TOP ACTIVATIONS
MAX = 0.090

. As the waves crashed upon the shore , Bob could
upset . She tri pped over one of Tim my 's
, " Spot , stop ! You are ruining our line
But then the sky became dark and the wind became strong
happens . The box twists too much and breaks . The
Hey , hey , hey ! What is going on here
But then the sky became dark and loud . Big drops
" Hey , you kids ! Stop that ! This is
mirror . He tri pped over a rock and fell down
wrong . Lily tri pped over a scarf and fell down
" Bad dog , Spot ! You ruined our dress !"
" O w ! Ow ! Ow !" Tom says .
happened . Mia tri pped over a cord and fell .
dropped things and tri pped over her feet . One day
w ! Ow ! Ow ! It hurts !"
" O w ! That hurts . Why did
Anna , Ben , stop ! There is a big ,
" O w ! Ow ! Ow !" he cried .
" O w ! Ow ! Ow ! It hurts !"
" Tom , stop it ! Toy , stop it !

MIN ACTIVATIONS
MIN = -0.106

for taking her to the carn ival . They hugged her
was proud of John and Kinder g arten ers learned an
so excited ! She loved pic n ics and spending time
and nodded . He loved pic n ics and couldn 't
She wanted to make a coll age out of the beautiful
that said " Welcome to Kinder g arten !"
, Max , to the carn ival . Everywhere they looked
about we have our own carn ival at home ? We
. She loved to have pic n ics with her family
excited to go to the carn ival with her mom and
Can we make a vacation coll age ?" Leo asked .
their salad and have happy pic n ics together . <|endoftext|>
, ready to have more pic n ics in the future
, Lily went to a carn ival with her mom my
mom my put on their apr ons and started cooking .
girl named Lily who loved pic n ics . She would
family were ready to go pic n icking again . But
� Thank you ! I recommend this one ! â €
a family who really enjoyed pic n ics . They loved
liked to play and have pic n ics . One day

INTERVAL 0.041 - 0.090
CONTAINS 2.244%

a boat on the river . The boat is empty .
. Tom my looked around and saw the rows
to Anna . Anna reached out her hand and the bird
the goat . Mia b anged the pot with a spoon
was so strong that it knocked over all the furniture and

INTERVAL -0.008 - 0.041
CONTAINS 62.121%

grabbed some clay and paint and brought them outside . She
she was going to keep her promise and she ran off
been there for a long time . He was curious and
learned new things until the sun went down . It was
picture of a witch on the cover and many strange words

INTERVAL -0.057 - -0.008
CONTAINS 35.555%

size to sail back home . The animals
Jack 's mum said he had done a good job
One day Bob encountered a maze that he couldn 't beat
air . The wild animal created a bubble
Can we keep the newspaper ? I want to read it

INTERVAL -0.106 - -0.057
CONTAINS 0.081%

thankful her mom my had suggested going to church . <|endoftext|>
owl gave her a special prize . Lucy was so happy
my took him to the art studio . " Today ,
We love you ," Sam and Mia say .
G ina promised , and so the old man took
Token.
Token ID13
Feature activation-6.59e-03

Pos logit contributions
pron+0.007
 yes+0.007
 ceremony+0.007
 therapist+0.007
 Amen+0.007
Neg logit contributions
oky-0.003
angs-0.003
elly-0.003
 raining-0.003
umbles-0.003
Token As
Token ID1081
Feature activation+1.03e-03

Pos logit contributions
 yes+0.014
pron+0.014
 ceremony+0.014
 therapist+0.013
 couple+0.013
Neg logit contributions
oky-0.009
elly-0.009
angs-0.009
ases-0.009
 gaps-0.009
Token the
Token ID262
Feature activation-3.72e-03

Pos logit contributions
oky+0.002
elly+0.002
 raining+0.002
 shadows+0.002
 gaps+0.002
Neg logit contributions
pron-0.002
 yes-0.002
 ceremony-0.002
 therapist-0.002
quet-0.001
Token waves
Token ID9813
Feature activation-2.50e-02

Pos logit contributions
 yes+0.008
pron+0.008
 ceremony+0.007
 therapist+0.007
 medal+0.007
Neg logit contributions
oky-0.006
elly-0.005
angs-0.005
urious-0.005
umbles-0.005
Token crashed
Token ID14997
Feature activation+4.46e-02

Pos logit contributions
pron+0.058
 yes+0.056
 ceremony+0.055
 Amen+0.054
 therapist+0.053
Neg logit contributions
oky-0.029
elly-0.029
angs-0.028
umbles-0.027
ases-0.027
Token upon
Token ID2402
Feature activation+9.04e-02

Pos logit contributions
oky+0.066
elly+0.065
urious+0.063
angs+0.063
ases+0.060
Neg logit contributions
 yes-0.096
pron-0.089
 ceremony-0.087
 medal-0.084
 therapist-0.084
Token the
Token ID262
Feature activation+2.37e-02

Pos logit contributions
oky+0.130
elly+0.125
angs+0.124
 gaps+0.118
umbles+0.118
Neg logit contributions
 yes-0.193
pron-0.191
 ceremony-0.187
 therapist-0.177
 couple-0.174
Token shore
Token ID15191
Feature activation+1.98e-02

Pos logit contributions
oky+0.035
elly+0.034
angs+0.034
 gaps+0.032
umbles+0.032
Neg logit contributions
 yes-0.050
pron-0.049
 ceremony-0.048
 therapist-0.045
 medal-0.045
Token,
Token ID11
Feature activation+2.83e-03

Pos logit contributions
oky+0.030
elly+0.029
angs+0.028
 gaps+0.027
umbles+0.027
Neg logit contributions
 yes-0.042
pron-0.041
 ceremony-0.040
 therapist-0.038
 medal-0.037
Token Bob
Token ID5811
Feature activation+3.10e-02

Pos logit contributions
oky+0.004
elly+0.004
 shadows+0.004
angs+0.004
 trash+0.004
Neg logit contributions
pron-0.006
 ceremony-0.006
 yes-0.006
 therapist-0.005
 medal-0.005
Token could
Token ID714
Feature activation-1.66e-02

Pos logit contributions
oky+0.038
elly+0.037
angs+0.036
umbles+0.034
urious+0.034
Neg logit contributions
 yes-0.073
pron-0.071
 ceremony-0.070
 therapist-0.067
 medal-0.067
Token upset
Token ID9247
Feature activation+3.93e-02

Pos logit contributions
oky+0.012
elly+0.011
angs+0.011
umbles+0.010
urious+0.010
Neg logit contributions
 yes-0.029
pron-0.028
 ceremony-0.028
 therapist-0.027
 medal-0.027
Token.
Token ID13
Feature activation+2.40e-02

Pos logit contributions
oky+0.053
angs+0.052
 gaps+0.050
elly+0.050
urious+0.049
Neg logit contributions
 yes-0.089
pron-0.085
 ceremony-0.082
 therapist-0.080
 medal-0.079
Token She
Token ID1375
Feature activation+1.86e-02

Pos logit contributions
angs+0.033
oky+0.033
ases+0.033
elly+0.032
 gaps+0.031
Neg logit contributions
 yes-0.052
pron-0.051
 ceremony-0.048
 therapist-0.046
 goodbye-0.045
Token tri
Token ID1333
Feature activation+4.35e-02

Pos logit contributions
oky+0.030
elly+0.029
angs+0.029
urious+0.028
umbles+0.027
Neg logit contributions
 yes-0.037
pron-0.036
 ceremony-0.035
 therapist-0.033
 medal-0.033
Tokenpped
Token ID1496
Feature activation+4.84e-02

Pos logit contributions
oky+0.076
 gaps+0.072
urious+0.072
elly+0.071
 territory+0.071
Neg logit contributions
pron-0.082
 yes-0.080
 therapist-0.074
 ceremony-0.072
 couple-0.071
Token over
Token ID625
Feature activation+8.83e-02

Pos logit contributions
oky+0.074
angs+0.073
urious+0.073
elly+0.072
 territory+0.068
Neg logit contributions
 yes-0.098
pron-0.097
 ceremony-0.091
 therapist-0.090
 medal-0.090
Token one
Token ID530
Feature activation+2.59e-02

Pos logit contributions
oky+0.168
angs+0.164
elly+0.163
urious+0.160
ays+0.156
Neg logit contributions
 yes-0.159
pron-0.141
 medal-0.137
 couple-0.135
 ceremony-0.133
Token of
Token ID286
Feature activation+2.48e-02

Pos logit contributions
oky+0.038
elly+0.037
angs+0.036
 gaps+0.034
ases+0.034
Neg logit contributions
 yes-0.055
pron-0.054
 ceremony-0.053
 therapist-0.050
 couple-0.050
Token Tim
Token ID5045
Feature activation+3.19e-02

Pos logit contributions
oky+0.042
elly+0.041
angs+0.040
urious+0.038
umbles+0.038
Neg logit contributions
 yes-0.049
pron-0.048
 ceremony-0.046
 medal-0.044
 therapist-0.043
Tokenmy
Token ID1820
Feature activation+4.29e-02

Pos logit contributions
oky+0.036
 hed+0.034
 gaps+0.033
angs+0.033
elly+0.032
Neg logit contributions
pron-0.081
 yes-0.079
 ceremony-0.073
 medal-0.070
 therapist-0.069
Token's
Token ID338
Feature activation+3.15e-02

Pos logit contributions
oky+0.054
elly+0.052
angs+0.051
 gaps+0.048
umbles+0.048
Neg logit contributions
 yes-0.100
pron-0.098
 ceremony-0.096
 therapist-0.092
 medal-0.091
Token,
Token ID11
Feature activation+4.25e-02

Pos logit contributions
urious+0.091
oky+0.090
elly+0.087
 gaps+0.087
ASH+0.087
Neg logit contributions
 yes-0.090
 goodbye-0.083
 couple-0.070
 medal-0.069
pron-0.069
Token "
Token ID366
Feature activation+7.10e-02

Pos logit contributions
oky+0.072
elly+0.070
angs+0.069
umbles+0.066
 gaps+0.066
Neg logit contributions
 yes-0.081
pron-0.079
 ceremony-0.077
 therapist-0.073
 medal-0.072
TokenSpot
Token ID32565
Feature activation+5.30e-02

Pos logit contributions
angs+0.106
elly+0.104
oky+0.103
 territory+0.097
arter+0.096
Neg logit contributions
 yes-0.134
 couple-0.133
 therapist-0.132
pron-0.131
 medal-0.131
Token,
Token ID11
Feature activation+5.35e-02

Pos logit contributions
oky+0.095
elly+0.092
angs+0.092
 gaps+0.092
urious+0.092
Neg logit contributions
 yes-0.095
pron-0.088
 ceremony-0.087
 medal-0.086
 therapist-0.081
Token stop
Token ID2245
Feature activation+5.05e-02

Pos logit contributions
oky+0.089
angs+0.087
elly+0.086
ases+0.082
 gaps+0.082
Neg logit contributions
 yes-0.101
pron-0.100
 ceremony-0.097
 therapist-0.092
 couple-0.090
Token!
Token ID0
Feature activation+8.82e-02

Pos logit contributions
elly+0.079
oky+0.079
angs+0.077
urious+0.077
 gaps+0.072
Neg logit contributions
 yes-0.099
pron-0.094
 ceremony-0.094
 medal-0.091
 goodbye-0.089
Token You
Token ID921
Feature activation+5.70e-02

Pos logit contributions
oky+0.111
urious+0.109
angs+0.108
 gaps+0.106
elly+0.106
Neg logit contributions
 yes-0.197
pron-0.186
 therapist-0.184
 ceremony-0.183
 goodbye-0.180
Token are
Token ID389
Feature activation+2.32e-02

Pos logit contributions
elly+0.094
oky+0.094
urious+0.089
 territory+0.088
older+0.087
Neg logit contributions
 yes-0.111
 medal-0.103
pron-0.099
 ceremony-0.096
 prize-0.089
Token ruining
Token ID39842
Feature activation+4.54e-02

Pos logit contributions
elly+0.037
oky+0.036
urious+0.035
angs+0.033
ays+0.033
Neg logit contributions
 yes-0.047
pron-0.045
 ceremony-0.043
 medal-0.043
 couple-0.041
Token our
Token ID674
Feature activation+1.36e-02

Pos logit contributions
oky+0.071
elly+0.070
angs+0.069
urious+0.065
umbles+0.064
Neg logit contributions
 yes-0.091
pron-0.087
 ceremony-0.086
 medal-0.085
 therapist-0.082
Token line
Token ID1627
Feature activation-1.29e-02

Pos logit contributions
oky+0.021
elly+0.021
angs+0.020
urious+0.019
umbles+0.019
Neg logit contributions
 yes-0.028
pron-0.027
 ceremony-0.027
 medal-0.025
 couple-0.025
TokenBut
Token ID1537
Feature activation+1.74e-02

Pos logit contributions
oky+0.014
elly+0.014
angs+0.013
urious+0.013
 gaps+0.013
Neg logit contributions
 yes-0.017
 ceremony-0.017
pron-0.017
 medal-0.016
 therapist-0.016
Token then
Token ID788
Feature activation+1.90e-02

Pos logit contributions
oky+0.033
elly+0.032
angs+0.031
 raining+0.031
 gaps+0.031
Neg logit contributions
pron-0.029
 yes-0.028
 ceremony-0.028
 therapist-0.026
 medal-0.026
Token the
Token ID262
Feature activation+1.42e-03

Pos logit contributions
oky+0.028
elly+0.027
angs+0.027
 gaps+0.026
umbles+0.025
Neg logit contributions
 yes-0.040
pron-0.039
 ceremony-0.038
 therapist-0.036
 medal-0.036
Token sky
Token ID6766
Feature activation+2.97e-02

Pos logit contributions
oky+0.002
elly+0.002
 trash+0.002
 shadows+0.002
 gaps+0.002
Neg logit contributions
 yes-0.003
pron-0.003
 ceremony-0.003
 therapist-0.003
 Amen-0.003
Token became
Token ID2627
Feature activation+8.08e-02

Pos logit contributions
elly+0.051
oky+0.051
angs+0.050
ases+0.050
 territory+0.047
Neg logit contributions
 yes-0.054
pron-0.053
 ceremony-0.051
 therapist-0.049
 couple-0.049
Token dark
Token ID3223
Feature activation+8.81e-02

Pos logit contributions
elly+0.136
ases+0.134
angs+0.133
oky+0.128
okes+0.127
Neg logit contributions
 yes-0.153
pron-0.149
 ceremony-0.135
 couple-0.132
 medal-0.131
Token and
Token ID290
Feature activation+2.16e-02

Pos logit contributions
angs+0.141
roc+0.137
urious+0.134
ases+0.133
okes+0.133
Neg logit contributions
 yes-0.164
pron-0.158
 ceremony-0.157
 couple-0.150
 therapist-0.150
Token the
Token ID262
Feature activation+2.59e-02

Pos logit contributions
oky+0.033
elly+0.032
angs+0.032
umbles+0.030
 gaps+0.030
Neg logit contributions
 yes-0.044
pron-0.043
 ceremony-0.042
 therapist-0.040
 medal-0.040
Token wind
Token ID2344
Feature activation+4.45e-02

Pos logit contributions
oky+0.033
elly+0.031
 gaps+0.030
angs+0.030
 shadows+0.030
Neg logit contributions
 yes-0.061
pron-0.059
 ceremony-0.058
 therapist-0.055
 medal-0.054
Token became
Token ID2627
Feature activation+8.42e-02

Pos logit contributions
oky+0.070
elly+0.067
angs+0.067
 territory+0.064
 gaps+0.064
Neg logit contributions
pron-0.088
 yes-0.088
 ceremony-0.083
 therapist-0.082
 medal-0.080
Token strong
Token ID1913
Feature activation+3.52e-02

Pos logit contributions
elly+0.140
ases+0.132
oky+0.132
angs+0.129
urious+0.127
Neg logit contributions
 yes-0.164
pron-0.162
 ceremony-0.147
 saddle-0.144
 medal-0.143
Token happens
Token ID4325
Feature activation+2.71e-02

Pos logit contributions
oky+0.031
elly+0.030
angs+0.030
ases+0.028
umbles+0.028
Neg logit contributions
 yes-0.059
pron-0.058
 ceremony-0.057
 therapist-0.054
 couple-0.054
Token.
Token ID13
Feature activation+4.12e-02

Pos logit contributions
oky+0.048
elly+0.047
angs+0.047
urious+0.045
 gaps+0.044
Neg logit contributions
 yes-0.049
pron-0.043
 ceremony-0.043
 therapist-0.041
 medal-0.041
Token The
Token ID383
Feature activation+2.88e-03

Pos logit contributions
oky+0.049
angs+0.048
elly+0.048
urious+0.045
ases+0.044
Neg logit contributions
 yes-0.098
pron-0.095
 ceremony-0.093
 therapist-0.089
 couple-0.088
Token box
Token ID3091
Feature activation+2.06e-02

Pos logit contributions
 gaps+0.004
 trash+0.004
 shadows+0.004
oky+0.004
 pipes+0.004
Neg logit contributions
 yes-0.006
pron-0.006
 ceremony-0.006
 therapist-0.006
quet-0.005
Token twists
Token ID30953
Feature activation+3.20e-02

Pos logit contributions
oky+0.023
elly+0.023
angs+0.022
urious+0.020
umbles+0.020
Neg logit contributions
 yes-0.050
pron-0.048
 ceremony-0.048
 medal-0.046
 therapist-0.045
Token too
Token ID1165
Feature activation+8.80e-02

Pos logit contributions
oky+0.048
elly+0.047
urious+0.047
angs+0.046
 territory+0.045
Neg logit contributions
 yes-0.066
 medal-0.060
pron-0.060
 goodbye-0.059
 ceremony-0.059
Token much
Token ID881
Feature activation+5.44e-02

Pos logit contributions
oky+0.136
elly+0.133
angs+0.132
urious+0.127
umbles+0.125
Neg logit contributions
 yes-0.179
pron-0.170
 ceremony-0.167
 medal-0.160
 therapist-0.159
Token and
Token ID290
Feature activation+3.26e-02

Pos logit contributions
oky+0.077
elly+0.075
angs+0.075
urious+0.074
umbles+0.072
Neg logit contributions
 yes-0.117
pron-0.112
 ceremony-0.110
 medal-0.107
 therapist-0.104
Token breaks
Token ID9457
Feature activation+5.87e-02

Pos logit contributions
oky+0.037
elly+0.035
angs+0.035
 gaps+0.033
ases+0.032
Neg logit contributions
 yes-0.080
pron-0.079
 ceremony-0.078
 therapist-0.074
 couple-0.073
Token.
Token ID13
Feature activation+4.59e-02

Pos logit contributions
urious+0.101
elly+0.098
oky+0.097
roc+0.094
 territory+0.093
Neg logit contributions
 yes-0.107
pron-0.098
 medal-0.093
 goodbye-0.092
 ceremony-0.090
Token The
Token ID383
Feature activation+1.57e-02

Pos logit contributions
angs+0.058
oky+0.057
elly+0.057
urious+0.056
ases+0.054
Neg logit contributions
 yes-0.105
pron-0.102
 ceremony-0.098
 therapist-0.095
 couple-0.094
TokenHey
Token ID10814
Feature activation+2.63e-02

Pos logit contributions
angs+0.060
oky+0.060
elly+0.059
umbles+0.058
 territory+0.057
Neg logit contributions
 yes-0.104
pron-0.102
 ceremony-0.098
 therapist-0.097
 couple-0.096
Token,
Token ID11
Feature activation+3.13e-02

Pos logit contributions
oky+0.054
urious+0.052
elly+0.052
angs+0.052
 gaps+0.051
Neg logit contributions
 yes-0.046
 ceremony-0.039
 medal-0.038
pron-0.038
 couple-0.037
Token hey
Token ID17207
Feature activation+6.40e-02

Pos logit contributions
oky+0.057
elly+0.056
urious+0.054
angs+0.054
umbles+0.052
Neg logit contributions
 yes-0.060
 ceremony-0.053
pron-0.052
 medal-0.051
 goodbye-0.050
Token,
Token ID11
Feature activation+4.54e-02

Pos logit contributions
oky+0.125
angs+0.121
elly+0.119
urious+0.118
 gaps+0.117
Neg logit contributions
 yes-0.108
 ceremony-0.096
pron-0.096
 couple-0.092
 medal-0.090
Token hey
Token ID17207
Feature activation+6.61e-02

Pos logit contributions
oky+0.077
elly+0.077
angs+0.072
urious+0.072
umbles+0.070
Neg logit contributions
 yes-0.095
 ceremony-0.083
pron-0.082
 medal-0.081
 goodbye-0.079
Token!
Token ID0
Feature activation+8.76e-02

Pos logit contributions
oky+0.126
angs+0.121
elly+0.119
urious+0.118
 gaps+0.116
Neg logit contributions
 yes-0.113
 ceremony-0.102
pron-0.102
 medal-0.097
 couple-0.097
Token What
Token ID1867
Feature activation+5.67e-02

Pos logit contributions
urious+0.119
oky+0.113
 gaps+0.112
angs+0.112
 territory+0.112
Neg logit contributions
 yes-0.184
 goodbye-0.165
pron-0.164
 ceremony-0.164
 Amen-0.162
Token is
Token ID318
Feature activation+2.36e-02

Pos logit contributions
oky+0.098
 territory+0.094
arted+0.091
older+0.091
elly+0.091
Neg logit contributions
 yes-0.113
 medal-0.097
pron-0.096
 ceremony-0.090
ggie-0.087
Token going
Token ID1016
Feature activation+1.11e-02

Pos logit contributions
oky+0.042
elly+0.041
angs+0.041
 gaps+0.039
ases+0.039
Neg logit contributions
 yes-0.043
pron-0.041
 ceremony-0.040
 therapist-0.038
 couple-0.037
Token on
Token ID319
Feature activation+3.81e-02

Pos logit contributions
oky+0.020
elly+0.020
angs+0.019
urious+0.019
 gaps+0.019
Neg logit contributions
 yes-0.020
pron-0.019
 ceremony-0.019
 medal-0.018
 therapist-0.018
Token here
Token ID994
Feature activation+3.12e-02

Pos logit contributions
oky+0.046
elly+0.045
angs+0.042
ases+0.041
umbles+0.040
Neg logit contributions
 yes-0.092
pron-0.089
 ceremony-0.087
 therapist-0.084
 couple-0.083
TokenBut
Token ID1537
Feature activation+1.27e-02

Pos logit contributions
oky+0.003
elly+0.003
urious+0.003
angs+0.003
 gaps+0.003
Neg logit contributions
 yes-0.004
 ceremony-0.004
pron-0.004
 medal-0.004
 therapist-0.004
Token then
Token ID788
Feature activation+1.29e-02

Pos logit contributions
oky+0.021
 raining+0.021
elly+0.021
 shadows+0.021
 trash+0.020
Neg logit contributions
pron-0.023
 yes-0.022
 ceremony-0.022
quet-0.021
 medal-0.021
Token the
Token ID262
Feature activation-5.63e-03

Pos logit contributions
oky+0.019
elly+0.018
angs+0.018
 gaps+0.017
 shadows+0.017
Neg logit contributions
 yes-0.027
pron-0.027
 ceremony-0.026
 therapist-0.025
 medal-0.025
Token sky
Token ID6766
Feature activation+2.56e-02

Pos logit contributions
 yes+0.014
pron+0.013
 ceremony+0.012
 Amen+0.012
quet+0.012
Neg logit contributions
oky-0.007
 shadows-0.007
 trash-0.007
elly-0.006
 gaps-0.006
Token became
Token ID2627
Feature activation+7.53e-02

Pos logit contributions
oky+0.042
elly+0.042
angs+0.041
ases+0.041
 gaps+0.039
Neg logit contributions
 yes-0.049
pron-0.048
 ceremony-0.047
 therapist-0.044
 couple-0.044
Token dark
Token ID3223
Feature activation+8.72e-02

Pos logit contributions
elly+0.123
ases+0.121
angs+0.120
oky+0.116
okes+0.114
Neg logit contributions
 yes-0.148
pron-0.144
 ceremony-0.132
 couple-0.128
 saddle-0.126
Token and
Token ID290
Feature activation+1.88e-02

