.
Token ID13
Feature activation-5.52e-03

Pos logit contributions
|+0.003
 thanks+0.002
 cheered+0.002
Anna+0.002
 like+0.002
Neg logit contributions
ittens-0.007
 powers-0.006
 possessions-0.006
iously-0.006
belt-0.006
Token One
Token ID1881
Feature activation-2.71e-02

Pos logit contributions
ittens+0.008
 knees+0.007
 powers+0.006
bars+0.006
 cheeks+0.006
Neg logit contributions
|-0.009
 cheered-0.009
 thanks-0.009
 cal-0.008
Anna-0.008
Token day
Token ID1110
Feature activation-2.95e-02

Pos logit contributions
iously+0.051
 powers+0.051
ittens+0.050
belt+0.049
 knees+0.049
Neg logit contributions
|-0.034
Anna-0.031
 thanks-0.031
 welcome-0.027
 cheered-0.026