Pos logit contributions
angs+0.145
roc+0.144
ases+0.139
urious+0.139
okes+0.138
Neg logit contributions
 yes-0.155
 ceremony-0.150
pron-0.149
 couple-0.143
 therapist-0.142
Token loud
Token ID7812
Feature activation+5.20e-02

Pos logit contributions
oky+0.027
elly+0.026
angs+0.026
 gaps+0.024
umbles+0.024
Neg logit contributions
 yes-0.041
pron-0.040
 ceremony-0.039
 therapist-0.037
 medal-0.037
Token.
Token ID13
Feature activation+3.38e-02

Pos logit contributions
oky+0.067
elly+0.065
angs+0.064
 gaps+0.060
umbles+0.060
Neg logit contributions
 yes-0.120
pron-0.117
 ceremony-0.115
 therapist-0.109
 medal-0.109
Token Big
Token ID4403
Feature activation+2.42e-02

Pos logit contributions
oky+0.043
elly+0.042
angs+0.042
ases+0.039
urious+0.039
Neg logit contributions
 yes-0.079
pron-0.076
 ceremony-0.074
 therapist-0.072
 couple-0.071
Token drops
Token ID10532
Feature activation+3.11e-02

Pos logit contributions
oky+0.034
elly+0.033
angs+0.033
ases+0.031
umbles+0.031
Neg logit contributions
 yes-0.053
pron-0.051
 ceremony-0.051
 therapist-0.048
 medal-0.048
Token"
Token ID1
Feature activation+4.53e-02

Pos logit contributions
angs+0.036
 territory+0.036
ays+0.035
en+0.035
ASH+0.035
Neg logit contributions
 yes-0.021
pron-0.019
ves-0.018
 couple-0.018
 saddle-0.017
TokenHey
Token ID10814
Feature activation+2.44e-02

Pos logit contributions
angs+0.069
elly+0.066
umbles+0.066
oky+0.065
 territory+0.064
Neg logit contributions
 yes-0.091
pron-0.086
 couple-0.086
 therapist-0.084
 ceremony-0.084
Token,
Token ID11
Feature activation+2.41e-02

Pos logit contributions
ained+0.058
urious+0.057
elly+0.057
oky+0.056
ays+0.055
Neg logit contributions
 yes-0.036
 medal-0.026
 goodbye-0.025
 couple-0.024
 thank-0.024
Token you
Token ID345
Feature activation+5.30e-02

Pos logit contributions
oky+0.045
elly+0.045
urious+0.045
ained+0.044
umbles+0.043
Neg logit contributions
 yes-0.044
 ceremony-0.036
 medal-0.036
 goodbye-0.035
 couple-0.034
Token kids
Token ID3988
Feature activation+3.36e-02

Pos logit contributions
elly+0.106
oky+0.103
attered+0.103
udge+0.103
urious+0.102
Neg logit contributions
 yes-0.088
 medal-0.074
 thank-0.072
 goodbye-0.072
 prize-0.067
Token!
Token ID0
Feature activation+8.69e-02

Pos logit contributions
oky+0.053
elly+0.052
angs+0.051
urious+0.050
 gaps+0.049
Neg logit contributions
 yes-0.068
 ceremony-0.063
pron-0.062
 medal-0.060
 couple-0.058
Token Stop
Token ID13707
Feature activation+2.53e-02

Pos logit contributions
urious+0.128
oky+0.125
 gaps+0.125
angs+0.121
 territory+0.119
Neg logit contributions
 yes-0.165
 goodbye-0.150
 Amen-0.149
 therapist-0.146
 ceremony-0.145
Token that
Token ID326
Feature activation+1.46e-02

Pos logit contributions
oky+0.044
elly+0.044
urious+0.042
angs+0.042
 gaps+0.040
Neg logit contributions
 yes-0.047
pron-0.045
 ceremony-0.044
 medal-0.043
 therapist-0.042
Token!
Token ID0
Feature activation+8.04e-02

Pos logit contributions
oky+0.019
elly+0.018
angs+0.018
 gaps+0.017
urious+0.017
Neg logit contributions
 yes-0.033
pron-0.032
 ceremony-0.032
 medal-0.031
 therapist-0.030
Token This
Token ID770
Feature activation+1.87e-02

Pos logit contributions
urious+0.116
oky+0.113
 gaps+0.112
 territory+0.110
angs+0.107
Neg logit contributions
 yes-0.159
 Amen-0.148
 therapist-0.147
 goodbye-0.142
pron-0.141
Token is
Token ID318
Feature activation+2.23e-02

Pos logit contributions
oky+0.025
urious+0.024
umbles+0.024
angs+0.024
elly+0.024
Neg logit contributions
pron-0.041
 yes-0.040
 medal-0.038
 ceremony-0.038
 therapist-0.038
Token mirror
Token ID10162
Feature activation+1.59e-02

Pos logit contributions
oky+0.012
elly+0.012
angs+0.012
ases+0.011
umbles+0.011
Neg logit contributions
 yes-0.015
pron-0.015
 ceremony-0.015
 medal-0.014
 therapist-0.014
Token.
Token ID13
Feature activation+3.70e-02

Pos logit contributions
oky+0.016
elly+0.015
angs+0.014
umbles+0.013
ases+0.013
Neg logit contributions
pron-0.041
 yes-0.041
 ceremony-0.040
 Amen-0.038
 therapist-0.038
Token He
Token ID679
Feature activation+1.20e-02

Pos logit contributions
oky+0.045
elly+0.043
angs+0.042
urious+0.040
ases+0.039
Neg logit contributions
 yes-0.089
pron-0.086
 ceremony-0.085
 therapist-0.082
 medal-0.081
Token tri
Token ID1333
Feature activation+4.78e-02

Pos logit contributions
oky+0.019
elly+0.018
angs+0.018
umbles+0.017
ases+0.017
Neg logit contributions
 yes-0.026
pron-0.024
 ceremony-0.023
 therapist-0.023
 medal-0.023
Tokenpped
Token ID1496
Feature activation+5.12e-02

Pos logit contributions
oky+0.085
urious+0.083
 territory+0.082
 gaps+0.081
elly+0.079
Neg logit contributions
 yes-0.086
pron-0.082
 therapist-0.078
 ceremony-0.075
 couple-0.074
Token over
Token ID625
Feature activation+8.68e-02

Pos logit contributions
oky+0.085
urious+0.085
elly+0.083
angs+0.082
 territory+0.079
Neg logit contributions
 yes-0.097
pron-0.092
 medal-0.088
 therapist-0.088
 ceremony-0.088
Token a
Token ID257
Feature activation+1.02e-02

Pos logit contributions
oky+0.171
elly+0.167
urious+0.165
angs+0.163
ays+0.159
Neg logit contributions
 yes-0.152
 medal-0.128
 couple-0.128
 goodbye-0.126
 ceremony-0.123
Token rock
Token ID3881
Feature activation+3.09e-02

Pos logit contributions
 trash+0.015
elly+0.014
oky+0.014
angs+0.014
 gaps+0.014
Neg logit contributions
 yes-0.021
 ceremony-0.021
pron-0.019
 therapist-0.019
 Amen-0.019
Token and
Token ID290
Feature activation+2.72e-02

Pos logit contributions
oky+0.037
elly+0.036
angs+0.035
umbles+0.032
 gaps+0.032
Neg logit contributions
 yes-0.074
pron-0.073
 ceremony-0.071
 therapist-0.068
 medal-0.068
Token fell
Token ID3214
Feature activation+6.57e-02

Pos logit contributions
elly+0.049
oky+0.049
urious+0.047
angs+0.045
roc+0.044
Neg logit contributions
 yes-0.051
pron-0.047
 medal-0.046
 therapist-0.046
 goodbye-0.046
Token down
Token ID866
Feature activation+7.01e-02

Pos logit contributions
urious+0.119
oky+0.116
roc+0.115
elly+0.114
 territory+0.110
Neg logit contributions
 yes-0.117
pron-0.106
 goodbye-0.105
 medal-0.102
 saddle-0.102
Token wrong
Token ID2642
Feature activation+3.03e-02

Pos logit contributions
oky+0.040
elly+0.039
angs+0.038
umbles+0.036
 gaps+0.036
Neg logit contributions
 yes-0.054
pron-0.052
 ceremony-0.051
 therapist-0.049
 medal-0.048
Token.
Token ID13
Feature activation+4.18e-02

Pos logit contributions
oky+0.042
elly+0.041
angs+0.040
 gaps+0.038
urious+0.038
Neg logit contributions
 yes-0.067
pron-0.065
 ceremony-0.064
 therapist-0.061
 medal-0.060
Token Lily
Token ID20037
Feature activation+3.28e-02

Pos logit contributions
oky+0.054
angs+0.054
elly+0.053
urious+0.052
ases+0.051
Neg logit contributions
 yes-0.094
pron-0.090
 ceremony-0.089
 therapist-0.085
 couple-0.085
Token tri
Token ID1333
Feature activation+4.58e-02

Pos logit contributions
oky+0.044
angs+0.042
elly+0.042
ases+0.041
 gaps+0.039
Neg logit contributions
 yes-0.073
pron-0.072
 ceremony-0.070
 therapist-0.068
 couple-0.067
Tokenpped
Token ID1496
Feature activation+5.40e-02

Pos logit contributions
oky+0.081
 territory+0.079
urious+0.079
 gaps+0.078
roc+0.076
Neg logit contributions
 yes-0.083
pron-0.081
 therapist-0.077
 ceremony-0.075
 couple-0.074
Token over
Token ID625
Feature activation+8.66e-02

Pos logit contributions
oky+0.075
angs+0.073
elly+0.073
urious+0.072
 territory+0.068
Neg logit contributions
 yes-0.117
pron-0.114
 ceremony-0.111
 therapist-0.109
 medal-0.107
Token a
Token ID257
Feature activation+1.36e-02

Pos logit contributions
oky+0.145
elly+0.140
angs+0.140
urious+0.137
umbles+0.134
Neg logit contributions
 yes-0.172
pron-0.157
 ceremony-0.156
 medal-0.151
 couple-0.150
Token scarf
Token ID36953
Feature activation+6.79e-03

Pos logit contributions
 trash+0.021
angs+0.019
 shadows+0.019
elly+0.018
 gaps+0.018
Neg logit contributions
 yes-0.028
 ceremony-0.027
 Amen-0.025
quet-0.025
 therapist-0.024
Token and
Token ID290
Feature activation+2.33e-02

Pos logit contributions
oky+0.008
elly+0.007
angs+0.007
umbles+0.007
ases+0.007
Neg logit contributions
 yes-0.017
pron-0.016
 ceremony-0.016
 therapist-0.015
 couple-0.015
Token fell
Token ID3214
Feature activation+6.92e-02

Pos logit contributions
oky+0.041
elly+0.040
urious+0.039
angs+0.038
roc+0.037
Neg logit contributions
 yes-0.045
pron-0.043
 therapist-0.040
 medal-0.040
 ceremony-0.039
Token down
Token ID866
Feature activation+7.59e-02

Pos logit contributions
urious+0.121
oky+0.118
roc+0.116
elly+0.115
 territory+0.114
Neg logit contributions
 yes-0.127
pron-0.119
 goodbye-0.112
 ceremony-0.112
 therapist-0.112
Token"
Token ID1
Feature activation+4.72e-02

Pos logit contributions
oky+0.037
angs+0.036
elly+0.036
urious+0.034
 gaps+0.034
Neg logit contributions
 yes-0.038
pron-0.037
 ceremony-0.036
 therapist-0.034
 medal-0.034
TokenBad
Token ID22069
Feature activation+3.04e-02

Pos logit contributions
oky+0.063
angs+0.062
elly+0.062
umbles+0.058
urious+0.057
Neg logit contributions
 yes-0.107
pron-0.105
 ceremony-0.101
 therapist-0.099
 couple-0.097
Token dog
Token ID3290
Feature activation+3.57e-02

Pos logit contributions
oky+0.049
elly+0.048
angs+0.047
 gaps+0.045
umbles+0.045
Neg logit contributions
 yes-0.061
pron-0.059
 ceremony-0.058
 medal-0.055
 therapist-0.055
Token,
Token ID11
Feature activation+2.71e-02

Pos logit contributions
oky+0.053
elly+0.051
angs+0.050
urious+0.050
 gaps+0.049
Neg logit contributions
 yes-0.075
 ceremony-0.071
pron-0.071
 medal-0.068
 therapist-0.067
Token Spot
Token ID15899
Feature activation+6.00e-02

Pos logit contributions
angs+0.039
 trash+0.039
oky+0.038
 spiders+0.038
ases+0.037
Neg logit contributions
pron-0.058
 ceremony-0.055
 yes-0.054
 therapist-0.053
 couple-0.051
Token!
Token ID0
Feature activation+8.65e-02

Pos logit contributions
oky+0.090
elly+0.087
angs+0.087
urious+0.084
 gaps+0.083
Neg logit contributions
 yes-0.123
pron-0.118
 ceremony-0.117
 medal-0.112
 therapist-0.111
Token You
Token ID921
Feature activation+4.70e-02

Pos logit contributions
oky+0.102
urious+0.100
 gaps+0.098
angs+0.098
elly+0.095
Neg logit contributions
 yes-0.203
pron-0.191
 ceremony-0.188
 therapist-0.186
 goodbye-0.183
Token ruined
Token ID20484
Feature activation+4.50e-02

Pos logit contributions
oky+0.075
elly+0.073
 territory+0.069
urious+0.068
ASH+0.066
Neg logit contributions
 yes-0.099
 medal-0.090
pron-0.089
 ceremony-0.087
 goodbye-0.081
Token our
Token ID674
Feature activation+1.73e-02

Pos logit contributions
oky+0.062
elly+0.060
angs+0.059
urious+0.055
umbles+0.055
Neg logit contributions
 yes-0.100
pron-0.098
 ceremony-0.096
 medal-0.092
 therapist-0.091
Token dress
Token ID6576
Feature activation-2.32e-03

Pos logit contributions
oky+0.030
angs+0.029
elly+0.029
umbles+0.027
ases+0.027
Neg logit contributions
 yes-0.033
pron-0.033
 ceremony-0.032
 medal-0.031
 therapist-0.029
Token!"
Token ID2474
Feature activation+2.49e-03

Pos logit contributions
 yes+0.006
pron+0.006
 ceremony+0.006
 therapist+0.005
 couple+0.005
Neg logit contributions
oky-0.002
elly-0.002
angs-0.002
umbles-0.002
 gaps-0.002
Token"
Token ID1
Feature activation+4.06e-02

Pos logit contributions
oky+0.042
angs+0.042
elly+0.041
ases+0.040
urious+0.040
Neg logit contributions
 yes-0.033
pron-0.032
 ceremony-0.030
 therapist-0.029
 couple-0.028
TokenO
Token ID46
Feature activation+2.98e-02

Pos logit contributions
oky+0.060
elly+0.058
angs+0.058
umbles+0.055
urious+0.054
Neg logit contributions
 yes-0.087
pron-0.085
 ceremony-0.081
 therapist-0.080
 couple-0.078
Tokenw
Token ID86
Feature activation+3.51e-02

Pos logit contributions
oky+0.044
angs+0.044
elly+0.043
 gaps+0.043
 shadows+0.043
Neg logit contributions
 yes-0.059
pron-0.059
 ceremony-0.057
 medal-0.055
 therapist-0.055
Token!
Token ID0
Feature activation+8.41e-02

Pos logit contributions
oky+0.060
elly+0.058
 gaps+0.055
urious+0.055
angs+0.054
Neg logit contributions
 yes-0.068
pron-0.065
 ceremony-0.062
 medal-0.060
 therapist-0.059
Token Ow
Token ID11960
Feature activation+4.04e-02

Pos logit contributions
urious+0.091
oky+0.089
ained+0.088
 gaps+0.086
yards+0.084
Neg logit contributions
 yes-0.200
pron-0.187
 goodbye-0.182
 medal-0.179
 therapist-0.179
Token!
Token ID0
Feature activation+8.64e-02

Pos logit contributions
oky+0.060
elly+0.058
angs+0.056
urious+0.055
 gaps+0.055
Neg logit contributions
 yes-0.083
pron-0.081
 ceremony-0.079
 medal-0.077
 therapist-0.075
Token Ow
Token ID11960
Feature activation+4.37e-02

Pos logit contributions
urious+0.076
oky+0.074
ains+0.070
elly+0.070
yards+0.069
Neg logit contributions
 yes-0.228
pron-0.212
 goodbye-0.206
 medal-0.205
 therapist-0.202
Token!"
Token ID2474
Feature activation+5.54e-03

Pos logit contributions
oky+0.066
elly+0.064
angs+0.063
urious+0.062
 gaps+0.061
Neg logit contributions
 yes-0.088
pron-0.086
 ceremony-0.084
 medal-0.081
 therapist-0.080
Token Tom
Token ID4186
Feature activation+4.30e-02

Pos logit contributions
oky+0.009
elly+0.009
angs+0.009
urious+0.009
ases+0.009
Neg logit contributions
 yes-0.011
pron-0.010
 ceremony-0.010
 therapist-0.009
 medal-0.009
Token says
Token ID1139
Feature activation+1.46e-02

Pos logit contributions
oky+0.078
ained+0.077
ains+0.077
elly+0.077
arter+0.076
Neg logit contributions
 yes-0.070
 therapist-0.061
 goodbye-0.061
 medal-0.058
 pony-0.057
Token.
Token ID13
Feature activation+5.29e-02

Pos logit contributions
oky+0.014
angs+0.014
elly+0.013
umbles+0.013
ases+0.012
Neg logit contributions
pron-0.039
 ceremony-0.038
 yes-0.036
 medal-0.036
 therapist-0.036
Token happened
Token ID3022
Feature activation+3.73e-02

Pos logit contributions
oky+0.037
elly+0.035
angs+0.035
urious+0.034
umbles+0.033
Neg logit contributions
 yes-0.057
pron-0.055
 ceremony-0.055
 medal-0.052
 therapist-0.052
Token.
Token ID13
Feature activation+4.55e-02

Pos logit contributions
oky+0.063
elly+0.061
angs+0.060
urious+0.058
 gaps+0.058
Neg logit contributions
 yes-0.073
pron-0.068
 ceremony-0.065
 medal-0.063
 therapist-0.062
Token Mia
Token ID32189
Feature activation+3.79e-02

Pos logit contributions
urious+0.065
angs+0.061
 territory+0.061
eds+0.061
elly+0.060
Neg logit contributions
 yes-0.097
pron-0.087
 ceremony-0.085
 couple-0.084
 goodbye-0.083
Token tri
Token ID1333
Feature activation+5.13e-02

Pos logit contributions
oky+0.053
elly+0.051
angs+0.050
ases+0.048
urious+0.047
Neg logit contributions
 yes-0.082
pron-0.079
 ceremony-0.078
 therapist-0.076
 medal-0.074
Tokenpped
Token ID1496
Feature activation+5.66e-02

Pos logit contributions
oky+0.100
 territory+0.099
urious+0.098
 gaps+0.096
roc+0.095
Neg logit contributions
 yes-0.078
pron-0.076
 therapist-0.073
 couple-0.069
 medal-0.067
Token over
Token ID625
Feature activation+8.61e-02

Pos logit contributions
urious+0.096
oky+0.094
angs+0.092
 territory+0.091
elly+0.091
Neg logit contributions
 yes-0.102
pron-0.098
 therapist-0.096
 medal-0.094
 ceremony-0.093
Token a
Token ID257
Feature activation+1.11e-02

Pos logit contributions
oky+0.164
elly+0.159
angs+0.158
urious+0.157
 territory+0.154
Neg logit contributions
 yes-0.153
 couple-0.131
 medal-0.130
pron-0.130
 ceremony-0.129
Token cord
Token ID15050
Feature activation+2.76e-02

Pos logit contributions
 trash+0.016
elly+0.015
oky+0.015
 gaps+0.014
angs+0.014
Neg logit contributions
 yes-0.024
 ceremony-0.024
 therapist-0.022
 Amen-0.022
quet-0.021
Token and
Token ID290
Feature activation+3.18e-02

Pos logit contributions
oky+0.035
elly+0.034
angs+0.033
urious+0.031
umbles+0.031
Neg logit contributions
 yes-0.064
pron-0.062
 ceremony-0.061
 therapist-0.059
 medal-0.058
Token fell
Token ID3214
Feature activation+6.94e-02

Pos logit contributions
elly+0.062
oky+0.061
urious+0.060
roc+0.058
older+0.056
Neg logit contributions
 yes-0.055
pron-0.051
 therapist-0.050
 medal-0.049
 goodbye-0.049
Token.
Token ID13
Feature activation+5.64e-02

Pos logit contributions
urious+0.137
roc+0.135
oky+0.128
 territory+0.127
elly+0.126
Neg logit contributions
 yes-0.110
 goodbye-0.100
pron-0.099
 saddle-0.098
 medal-0.096
Token dropped
Token ID5710
Feature activation+3.83e-02

Pos logit contributions
oky+0.024
elly+0.023
angs+0.023
ays+0.022
urious+0.022
Neg logit contributions
 yes-0.028
pron-0.027
 ceremony-0.026
 therapist-0.025
 medal-0.024
Token things
Token ID1243
Feature activation+1.73e-02

Pos logit contributions
oky+0.068
urious+0.068
elly+0.068
angs+0.066
umbles+0.065
Neg logit contributions
 yes-0.067
pron-0.063
 ceremony-0.062
 medal-0.061
 goodbye-0.061
Token and
Token ID290
Feature activation+7.61e-03

Pos logit contributions
oky+0.023
elly+0.023
angs+0.022
 trash+0.022
 gaps+0.021
Neg logit contributions
pron-0.038
 yes-0.037
 ceremony-0.037
 Amen-0.036
 couple-0.036
Token tri
Token ID1333
Feature activation+3.70e-02

Pos logit contributions
oky+0.009
 shadows+0.009
 gaps+0.009
angs+0.009
elly+0.009
Neg logit contributions
 yes-0.017
pron-0.017
 ceremony-0.017
 medal-0.016
 therapist-0.016
Tokenpped
Token ID1496
Feature activation+5.10e-02

Pos logit contributions
oky+0.063
elly+0.059
urious+0.059
 gaps+0.059
 territory+0.056
Neg logit contributions
 yes-0.070
pron-0.069
 therapist-0.065
 ceremony-0.063
 couple-0.062
Token over
Token ID625
Feature activation+8.59e-02

Pos logit contributions
oky+0.078
elly+0.076
urious+0.074
angs+0.074
 gaps+0.070
Neg logit contributions
 yes-0.104
pron-0.101
 ceremony-0.097
 therapist-0.095
 medal-0.094
Token her
Token ID607
Feature activation+4.97e-02

Pos logit contributions
oky+0.144
elly+0.140
angs+0.137
urious+0.134
umbles+0.133
Neg logit contributions
 yes-0.168
pron-0.157
 ceremony-0.153
 medal-0.147
 couple-0.146
Token feet
Token ID3625
Feature activation+2.26e-02

Pos logit contributions
 shadows+0.065
 trash+0.064
 territory+0.063
angs+0.063
oky+0.062
Neg logit contributions
 yes-0.108
 ceremony-0.107
pron-0.105
 Amen-0.103
quet-0.100
Token.
Token ID13
Feature activation+2.06e-02

Pos logit contributions
oky+0.028
elly+0.028
angs+0.027
umbles+0.026
 gaps+0.025
Neg logit contributions
 yes-0.053
pron-0.052
 ceremony-0.051
 therapist-0.049
 medal-0.048
Token One
Token ID1881
Feature activation+1.48e-02

Pos logit contributions
oky+0.032
angs+0.032
elly+0.031
ases+0.031
umbles+0.030
Neg logit contributions
 yes-0.042
pron-0.041
 ceremony-0.039
 therapist-0.037
 goodbye-0.036
Token day
Token ID1110
Feature activation-3.77e-04

Pos logit contributions
oky+0.031
angs+0.031
elly+0.030
ases+0.030
 gaps+0.030
Neg logit contributions
 yes-0.022
pron-0.021
 ceremony-0.020
 therapist-0.019
 medal-0.019
Tokenw
Token ID86
Feature activation+3.51e-02

Pos logit contributions
angs+0.048
oky+0.047
 territory+0.047
 gaps+0.046
 shadows+0.046
Neg logit contributions
pron-0.062
 yes-0.061
 ceremony-0.058
 medal-0.057
 therapist-0.056
Token!
Token ID0
Feature activation+8.23e-02

Pos logit contributions
oky+0.067
elly+0.064
urious+0.063
 gaps+0.063
 territory+0.062
Neg logit contributions
 yes-0.062
pron-0.058
 medal-0.052
 ceremony-0.052
 goodbye-0.051
Token Ow
Token ID11960
Feature activation+3.77e-02

Pos logit contributions
 territory+0.119
urious+0.118
 gaps+0.113
ained+0.112
yards+0.111
Neg logit contributions
 yes-0.159
pron-0.149
 goodbye-0.138
 therapist-0.137
 Amen-0.133
Token!
Token ID0
Feature activation+8.50e-02

Pos logit contributions
oky+0.054
elly+0.051
urious+0.051
 territory+0.051
angs+0.051
Neg logit contributions
 yes-0.078
pron-0.077
 ceremony-0.073
 medal-0.073
 therapist-0.070
Token Ow
Token ID11960
Feature activation+4.23e-02

Pos logit contributions
 territory+0.102
urious+0.101
oky+0.096
elly+0.095
 gaps+0.094
Neg logit contributions
 yes-0.194
pron-0.181
 goodbye-0.169
 Amen-0.168
 therapist-0.167
Token!
Token ID0
Feature activation+8.57e-02

Pos logit contributions
oky+0.062
elly+0.059
urious+0.059
 territory+0.059
angs+0.058
Neg logit contributions
 yes-0.086
pron-0.085
 ceremony-0.081
 medal-0.080
 therapist-0.077
Token It
Token ID632
Feature activation+4.85e-02

Pos logit contributions
 territory+0.104
urious+0.104
oky+0.098
elly+0.097
 gaps+0.096
Neg logit contributions
 yes-0.197
pron-0.184
 Amen-0.171
 goodbye-0.171
 therapist-0.170
Token hurts
Token ID20406
Feature activation+8.00e-02

Pos logit contributions
older+0.068
yards+0.067
elly+0.067
ooks+0.066
ubs+0.066
Neg logit contributions
 yes-0.097
pron-0.093
 medal-0.092
 maker-0.086
 therapist-0.086
Token!"
Token ID2474
Feature activation+2.26e-02

Pos logit contributions
urious+0.151
oky+0.149
 territory+0.148
angs+0.146
ays+0.146
Neg logit contributions
 yes-0.120
pron-0.104
 goodbye-0.103
 medal-0.099
quet-0.096
Token
Token ID198
Feature activation+1.91e-02

Pos logit contributions
angs+0.043
urious+0.042
ains+0.041
elly+0.041
 gaps+0.041
Neg logit contributions
 yes-0.039
pron-0.035
 couple-0.033
 ceremony-0.033
 therapist-0.033
Token
Token ID198
Feature activation+1.48e-02

Pos logit contributions
angs+0.036
elly+0.035
oky+0.035
 territory+0.035
 gaps+0.035
Neg logit contributions
 yes-0.031
pron-0.029
 therapist-0.027
 ceremony-0.026
 couple-0.026
Token
Token ID198
Feature activation+2.72e-02

Pos logit contributions
urious+0.088
angs+0.087
oky+0.087
elly+0.083
 territory+0.083
Neg logit contributions
 yes-0.123
pron-0.118
 ceremony-0.111
 therapist-0.110
 couple-0.108
Token
Token ID198
Feature activation+2.06e-02

Pos logit contributions
oky+0.054
angs+0.054
 territory+0.053
elly+0.052
ASH+0.052
Neg logit contributions
 yes-0.040
pron-0.037
 therapist-0.034
 Amen-0.034
 ceremony-0.034
Token"
Token ID1
Feature activation+4.52e-02

Pos logit contributions
angs+0.045
oky+0.044
 territory+0.044
elly+0.043
ASH+0.042
Neg logit contributions
 yes-0.029
pron-0.028
 ceremony-0.026
 therapist-0.026
 couple-0.025
TokenO
Token ID46
Feature activation+3.55e-02

Pos logit contributions
angs+0.074
oky+0.074
elly+0.072
umbles+0.072
 territory+0.071
Neg logit contributions
 yes-0.087
pron-0.087
 therapist-0.082
 ceremony-0.079
 medal-0.078
Tokenw
Token ID86
Feature activation+3.68e-02

Pos logit contributions
angs+0.055
 territory+0.054
 gaps+0.054
 shadows+0.054
oky+0.054
Neg logit contributions
pron-0.068
 yes-0.065
 ceremony-0.063
 medal-0.062
 therapist-0.062
Token!
Token ID0
Feature activation+8.57e-02

Pos logit contributions
oky+0.066
elly+0.063
 gaps+0.063
urious+0.062
 territory+0.061
Neg logit contributions
 yes-0.067
pron-0.065
 medal-0.059
 ceremony-0.058
 therapist-0.057
Token That
Token ID1320
Feature activation+4.21e-02

Pos logit contributions
ained+0.116
urious+0.114
 gaps+0.110
yards+0.109
 territory+0.108
Neg logit contributions
 yes-0.171
pron-0.164
 goodbye-0.157
 therapist-0.155
 medal-0.153
Token hurts
Token ID20406
Feature activation+8.01e-02

Pos logit contributions
oky+0.052
elly+0.050
urious+0.048
ains+0.047
 gaps+0.047
Neg logit contributions
 yes-0.096
pron-0.095
 medal-0.094
 therapist-0.091
 ceremony-0.090
Token.
Token ID13
Feature activation+7.56e-02

Pos logit contributions
ains+0.131
oky+0.129
urious+0.128
 territory+0.128
angs+0.127
Neg logit contributions
 yes-0.142
pron-0.137
 medal-0.136
 ceremony-0.126
 goodbye-0.125
Token Why
Token ID4162
Feature activation+3.76e-02

Pos logit contributions
urious+0.119
 gaps+0.112
oky+0.111
yards+0.111
ains+0.110
Neg logit contributions
 yes-0.146
pron-0.134
 goodbye-0.132
 therapist-0.132
 Amen-0.128
Token did
Token ID750
Feature activation-1.38e-02

Pos logit contributions
oky+0.075
elly+0.072
angs+0.069
 territory+0.069
urious+0.069
Neg logit contributions
 yes-0.067
pron-0.063
 medal-0.058
 ceremony-0.056
 therapist-0.053
TokenAnna
Token ID31160
Feature activation+7.30e-02

Pos logit contributions
oky+0.050
elly+0.048
angs+0.048
umbles+0.046
urious+0.044
Neg logit contributions
 yes-0.105
pron-0.101
 ceremony-0.100
 therapist-0.097
 couple-0.096
Token,
Token ID11
Feature activation+3.82e-02

Pos logit contributions
oky+0.136
urious+0.132
elly+0.132
angs+0.130
 gaps+0.130
Neg logit contributions
 yes-0.125
 ceremony-0.115
pron-0.114
 medal-0.107
 couple-0.106
Token Ben
Token ID3932
Feature activation+6.21e-02

Pos logit contributions
oky+0.056
elly+0.055
angs+0.053
urious+0.051
umbles+0.051
Neg logit contributions
 yes-0.083
pron-0.079
 ceremony-0.078
 therapist-0.074
 medal-0.074
Token,
Token ID11
Feature activation+5.21e-02

Pos logit contributions
oky+0.117
elly+0.114
angs+0.113
urious+0.113
 gaps+0.111
Neg logit contributions
 yes-0.104
pron-0.098
 ceremony-0.097
 medal-0.092
 therapist-0.090
Token stop
Token ID2245
Feature activation+4.73e-02

Pos logit contributions
oky+0.090
elly+0.089
urious+0.084
angs+0.083
umbles+0.082
Neg logit contributions
 yes-0.105
pron-0.095
 ceremony-0.095
 medal-0.090
 goodbye-0.089
Token!
Token ID0
Feature activation+8.55e-02

Pos logit contributions
oky+0.084
elly+0.084
urious+0.083
angs+0.080
 gaps+0.078
Neg logit contributions
 yes-0.084
 ceremony-0.078
pron-0.076
 medal-0.075
 goodbye-0.074
Token There
Token ID1318
Feature activation+5.41e-02

Pos logit contributions
urious+0.119
 gaps+0.117
oky+0.116
ained+0.112
angs+0.111
Neg logit contributions
 yes-0.175
 goodbye-0.165
 therapist-0.160
 ceremony-0.158
 Amen-0.156
Token is
Token ID318
Feature activation+3.66e-02

Pos logit contributions
oky+0.075
elly+0.073
angs+0.069
ases+0.066
older+0.066
Neg logit contributions
 yes-0.120
 ceremony-0.114
 medal-0.111
pron-0.109
 therapist-0.106
Token a
Token ID257
Feature activation+6.35e-05

Pos logit contributions
elly+0.064
oky+0.064
urious+0.060
angs+0.059
umbles+0.059
Neg logit contributions
 yes-0.070
pron-0.063
 ceremony-0.063
 medal-0.062
 therapist-0.060
Token big
Token ID1263
Feature activation+2.35e-02

Pos logit contributions
oky+0.000
elly+0.000
angs+0.000
 trash+0.000
 shadows+0.000
Neg logit contributions
 yes-0.000
 ceremony-0.000
pron-0.000
 therapist-0.000
 couple-0.000
Token,
Token ID11
Feature activation+1.79e-02

Pos logit contributions
oky+0.037
elly+0.036
angs+0.035
 gaps+0.034
umbles+0.034
Neg logit contributions
 yes-0.048
pron-0.046
 ceremony-0.045
 therapist-0.043
 medal-0.042
Token"
Token ID1
Feature activation+4.88e-02

Pos logit contributions
angs+0.031
oky+0.031
elly+0.030
ases+0.029
 territory+0.029
Neg logit contributions
 yes-0.037
pron-0.037
 ceremony-0.035
 therapist-0.034
 couple-0.033
TokenO
Token ID46
Feature activation+3.18e-02

Pos logit contributions
oky+0.078
angs+0.078
elly+0.077
umbles+0.074
urious+0.073
Neg logit contributions
 yes-0.096
pron-0.093
 therapist-0.089
 ceremony-0.087
 couple-0.086
Tokenw
Token ID86
Feature activation+3.51e-02

Pos logit contributions
angs+0.048
oky+0.048
 gaps+0.047
elly+0.047
 shadows+0.046
Neg logit contributions
pron-0.062
 yes-0.062
 ceremony-0.058
 medal-0.057
 therapist-0.057
Token!
Token ID0
Feature activation+8.35e-02

Pos logit contributions
oky+0.061
elly+0.058
urious+0.057
 gaps+0.056
 territory+0.055
Neg logit contributions
 yes-0.067
pron-0.064
 medal-0.059
 ceremony-0.058
 goodbye-0.057
Token Ow
Token ID11960
Feature activation+3.60e-02

Pos logit contributions
urious+0.084
oky+0.080
ained+0.080
 gaps+0.079
yards+0.079
Neg logit contributions
 yes-0.200
pron-0.188
 goodbye-0.186
 therapist-0.181
 medal-0.176
Token!
Token ID0
Feature activation+8.52e-02

Pos logit contributions
oky+0.049
elly+0.047
angs+0.046
urious+0.045
 territory+0.045
Neg logit contributions
 yes-0.078
pron-0.077
 ceremony-0.074
 medal-0.073
 therapist-0.071
Token Ow
Token ID11960
Feature activation+3.87e-02

Pos logit contributions
urious+0.070
oky+0.067
 territory+0.065
elly+0.064
 gaps+0.063
Neg logit contributions
 yes-0.227
pron-0.213
 goodbye-0.208
 therapist-0.204
 ceremony-0.201
Token!"
Token ID2474
Feature activation+3.72e-03

Pos logit contributions
oky+0.054
elly+0.052
angs+0.051
urious+0.050
 territory+0.049
Neg logit contributions
 yes-0.083
pron-0.081
 ceremony-0.078
 medal-0.077
 therapist-0.075
Token he
Token ID339
Feature activation+4.50e-02

Pos logit contributions
oky+0.006
elly+0.006
angs+0.006
urious+0.006
ases+0.006
Neg logit contributions
 yes-0.008
pron-0.007
 ceremony-0.007
 therapist-0.007
 couple-0.007
Token cried
Token ID16896
Feature activation+6.14e-02

Pos logit contributions
oky+0.084
elly+0.082
ains+0.077
urious+0.077
angs+0.076
Neg logit contributions
 yes-0.080
pron-0.072
 therapist-0.071
 couple-0.069
 ceremony-0.068
Token.
Token ID13
Feature activation+4.97e-02

Pos logit contributions
urious+0.117
 territory+0.114
oky+0.113
elly+0.112
 gaps+0.111
Neg logit contributions
 yes-0.108
 goodbye-0.093
 couple-0.084
 medal-0.082
 therapist-0.082
Token "
Token ID366
Feature activation+5.26e-02

Pos logit contributions
oky+0.035
angs+0.034
 Why+0.033
 raining+0.033
 shadows+0.033
Neg logit contributions
 ceremony-0.068
pron-0.065
 yes-0.064
 medal-0.063
 therapist-0.062
TokenO
Token ID46
Feature activation+3.19e-02

Pos logit contributions
angs+0.095
 territory+0.090
elly+0.089
ains+0.088
oky+0.087
Neg logit contributions
pron-0.089
 yes-0.087
 therapist-0.086
 couple-0.082
 medal-0.078
Tokenw
Token ID86
Feature activation+3.51e-02

Pos logit contributions
angs+0.048
oky+0.047
 territory+0.047
 gaps+0.046
 shadows+0.046
Neg logit contributions
pron-0.062
 yes-0.061
 ceremony-0.058
 medal-0.057
 therapist-0.056
Token!
Token ID0
Feature activation+8.23e-02

Pos logit contributions
oky+0.067
elly+0.064
urious+0.063
 gaps+0.063
 territory+0.062
Neg logit contributions
 yes-0.062
pron-0.058
 medal-0.052
 ceremony-0.052
 goodbye-0.051
Token Ow
Token ID11960
Feature activation+3.77e-02

Pos logit contributions
 territory+0.119
urious+0.118
 gaps+0.113
ained+0.112
yards+0.111
Neg logit contributions
 yes-0.159
pron-0.149
 goodbye-0.138
 therapist-0.137
 Amen-0.133
Token!
Token ID0
Feature activation+8.50e-02

Pos logit contributions
oky+0.054
elly+0.051
urious+0.051
 territory+0.051
angs+0.051
Neg logit contributions
 yes-0.078
pron-0.077
 ceremony-0.073
 medal-0.073
 therapist-0.070
Token Ow
Token ID11960
Feature activation+4.23e-02

Pos logit contributions
 territory+0.102
urious+0.101
oky+0.096
elly+0.095
 gaps+0.094
Neg logit contributions
 yes-0.194
pron-0.181
 goodbye-0.169
 Amen-0.168
 therapist-0.167
Token!
Token ID0
Feature activation+8.57e-02

Pos logit contributions
oky+0.062
elly+0.059
urious+0.059
 territory+0.059
angs+0.058
Neg logit contributions
 yes-0.086
pron-0.085
 ceremony-0.081
 medal-0.080
 therapist-0.077
Token It
Token ID632
Feature activation+4.85e-02

Pos logit contributions
 territory+0.104
urious+0.104
oky+0.098
elly+0.097
 gaps+0.096
Neg logit contributions
 yes-0.197
pron-0.184
 Amen-0.171
 goodbye-0.171
 therapist-0.170
Token hurts
Token ID20406
Feature activation+8.00e-02

Pos logit contributions
older+0.068
yards+0.067
elly+0.067
ooks+0.066
ubs+0.066
Neg logit contributions
 yes-0.097
pron-0.093
 medal-0.092
 maker-0.086
 therapist-0.086
Token!"
Token ID2474
Feature activation+2.26e-02

Pos logit contributions
urious+0.151
oky+0.149
 territory+0.148
angs+0.146
ays+0.146
Neg logit contributions
 yes-0.120
pron-0.104
 goodbye-0.103
 medal-0.099
quet-0.096
Token"
Token ID1
Feature activation+4.37e-02

Pos logit contributions
angs+0.033
oky+0.032
elly+0.032
 territory+0.031
urious+0.030
Neg logit contributions
 yes-0.030
pron-0.029
 ceremony-0.028
 therapist-0.026
 couple-0.026
TokenTom
Token ID13787
Feature activation+5.67e-02

Pos logit contributions
angs+0.058
oky+0.058
elly+0.057
umbles+0.055
 territory+0.054
Neg logit contributions
 yes-0.097
pron-0.095
 ceremony-0.091
 couple-0.090
 therapist-0.090
Token,
Token ID11
Feature activation+3.37e-02

Pos logit contributions
oky+0.103
elly+0.101
angs+0.099
urious+0.097
 gaps+0.097
Neg logit contributions
 yes-0.102
pron-0.096
 ceremony-0.095
 medal-0.090
 therapist-0.087
Token stop
Token ID2245
Feature activation+4.74e-02

Pos logit contributions
oky+0.051
elly+0.050
angs+0.048
umbles+0.046
urious+0.046
Neg logit contributions
 yes-0.072
pron-0.069
 ceremony-0.068
 therapist-0.064
 medal-0.064
Token it
Token ID340
Feature activation+3.55e-02

Pos logit contributions
oky+0.086
elly+0.085
angs+0.083
urious+0.082
 gaps+0.079
Neg logit contributions
 yes-0.084
pron-0.080
 ceremony-0.079
 medal-0.075
 therapist-0.074
Token!
Token ID0
Feature activation+8.49e-02

Pos logit contributions
oky+0.049
elly+0.048
angs+0.047
 gaps+0.045
urious+0.045
Neg logit contributions
 yes-0.078
pron-0.076
 ceremony-0.074
 medal-0.071
 therapist-0.070
Token Toy
Token ID10977
Feature activation+1.22e-02

Pos logit contributions
urious+0.125
 gaps+0.121
angs+0.120
oky+0.119
 territory+0.116
Neg logit contributions
 yes-0.164
pron-0.153
 goodbye-0.151
 therapist-0.150
 Amen-0.147
Token,
Token ID11
Feature activation+3.37e-02

Pos logit contributions
oky+0.012
angs+0.011
elly+0.011
ases+0.011
umbles+0.010
Neg logit contributions
 yes-0.032
pron-0.032
 ceremony-0.031
 couple-0.030
 therapist-0.030
Token stop
Token ID2245
Feature activation+5.03e-02

Pos logit contributions
oky+0.051
angs+0.050
elly+0.049
 gaps+0.048
 trash+0.048
Neg logit contributions
pron-0.067
 yes-0.067
 ceremony-0.066
 therapist-0.063
 couple-0.062
Token it
Token ID340
Feature activation+3.54e-02

Pos logit contributions
oky+0.073
elly+0.072
angs+0.071
urious+0.069
 gaps+0.066
Neg logit contributions
 yes-0.106
pron-0.102
 ceremony-0.101
 medal-0.097
 therapist-0.095
Token!
Token ID0
Feature activation+7.99e-02

Pos logit contributions
oky+0.047
elly+0.046
angs+0.045
urious+0.043
 gaps+0.043
Neg logit contributions
 yes-0.080
pron-0.077
 ceremony-0.075
 medal-0.072
 therapist-0.071
Token for
Token ID329
Feature activation-3.62e-02

Pos logit contributions
pron+0.057
 yes+0.052
ves+0.052
 Amen+0.052
 therapist+0.052
Neg logit contributions
my-0.017
 finds-0.015
en-0.014
elly-0.013
umbles-0.013
Token taking
Token ID2263
Feature activation-2.45e-02

Pos logit contributions
 therapist+0.092
pron+0.090
 saddle+0.089
 yes+0.087
ves+0.086
Neg logit contributions
ases-0.029
 raining-0.027
 spiders-0.025
 shadows-0.025
ASH-0.025
Token her
Token ID607
Feature activation+6.25e-03

Pos logit contributions
pron+0.058
 yes+0.057
 ceremony+0.053
 therapist+0.052
 Amen+0.051
Neg logit contributions
 shadows-0.029
ases-0.029
 trash-0.029
oky-0.029
elly-0.028
Token to
Token ID284
Feature activation-1.06e-02

Pos logit contributions
oky+0.008
 finds+0.008
elly+0.008
angs+0.008
ases+0.008
Neg logit contributions
pron-0.013
 Amen-0.013
 yes-0.013
 therapist-0.013
 ceremony-0.013
Token the
Token ID262
Feature activation-2.98e-02

Pos logit contributions
 yes+0.025
pron+0.025
 therapist+0.025
 ceremony+0.024
 saddle+0.023
Neg logit contributions
 raining-0.011
 shadows-0.011
ases-0.011
 gaps-0.010
 trash-0.010
Token carn
Token ID18466
Feature activation-9.78e-02

Pos logit contributions
 yes+0.061
pron+0.061
 therapist+0.057
 ceremony+0.056
quet+0.055
Neg logit contributions
 shadows-0.042
 trash-0.042
oky-0.042
 territory-0.040
 gaps-0.039
Tokenival
Token ID2473
Feature activation-5.68e-02

Pos logit contributions
 Amen+0.111
 yes+0.109
 saddle+0.109
 therapist+0.104
 pony+0.102
Neg logit contributions
elly-0.226
oky-0.222
udd-0.215
urious-0.208
umpy-0.207
Token.
Token ID13
Feature activation-1.25e-02

Pos logit contributions
pron+0.157
 Amen+0.150
 yes+0.148
 therapist+0.139
 saddle+0.137
Neg logit contributions
 shadows-0.039
elly-0.039
 territory-0.038
oky-0.037
 raining-0.037
Token They
Token ID1119
Feature activation-3.35e-02

Pos logit contributions
 yes+0.027
pron+0.027
 ceremony+0.026
 therapist+0.025
 goodbye+0.025
Neg logit contributions
oky-0.017
angs-0.017
elly-0.017
 gaps-0.016
ases-0.016
Token hugged
Token ID41130
Feature activation+8.48e-03

Pos logit contributions
pron+0.087
 therapist+0.081
quet+0.080
 ceremony+0.080
 Amen+0.078
Neg logit contributions
my-0.030
 finds-0.028
 tubes-0.027
ety-0.027
iz-0.026
Token her
Token ID607
Feature activation+1.64e-02

Pos logit contributions
elly+0.006
 shadows+0.006
oky+0.006
en+0.006
ases+0.006
Neg logit contributions
pron-0.024
 ceremony-0.023
 yes-0.022
 medal-0.022
 therapist-0.022
Token was
Token ID373
Feature activation-1.38e-02

Pos logit contributions
pron+0.007
 saddle+0.006
 ceremony+0.006
 yes+0.006
 therapist+0.006
Neg logit contributions
urious-0.003
elly-0.003
oky-0.002
ases-0.002
 Why-0.002
Token proud
Token ID6613
Feature activation-1.04e-02

Pos logit contributions
pron+0.031
 yes+0.030
 ceremony+0.029
 medal+0.029
 therapist+0.029
Neg logit contributions
umbles-0.017
 raining-0.016
oky-0.016
 afraid-0.016
angs-0.016
Token of
Token ID286
Feature activation-3.11e-03

Pos logit contributions
 yes+0.022
pron+0.021
 ceremony+0.021
 therapist+0.020
 medal+0.020
Neg logit contributions
oky-0.016
elly-0.015
angs-0.015
 gaps-0.014
umbles-0.014
Token John
Token ID1757
Feature activation-4.04e-03

Pos logit contributions
pron+0.007
 ceremony+0.007
 therapist+0.006
 yes+0.006
 saddle+0.006
Neg logit contributions
oky-0.004
urious-0.004
elly-0.004
ases-0.004
ASH-0.004
Token and
Token ID290
Feature activation-4.76e-02

Pos logit contributions
pron+0.011
 yes+0.011
 ceremony+0.011
 therapist+0.010
 saddle+0.010
Neg logit contributions
elly-0.003
oky-0.003
angs-0.003
urious-0.002
 finds-0.002
Token Kinder
Token ID46832
Feature activation-9.74e-02

Pos logit contributions
pron+0.110
 yes+0.098
 ceremony+0.095
quet+0.094
 saddle+0.093
Neg logit contributions
 shadows-0.061
 finds-0.060
 pipes-0.059
 wonders-0.058
 trash-0.058
Tokeng
Token ID70
Feature activation-4.00e-02

Pos logit contributions
pron+0.181
 pony+0.179
 yes+0.178
 therapist+0.174
 saddle+0.172
Neg logit contributions
ases-0.134
atters-0.124
ASH-0.124
en-0.123
 Fighting-0.122
Tokenarten
Token ID23996
Feature activation-1.06e-02

Pos logit contributions
 yes+0.083
pron+0.080
 ceremony+0.075
 therapist+0.072
 saddle+0.072
Neg logit contributions
oky-0.064
elly-0.064
urious-0.062
umbles-0.061
angs-0.060
Tokeners
Token ID364
Feature activation-2.76e-02

Pos logit contributions
pron+0.027
 yes+0.025
 ceremony+0.024
 Amen+0.024
 saddle+0.024
Neg logit contributions
oky-0.011
elly-0.011
angs-0.011
 shadows-0.011
 gaps-0.010
Token learned
Token ID4499
Feature activation+3.62e-03

Pos logit contributions
pron+0.073
 Amen+0.068
 therapist+0.066
 saddle+0.065
 yes+0.065
Neg logit contributions
ases-0.022
 shadows-0.022
 finds-0.022
umbles-0.021
angs-0.021
Token an
Token ID281
Feature activation-2.08e-02

Pos logit contributions
oky+0.005
elly+0.005
angs+0.005
umbles+0.005
 gaps+0.005
Neg logit contributions
pron-0.008
 yes-0.008
 ceremony-0.008
 therapist-0.007
 couple-0.007
Token so
Token ID523
Feature activation-2.14e-02

Pos logit contributions
 yes+0.027
pron+0.027
 ceremony+0.026
 medal+0.025
 therapist+0.025
Neg logit contributions
oky-0.020
elly-0.019
angs-0.019
umbles-0.018
 raining-0.018
Token excited
Token ID6568
Feature activation-1.95e-02

Pos logit contributions
 yes+0.038
pron+0.038
 ceremony+0.037
 medal+0.035
 therapist+0.035
Neg logit contributions
oky-0.038
elly-0.038
angs-0.036
umbles-0.035
urious-0.035
Token!
Token ID0
Feature activation-1.48e-03

Pos logit contributions
 yes+0.039
pron+0.038
 ceremony+0.037
 therapist+0.035
 couple+0.035
Neg logit contributions
oky-0.031
angs-0.030
elly-0.030
ases-0.029
 gaps-0.029
Token She
Token ID1375
Feature activation-8.57e-03

Pos logit contributions
 yes+0.003
pron+0.003
 ceremony+0.003
 therapist+0.003
 couple+0.003
Neg logit contributions
angs-0.002
oky-0.002
elly-0.002
ases-0.002
 gaps-0.002
Token loved
Token ID6151
Feature activation-2.07e-02

Pos logit contributions
 yes+0.020
 ceremony+0.020
pron+0.019
quet+0.019
 medal+0.019
Neg logit contributions
 finds-0.009
urious-0.009
oky-0.009
elly-0.009
 trash-0.008
Token pic
Token ID8301
Feature activation-9.16e-02

Pos logit contributions
 yes+0.046
pron+0.045
 therapist+0.044
quet+0.043
 ceremony+0.042
Neg logit contributions
 spiders-0.027
 raining-0.027
 shadows-0.027
 trash-0.026
 tubes-0.024
Tokenn
Token ID77
Feature activation-2.00e-02

Pos logit contributions
 therapist+0.144
 couple+0.140
 yes+0.139
 medal+0.137
 ceremony+0.137
Neg logit contributions
urious-0.149
iz-0.149
en-0.147
ubs-0.147
ASH-0.145
Tokenics
Token ID873
Feature activation-3.03e-02

Pos logit contributions
 yes+0.029
 ceremony+0.029
pron+0.028
 therapist+0.027
 medal+0.027
Neg logit contributions
umbles-0.041
ubs-0.040
oky-0.039
angs-0.039
urious-0.039
Token and
Token ID290
Feature activation-1.76e-02

Pos logit contributions
pron+0.086
 yes+0.081
 Amen+0.081
 ceremony+0.081
 therapist+0.078
Neg logit contributions
elly-0.021
oky-0.019
 shadows-0.016
 raining-0.016
 because-0.016
Token spending
Token ID4581
Feature activation-2.63e-02

Pos logit contributions
pron+0.039
 yes+0.038
 ceremony+0.038
 medal+0.037
 therapist+0.037
Neg logit contributions
 raining-0.021
 shadows-0.020
 finds-0.020
 tubes-0.020
 hed-0.020
Token time
Token ID640
Feature activation-5.21e-03

Pos logit contributions
 yes+0.066
pron+0.062
 ceremony+0.061
 therapist+0.061
quet+0.058
Neg logit contributions
oky-0.027
elly-0.027
 trash-0.026
 gaps-0.026
 raining-0.026
Token and
Token ID290
Feature activation-3.46e-02

Pos logit contributions
oky+0.038
elly+0.037
angs+0.036
ases+0.034
 gaps+0.034
Neg logit contributions
 yes-0.079
pron-0.076
 ceremony-0.075
 therapist-0.072
 medal-0.071
Token nodded
Token ID14464
Feature activation+1.83e-02

Pos logit contributions
pron+0.077
 ceremony+0.074
 Amen+0.074
quet+0.073
 yes+0.072
Neg logit contributions
 Sam-0.041
 finds-0.040
 trash-0.039
 shadows-0.038
 wonders-0.037
Token.
Token ID13
Feature activation+6.29e-04

Pos logit contributions
 raining+0.015
oky+0.014
en+0.014
elly+0.013
 shadows+0.013
Neg logit contributions
pron-0.048
 ceremony-0.047
 therapist-0.046
 medal-0.045
quet-0.044
Token He
Token ID679
Feature activation-1.90e-02

Pos logit contributions
angs+0.001
oky+0.001
elly+0.001
ases+0.001
 gaps+0.001
Neg logit contributions
 yes-0.001
pron-0.001
 ceremony-0.001
 goodbye-0.001
 couple-0.001
Token loved
Token ID6151
Feature activation-2.41e-02

Pos logit contributions
pron+0.044
 ceremony+0.044
 yes+0.043
quet+0.042
 Amen+0.042
Neg logit contributions
urious-0.020
 finds-0.020
elly-0.020
oky-0.020
 wonders-0.019
Token pic
Token ID8301
Feature activation-9.11e-02

Pos logit contributions
pron+0.059
 yes+0.059
 therapist+0.057
 ceremony+0.056
quet+0.055
Neg logit contributions
 spiders-0.027
 raining-0.027
 shadows-0.027
 trash-0.024
 pipes-0.024
Tokenn
Token ID77
Feature activation-1.96e-02

Pos logit contributions
 therapist+0.151
 couple+0.147
pron+0.143
 pony+0.142
 ceremony+0.141
Neg logit contributions
iz-0.146
en-0.144
urious-0.141
ichever-0.140
ASH-0.140
Tokenics
Token ID873
Feature activation-3.25e-02

Pos logit contributions
 ceremony+0.031
pron+0.031
 yes+0.030
 therapist+0.029
 medal+0.028
Neg logit contributions
umbles-0.039
ubs-0.037
angs-0.037
ains-0.036
 raining-0.036
Token and
Token ID290
Feature activation-2.28e-02

Pos logit contributions
pron+0.093
 ceremony+0.084
 Amen+0.084
 yes+0.082
 therapist+0.082
Neg logit contributions
elly-0.022
oky-0.021
 because-0.020
 shadows-0.020
 territory-0.019
Token couldn
Token ID3521
Feature activation-3.53e-02

Pos logit contributions
pron+0.052
 yes+0.050
 ceremony+0.049
quet+0.048
 medal+0.048
Neg logit contributions
 raining-0.027
 shadows-0.026
 finds-0.026
 hed-0.026
 trash-0.025
Token't
Token ID470
Feature activation+5.82e-03

Pos logit contributions
pron+0.071
 ceremony+0.070
 yes+0.069
 couple+0.064
 medal+0.063
Neg logit contributions
umbles-0.054
oky-0.054
elly-0.052
 raining-0.052
ays-0.052
Token She
Token ID1375
Feature activation-2.33e-02

Pos logit contributions
 yes+0.038
pron+0.035
 ceremony+0.035
 couple+0.034
 goodbye+0.033
Neg logit contributions
angs-0.025
oky-0.024
elly-0.024
 territory-0.024
 gaps-0.023
Token wanted
Token ID2227
Feature activation-3.24e-02

Pos logit contributions
pron+0.051
 yes+0.050
 ceremony+0.050
 Amen+0.049
 therapist+0.048
Neg logit contributions
 finds-0.029
oky-0.026
elly-0.026
okes-0.026
urious-0.026
Token to
Token ID284
Feature activation-2.86e-02

Pos logit contributions
 yes+0.062
pron+0.061
 ceremony+0.059
 therapist+0.056
 medal+0.055
Neg logit contributions
oky-0.054
elly-0.053
angs-0.053
 gaps-0.050
ases-0.050
Token make
Token ID787
Feature activation-5.58e-02

Pos logit contributions
pron+0.066
 yes+0.063
 therapist+0.063
 ceremony+0.062
 goodbye+0.058
Neg logit contributions
ases-0.034
ubs-0.032
 gaps-0.032
umbles-0.032
 shadows-0.032
Token a
Token ID257
Feature activation-4.26e-02

Pos logit contributions
 yes+0.122
pron+0.121
 ceremony+0.117
 therapist+0.112
 medal+0.110
Neg logit contributions
oky-0.077
angs-0.075
elly-0.074
 shadows-0.071
 gaps-0.071
Token coll
Token ID2927
Feature activation-8.93e-02

Pos logit contributions
 yes+0.086
 therapist+0.083
pron+0.080
 ceremony+0.078
 Amen+0.076
Neg logit contributions
 trash-0.065
 shadows-0.062
oky-0.062
 territory-0.060
 gaps-0.058
Tokenage
Token ID496
Feature activation-2.24e-02

Pos logit contributions
 therapist+0.161
 yes+0.159
pron+0.156
 ceremony+0.151
 medal+0.145
Neg logit contributions
ases-0.141
angs-0.140
ubs-0.136
umbles-0.135
OOOO-0.132
Token out
Token ID503
Feature activation+8.70e-03

Pos logit contributions
pron+0.055
 therapist+0.054
 Amen+0.052
 yes+0.052
 ceremony+0.051
Neg logit contributions
 raining-0.021
 shadows-0.020
 apart-0.019
 finds-0.019
oky-0.019
Token of
Token ID286
Feature activation-2.60e-03

Pos logit contributions
oky+0.010
angs+0.010
elly+0.010
 shadows+0.010
 raining+0.009
Neg logit contributions
pron-0.021
 yes-0.020
 therapist-0.020
 ceremony-0.019
 couple-0.019
Token the
Token ID262
Feature activation+1.33e-02

Pos logit contributions
 yes+0.006
pron+0.006
 therapist+0.005
 ceremony+0.005
 Amen+0.005
Neg logit contributions
 trash-0.003
 shadows-0.003
 gaps-0.003
 spiders-0.003
 pipes-0.003
Token beautiful
Token ID4950
Feature activation-2.83e-03

Pos logit contributions
oky+0.018
elly+0.017
 gaps+0.017
 shadows+0.017
 trash+0.016
Neg logit contributions
 yes-0.030
pron-0.029
 ceremony-0.028
 therapist-0.027
 medal-0.027
Token that
Token ID326
Feature activation+3.04e-03

Pos logit contributions
pron+0.023
 yes+0.021
 Amen+0.021
 ceremony+0.021
 therapist+0.021
Neg logit contributions
oky-0.016
elly-0.015
 trash-0.014
 sees-0.014
 gaps-0.014
Token said
Token ID531
Feature activation-2.10e-02

Pos logit contributions
oky+0.005
angs+0.005
elly+0.005
 shadows+0.005
 gaps+0.005
Neg logit contributions
pron-0.006
 yes-0.006
 ceremony-0.006
 saddle-0.005
 medal-0.005
Token "
Token ID366
Feature activation+1.15e-02

Pos logit contributions
pron+0.049
 saddle+0.047
 ceremony+0.047
 therapist+0.046
 Amen+0.046
Neg logit contributions
angs-0.023
 Why-0.022
 pipes-0.022
 tubes-0.021
 raining-0.021
TokenWelcome
Token ID14618
Feature activation-5.96e-04

Pos logit contributions
oky+0.018
elly+0.018
angs+0.017
ases+0.017
urious+0.016
Neg logit contributions
 yes-0.024
pron-0.023
 ceremony-0.022
 medal-0.021
 goodbye-0.021
Token to
Token ID284
Feature activation+1.91e-03

Pos logit contributions
 yes+0.001
pron+0.001
 ceremony+0.001
 therapist+0.001
 medal+0.001
Neg logit contributions
oky-0.001
elly-0.001
angs-0.001
umbles-0.001
ases-0.001
Token Kinder
Token ID46832
Feature activation-8.92e-02

Pos logit contributions
oky+0.003
elly+0.002
angs+0.002
ases+0.002
umbles+0.002
Neg logit contributions
pron-0.004
 yes-0.004
 ceremony-0.004
 therapist-0.004
 medal-0.004
Tokeng
Token ID70
Feature activation-3.27e-02

Pos logit contributions
 yes+0.168
pron+0.156
 saddle+0.145
 therapist+0.141
 pony+0.138
Neg logit contributions
ases-0.137
elly-0.129
oky-0.127
ASH-0.127
roc-0.126
Tokenarten
Token ID23996
Feature activation+5.40e-03

Pos logit contributions
 yes+0.073
pron+0.067
 ceremony+0.064
 therapist+0.062
 saddle+0.062
Neg logit contributions
elly-0.048
oky-0.047
umbles-0.046
ases-0.044
angs-0.044
Token!"
Token ID2474
Feature activation-2.37e-02

Pos logit contributions
oky+0.007
elly+0.007
angs+0.006
ases+0.006
umbles+0.006
Neg logit contributions
 yes-0.012
pron-0.012
 ceremony-0.012
 therapist-0.011
 medal-0.011
Token
Token ID198
Feature activation-1.91e-02

Pos logit contributions
pron+0.068
 yes+0.065
 ceremony+0.064
 medal+0.063
 saddle+0.063
Neg logit contributions
oky-0.018
elly-0.018
umbles-0.015
 Maybe-0.014
 shadows-0.014
Token
Token ID198
Feature activation-1.82e-02

Pos logit contributions
 yes+0.052
pron+0.052
 ceremony+0.051
 medal+0.049
 therapist+0.048
Neg logit contributions
elly-0.015
oky-0.015
umbles-0.014
ubs-0.014
 shadows-0.013
Token,
Token ID11
Feature activation-1.38e-02

Pos logit contributions
pron+0.027
 yes+0.027
 ceremony+0.026
 therapist+0.024
 medal+0.024
Neg logit contributions
oky-0.019
elly-0.018
angs-0.017
 shadows-0.017
 gaps-0.017
Token Max
Token ID5436
Feature activation-2.02e-03

Pos logit contributions
 yes+0.029
pron+0.029
 ceremony+0.028
 therapist+0.027
 medal+0.027
Neg logit contributions
oky-0.020
elly-0.019
angs-0.019
 gaps-0.018
 raining-0.018
Token,
Token ID11
Feature activation+1.09e-02

Pos logit contributions
pron+0.005
 yes+0.005
 ceremony+0.005
 medal+0.005
 therapist+0.005
Neg logit contributions
oky-0.002
elly-0.002
angs-0.002
umbles-0.002
 finds-0.002
Token to
Token ID284
Feature activation-1.83e-02

Pos logit contributions
oky+0.014
elly+0.013
angs+0.013
 gaps+0.012
umbles+0.012
Neg logit contributions
 yes-0.025
pron-0.025
 ceremony-0.025
 therapist-0.023
 medal-0.023
Token the
Token ID262
Feature activation-2.09e-02

Pos logit contributions
pron+0.044
 therapist+0.043
 yes+0.042
 ceremony+0.042
quet+0.041
Neg logit contributions
 raining-0.018
ases-0.018
 trash-0.018
 Sam-0.017
 tubes-0.017
Token carn
Token ID18466
Feature activation-8.64e-02

Pos logit contributions
 yes+0.047
pron+0.045
 ceremony+0.043
quet+0.042
 therapist+0.042
Neg logit contributions
oky-0.027
 trash-0.026
 shadows-0.026
elly-0.025
 territory-0.025
Tokenival
Token ID2473
Feature activation-4.87e-02

Pos logit contributions
 yes+0.098
 Amen+0.093
 saddle+0.090
 therapist+0.089
pron+0.086
Neg logit contributions
elly-0.205
oky-0.204
udd-0.191
urious-0.189
umpy-0.187
Token.
Token ID13
Feature activation+9.19e-03

Pos logit contributions
pron+0.135
 yes+0.128
 Amen+0.127
 therapist+0.120
 ceremony+0.119
Neg logit contributions
elly-0.036
oky-0.035
umbles-0.034
 territory-0.033
 finds-0.032
Token Everywhere
Token ID48201
Feature activation-2.66e-02

Pos logit contributions
oky+0.014
elly+0.014
angs+0.014
ases+0.013
urious+0.013
Neg logit contributions
 yes-0.019
pron-0.019
 ceremony-0.018
 therapist-0.017
 couple-0.017
Token they
Token ID484
Feature activation-1.69e-02

Pos logit contributions
pron+0.049
 yes+0.049
 ceremony+0.048
quet+0.047
 couple+0.044
Neg logit contributions
oky-0.042
elly-0.042
 trash-0.041
 finds-0.041
 shadows-0.040
Token looked
Token ID3114
Feature activation+1.57e-02

Pos logit contributions
 yes+0.038
pron+0.038
 ceremony+0.036
 therapist+0.035
quet+0.034
Neg logit contributions
oky-0.021
elly-0.021
angs-0.020
umbles-0.019
 finds-0.019
Token about
Token ID546
Feature activation-1.28e-02

Pos logit contributions
oky+0.013
elly+0.012
angs+0.012
umbles+0.011
urious+0.011
Neg logit contributions
 yes-0.018
 ceremony-0.018
pron-0.018
 therapist-0.017
 couple-0.017
Token we
Token ID356
Feature activation-1.20e-02

Pos logit contributions
pron+0.030
 therapist+0.027
 yes+0.027
 ceremony+0.027
quet+0.025
Neg logit contributions
 pipes-0.016
 spiders-0.016
 raining-0.016
 shadows-0.016
 territory-0.015
Token have
Token ID423
Feature activation-1.67e-02

Pos logit contributions
pron+0.026
 therapist+0.025
 yes+0.025
 ceremony+0.024
 couple+0.023
Neg logit contributions
oky-0.015
 raining-0.015
angs-0.015
umbles-0.015
elly-0.015
Token our
Token ID674
Feature activation+3.40e-03

Pos logit contributions
pron+0.037
 yes+0.036
 therapist+0.035
 ceremony+0.034
 Amen+0.034
Neg logit contributions
oky-0.022
elly-0.021
 trash-0.021
 gaps-0.021
angs-0.021
Token own
Token ID898
Feature activation+5.71e-03

Pos logit contributions
oky+0.006
 territory+0.006
elly+0.006
angs+0.006
 shadows+0.005
Neg logit contributions
pron-0.006
 yes-0.006
 therapist-0.006
 ceremony-0.006
quet-0.006
Token carn
Token ID18466
Feature activation-8.57e-02

Pos logit contributions
oky+0.010
 territory+0.010
elly+0.010
angs+0.010
 shadows+0.010
Neg logit contributions
 yes-0.010
pron-0.009
 therapist-0.009
 ceremony-0.009
quet-0.008
Tokenival
Token ID2473
Feature activation-5.16e-02

Pos logit contributions
 Amen+0.101
 therapist+0.094
 yes+0.091
 saddle+0.088
pron+0.088
Neg logit contributions
elly-0.200
oky-0.193
umpy-0.186
udd-0.184
ases-0.182
Token at
Token ID379
Feature activation-6.63e-03

Pos logit contributions
pron+0.117
 yes+0.115
 therapist+0.112
 Amen+0.109
 ceremony+0.108
Neg logit contributions
 finds-0.058
 territory-0.058
elly-0.058
oky-0.057
ases-0.054
Token home
Token ID1363
Feature activation+4.76e-03

Pos logit contributions
 yes+0.015
pron+0.014
 ceremony+0.013
 therapist+0.013
 couple+0.013
Neg logit contributions
oky-0.009
elly-0.009
umbles-0.009
ases-0.009
 gaps-0.008
Token?
Token ID30
Feature activation-3.06e-03

Pos logit contributions
oky+0.006
elly+0.006
angs+0.005
umbles+0.005
ases+0.005
Neg logit contributions
 yes-0.011
pron-0.011
 ceremony-0.011
 therapist-0.010
 medal-0.010
Token We
Token ID775
Feature activation-2.12e-02

Pos logit contributions
pron+0.008
 ceremony+0.008
 yes+0.008
 medal+0.007
 couple+0.007
Neg logit contributions
oky-0.003
elly-0.003
angs-0.003
umbles-0.003
ases-0.003
Token.
Token ID13
Feature activation+2.48e-02

Pos logit contributions
oky+0.028
angs+0.028
 gaps+0.027
ays+0.027
ases+0.027
Neg logit contributions
 yes-0.023
pron-0.022
 ceremony-0.021
 Amen-0.021
 couple-0.020
Token She
Token ID1375
Feature activation+1.72e-02

Pos logit contributions
angs+0.041
oky+0.039
ases+0.039
 territory+0.039
umbles+0.038
Neg logit contributions
 yes-0.050
pron-0.047
 ceremony-0.043
 goodbye-0.042
 therapist-0.041
Token loved
Token ID6151
Feature activation-7.51e-03

Pos logit contributions
oky+0.024
elly+0.024
angs+0.023
umbles+0.022
urious+0.022
Neg logit contributions
 yes-0.038
pron-0.036
 ceremony-0.036
 therapist-0.034
 medal-0.034
Token to
Token ID284
Feature activation+1.96e-03

Pos logit contributions
 yes+0.018
pron+0.016
 ceremony+0.016
 therapist+0.016
quet+0.015
Neg logit contributions
 raining-0.010
oky-0.010
 shadows-0.009
elly-0.009
 spiders-0.009
Token have
Token ID423
Feature activation-6.80e-03

Pos logit contributions
 raining+0.002
 tubes+0.002
 trash+0.002
 shadows+0.002
ases+0.002
Neg logit contributions
 therapist-0.004
 yes-0.004
 ceremony-0.004
pron-0.004
 couple-0.004
Token pic
Token ID8301
Feature activation-8.53e-02

Pos logit contributions
 yes+0.013
pron+0.013
 therapist+0.013
 ceremony+0.013
 Amen+0.012
Neg logit contributions
 trash-0.010
 shadows-0.010
oky-0.010
elly-0.010
 raining-0.010
Tokenn
Token ID77
Feature activation-1.14e-02

Pos logit contributions
 therapist+0.133
 yes+0.130
pron+0.125
 couple+0.124
 ceremony+0.121
Neg logit contributions
ubs-0.152
urious-0.152
ases-0.149
en-0.148
 finds-0.148
Tokenics
Token ID873
Feature activation-2.89e-02

Pos logit contributions
 yes+0.016
 ceremony+0.015
pron+0.015
 therapist+0.014
 couple+0.014
Neg logit contributions
umbles-0.024
oky-0.024
elly-0.024
ubs-0.023
angs-0.023
Token with
Token ID351
Feature activation+1.03e-02

Pos logit contributions
pron+0.072
 yes+0.069
 ceremony+0.069
 therapist+0.069
 Amen+0.066
Neg logit contributions
elly-0.029
oky-0.026
 raining-0.025
ases-0.025
 finds-0.024
Token her
Token ID607
Feature activation+1.70e-02

Pos logit contributions
 trash+0.012
 raining+0.011
 shadows+0.011
 spiders+0.011
elly+0.010
Neg logit contributions
 yes-0.024
pron-0.024
 ceremony-0.024
 therapist-0.023
 medal-0.023
Token family
Token ID1641
Feature activation-4.14e-03

Pos logit contributions
 trash+0.020
 shadows+0.019
 raining+0.018
yards+0.017
 tubes+0.017
Neg logit contributions
 yes-0.038
pron-0.037
 ceremony-0.037
quet-0.037
ner-0.036
Token excited
Token ID6568
Feature activation-8.91e-03

Pos logit contributions
 yes+0.024
pron+0.023
 ceremony+0.023
 therapist+0.021
 couple+0.021
Neg logit contributions
oky-0.024
elly-0.024
angs-0.024
 gaps-0.023
ases-0.023
Token to
Token ID284
Feature activation-2.39e-02

Pos logit contributions
 yes+0.015
pron+0.014
 ceremony+0.014
 couple+0.013
 medal+0.013
Neg logit contributions
angs-0.017
oky-0.016
ases-0.016
 gaps-0.016
ASH-0.016
Token go
Token ID467
Feature activation-2.11e-02

Pos logit contributions
 yes+0.055
pron+0.054
 therapist+0.054
 ceremony+0.051
 medal+0.050
Neg logit contributions
ases-0.028
umbles-0.027
 raining-0.027
ubs-0.026
 shadows-0.026
Token to
Token ID284
Feature activation-4.38e-03

Pos logit contributions
 yes+0.042
pron+0.040
 ceremony+0.039
 therapist+0.038
 medal+0.036
Neg logit contributions
oky-0.034
elly-0.033
angs-0.033
ases-0.031
umbles-0.031
Token the
Token ID262
Feature activation-1.15e-02

Pos logit contributions
 yes+0.010
pron+0.010
 therapist+0.010
 ceremony+0.010
quet+0.009
Neg logit contributions
 shadows-0.005
 raining-0.005
oky-0.005
elly-0.005
 finds-0.005
Token carn
Token ID18466
Feature activation-8.52e-02

Pos logit contributions
 yes+0.025
pron+0.024
 ceremony+0.023
 therapist+0.023
 couple+0.022
Neg logit contributions
oky-0.017
elly-0.016
 shadows-0.015
 trash-0.015
 gaps-0.015
Tokenival
Token ID2473
Feature activation-5.11e-02

Pos logit contributions
 yes+0.088
 saddle+0.077
 therapist+0.076
 Amen+0.075
pron+0.075
Neg logit contributions
elly-0.215
oky-0.213
urious-0.199
umpy-0.196
ases-0.194
Token with
Token ID351
Feature activation+5.03e-03

Pos logit contributions
pron+0.139
 yes+0.134
 Amen+0.125
 therapist+0.124
 ceremony+0.124
Neg logit contributions
elly-0.043
oky-0.041
 finds-0.038
umbles-0.037
 territory-0.036
Token her
Token ID607
Feature activation+8.16e-03

Pos logit contributions
oky+0.007
elly+0.007
angs+0.007
ases+0.007
 shadows+0.007
Neg logit contributions
 yes-0.011
pron-0.011
 ceremony-0.010
 therapist-0.010
 medal-0.010
Token mom
Token ID1995
Feature activation-6.08e-03

Pos logit contributions
 shadows+0.011
elly+0.011
oky+0.011
 tubes+0.011
 territory+0.011
Neg logit contributions
pron-0.016
 yes-0.016
 ceremony-0.016
 therapist-0.015
quet-0.015
Token and
Token ID290
Feature activation-3.93e-02

Pos logit contributions
 yes+0.018
pron+0.017
 ceremony+0.017
 therapist+0.017
 medal+0.017
Neg logit contributions
oky-0.004
elly-0.004
angs-0.003
urious-0.003
umbles-0.003
TokenCan
Token ID6090
Feature activation-4.42e-02

Pos logit contributions
oky+0.001
elly+0.001
 Why+0.001
 Maybe+0.001
urious+0.001
Neg logit contributions
 ceremony-0.002
pron-0.002
 goodbye-0.002
 yes-0.002
 medal-0.002
Token we
Token ID356
Feature activation-3.16e-02

Pos logit contributions
pron+0.117
 ceremony+0.111
 saddle+0.107
 couple+0.106
quet+0.104
Neg logit contributions
 Maybe-0.045
 Why-0.041
 Sam-0.040
 Don-0.038
 Jen-0.038
Token make
Token ID787
Feature activation-5.03e-02

Pos logit contributions
pron+0.077
 therapist+0.076
 yes+0.070
 ceremony+0.070
 couple+0.068
Neg logit contributions
ases-0.031
oky-0.031
 raining-0.030
 trash-0.030
 finds-0.030
Token a
Token ID257
Feature activation-3.66e-02

Pos logit contributions
pron+0.119
 yes+0.116
 therapist+0.113
 ceremony+0.111
 saddle+0.106
Neg logit contributions
 shadows-0.061
ases-0.058
oky-0.058
angs-0.058
 tubes-0.058
Token vacation
Token ID14600
Feature activation-4.60e-02

Pos logit contributions
 yes+0.068
 therapist+0.066
pron+0.062
quet+0.059
 ceremony+0.059
Neg logit contributions
 trash-0.062
oky-0.060
 shadows-0.059
 territory-0.057
 tubes-0.056
Token coll
Token ID2927
Feature activation-8.41e-02

Pos logit contributions
pron+0.107
 yes+0.107
 therapist+0.107
 ceremony+0.102
 saddle+0.101
Neg logit contributions
elly-0.050
oky-0.049
 finds-0.045
 raining-0.045
 trash-0.041
Tokenage
Token ID496
Feature activation-1.53e-02

Pos logit contributions
 therapist+0.159
pron+0.153
 yes+0.150
 ceremony+0.145
 medal+0.138
Neg logit contributions
ases-0.134
angs-0.121
umbles-0.118
ubs-0.116
OOOO-0.116
Token?"
Token ID1701
Feature activation-3.11e-02

Pos logit contributions
pron+0.036
 yes+0.036
 therapist+0.036
 ceremony+0.036
 couple+0.035
Neg logit contributions
oky-0.015
 raining-0.014
elly-0.014
ases-0.014
angs-0.013
Token Leo
Token ID19632
Feature activation-1.74e-02

Pos logit contributions
pron+0.091
quet+0.086
 medal+0.085
 ceremony+0.084
 saddle+0.084
Neg logit contributions
 Sam-0.022
oky-0.018
 shadows-0.017
 L-0.017
 raining-0.017
Token asked
Token ID1965
Feature activation-7.05e-03

Pos logit contributions
pron+0.041
quet+0.040
 ceremony+0.039
 medal+0.039
 yes+0.039
Neg logit contributions
en-0.018
urious-0.018
 wonders-0.018
elly-0.018
my-0.018
Token.
Token ID13
Feature activation-3.32e-03

Pos logit contributions
pron+0.018
 ceremony+0.018
 medal+0.017
 yes+0.017
 saddle+0.017
Neg logit contributions
angs-0.007
elly-0.006
oky-0.006
ases-0.006
umbles-0.006
Token their
Token ID511
Feature activation+1.86e-02

Pos logit contributions
 yes+0.032
pron+0.030
 ceremony+0.029
 medal+0.028
 couple+0.028
Neg logit contributions
oky-0.028
angs-0.027
elly-0.027
umbles-0.026
ases-0.025
Token salad
Token ID20698
Feature activation-2.98e-02

Pos logit contributions
oky+0.043
elly+0.042
angs+0.042
umbles+0.040
ases+0.040
Neg logit contributions
 yes-0.025
pron-0.024
 ceremony-0.023
 medal-0.021
 couple-0.020
Token and
Token ID290
Feature activation-7.42e-03

Pos logit contributions
pron+0.065
 yes+0.065
 therapist+0.063
 ceremony+0.061
 Amen+0.060
Neg logit contributions
elly-0.038
oky-0.037
 finds-0.037
 gaps-0.035
ases-0.035
Token have
Token ID423
Feature activation-2.57e-02

Pos logit contributions
pron+0.015
 yes+0.015
 therapist+0.015
 ceremony+0.015
 saddle+0.014
Neg logit contributions
 finds-0.011
 shadows-0.010
 gaps-0.010
 trash-0.010
 spiders-0.010
Token happy
Token ID3772
Feature activation-1.71e-02

Pos logit contributions
 yes+0.053
pron+0.053
 therapist+0.051
 ceremony+0.051
 medal+0.048
Neg logit contributions
oky-0.037
elly-0.036
 gaps-0.036
 shadows-0.035
angs-0.035
Token pic
Token ID8301
Feature activation-8.40e-02

Pos logit contributions
 yes+0.032
pron+0.031
 ceremony+0.030
 medal+0.028
 couple+0.028
Neg logit contributions
oky-0.030
angs-0.029
elly-0.029
umbles-0.027
urious-0.027
Tokenn
Token ID77
Feature activation-2.18e-02

Pos logit contributions
 therapist+0.133
pron+0.130
 couple+0.127
 yes+0.125
 pony+0.123
Neg logit contributions
ases-0.142
roc-0.140
OOOO-0.139
urious-0.138
iz-0.136
Tokenics
Token ID873
Feature activation-3.23e-02

Pos logit contributions
 yes+0.031
pron+0.030
 ceremony+0.029
 therapist+0.028
 medal+0.027
Neg logit contributions
umbles-0.047
ases-0.046
angs-0.046
oky-0.046
elly-0.045
Token together
Token ID1978
Feature activation-2.07e-02

Pos logit contributions
pron+0.077
 yes+0.070
 ceremony+0.068
 therapist+0.068
 saddle+0.064
Neg logit contributions
elly-0.040
ases-0.040
oky-0.039
 finds-0.037
 territory-0.036
Token.
Token ID13
Feature activation-9.07e-03

Pos logit contributions
pron+0.057
 therapist+0.055
 yes+0.055
 ceremony+0.054
 saddle+0.053
Neg logit contributions
elly-0.015
oky-0.015
ases-0.015
 raining-0.014
umbles-0.013
Token<|endoftext|>
Token ID50256
Feature activation+1.64e-02

Pos logit contributions
 yes+0.016
 goodbye+0.015
 ceremony+0.014
 couple+0.014
pron+0.014
Neg logit contributions
angs-0.017
oky-0.016
urious-0.015
 gaps-0.015
 pipes-0.015
Token,
Token ID11
Feature activation-2.91e-03

Pos logit contributions
oky+0.008
elly+0.008
 raining+0.008
 finds+0.008
umbles+0.008
Neg logit contributions
pron-0.019
 yes-0.019
 ceremony-0.018
 therapist-0.018
 medal-0.018
Token ready
Token ID3492
Feature activation-2.30e-02

Pos logit contributions
 yes+0.005
pron+0.005
 ceremony+0.005
 therapist+0.005
 medal+0.005
Neg logit contributions
oky-0.005
elly-0.005
 raining-0.004
angs-0.004
 gaps-0.004
Token to
Token ID284
Feature activation-2.54e-02

Pos logit contributions
pron+0.052
 yes+0.052
 therapist+0.051
 Amen+0.051
 ceremony+0.051
Neg logit contributions
oky-0.027
 raining-0.027
elly-0.026
 finds-0.025
OOOO-0.024
Token have
Token ID423
Feature activation-3.12e-02

Pos logit contributions
 therapist+0.063
pron+0.061
 yes+0.059
 couple+0.057
 saddle+0.055
Neg logit contributions
 raining-0.024
 finds-0.023
 shadows-0.023
 trash-0.023
 Sam-0.022
Token more
Token ID517
Feature activation-6.93e-03

Pos logit contributions
pron+0.071
 yes+0.070
 therapist+0.069
 ceremony+0.066
 Amen+0.066
Neg logit contributions
 raining-0.037
 trash-0.036
 shadows-0.036
oky-0.035
 gaps-0.035
Token pic
Token ID8301
Feature activation-8.38e-02

Pos logit contributions
pron+0.015
 yes+0.015
 therapist+0.015
 ceremony+0.014
 Amen+0.014
Neg logit contributions
elly-0.010
oky-0.009
 trash-0.009
 finds-0.009
 gaps-0.009
Tokenn
Token ID77
Feature activation-1.04e-02

Pos logit contributions
 therapist+0.143
pron+0.134
 pony+0.126
 yes+0.126
 Amen+0.123
Neg logit contributions
OOOO-0.135
ases-0.134
 finds-0.133
ubs-0.130
elly-0.130
Tokenics
Token ID873
Feature activation-3.39e-02

Pos logit contributions
 yes+0.014
pron+0.014
 ceremony+0.013
 therapist+0.013
 medal+0.012
Neg logit contributions
oky-0.023
umbles-0.023
elly-0.022
angs-0.022
ases-0.022
Token in
Token ID287
Feature activation+7.19e-03

Pos logit contributions
pron+0.091
 Amen+0.085
 yes+0.085
 therapist+0.083
 ceremony+0.081
Neg logit contributions
elly-0.028
 finds-0.026
oky-0.026
yards-0.025
ases-0.025
Token the
Token ID262
Feature activation+2.43e-02

Pos logit contributions
 raining+0.007
oky+0.007
 trash+0.007
elly+0.007
 gaps+0.006
Neg logit contributions
 yes-0.018
pron-0.018
 therapist-0.017
 medal-0.017
 saddle-0.017
Token future
Token ID2003
Feature activation-8.79e-03

Pos logit contributions
oky+0.031
elly+0.029
 trash+0.028
 gaps+0.028
 shadows+0.028
Neg logit contributions
 yes-0.057
pron-0.055
 ceremony-0.054
 therapist-0.053
 couple-0.051
Token,
Token ID11
Feature activation-8.48e-03

Pos logit contributions
 yes+0.013
pron+0.012
 ceremony+0.012
 goodbye+0.011
 medal+0.011
Neg logit contributions
oky-0.013
angs-0.013
urious-0.013
elly-0.013
 gaps-0.013
Token Lily
Token ID20037
Feature activation+8.68e-03

Pos logit contributions
 ceremony+0.018
 yes+0.017
pron+0.017
 therapist+0.017
 saddle+0.017
Neg logit contributions
oky-0.011
elly-0.011
 trash-0.011
 raining-0.011
 shadows-0.011
Token went
Token ID1816
Feature activation+4.70e-03

Pos logit contributions
angs+0.017
ases+0.016
oky+0.016
ric+0.015
arter+0.015
Neg logit contributions
pron-0.015
 yes-0.014
 ceremony-0.014
 therapist-0.014
 couple-0.013
Token to
Token ID284
Feature activation-3.85e-03

Pos logit contributions
oky+0.007
elly+0.007
angs+0.006
 raining+0.006
 shadows+0.006
Neg logit contributions
 yes-0.010
pron-0.010
 ceremony-0.009
 therapist-0.009
 couple-0.009
Token a
Token ID257
Feature activation-3.74e-02

Pos logit contributions
 yes+0.008
pron+0.007
 ceremony+0.007
 medal+0.007
 therapist+0.007
Neg logit contributions
oky-0.006
elly-0.006
angs-0.006
umbles-0.006
ases-0.006
Token carn
Token ID18466
Feature activation-8.33e-02

Pos logit contributions
 yes+0.080
 therapist+0.073
 Amen+0.071
quet+0.071
 ceremony+0.071
Neg logit contributions
oky-0.053
 trash-0.053
elly-0.052
 raining-0.050
 shadows-0.049
Tokenival
Token ID2473
Feature activation-4.86e-02

Pos logit contributions
 yes+0.087
 therapist+0.080
 ceremony+0.077
 saddle+0.076
pron+0.076
Neg logit contributions
elly-0.207
oky-0.204
urious-0.189
ases-0.187
angs-0.186
Token with
Token ID351
Feature activation+1.56e-02

Pos logit contributions
pron+0.125
 yes+0.124
 Amen+0.113
 therapist+0.112
 ceremony+0.112
Neg logit contributions
elly-0.050
oky-0.048
ases-0.042
 finds-0.042
umbles-0.042
Token her
Token ID607
Feature activation+1.11e-02

Pos logit contributions
oky+0.023
elly+0.023
angs+0.023
ases+0.022
umbles+0.022
Neg logit contributions
pron-0.032
 yes-0.032
 ceremony-0.030
 therapist-0.029
 medal-0.029
Token mom
Token ID1995
Feature activation+2.44e-03

Pos logit contributions
elly+0.017
oky+0.017
 shadows+0.017
angs+0.017
 territory+0.017
Neg logit contributions
pron-0.021
 yes-0.021
 ceremony-0.020
 therapist-0.019
 Amen-0.019
Tokenmy
Token ID1820
Feature activation+9.11e-03

Pos logit contributions
oky+0.002
elly+0.002
angs+0.002
umbles+0.002
 gaps+0.002
Neg logit contributions
 yes-0.007
pron-0.007
 ceremony-0.007
 therapist-0.006
 medal-0.006
Token mom
Token ID1995
Feature activation+1.00e-02

Pos logit contributions
 yes+0.003
 ceremony+0.003
 therapist+0.003
pron+0.003
quet+0.003
Neg logit contributions
 trash-0.002
 shadows-0.002
oky-0.002
 tubes-0.002
 raining-0.002
Tokenmy
Token ID1820
Feature activation-2.80e-03

Pos logit contributions
oky+0.003
elly+0.002
angs+0.002
urious+0.001
umbles+0.001
Neg logit contributions
 yes-0.033
pron-0.032
 ceremony-0.032
 medal-0.032
 therapist-0.032
Token put
Token ID1234
Feature activation-4.92e-03

Pos logit contributions
pron+0.007
 yes+0.007
 medal+0.007
 ceremony+0.007
 therapist+0.007
Neg logit contributions
oky-0.003
 finds-0.002
my-0.002
 trash-0.002
urious-0.002
Token on
Token ID319
Feature activation+2.69e-03

Pos logit contributions
 yes+0.011
 ceremony+0.011
pron+0.011
 therapist+0.010
quet+0.010
Neg logit contributions
 trash-0.006
oky-0.006
ays-0.006
 gaps-0.006
 tubes-0.006
Token their
Token ID511
Feature activation+6.98e-03

Pos logit contributions
oky+0.003
 trash+0.003
elly+0.003
 gaps+0.003
 pipes+0.003
Neg logit contributions
 yes-0.006
pron-0.006
 ceremony-0.006
 therapist-0.006
quet-0.006
Token apr
Token ID46593
Feature activation-8.29e-02

Pos logit contributions
 trash+0.012
 finds+0.012
oky+0.011
 raining+0.011
 pipes+0.011
Neg logit contributions
 therapist-0.012
 Amen-0.012
quet-0.012
 yes-0.012
 ceremony-0.012
Tokenons
Token ID684
Feature activation-2.57e-02

Pos logit contributions
 yes+0.178
 medal+0.162
 therapist+0.158
 goodbye+0.158
 couple+0.154
Neg logit contributions
urious-0.117
oky-0.116
ASH-0.114
ays-0.114
elly-0.114
Token and
Token ID290
Feature activation-2.29e-02

Pos logit contributions
 Amen+0.071
pron+0.070
 yes+0.069
 medal+0.068
 therapist+0.067
Neg logit contributions
oky-0.018
elly-0.017
my-0.016
ays-0.015
 tubes-0.015
Token started
Token ID2067
Feature activation+2.87e-03

Pos logit contributions
 yes+0.051
 ceremony+0.051
pron+0.050
 medal+0.049
quet+0.049
Neg logit contributions
 trash-0.028
 tubes-0.028
 pipes-0.027
 finds-0.027
oky-0.027
Token cooking
Token ID10801
Feature activation-1.97e-02

Pos logit contributions
 raining+0.004
oky+0.004
 pipes+0.003
umbles+0.003
 trash+0.003
Neg logit contributions
 yes-0.007
 medal-0.006
 therapist-0.006
 ceremony-0.006
pron-0.006
Token.
Token ID13
Feature activation+4.59e-03

Pos logit contributions
 yes+0.049
 ceremony+0.048
pron+0.048
 Amen+0.047
 therapist+0.047
Neg logit contributions
oky-0.020
 trash-0.020
 pipes-0.018
elly-0.018
 gaps-0.018
Token girl
Token ID2576
Feature activation-2.41e-03

Pos logit contributions
oky+0.012
elly+0.011
 trash+0.010
 shadows+0.010
 raining+0.010
Neg logit contributions
 yes-0.021
pron-0.020
 ceremony-0.020
 therapist-0.019
ves-0.019
Token named
Token ID3706
Feature activation+5.10e-03

Pos logit contributions
 yes+0.005
pron+0.004
 ceremony+0.004
 therapist+0.004
 couple+0.004
Neg logit contributions
oky-0.004
angs-0.004
elly-0.004
 gaps-0.004
umbles-0.004
Token Lily
Token ID20037
Feature activation+1.20e-02

Pos logit contributions
oky+0.007
elly+0.006
angs+0.006
ases+0.006
umbles+0.006
Neg logit contributions
 yes-0.012
pron-0.012
 ceremony-0.011
 therapist-0.011
 couple-0.011
Token who
Token ID508
Feature activation+1.11e-02

Pos logit contributions
oky+0.022
angs+0.022
 gaps+0.021
elly+0.021
ays+0.021
Neg logit contributions
 yes-0.020
pron-0.020
 ceremony-0.019
 Amen-0.018
 couple-0.018
Token loved
Token ID6151
Feature activation-3.46e-03

Pos logit contributions
oky+0.018
angs+0.017
elly+0.017
ases+0.016
 gaps+0.016
Neg logit contributions
 yes-0.023
pron-0.022
 ceremony-0.021
 therapist-0.020
 medal-0.020
Token pic
Token ID8301
Feature activation-8.29e-02

Pos logit contributions
 yes+0.008
pron+0.008
 ceremony+0.008
 therapist+0.008
 medal+0.007
Neg logit contributions
 raining-0.004
oky-0.004
 shadows-0.004
 spiders-0.004
 trash-0.004
Tokenn
Token ID77
Feature activation-6.24e-03

Pos logit contributions
 therapist+0.130
 yes+0.129
 couple+0.128
pron+0.123
 ceremony+0.121
Neg logit contributions
urious-0.139
en-0.134
iz-0.133
ubs-0.133
ASH-0.132
Tokenics
Token ID873
Feature activation-2.44e-02

Pos logit contributions
 yes+0.008
 ceremony+0.008
pron+0.008
 therapist+0.007
 medal+0.007
Neg logit contributions
oky-0.014
umbles-0.014
elly-0.014
angs-0.014
urious-0.013
Token.
Token ID13
Feature activation+1.21e-02

Pos logit contributions
pron+0.067
 yes+0.064
 ceremony+0.063
 therapist+0.061
 medal+0.061
Neg logit contributions
elly-0.022
oky-0.020
 raining-0.017
 trash-0.016
 because-0.016
Token She
Token ID1375
Feature activation+3.18e-03

Pos logit contributions
angs+0.018
oky+0.018
ases+0.017
elly+0.017
 territory+0.017
Neg logit contributions
 yes-0.025
pron-0.025
 ceremony-0.024
 therapist-0.022
 couple-0.022
Token would
Token ID561
Feature activation-3.57e-02

Pos logit contributions
 finds+0.004
elly+0.004
 raining+0.004
oky+0.004
 trash+0.004
Neg logit contributions
 yes-0.007
quet-0.007
pron-0.007
 ceremony-0.007
 medal-0.007
Token family
Token ID1641
Feature activation-1.38e-02

Pos logit contributions
pron+0.014
 Amen+0.013
quet+0.013
 ceremony+0.013
 yes+0.013
Neg logit contributions
 shadows-0.007
 trash-0.006
 spiders-0.006
 finds-0.006
 territory-0.006
Token were
Token ID547
Feature activation-9.75e-03

Pos logit contributions
pron+0.037
 yes+0.035
 Amen+0.035
 medal+0.035
quet+0.034
Neg logit contributions
 finds-0.011
my-0.010
umbles-0.010
oky-0.009
 trash-0.009
Token ready
Token ID3492
Feature activation-3.15e-02

Pos logit contributions
 yes+0.022
pron+0.022
 medal+0.022
 therapist+0.021
 ceremony+0.020
Neg logit contributions
 raining-0.012
umbles-0.011
oky-0.011
ained-0.011
 shadows-0.011
Token to
Token ID284
Feature activation-3.23e-02

Pos logit contributions
pron+0.077
 therapist+0.077
 Amen+0.074
 medal+0.074
 ceremony+0.073
Neg logit contributions
 raining-0.031
oky-0.029
elly-0.028
 finds-0.026
umbles-0.026
Token go
Token ID467
Feature activation-2.91e-02

Pos logit contributions
pron+0.082
 therapist+0.080
 yes+0.079
 couple+0.075
 ceremony+0.073
Neg logit contributions
 shadows-0.028
 drains-0.028
en-0.028
 trash-0.027
 finds-0.027
Token pic
Token ID8301
Feature activation-8.28e-02

Pos logit contributions
pron+0.069
 yes+0.067
 therapist+0.063
 ceremony+0.062
 medal+0.060
Neg logit contributions
oky-0.036
elly-0.036
 finds-0.035
 raining-0.035
ases-0.034
Tokenn
Token ID77
Feature activation-1.13e-02

Pos logit contributions
pron+0.150
 therapist+0.149
 yes+0.144
 medal+0.130
 couple+0.129
Neg logit contributions
en-0.125
ubs-0.122
 raining-0.120
eds-0.119
umbles-0.119
Tokenicking
Token ID7958
Feature activation-9.66e-03

Pos logit contributions
 yes+0.017
pron+0.017
 ceremony+0.015
 therapist+0.015
 medal+0.015
Neg logit contributions
umbles-0.023
oky-0.023
elly-0.023
angs-0.022
ubs-0.022
Token again
Token ID757
Feature activation-1.15e-02

Pos logit contributions
pron+0.025
 yes+0.024
 ceremony+0.023
 therapist+0.022
 medal+0.022
Neg logit contributions
 shadows-0.010
oky-0.010
elly-0.009
 raining-0.009
 gaps-0.009
Token.
Token ID13
Feature activation-9.24e-03

Pos logit contributions
pron+0.030
 yes+0.029
 ceremony+0.028
 therapist+0.028
 medal+0.028
Neg logit contributions
oky-0.011
elly-0.011
 raining-0.011
 territory-0.010
 shadows-0.010
Token But
Token ID887
Feature activation-5.88e-03

Pos logit contributions
 yes+0.022
pron+0.022
 ceremony+0.021
 medal+0.020
 therapist+0.020
Neg logit contributions
oky-0.011
elly-0.011
angs-0.010
umbles-0.010
 gaps-0.010
Token�
Token ID241
Feature activation+3.80e-03

Pos logit contributions
 yes+0.073
pron+0.070
 ceremony+0.069
 therapist+0.066
 medal+0.065
Neg logit contributions
oky-0.051
elly-0.049
angs-0.049
umbles-0.048
urious-0.047
TokenThank
Token ID10449
Feature activation-4.00e-02

Pos logit contributions
elly+0.006
oky+0.006
angs+0.005
umbles+0.005
ases+0.005
Neg logit contributions
 yes-0.008
 ceremony-0.008
pron-0.008
 medal-0.007
 therapist-0.007
Token you
Token ID345
Feature activation-1.34e-02

Pos logit contributions
pron+0.102
 saddle+0.097
 ceremony+0.096
 medal+0.094
 vows+0.090
Neg logit contributions
elly-0.038
 Why-0.038
ases-0.037
iz-0.034
 yourself-0.034
Token!
Token ID0
Feature activation-1.98e-02

Pos logit contributions
pron+0.032
 ceremony+0.031
 therapist+0.030
 medal+0.030
 yes+0.030
Neg logit contributions
elly-0.013
oky-0.012
 L-0.011
iz-0.011
angs-0.011
Token I
Token ID314
Feature activation-2.30e-02

Pos logit contributions
pron+0.048
 yes+0.048
 ceremony+0.047
 medal+0.045
 therapist+0.044
Neg logit contributions
elly-0.023
oky-0.023
angs-0.021
umbles-0.020
ases-0.020
Token recommend
Token ID4313
Feature activation-8.27e-02

Pos logit contributions
 yes+0.053
pron+0.052
 ceremony+0.052
 therapist+0.049
 medal+0.049
Neg logit contributions
oky-0.028
elly-0.028
angs-0.027
umbles-0.025
ases-0.025
Token this
Token ID428
Feature activation-5.22e-02

Pos logit contributions
pron+0.182
 Amen+0.179
 saddle+0.171
 ceremony+0.170
 therapist+0.167
Neg logit contributions
 spiders-0.088
 pipes-0.086
 Sam-0.084
 yourself-0.083
 comes-0.082
Token one
Token ID530
Feature activation-3.55e-02

Pos logit contributions
 yes+0.102
pron+0.098
 therapist+0.095
 ceremony+0.094
 Amen+0.093
Neg logit contributions
 trash-0.074
elly-0.073
oky-0.072
 raining-0.070
 finds-0.068
Token!
Token ID0
Feature activation-1.69e-02

Pos logit contributions
pron+0.078
 yes+0.078
 ceremony+0.078
 therapist+0.076
 Amen+0.075
Neg logit contributions
elly-0.042
oky-0.040
urious-0.038
 territory-0.037
 raining-0.036
Tokenâ
Token ID22940
Feature activation-1.53e-02

Pos logit contributions
pron+0.040
 yes+0.039
 ceremony+0.039
 medal+0.037
 therapist+0.036
Neg logit contributions
elly-0.020
oky-0.020
angs-0.018
umbles-0.018
ases-0.017
Token€
Token ID26391
Feature activation-3.28e-02

Pos logit contributions
 yes+0.030
pron+0.029
 ceremony+0.027
 couple+0.027
 medal+0.027
Neg logit contributions
oky-0.025
elly-0.024
ASH-0.023
urious-0.023
umbles-0.022
Token a
Token ID257
Feature activation-2.81e-02

Pos logit contributions
oky+0.036
elly+0.035
angs+0.035
umbles+0.033
 gaps+0.033
Neg logit contributions
 yes-0.049
pron-0.047
 ceremony-0.046
 therapist-0.044
 medal-0.044
Token family
Token ID1641
Feature activation-2.14e-02

Pos logit contributions
 yes+0.067
 ceremony+0.066
 therapist+0.064
pron+0.063
quet+0.063
Neg logit contributions
oky-0.031
elly-0.030
 trash-0.029
 raining-0.027
 shadows-0.026
Token who
Token ID508
Feature activation+1.60e-02

Pos logit contributions
 yes+0.048
pron+0.047
 ceremony+0.045
 therapist+0.044
 medal+0.044
Neg logit contributions
oky-0.029
elly-0.029
angs-0.027
umbles-0.026
ases-0.026
Token really
Token ID1107
Feature activation+5.68e-03

Pos logit contributions
oky+0.026
elly+0.025
angs+0.025
 gaps+0.024
urious+0.023
Neg logit contributions
 yes-0.032
pron-0.031
 ceremony-0.030
 therapist-0.029
 couple-0.028
Token enjoyed
Token ID8359
Feature activation-1.41e-03

Pos logit contributions
oky+0.007
elly+0.007
angs+0.007
umbles+0.006
ases+0.006
Neg logit contributions
 yes-0.013
pron-0.013
 ceremony-0.013
 therapist-0.012
 medal-0.012
Token pic
Token ID8301
Feature activation-8.17e-02

Pos logit contributions
 therapist+0.004
 yes+0.004
pron+0.003
 ceremony+0.003
quet+0.003
Neg logit contributions
 raining-0.002
 shadows-0.001
 pipes-0.001
 spiders-0.001
 tubes-0.001
Tokenn
Token ID77
Feature activation-3.01e-04

Pos logit contributions
 therapist+0.137
 yes+0.133
pron+0.132
 couple+0.129
 medal+0.124
Neg logit contributions
ubs-0.132
en-0.131
urious-0.127
ills-0.126
iz-0.126
Tokenics
Token ID873
Feature activation-3.14e-02

Pos logit contributions
 yes+0.000
pron+0.000
 ceremony+0.000
 therapist+0.000
 medal+0.000
Neg logit contributions
oky-0.001
elly-0.001
angs-0.001
umbles-0.001
urious-0.001
Token.
Token ID13
Feature activation+9.42e-03

Pos logit contributions
pron+0.090
 yes+0.086
 ceremony+0.084
 therapist+0.084
 medal+0.081
Neg logit contributions
elly-0.021
oky-0.020
 raining-0.019
 because-0.018
 than-0.017
Token They
Token ID1119
Feature activation-1.58e-02

Pos logit contributions
angs+0.011
oky+0.011
elly+0.011
ases+0.010
urious+0.010
Neg logit contributions
 yes-0.023
pron-0.022
 ceremony-0.022
 couple-0.021
 therapist-0.021
Token loved
Token ID6151
Feature activation-1.14e-02

Pos logit contributions
pron+0.039
 yes+0.038
 ceremony+0.037
quet+0.037
 therapist+0.037
Neg logit contributions
 raining-0.015
 finds-0.014
 trash-0.014
elly-0.014
oky-0.014
Token liked
Token ID8288
Feature activation-5.77e-03

Pos logit contributions
 yes+0.029
pron+0.028
 ceremony+0.028
 therapist+0.026
 medal+0.026
Neg logit contributions
oky-0.019
elly-0.018
angs-0.018
 gaps-0.017
umbles-0.017
Token to
Token ID284
Feature activation+3.75e-03

Pos logit contributions
 yes+0.012
pron+0.012
 ceremony+0.012
 therapist+0.012
quet+0.011
Neg logit contributions
oky-0.008
elly-0.008
 raining-0.008
 shadows-0.008
angs-0.008
Token play
Token ID711
Feature activation-2.29e-02

Pos logit contributions
ases+0.004
 tubes+0.004
 shadows+0.004
 pipes+0.004
 raining+0.004
Neg logit contributions
pron-0.009
 therapist-0.009
 yes-0.008
 ceremony-0.008
 couple-0.008
Token and
Token ID290
Feature activation+7.78e-03

Pos logit contributions
pron+0.044
 yes+0.044
 ceremony+0.044
 therapist+0.042
 couple+0.040
Neg logit contributions
oky-0.036
elly-0.035
ases-0.035
 shadows-0.034
angs-0.034
Token have
Token ID423
Feature activation+2.43e-03

Pos logit contributions
 raining+0.009
 shadows+0.009
 tubes+0.008
 finds+0.008
 pipes+0.008
Neg logit contributions
pron-0.019
 therapist-0.019
 ceremony-0.018
quet-0.018
 yes-0.018
Token pic
Token ID8301
Feature activation-8.14e-02

Pos logit contributions
oky+0.004
elly+0.004
angs+0.004
 gaps+0.004
 shadows+0.004
Neg logit contributions
pron-0.005
 yes-0.005
 ceremony-0.005
 therapist-0.004
 medal-0.004
Tokenn
Token ID77
Feature activation-2.09e-03

Pos logit contributions
 therapist+0.129
pron+0.122
 yes+0.119
 couple+0.118
 ceremony+0.117
Neg logit contributions
ases-0.148
ubs-0.146
umbles-0.144
urious-0.143
angs-0.142
Tokenics
Token ID873
Feature activation-1.90e-02

Pos logit contributions
 yes+0.003
pron+0.003
 ceremony+0.003
 therapist+0.002
 couple+0.002
Neg logit contributions
oky-0.005
umbles-0.005
angs-0.005
elly-0.005
ases-0.005
Token.
Token ID13
Feature activation+4.23e-03

Pos logit contributions
pron+0.047
 therapist+0.044
 ceremony+0.044
 yes+0.043
quet+0.042
Neg logit contributions
elly-0.020
ases-0.020
oky-0.019
 finds-0.018
yards-0.018
Token One
Token ID1881
Feature activation+4.06e-03

Pos logit contributions
angs+0.008
oky+0.007
elly+0.007
ases+0.007
umbles+0.007
Neg logit contributions
 yes-0.008
pron-0.007
 ceremony-0.007
 couple-0.006
 goodbye-0.006
Token day
Token ID1110
Feature activation-1.48e-02

Pos logit contributions
oky+0.008
elly+0.008
angs+0.008
umbles+0.007
urious+0.007
Neg logit contributions
 yes-0.007
pron-0.006
 ceremony-0.006
 therapist-0.006
 medal-0.006
Token a
Token ID257
Feature activation-1.87e-02

Pos logit contributions
oky+0.042
elly+0.041
angs+0.041
 gaps+0.038
umbles+0.038
Neg logit contributions
 yes-0.060
pron-0.058
 ceremony-0.057
 therapist-0.054
 medal-0.054
Token boat
Token ID8848
Feature activation-1.38e-03

Pos logit contributions
 yes+0.042
 ceremony+0.040
pron+0.039
 therapist+0.038
 goodbye+0.037
Neg logit contributions
oky-0.026
 trash-0.024
elly-0.024
 gaps-0.024
 shadows-0.024
Token on
Token ID319
Feature activation+2.86e-02

Pos logit contributions
pron+0.003
 yes+0.003
 ceremony+0.003
 therapist+0.003
 couple+0.003
Neg logit contributions
oky-0.002
angs-0.002
elly-0.002
ases-0.002
umbles-0.002
Token the
Token ID262
Feature activation+1.61e-02

Pos logit contributions
oky+0.035
 gaps+0.033
elly+0.033
 shadows+0.032
angs+0.032
Neg logit contributions
 yes-0.068
pron-0.067
 ceremony-0.065
 therapist-0.062
 medal-0.060
Token river
Token ID7850
Feature activation+1.04e-02

Pos logit contributions
oky+0.018
 gaps+0.018
 shadows+0.018
 pipes+0.018
 trash+0.017
Neg logit contributions
 yes-0.040
pron-0.039
 ceremony-0.037
 therapist-0.036
quet-0.035
Token.
Token ID13
Feature activation+4.29e-02

Pos logit contributions
oky+0.013
elly+0.012
angs+0.012
umbles+0.011
 gaps+0.011
Neg logit contributions
 yes-0.025
pron-0.024
 ceremony-0.024
 therapist-0.023
 medal-0.022
Token The
Token ID383
Feature activation+2.12e-03

Pos logit contributions
oky+0.043
elly+0.041
angs+0.038
 gaps+0.036
umbles+0.036
Neg logit contributions
 yes-0.112
pron-0.112
 ceremony-0.109
 medal-0.104
 therapist-0.103
Token boat
Token ID8848
Feature activation+1.23e-02

Pos logit contributions
 gaps+0.004
oky+0.004
 pipes+0.003
 shadows+0.003
 trash+0.003
Neg logit contributions
 yes-0.004
pron-0.004
 ceremony-0.004
 therapist-0.004
quet-0.004
Token is
Token ID318
Feature activation+6.22e-03

Pos logit contributions
oky+0.011
elly+0.010
angs+0.010
 gaps+0.010
ases+0.010
Neg logit contributions
 yes-0.033
pron-0.033
 ceremony-0.032
 therapist-0.031
 couple-0.030
Token empty
Token ID6565
Feature activation+3.44e-02

Pos logit contributions
oky+0.008
angs+0.008
 raining+0.008
 gaps+0.008
umbles+0.008
Neg logit contributions
 yes-0.014
pron-0.014
 ceremony-0.014
 therapist-0.013
 couple-0.013
Token.
Token ID13
Feature activation+4.00e-02

Pos logit contributions
oky+0.045
elly+0.043
angs+0.043
 gaps+0.040
umbles+0.040
Neg logit contributions
 yes-0.079
pron-0.077
 ceremony-0.076
 therapist-0.072
 medal-0.071
Token.
Token ID13
Feature activation+1.98e-02

Pos logit contributions
oky+0.074
angs+0.072
elly+0.071
ases+0.067
umbles+0.067
Neg logit contributions
 yes-0.138
pron-0.132
 ceremony-0.129
 therapist-0.124
 medal-0.123
Token
Token ID198
Feature activation+5.65e-03

Pos logit contributions
angs+0.038
ases+0.038
 territory+0.035
 gaps+0.035
oky+0.034
Neg logit contributions
 yes-0.035
pron-0.031
 therapist-0.029
 goodbye-0.029
 couple-0.029
Token
Token ID198
Feature activation+2.10e-04

Pos logit contributions
oky+0.008
elly+0.008
angs+0.008
 gaps+0.007
ases+0.007
Neg logit contributions
 yes-0.012
pron-0.012
 ceremony-0.011
 therapist-0.011
 medal-0.011
TokenTom
Token ID13787
Feature activation+1.70e-02

Pos logit contributions
oky+0.000
elly+0.000
urious+0.000
angs+0.000
umbles+0.000
Neg logit contributions
 yes-0.000
 ceremony-0.000
pron-0.000
 medal-0.000
 therapist-0.000
Tokenmy
Token ID1820
Feature activation+2.66e-02

Pos logit contributions
oky+0.016
elly+0.015
ases+0.014
angs+0.014
 gaps+0.013
Neg logit contributions
 yes-0.046
pron-0.046
 ceremony-0.043
 therapist-0.042
 saddle-0.041
Token looked
Token ID3114
Feature activation+4.54e-02

Pos logit contributions
oky+0.034
angs+0.032
elly+0.032
urious+0.031
umbles+0.031
Neg logit contributions
 yes-0.060
pron-0.060
 ceremony-0.059
 medal-0.055
 therapist-0.055
Token around
Token ID1088
Feature activation+3.90e-02

Pos logit contributions
oky+0.072
ases+0.071
elly+0.070
ASH+0.070
angs+0.070
Neg logit contributions
 yes-0.092
 goodbye-0.084
pron-0.083
 ceremony-0.083
 medal-0.080
Token and
Token ID290
Feature activation-6.00e-04

Pos logit contributions
oky+0.051
elly+0.050
angs+0.049
umbles+0.046
ases+0.046
Neg logit contributions
 yes-0.090
pron-0.087
 ceremony-0.086
 therapist-0.081
 medal-0.081
Token saw
Token ID2497
Feature activation+3.33e-02

Pos logit contributions
 yes+0.001
pron+0.001
 ceremony+0.001
 therapist+0.001
 couple+0.001
Neg logit contributions
oky-0.001
elly-0.001
angs-0.001
ases-0.001
umbles-0.001
Token the
Token ID262
Feature activation+9.37e-03

Pos logit contributions
oky+0.051
elly+0.050
angs+0.049
umbles+0.046
urious+0.046
Neg logit contributions
 yes-0.069
pron-0.067
 ceremony-0.066
 therapist-0.063
 medal-0.062
Token rows
Token ID15274
Feature activation-7.49e-03

Pos logit contributions
oky+0.014
elly+0.014
angs+0.013
umbles+0.013
ases+0.013
Neg logit contributions
 yes-0.020
pron-0.019
 ceremony-0.019
 medal-0.018
 couple-0.018
Token to
Token ID284
Feature activation-1.21e-02

Pos logit contributions
oky+0.032
elly+0.030
angs+0.030
 shadows+0.029
 gaps+0.029
Neg logit contributions
pron-0.071
 ceremony-0.067
 yes-0.066
 therapist-0.065
 medal-0.063
Token Anna
Token ID11735
Feature activation+1.19e-02

Pos logit contributions
pron+0.031
 ceremony+0.029
quet+0.028
 yes+0.028
 medal+0.028
Neg logit contributions
 finds-0.012
 spiders-0.012
 shadows-0.012
 trash-0.012
 hears-0.011
Token.
Token ID13
Feature activation+8.36e-03

Pos logit contributions
angs+0.010
elly+0.009
oky+0.009
umbles+0.009
 finds+0.009
Neg logit contributions
pron-0.032
 yes-0.032
 ceremony-0.031
 therapist-0.030
 couple-0.030
Token Anna
Token ID11735
Feature activation-4.60e-03

Pos logit contributions
oky+0.010
elly+0.010
 gaps+0.009
angs+0.009
umbles+0.009
Neg logit contributions
 yes-0.020
 ceremony-0.020
pron-0.020
 medal-0.019
 couple-0.018
Token reached
Token ID4251
Feature activation+1.52e-02

Pos logit contributions
pron+0.010
 yes+0.010
 ceremony+0.010
 medal+0.009
 therapist+0.009
Neg logit contributions
oky-0.006
 finds-0.006
elly-0.006
angs-0.006
umbles-0.005
Token out
Token ID503
Feature activation+4.19e-02

Pos logit contributions
oky+0.017
elly+0.017
angs+0.016
umbles+0.015
 gaps+0.015
Neg logit contributions
 yes-0.038
pron-0.037
 ceremony-0.036
 therapist-0.034
 medal-0.034
Token her
Token ID607
Feature activation+2.05e-02

Pos logit contributions
oky+0.063
elly+0.062
angs+0.061
ases+0.058
umbles+0.057
Neg logit contributions
pron-0.087
 yes-0.086
 ceremony-0.084
 therapist-0.080
 medal-0.079
Token hand
Token ID1021
Feature activation+6.04e-03

Pos logit contributions
oky+0.022
elly+0.022
angs+0.022
 gaps+0.021
 territory+0.021
Neg logit contributions
 yes-0.050
pron-0.050
 ceremony-0.048
 therapist-0.048
 medal-0.046
Token and
Token ID290
Feature activation-3.09e-02

Pos logit contributions
oky+0.005
angs+0.005
elly+0.005
 raining+0.004
umbles+0.004
Neg logit contributions
pron-0.016
 ceremony-0.016
 medal-0.015
 couple-0.015
 therapist-0.015
Token the
Token ID262
Feature activation-3.68e-03

Pos logit contributions
pron+0.067
 ceremony+0.066
 yes+0.065
 Amen+0.062
quet+0.061
Neg logit contributions
 finds-0.038
 trash-0.038
oky-0.038
 shadows-0.037
 gaps-0.037
Token bird
Token ID6512
Feature activation-5.88e-03

Pos logit contributions
 yes+0.008
pron+0.008
 Amen+0.007
 ceremony+0.007
 therapist+0.007
Neg logit contributions
 shadows-0.005
 trash-0.005
 gaps-0.005
oky-0.005
 finds-0.005
Token the
Token ID262
Feature activation-7.27e-03

Pos logit contributions
oky+0.034
elly+0.034
angs+0.033
urious+0.030
umbles+0.030
Neg logit contributions
 yes-0.042
 ceremony-0.039
pron-0.038
 couple-0.037
 therapist-0.036
Token goat
Token ID26917
Feature activation+1.77e-02

Pos logit contributions
 yes+0.014
pron+0.013
 ceremony+0.013
 therapist+0.012
 medal+0.012
Neg logit contributions
oky-0.013
elly-0.012
 trash-0.012
angs-0.012
 shadows-0.012
Token.
Token ID13
Feature activation+4.13e-02

Pos logit contributions
angs+0.013
oky+0.013
 shadows+0.013
 spiders+0.012
umbles+0.012
Neg logit contributions
pron-0.051
 ceremony-0.048
 yes-0.048
 therapist-0.046
 couple-0.046
Token Mia
Token ID32189
Feature activation+2.67e-02

Pos logit contributions
oky+0.059
elly+0.058
angs+0.058
urious+0.055
 gaps+0.053
Neg logit contributions
 yes-0.091
pron-0.086
 ceremony-0.083
 therapist-0.080
 couple-0.080
Token b
Token ID275
Feature activation-4.25e-03

Pos logit contributions
oky+0.037
elly+0.036
angs+0.035
umbles+0.033
 gaps+0.033
Neg logit contributions
 yes-0.059
pron-0.058
 ceremony-0.057
 therapist-0.054
 medal-0.053
Tokenanged
Token ID5102
Feature activation+4.50e-02

Pos logit contributions
 yes+0.011
 ceremony+0.010
pron+0.010
 couple+0.010
 therapist+0.010
Neg logit contributions
 shadows-0.004
 territory-0.004
oky-0.004
 raining-0.004
 gaps-0.004
Token the
Token ID262
Feature activation+1.73e-02

Pos logit contributions
oky+0.080
elly+0.078
angs+0.077
umbles+0.073
 gaps+0.073
Neg logit contributions
 yes-0.084
pron-0.081
 ceremony-0.079
 therapist-0.074
 medal-0.074
Token pot
Token ID1787
Feature activation+2.81e-02

Pos logit contributions
oky+0.026
angs+0.025
 trash+0.025
 gaps+0.025
elly+0.025
Neg logit contributions
 yes-0.038
 ceremony-0.035
pron-0.035
 medal-0.033
 therapist-0.032
Token with
Token ID351
Feature activation+4.06e-02

Pos logit contributions
oky+0.031
angs+0.030
elly+0.029
 gaps+0.028
ases+0.028
Neg logit contributions
pron-0.070
 ceremony-0.068
 yes-0.068
 therapist-0.065
 couple-0.064
Token a
Token ID257
Feature activation+4.38e-03

Pos logit contributions
oky+0.070
elly+0.070
urious+0.066
angs+0.065
 territory+0.063
Neg logit contributions
 yes-0.080
 ceremony-0.072
pron-0.072
 medal-0.070
 goodbye-0.070
Token spoon
Token ID24556
Feature activation+2.27e-02

Pos logit contributions
oky+0.006
angs+0.006
elly+0.006
 trash+0.006
 gaps+0.006
Neg logit contributions
 yes-0.009
 ceremony-0.009
pron-0.009
 therapist-0.009
 couple-0.008
Token was
Token ID373
Feature activation+1.38e-02

Pos logit contributions
oky+0.033
elly+0.032
angs+0.031
urious+0.030
ases+0.029
Neg logit contributions
 yes-0.045
pron-0.044
 ceremony-0.043
 therapist-0.041
 medal-0.040
Token so
Token ID523
Feature activation+2.64e-03

Pos logit contributions
oky+0.020
elly+0.020
angs+0.019
ases+0.018
urious+0.018
Neg logit contributions
 yes-0.029
pron-0.029
 ceremony-0.028
 therapist-0.027
 medal-0.026
Token strong
Token ID1913
Feature activation+3.18e-03

Pos logit contributions
oky+0.004
elly+0.004
angs+0.003
umbles+0.003
 gaps+0.003
Neg logit contributions
 yes-0.006
pron-0.006
 ceremony-0.006
 therapist-0.005
 medal-0.005
Token that
Token ID326
Feature activation+1.06e-02

Pos logit contributions
oky+0.005
elly+0.005
angs+0.005
 gaps+0.005
ases+0.005
Neg logit contributions
 yes-0.006
pron-0.006
 ceremony-0.006
 therapist-0.005
 couple-0.005
Token it
Token ID340
Feature activation+1.92e-02

Pos logit contributions
oky+0.019
 raining+0.018
 shadows+0.018
elly+0.018
 gaps+0.018
Neg logit contributions
 yes-0.018
pron-0.018
 ceremony-0.018
 saddle-0.017
 therapist-0.016
Token knocked
Token ID13642
Feature activation+4.57e-02

Pos logit contributions
oky+0.029
elly+0.029
angs+0.028
ases+0.027
urious+0.026
Neg logit contributions
 yes-0.040
pron-0.039
 ceremony-0.038
 therapist-0.036
 medal-0.036
Token over
Token ID625
Feature activation+5.17e-02

Pos logit contributions
oky+0.065
angs+0.065
elly+0.065
urious+0.064
 territory+0.061
Neg logit contributions
 yes-0.096
pron-0.093
 ceremony-0.089
 therapist-0.086
 goodbye-0.085
Token all
Token ID477
Feature activation+4.43e-02

Pos logit contributions
oky+0.083
angs+0.083
elly+0.081
urious+0.079
umbles+0.078
Neg logit contributions
 yes-0.104
pron-0.097
 ceremony-0.096
 couple-0.091
 goodbye-0.090
Token the
Token ID262
Feature activation+1.80e-02

Pos logit contributions
angs+0.074
oky+0.073
elly+0.072
urious+0.069
 territory+0.069
Neg logit contributions
 yes-0.082
 ceremony-0.081
pron-0.080
 therapist-0.075
 goodbye-0.073
Token furniture
Token ID13091
Feature activation+1.55e-03

Pos logit contributions
oky+0.024
elly+0.024
angs+0.024
umbles+0.023
ases+0.023
Neg logit contributions
 yes-0.040
pron-0.039
 ceremony-0.039
 therapist-0.036
 couple-0.036
Token and
Token ID290
Feature activation+2.64e-03

Pos logit contributions
oky+0.001
elly+0.001
 gaps+0.001
angs+0.001
umbles+0.001
Neg logit contributions
pron-0.004
 yes-0.004
 ceremony-0.004
 medal-0.004
 Amen-0.004
Token grabbed
Token ID13176
Feature activation+6.71e-03

Pos logit contributions
angs+0.036
oky+0.035
ric+0.034
arter+0.034
ases+0.034
Neg logit contributions
pron-0.033
 ceremony-0.033
 yes-0.033
 therapist-0.033
 couple-0.032
Token some
Token ID617
Feature activation+4.41e-03

Pos logit contributions
oky+0.010
elly+0.010
angs+0.010
 gaps+0.009
ases+0.009
Neg logit contributions
 yes-0.014
pron-0.014
 ceremony-0.013
 therapist-0.013
 medal-0.012
Token clay
Token ID21558
Feature activation-1.94e-02

Pos logit contributions
oky+0.006
elly+0.006
angs+0.006
 gaps+0.005
 trash+0.005
Neg logit contributions
 yes-0.010
pron-0.010
 ceremony-0.010
 therapist-0.009
 medal-0.009
Token and
Token ID290
Feature activation-9.49e-03

Pos logit contributions
 yes+0.044
pron+0.043
 ceremony+0.042
 therapist+0.040
 medal+0.040
Neg logit contributions
oky-0.026
elly-0.025
angs-0.024
 gaps-0.023
ases-0.023
Token paint
Token ID7521
Feature activation-1.22e-02

Pos logit contributions
 yes+0.021
pron+0.020
 ceremony+0.020
 therapist+0.019
 medal+0.019
Neg logit contributions
oky-0.013
elly-0.013
angs-0.013
 gaps-0.012
 trash-0.012
Token and
Token ID290
Feature activation-2.45e-03

Pos logit contributions
 yes+0.027
pron+0.027
 ceremony+0.026
 therapist+0.025
 medal+0.025
Neg logit contributions
oky-0.017
elly-0.016
angs-0.016
 gaps-0.015
ases-0.015
Token brought
Token ID3181
Feature activation-9.95e-03

Pos logit contributions
 yes+0.006
pron+0.005
 ceremony+0.005
 therapist+0.005
 medal+0.005
Neg logit contributions
oky-0.003
 gaps-0.003
angs-0.003
elly-0.003
 shadows-0.003
Token them
Token ID606
Feature activation-1.16e-02

Pos logit contributions
 yes+0.019
pron+0.018
 ceremony+0.018
 therapist+0.018
 medal+0.017
Neg logit contributions
oky-0.017
 gaps-0.016
 shadows-0.016
angs-0.016
 trash-0.016
Token outside
Token ID2354
Feature activation+1.17e-02

Pos logit contributions
pron+0.027
 therapist+0.027
 yes+0.026
 ceremony+0.026
 Amen+0.026
Neg logit contributions
angs-0.014
oky-0.014
 gaps-0.013
ases-0.013
 trash-0.013
Token.
Token ID13
Feature activation+1.44e-02

Pos logit contributions
 raining+0.009
oky+0.009
elly+0.009
 shadows+0.008
angs+0.008
Neg logit contributions
 yes-0.032
pron-0.032
 ceremony-0.031
 medal-0.031
 therapist-0.031
Token She
Token ID1375
Feature activation+6.07e-03

Pos logit contributions
oky+0.020
elly+0.020
angs+0.020
ases+0.018
 gaps+0.018
Neg logit contributions
 yes-0.031
pron-0.030
 ceremony-0.030
 therapist-0.029
 couple-0.028
Token she
Token ID673
Feature activation-1.30e-02

Pos logit contributions
pron+0.080
 saddle+0.075
 ceremony+0.072
 timer+0.071
nes+0.070
Neg logit contributions
 accidents-0.032
 Why-0.031
 because-0.031
 Sam-0.030
 or-0.029
Token was
Token ID373
Feature activation-3.33e-02

Pos logit contributions
 ceremony+0.030
pron+0.030
 yes+0.029
 couple+0.028
 medal+0.028
Neg logit contributions
elly-0.015
urious-0.015
oky-0.014
 finds-0.014
angs-0.014
Token going
Token ID1016
Feature activation-2.87e-02

Pos logit contributions
pron+0.078
ves+0.078
 therapist+0.077
 saddle+0.076
 medal+0.076
Neg logit contributions
 raining-0.034
 afraid-0.034
 scared-0.030
 apart-0.029
 Why-0.028
Token to
Token ID284
Feature activation-1.61e-02

Pos logit contributions
pron+0.068
 yes+0.066
 ceremony+0.064
 therapist+0.064
 Amen+0.062
Neg logit contributions
oky-0.032
elly-0.031
 raining-0.031
 finds-0.031
ases-0.030
Token keep
Token ID1394
Feature activation-1.84e-02

Pos logit contributions
pron+0.037
 therapist+0.035
 yes+0.034
 ceremony+0.033
 saddle+0.033
Neg logit contributions
 shadows-0.019
 raining-0.019
 trash-0.018
 finds-0.018
 causes-0.018
Token her
Token ID607
Feature activation+1.35e-02

Pos logit contributions
pron+0.044
 yes+0.043
 ceremony+0.042
 therapist+0.041
 medal+0.041
Neg logit contributions
 shadows-0.020
 raining-0.020
 spiders-0.018
 trash-0.018
 finds-0.018
Token promise
Token ID6991
Feature activation-1.09e-02

Pos logit contributions
 territory+0.019
 shadows+0.019
 raining+0.018
 trash+0.018
 finds+0.017
Neg logit contributions
pron-0.028
 therapist-0.026
 yes-0.026
 ceremony-0.026
 couple-0.025
Token and
Token ID290
Feature activation-3.91e-02

Pos logit contributions
pron+0.029
 ceremony+0.028
 Amen+0.027
 therapist+0.027
 couple+0.027
Neg logit contributions
 raining-0.008
elly-0.008
 apart-0.008
 because-0.008
umbles-0.007
Token she
Token ID673
Feature activation-2.20e-02

Pos logit contributions
pron+0.088
 yes+0.077
 ceremony+0.077
 saddle+0.076
 couple+0.076
Neg logit contributions
 finds-0.050
 shadows-0.047
fired-0.046
 causes-0.045
 Sam-0.045
Token ran
Token ID4966
Feature activation-1.29e-02

Pos logit contributions
pron+0.054
 ceremony+0.052
quet+0.050
 couple+0.049
 yes+0.049
Neg logit contributions
 finds-0.021
 wasn-0.020
 wonders-0.019
my-0.019
urious-0.018
Token off
Token ID572
Feature activation+1.53e-02

Pos logit contributions
pron+0.034
 yes+0.032
 ceremony+0.030
 therapist+0.030
 Amen+0.030
Neg logit contributions
 apart-0.013
 shadows-0.013
oky-0.013
elly-0.012
en-0.012
Token been
Token ID587
Feature activation+4.05e-02

Pos logit contributions
oky+0.023
elly+0.022
angs+0.022
 gaps+0.020
umbles+0.020
Neg logit contributions
 yes-0.036
pron-0.035
 ceremony-0.034
 therapist-0.033
 medal-0.032
Token there
Token ID612
Feature activation+4.27e-03

Pos logit contributions
oky+0.057
elly+0.055
angs+0.054
umbles+0.051
urious+0.051
Neg logit contributions
 yes-0.089
pron-0.087
 ceremony-0.085
 therapist-0.081
 medal-0.080
Token for
Token ID329
Feature activation+6.55e-03

Pos logit contributions
oky+0.005
elly+0.005
angs+0.005
 raining+0.004
 gaps+0.004
Neg logit contributions
pron-0.010
 yes-0.010
 ceremony-0.010
 therapist-0.010
 medal-0.010
Token a
Token ID257
Feature activation-3.83e-02

Pos logit contributions
oky+0.008
 shadows+0.008
 gaps+0.008
angs+0.008
elly+0.008
Neg logit contributions
pron-0.015
 yes-0.015
 ceremony-0.014
 therapist-0.014
 medal-0.013
Token long
Token ID890
Feature activation-1.71e-02

Pos logit contributions
 therapist+0.070
 ceremony+0.068
 yes+0.067
quet+0.067
pron+0.066
Neg logit contributions
 raining-0.057
 trash-0.056
oky-0.055
 spiders-0.053
 shadows-0.052
Token time
Token ID640
Feature activation+1.94e-03

Pos logit contributions
 yes+0.044
 therapist+0.042
 ceremony+0.041
pron+0.041
quet+0.041
Neg logit contributions
 raining-0.015
elly-0.015
oky-0.015
 finds-0.014
 gaps-0.014
Token.
Token ID13
Feature activation-8.65e-03

Pos logit contributions
oky+0.002
elly+0.002
angs+0.002
 gaps+0.002
umbles+0.002
Neg logit contributions
 yes-0.005
pron-0.005
 ceremony-0.004
 therapist-0.004
 medal-0.004
Token He
Token ID679
Feature activation-8.61e-03

Pos logit contributions
 yes+0.021
pron+0.021
 ceremony+0.020
 medal+0.020
 therapist+0.019
Neg logit contributions
oky-0.010
elly-0.010
angs-0.009
umbles-0.009
 gaps-0.009
Token was
Token ID373
Feature activation-1.18e-02

Pos logit contributions
pron+0.021
 yes+0.020
 ceremony+0.020
quet+0.019
 medal+0.019
Neg logit contributions
oky-0.009
elly-0.009
urious-0.009
 finds-0.009
angs-0.009
Token curious
Token ID11040
Feature activation+9.62e-03

Pos logit contributions
pron+0.026
 yes+0.026
 ceremony+0.025
 medal+0.025
 therapist+0.025
Neg logit contributions
 raining-0.015
oky-0.014
umbles-0.014
angs-0.014
 shadows-0.014
Token and
Token ID290
Feature activation-2.78e-02

Pos logit contributions
oky+0.011
elly+0.011
angs+0.010
 shadows+0.010
urious+0.010
Neg logit contributions
pron-0.023
 yes-0.023
 ceremony-0.023
 therapist-0.022
 medal-0.021
Token learned
Token ID4499
Feature activation+3.68e-03

Pos logit contributions
pron+0.038
 yes+0.035
 therapist+0.035
quet+0.034
 ceremony+0.034
Neg logit contributions
 shadows-0.015
 finds-0.015
 raining-0.015
 tubes-0.014
 spiders-0.014
Token new
Token ID649
Feature activation-1.50e-02

Pos logit contributions
elly+0.005
oky+0.005
angs+0.005
 shadows+0.005
 trash+0.005
Neg logit contributions
pron-0.008
 ceremony-0.008
 yes-0.008
 therapist-0.007
 Amen-0.007
Token things
Token ID1243
Feature activation-3.55e-03

Pos logit contributions
 yes+0.035
 ceremony+0.033
pron+0.033
 medal+0.032
 therapist+0.031
Neg logit contributions
oky-0.020
elly-0.019
angs-0.019
umbles-0.018
 gaps-0.018
Token until
Token ID1566
Feature activation+5.83e-03

Pos logit contributions
pron+0.009
 yes+0.008
 ceremony+0.008
 therapist+0.008
 couple+0.008
Neg logit contributions
elly-0.004
oky-0.004
angs-0.004
 gaps-0.004
ases-0.003
Token the
Token ID262
Feature activation-1.06e-02

Pos logit contributions
 raining+0.009
oky+0.009
 trash+0.009
 gaps+0.008
 finds+0.008
Neg logit contributions
pron-0.011
 yes-0.011
 saddle-0.011
 therapist-0.011
 Amen-0.011
Token sun
Token ID4252
Feature activation-1.11e-03

Pos logit contributions
 yes+0.019
pron+0.018
 therapist+0.018
 ceremony+0.018
 Amen+0.016
Neg logit contributions
 shadows-0.018
oky-0.018
 trash-0.017
 spiders-0.017
 gaps-0.017
Token went
Token ID1816
Feature activation+1.12e-02

Pos logit contributions
 yes+0.003
pron+0.003
 ceremony+0.003
 medal+0.002
 couple+0.002
Neg logit contributions
oky-0.001
elly-0.001
angs-0.001
umbles-0.001
 gaps-0.001
Token down
Token ID866
Feature activation+1.56e-02

Pos logit contributions
oky+0.012
elly+0.011
angs+0.011
umbles+0.010
 gaps+0.010
Neg logit contributions
 yes-0.029
pron-0.028
 ceremony-0.027
 therapist-0.026
 medal-0.026
Token.
Token ID13
Feature activation-1.26e-02

Pos logit contributions
oky+0.023
angs+0.022
elly+0.022
ases+0.021
urious+0.021
Neg logit contributions
 yes-0.033
pron-0.032
 ceremony-0.032
 therapist-0.030
 medal-0.030
Token It
Token ID632
Feature activation-1.22e-02

Pos logit contributions
 yes+0.021
 couple+0.020
 ceremony+0.020
 goodbye+0.020
pron+0.019
Neg logit contributions
angs-0.025
ases-0.023
oky-0.022
 pipes-0.022
 gaps-0.022
Token was
Token ID373
Feature activation-7.14e-03

Pos logit contributions
 yes+0.027
 ceremony+0.026
pron+0.026
 therapist+0.025
 medal+0.024
Neg logit contributions
oky-0.018
angs-0.017
elly-0.017
ases-0.016
umbles-0.015
Token picture
Token ID4286
Feature activation-1.49e-02

Pos logit contributions
 yes+0.019
 ceremony+0.018
 therapist+0.018
pron+0.017
quet+0.017
Neg logit contributions
 shadows-0.014
 trash-0.014
oky-0.013
 gaps-0.013
 territory-0.013
Token of
Token ID286
Feature activation+1.74e-02

Pos logit contributions
 yes+0.034
pron+0.033
 ceremony+0.033
 therapist+0.031
 Amen+0.031
Neg logit contributions
oky-0.019
elly-0.019
angs-0.019
 gaps-0.017
 shadows-0.017
Token a
Token ID257
Feature activation-2.46e-02

Pos logit contributions
oky+0.023
angs+0.022
elly+0.022
 shadows+0.022
 gaps+0.021
Neg logit contributions
pron-0.039
 yes-0.039
 ceremony-0.037
 therapist-0.036
 couple-0.035
Token witch
Token ID16365
Feature activation-8.47e-03

Pos logit contributions
 yes+0.046
 ceremony+0.043
quet+0.043
 therapist+0.043
pron+0.042
Neg logit contributions
 shadows-0.038
 trash-0.038
oky-0.036
 spiders-0.035
 territory-0.035
Token on
Token ID319
Feature activation+2.78e-02

Pos logit contributions
pron+0.020
 yes+0.020
 ceremony+0.019
 couple+0.018
 therapist+0.018
Neg logit contributions
angs-0.009
oky-0.009
 shadows-0.009
 spiders-0.009
elly-0.009
Token the
Token ID262
Feature activation+5.88e-03

Pos logit contributions
oky+0.041
angs+0.040
elly+0.039
 shadows+0.039
 gaps+0.038
Neg logit contributions
 yes-0.058
pron-0.056
 ceremony-0.056
 therapist-0.053
 couple-0.052
Token cover
Token ID3002
Feature activation-4.12e-03

Pos logit contributions
 shadows+0.009
 trash+0.008
 gaps+0.008
 spiders+0.008
oky+0.008
Neg logit contributions
 yes-0.012
pron-0.012
 ceremony-0.011
quet-0.011
 therapist-0.011
Token and
Token ID290
Feature activation-6.61e-03

Pos logit contributions
 yes+0.010
pron+0.010
 ceremony+0.010
 Amen+0.009
 couple+0.009
Neg logit contributions
elly-0.004
oky-0.004
angs-0.004
umbles-0.004
 shadows-0.004
Token many
Token ID867
Feature activation-1.24e-02

Pos logit contributions
pron+0.014
 yes+0.014
 ceremony+0.013
 therapist+0.013
 medal+0.012
Neg logit contributions
oky-0.009
angs-0.009
 shadows-0.009
 gaps-0.009
 spiders-0.009
Token strange
Token ID6283
Feature activation+1.51e-02

Pos logit contributions
 yes+0.027
pron+0.026
 ceremony+0.026
 therapist+0.025
 medal+0.024
Neg logit contributions
oky-0.017
elly-0.017
angs-0.017
 gaps-0.016
 shadows-0.016
Token words
Token ID2456
Feature activation-2.67e-03

Pos logit contributions
oky+0.021
elly+0.020
angs+0.020
 gaps+0.019
ases+0.018
Neg logit contributions
 yes-0.034
pron-0.033
 ceremony-0.032
 therapist-0.030
 medal-0.030
Token size
Token ID2546
Feature activation-4.26e-03

Pos logit contributions
oky+0.016
angs+0.016
elly+0.015
ases+0.014
okes+0.014
Neg logit contributions
 ceremony-0.029
 yes-0.028
pron-0.028
 medal-0.027
 couple-0.027
Token to
Token ID284
Feature activation-4.27e-03

Pos logit contributions
pron+0.010
 yes+0.010
 ceremony+0.009
 Amen+0.009
 therapist+0.009
Neg logit contributions
oky-0.005
elly-0.005
angs-0.005
 gaps-0.005
umbles-0.005
Token sail
Token ID14936
Feature activation-2.74e-02

Pos logit contributions
pron+0.009
 therapist+0.009
 yes+0.008
 ceremony+0.008
 medal+0.008
Neg logit contributions
ases-0.006
 gaps-0.006
oky-0.006
 raining-0.006
en-0.005
Token back
Token ID736
Feature activation+2.65e-02

Pos logit contributions
pron+0.065
 yes+0.064
 ceremony+0.062
 therapist+0.060
 Amen+0.060
Neg logit contributions
oky-0.031
elly-0.031
angs-0.030
 gaps-0.029
 shadows-0.029
Token home
Token ID1363
Feature activation+1.70e-02

Pos logit contributions
oky+0.039
elly+0.038
angs+0.037
umbles+0.036
 gaps+0.036
Neg logit contributions
 yes-0.057
pron-0.056
 ceremony-0.053
 therapist-0.051
 medal-0.050
Token.
Token ID13
Feature activation-1.07e-02

Pos logit contributions
oky+0.016
elly+0.016
umbles+0.015
 gaps+0.014
angs+0.014
Neg logit contributions
pron-0.044
 yes-0.043
 ceremony-0.042
 Amen-0.041
 therapist-0.041
Token
Token ID220
Feature activation+3.81e-02

Pos logit contributions
 yes+0.025
pron+0.025
 ceremony+0.024
 medal+0.023
 therapist+0.023
Neg logit contributions
oky-0.013
elly-0.013
angs-0.012
umbles-0.012
 gaps-0.012
Token
Token ID198
Feature activation-2.09e-02

Pos logit contributions
oky+0.053
elly+0.052
angs+0.051
 gaps+0.048
urious+0.048
Neg logit contributions
 yes-0.084
pron-0.081
 ceremony-0.079
 therapist-0.076
 medal-0.075
Token
Token ID198
Feature activation-2.35e-02

Pos logit contributions
 yes+0.054
 ceremony+0.053
pron+0.053
 medal+0.051
 therapist+0.050
Neg logit contributions
oky-0.020
elly-0.020
umbles-0.019
angs-0.018
ases-0.018
TokenThe
Token ID464
Feature activation-1.75e-02

Pos logit contributions
 yes+0.054
 ceremony+0.053
pron+0.051
 medal+0.051
 goodbye+0.050
Neg logit contributions
elly-0.028
urious-0.028
oky-0.027
ubs-0.026
umbles-0.026
Token animals
Token ID4695
Feature activation-2.22e-02

Pos logit contributions
pron+0.040
 yes+0.039
 therapist+0.036
quet+0.036
 ceremony+0.035
Neg logit contributions
 shadows-0.023
 raining-0.022
 trash-0.021
 gaps-0.021
 pipes-0.021
Token
Token ID198
Feature activation-2.60e-02

Pos logit contributions
 yes+0.054
pron+0.052
 ceremony+0.052
 therapist+0.049
 medal+0.049
Neg logit contributions
oky-0.030
elly-0.029
angs-0.028
umbles-0.027
urious-0.027
TokenJack
Token ID14295
Feature activation-6.19e-03

Pos logit contributions
 yes+0.052
 ceremony+0.051
pron+0.050
 therapist+0.048
 medal+0.048
Neg logit contributions
elly-0.039
oky-0.039
urious-0.038
angs-0.036
 gaps-0.036
Token's
Token ID338
Feature activation-2.69e-02

Pos logit contributions
 yes+0.015
pron+0.014
 ceremony+0.014
 medal+0.014
quet+0.013
Neg logit contributions
elly-0.007
oky-0.007
urious-0.007
umbles-0.007
angs-0.006
Token mum
Token ID25682
Feature activation+4.15e-03

Pos logit contributions
pron+0.044
 yes+0.043
 ceremony+0.042
quet+0.040
 therapist+0.039
Neg logit contributions
 shadows-0.048
urious-0.047
elly-0.047
umbles-0.047
oky-0.047
Token said
Token ID531
Feature activation-2.07e-02

Pos logit contributions
my+0.004
 finds+0.004
oky+0.004
en+0.004
angs+0.004
Neg logit contributions
pron-0.010
 medal-0.010
 ceremony-0.010
 yes-0.009
 Amen-0.009
Token he
Token ID339
Feature activation-9.30e-03

Pos logit contributions
pron+0.052
 saddle+0.052
 ceremony+0.052
quet+0.050
 wedding+0.049
Neg logit contributions
 Why-0.017
 comes-0.015
 because-0.014
 L-0.014
 Sam-0.014
Token had
Token ID550
Feature activation-1.37e-02

Pos logit contributions
 yes+0.021
 ceremony+0.021
pron+0.021
 medal+0.020
 therapist+0.020
Neg logit contributions
oky-0.011
elly-0.011
angs-0.011
urious-0.010
umbles-0.010
Token done
Token ID1760
Feature activation-4.98e-03

Pos logit contributions
 yes+0.030
pron+0.030
 ceremony+0.030
quet+0.029
 therapist+0.029
Neg logit contributions
oky-0.017
 raining-0.016
angs-0.016
elly-0.016
 gaps-0.016
Token a
Token ID257
Feature activation-3.95e-02

Pos logit contributions
 ceremony+0.012
pron+0.012
 yes+0.012
quet+0.012
 saddle+0.012
Neg logit contributions
 raining-0.005
 shadows-0.005
 spiders-0.004
 pipes-0.004
 tubes-0.004
Token good
Token ID922
Feature activation-2.67e-02

Pos logit contributions
 yes+0.076
pron+0.075
 ceremony+0.074
 therapist+0.071
quet+0.070
Neg logit contributions
oky-0.060
elly-0.059
 trash-0.058
 raining-0.056
urious-0.056
Token job
Token ID1693
Feature activation-1.68e-02

Pos logit contributions
 yes+0.051
pron+0.049
 ceremony+0.047
 therapist+0.044
 medal+0.044
Neg logit contributions
oky-0.045
elly-0.045
angs-0.043
umbles-0.041
urious-0.041
TokenOne
Token ID3198
Feature activation-7.15e-03

Pos logit contributions
 yes+0.021
pron+0.021
 ceremony+0.021
 therapist+0.019
 medal+0.019
Neg logit contributions
oky-0.016
elly-0.016
angs-0.015
urious-0.015
umbles-0.015
Token day
Token ID1110
Feature activation-1.55e-02

Pos logit contributions
 yes+0.012
pron+0.012
 ceremony+0.012
 therapist+0.011
 medal+0.011
Neg logit contributions
oky-0.013
elly-0.013
angs-0.013
urious-0.012
umbles-0.012
Token Bob
Token ID5811
Feature activation+1.09e-02

Pos logit contributions
 yes+0.030
 ceremony+0.027
pron+0.027
 couple+0.026
 therapist+0.026
Neg logit contributions
oky-0.027
angs-0.026
elly-0.026
urious-0.025
 gaps-0.025
Token encountered
Token ID12956
Feature activation+2.21e-02

Pos logit contributions
oky+0.018
angs+0.018
elly+0.017
ases+0.017
 gaps+0.017
Neg logit contributions
 yes-0.020
 ceremony-0.020
 couple-0.019
 therapist-0.019
 medal-0.018
Token a
Token ID257
Feature activation-2.43e-02

Pos logit contributions
oky+0.036
elly+0.035
angs+0.034
urious+0.033
ases+0.032
Neg logit contributions
 yes-0.045
pron-0.042
 ceremony-0.042
 medal-0.040
 therapist-0.040
Token maze
Token ID31237
Feature activation-1.98e-02

Pos logit contributions
 yes+0.055
 ceremony+0.052
pron+0.052
 therapist+0.052
quet+0.051
Neg logit contributions
oky-0.030
 trash-0.030
 raining-0.029
elly-0.028
 territory-0.028
Token that
Token ID326
Feature activation+2.39e-03

Pos logit contributions
 yes+0.041
pron+0.040
 ceremony+0.040
 therapist+0.038
 medal+0.037
Neg logit contributions
oky-0.030
elly-0.029
angs-0.028
 gaps-0.027
umbles-0.027
Token he
Token ID339
Feature activation+1.22e-02

Pos logit contributions
oky+0.004
elly+0.004
angs+0.003
ases+0.003
umbles+0.003
Neg logit contributions
 yes-0.005
pron-0.005
 ceremony-0.005
 therapist-0.005
 medal-0.005
Token couldn
Token ID3521
Feature activation-1.39e-02

Pos logit contributions
oky+0.016
elly+0.015
angs+0.015
ases+0.014
 gaps+0.014
Neg logit contributions
 yes-0.029
pron-0.028
 ceremony-0.027
 therapist-0.026
 medal-0.026
Token't
Token ID470
Feature activation+2.55e-02

Pos logit contributions
 yes+0.023
pron+0.023
 ceremony+0.022
 therapist+0.020
 couple+0.020
Neg logit contributions
oky-0.027
elly-0.026
angs-0.026
umbles-0.026
ases-0.025
Token beat
Token ID4405
Feature activation-1.00e-02

Pos logit contributions
oky+0.030
angs+0.029
elly+0.029
ases+0.028
umbles+0.028
Neg logit contributions
pron-0.061
 yes-0.059
 ceremony-0.058
 therapist-0.057
 medal-0.054
Token air
Token ID1633
Feature activation-7.04e-03

Pos logit contributions
oky+0.027
elly+0.026
angs+0.025
 gaps+0.025
ases+0.024
Neg logit contributions
 yes-0.040
pron-0.039
 ceremony-0.038
 therapist-0.036
 medal-0.035
Token.
Token ID13
Feature activation-2.83e-03

Pos logit contributions
pron+0.019
 yes+0.019
 ceremony+0.018
 Amen+0.018
 therapist+0.017
Neg logit contributions
oky-0.006
angs-0.006
elly-0.006
 raining-0.006
 gaps-0.005
Token
Token ID220
Feature activation+4.32e-02

Pos logit contributions
 yes+0.005
pron+0.005
 ceremony+0.004
 medal+0.004
 therapist+0.004
Neg logit contributions
oky-0.005
elly-0.005
angs-0.005
umbles-0.005
 gaps-0.005
Token
Token ID198
Feature activation-1.26e-02

Pos logit contributions
oky+0.071
elly+0.069
angs+0.069
 gaps+0.066
urious+0.064
Neg logit contributions
 yes-0.084
pron-0.079
 ceremony-0.075
 therapist-0.073
 couple-0.071
Token
Token ID198
Feature activation-1.13e-02

Pos logit contributions
 yes+0.031
pron+0.030
 ceremony+0.030
 medal+0.028
 therapist+0.028
Neg logit contributions
oky-0.015
elly-0.014
angs-0.013
umbles-0.013
urious-0.013
TokenThe
Token ID464
Feature activation-1.47e-02

Pos logit contributions
 yes+0.023
 ceremony+0.023
pron+0.022
 medal+0.021
 therapist+0.021
Neg logit contributions
oky-0.017
elly-0.016
urious-0.016
 gaps-0.015
umbles-0.015
Token wild
Token ID4295
Feature activation+4.67e-03

Pos logit contributions
 yes+0.032
pron+0.031
 ceremony+0.030
 therapist+0.029
 medal+0.028
Neg logit contributions
oky-0.021
elly-0.020
 shadows-0.020
urious-0.020
 trash-0.020
Token animal
Token ID5044
Feature activation-3.07e-03

Pos logit contributions
oky+0.008
angs+0.008
elly+0.008
ases+0.007
umbles+0.007
Neg logit contributions
 yes-0.009
pron-0.008
 ceremony-0.008
 medal-0.008
 couple-0.008
Token created
Token ID2727
Feature activation-1.97e-02

Pos logit contributions
pron+0.008
 yes+0.008
 ceremony+0.008
 medal+0.007
 therapist+0.007
Neg logit contributions
 shadows-0.003
urious-0.003
 finds-0.003
oky-0.003
 spiders-0.003
Token a
Token ID257
Feature activation-2.12e-02

Pos logit contributions
pron+0.044
 yes+0.044
 ceremony+0.043
 therapist+0.041
 medal+0.040
Neg logit contributions
oky-0.026
angs-0.025
elly-0.024
 shadows-0.024
 gaps-0.024
Token bubble
Token ID14310
Feature activation-3.54e-02

Pos logit contributions
 yes+0.047
 therapist+0.045
 ceremony+0.045
pron+0.044
quet+0.041
Neg logit contributions
 trash-0.028
oky-0.027
 shadows-0.027
 gaps-0.027
 territory-0.026
TokenCan
Token ID6090
Feature activation-4.57e-02

Pos logit contributions
oky+0.011
elly+0.011
urious+0.010
angs+0.010
ASH+0.010
Neg logit contributions
 yes-0.016
pron-0.015
 ceremony-0.015
 medal-0.015
 therapist-0.014
Token we
Token ID356
Feature activation-3.55e-02

Pos logit contributions
 ceremony+0.107
 saddle+0.107
pron+0.107
 couple+0.104
quet+0.101
Neg logit contributions
 causes-0.049
 raining-0.049
 Maybe-0.048
 shadows-0.047
 Don-0.047
Token keep
Token ID1394
Feature activation-1.45e-02

Pos logit contributions
 therapist+0.078
pron+0.077
ves+0.072
 ceremony+0.072
 yes+0.071
Neg logit contributions
my-0.044
 finds-0.040
oky-0.040
?-0.040
 raining-0.040
Token the
Token ID262
Feature activation+1.47e-03

Pos logit contributions
 yes+0.033
pron+0.033
 ceremony+0.032
 therapist+0.032
quet+0.030
Neg logit contributions
 shadows-0.018
 raining-0.017
oky-0.017
 territory-0.017
 spiders-0.017
Token newspaper
Token ID7533
Feature activation-3.89e-02

Pos logit contributions
oky+0.003
elly+0.003
angs+0.003
 gaps+0.003
urious+0.003
Neg logit contributions
 yes-0.002
pron-0.002
 ceremony-0.002
 therapist-0.002
 medal-0.002
Token?
Token ID30
Feature activation-1.05e-02

Pos logit contributions
 therapist+0.089
 couple+0.084
 ceremony+0.083
 yes+0.083
pron+0.083
Neg logit contributions
 raining-0.044
oky-0.041
 apart-0.040
elly-0.040
 finds-0.039
Token I
Token ID314
Feature activation-2.23e-03

Pos logit contributions
 ceremony+0.026
pron+0.026
 medal+0.025
 yes+0.025
 couple+0.025
Neg logit contributions
oky-0.011
elly-0.010
 Maybe-0.010
 Why-0.009
angs-0.009
Token want
Token ID765
Feature activation-3.57e-02

Pos logit contributions
 yes+0.006
pron+0.005
 ceremony+0.005
 therapist+0.005
 medal+0.005
Neg logit contributions
oky-0.002
elly-0.002
angs-0.002
umbles-0.002
 gaps-0.002
Token to
Token ID284
Feature activation-1.49e-02

Pos logit contributions
 yes+0.078
pron+0.078
 ceremony+0.074
 therapist+0.073
 saddle+0.071
Neg logit contributions
oky-0.048
 shadows-0.048
 spiders-0.046
 gaps-0.045
elly-0.045
Token read
Token ID1100
Feature activation-2.15e-02

Pos logit contributions
pron+0.034
 therapist+0.034
 yes+0.033
 ceremony+0.032
 couple+0.031
Neg logit contributions
umbles-0.016
 shadows-0.016
ases-0.016
 finds-0.015
 gaps-0.015
Token it
Token ID340
Feature activation-1.60e-02

Pos logit contributions
 therapist+0.045
 ceremony+0.045
pron+0.044
 couple+0.042
 saddle+0.042
Neg logit contributions
 shadows-0.027
 raining-0.027
oky-0.026
 gaps-0.025
 spiders-0.025
Token thankful
Token ID25535
Feature activation-1.89e-02

Pos logit contributions
pron+0.069
 medal+0.069
 therapist+0.068
 yes+0.067
 saddle+0.067
Neg logit contributions
 raining-0.042
umbles-0.037
 afraid-0.037
ained-0.037
iz-0.035
Token her
Token ID607
Feature activation+3.27e-03

Pos logit contributions
pron+0.042
 ceremony+0.040
 yes+0.040
 saddle+0.039
 Amen+0.039
Neg logit contributions
elly-0.024
oky-0.023
 shadows-0.022
 raining-0.022
 spiders-0.021
Token mom
Token ID1995
Feature activation+6.24e-03

Pos logit contributions
 shadows+0.005
 wonders+0.005
urious+0.005
oky+0.005
 finds+0.005
Neg logit contributions
pron-0.006
 yes-0.006
quet-0.006
 therapist-0.006
 ceremony-0.006
Tokenmy
Token ID1820
Feature activation-2.57e-03

Pos logit contributions
elly+0.001
oky+0.001
angs+0.000
urious+0.000
my+0.000
Neg logit contributions
 yes-0.021
pron-0.021
 ceremony-0.021
 therapist-0.020
 medal-0.020
Token had
Token ID550
Feature activation-3.11e-02

Pos logit contributions
pron+0.007
 ceremony+0.007
 yes+0.007
 medal+0.007
ves+0.006
Neg logit contributions
my-0.002
elly-0.002
 finds-0.002
oky-0.002
 shadows-0.002
Token suggested
Token ID5220
Feature activation-6.07e-02

Pos logit contributions
 yes+0.069
pron+0.067
 ceremony+0.066
 therapist+0.065
 medal+0.065
Neg logit contributions
oky-0.036
elly-0.036
urious-0.035
umbles-0.035
 finds-0.035
Token going
Token ID1016
Feature activation-4.24e-02

Pos logit contributions
 saddle+0.148
 medal+0.134
pron+0.134
 ceremony+0.132
 therapist+0.130
Neg logit contributions
 because-0.069
 raining-0.063
 Why-0.060
 spiders-0.059
 wasn-0.059
Token to
Token ID284
Feature activation-2.88e-02

Pos logit contributions
pron+0.097
 yes+0.093
 therapist+0.088
 ceremony+0.086
 Amen+0.082
Neg logit contributions
 raining-0.054
oky-0.054
elly-0.053
 shadows-0.053
ases-0.052
Token church
Token ID4928
Feature activation-3.15e-02

Pos logit contributions
pron+0.073
 yes+0.069
 therapist+0.069
 saddle+0.065
 ceremony+0.063
Neg logit contributions
 shadows-0.029
 raining-0.028
 spiders-0.027
 gaps-0.026
 finds-0.025
Token.
Token ID13
Feature activation-2.23e-02

Pos logit contributions
pron+0.077
 yes+0.072
 medal+0.072
 therapist+0.072
 saddle+0.071
Neg logit contributions
 raining-0.031
 finds-0.029
yards-0.029
 shadows-0.029
 territory-0.029
Token<|endoftext|>
Token ID50256
Feature activation+1.43e-02

Pos logit contributions
 yes+0.052
pron+0.050
 ceremony+0.050
 therapist+0.047
 medal+0.047
Neg logit contributions
oky-0.029
elly-0.028
angs-0.028
ases-0.026
 gaps-0.026
Token owl
Token ID39610
Feature activation-5.32e-03

Pos logit contributions
pron+0.038
 yes+0.038
 ceremony+0.037
 therapist+0.036
ves+0.035
Neg logit contributions
 shadows-0.026
urious-0.024
 territory-0.024
oky-0.024
 wonders-0.024
Token gave
Token ID2921
Feature activation-1.63e-02

Pos logit contributions
pron+0.012
 yes+0.012
 ceremony+0.012
 Amen+0.011
 therapist+0.011
Neg logit contributions
 finds-0.006
oky-0.006
angs-0.006
elly-0.006
 shadows-0.005
Token her
Token ID607
Feature activation+6.10e-03

Pos logit contributions
pron+0.036
 ceremony+0.034
 medal+0.034
 yes+0.034
 couple+0.032
Neg logit contributions
 shadows-0.021
 trash-0.021
oky-0.020
angs-0.020
ASH-0.020
Token a
Token ID257
Feature activation-3.22e-02

Pos logit contributions
angs+0.006
 shadows+0.006
 trash+0.006
 territory+0.006
oky+0.006
Neg logit contributions
pron-0.015
 yes-0.014
 ceremony-0.014
 therapist-0.013
 Amen-0.013
Token special
Token ID2041
Feature activation-2.74e-02

Pos logit contributions
 yes+0.063
 ceremony+0.062
 therapist+0.061
quet+0.059
 Amen+0.059
Neg logit contributions
 trash-0.043
oky-0.041
 shadows-0.040
angs-0.039
 finds-0.038
Token prize
Token ID11596
Feature activation-5.86e-02

Pos logit contributions
 yes+0.049
 therapist+0.048
pron+0.047
 ceremony+0.047
nes+0.047
Neg logit contributions
 territory-0.040
 finds-0.038
oky-0.038
 trash-0.038
elly-0.038
Token.
Token ID13
Feature activation-8.21e-03

Pos logit contributions
pron+0.173
 Amen+0.167
 ceremony+0.157
 yes+0.154
 therapist+0.151
Neg logit contributions
elly-0.034
angs-0.033
 than-0.029
 finds-0.028
oky-0.027
Token Lucy
Token ID22162
Feature activation-7.31e-03

Pos logit contributions
pron+0.020
 yes+0.020
 ceremony+0.020
 medal+0.020
 therapist+0.018
Neg logit contributions
oky-0.009
elly-0.009
umbles-0.008
 Maybe-0.008
 shadows-0.008
Token was
Token ID373
Feature activation-2.71e-02

Pos logit contributions
pron+0.018
 yes+0.018
 ceremony+0.018
 Amen+0.017
 medal+0.017
Neg logit contributions
umbles-0.007
 finds-0.007
urious-0.007
en-0.007
 shadows-0.006
Token so
Token ID523
Feature activation-3.17e-02

Pos logit contributions
pron+0.065
 ceremony+0.062
 therapist+0.061
 yes+0.060
 medal+0.060
Neg logit contributions
umbles-0.028
 afraid-0.028
 raining-0.027
angs-0.025
 apart-0.025
Token happy
Token ID3772
Feature activation-2.60e-02

Pos logit contributions
pron+0.067
 ceremony+0.062
 therapist+0.062
 yes+0.060
 saddle+0.059
Neg logit contributions
 afraid-0.045
umbles-0.042
oky-0.042
elly-0.041
urious-0.041
Tokenmy
Token ID1820
Feature activation+9.82e-03

Pos logit contributions
angs+0.014
oky+0.014
 territory+0.013
 gaps+0.013
elly+0.013
Neg logit contributions
pron-0.020
 yes-0.019
 ceremony-0.018
 couple-0.017
 therapist-0.017
Token took
Token ID1718
Feature activation-5.57e-03

Pos logit contributions
oky+0.017
angs+0.017
elly+0.016
 gaps+0.016
 territory+0.016
Neg logit contributions
 yes-0.019
pron-0.019
 ceremony-0.018
 couple-0.017
 therapist-0.017
Token him
Token ID683
Feature activation+6.05e-03

Pos logit contributions
 yes+0.012
pron+0.012
 ceremony+0.012
 therapist+0.011
 medal+0.011
Neg logit contributions
oky-0.008
elly-0.008
angs-0.007
umbles-0.007
ases-0.007
Token to
Token ID284
Feature activation-6.45e-03

Pos logit contributions
oky+0.011
elly+0.010
angs+0.010
 gaps+0.010
umbles+0.010
Neg logit contributions
 yes-0.011
pron-0.011
 ceremony-0.011
 therapist-0.010
 medal-0.010
Token the
Token ID262
Feature activation-2.19e-02

Pos logit contributions
 yes+0.015
pron+0.015
 ceremony+0.014
 therapist+0.014
 medal+0.014
Neg logit contributions
oky-0.007
 raining-0.007
 trash-0.007
elly-0.007
 gaps-0.007
Token art
Token ID1242
Feature activation-6.59e-02

Pos logit contributions
 yes+0.045
pron+0.042
 ceremony+0.040
 therapist+0.039
quet+0.038
Neg logit contributions
oky-0.034
 trash-0.033
elly-0.032
 shadows-0.031
 gaps-0.031
Token studio
Token ID8034
Feature activation-5.59e-02

Pos logit contributions
 yes+0.126
 Amen+0.115
 goodbye+0.112
 saddle+0.112
 therapist+0.110
Neg logit contributions
elly-0.108
oky-0.107
 tubes-0.101
 pipes-0.100
 gaps-0.100
Token.
Token ID13
Feature activation+1.42e-02

Pos logit contributions
 yes+0.140
pron+0.139
 medal+0.135
 ceremony+0.135
 therapist+0.134
Neg logit contributions
oky-0.054
elly-0.053
 raining-0.050
 tubes-0.049
angs-0.048
Token "
Token ID366
Feature activation+1.89e-02

Pos logit contributions
angs+0.022
ases+0.021
elly+0.021
urious+0.021
oky+0.021
Neg logit contributions
 yes-0.030
pron-0.029
 ceremony-0.027
 goodbye-0.026
 couple-0.026
TokenToday
Token ID8888
Feature activation+9.06e-03

Pos logit contributions
angs+0.029
oky+0.028
umbles+0.027
elly+0.027
ases+0.027
Neg logit contributions
 yes-0.040
pron-0.039
 ceremony-0.037
 couple-0.036
 therapist-0.035
Token,
Token ID11
Feature activation+7.38e-03

Pos logit contributions
oky+0.015
angs+0.015
elly+0.015
ases+0.014
urious+0.014
Neg logit contributions
 yes-0.018
pron-0.017
 ceremony-0.017
 medal-0.016
 therapist-0.016
Token We
Token ID775
Feature activation-2.51e-02

Pos logit contributions
oky+0.024
elly+0.023
angs+0.022
umbles+0.020
ases+0.020
Neg logit contributions
 yes-0.054
pron-0.053
 ceremony-0.052
 medal-0.049
 therapist-0.049
Token love
Token ID1842
Feature activation-2.74e-02

Pos logit contributions
pron+0.062
 yes+0.060
 ceremony+0.059
 therapist+0.058
 medal+0.057
Neg logit contributions
oky-0.025
angs-0.025
ases-0.024
elly-0.024
 finds-0.024
Token you
Token ID345
Feature activation-1.50e-03

Pos logit contributions
 yes+0.062
pron+0.061
 therapist+0.058
 ceremony+0.058
 saddle+0.057
Neg logit contributions
oky-0.037
 shadows-0.035
 spiders-0.035
 raining-0.035
elly-0.034
Token,"
Token ID553
Feature activation-3.37e-02

Pos logit contributions
pron+0.004
 therapist+0.004
 ceremony+0.004
 medal+0.004
 yes+0.003
Neg logit contributions
oky-0.001
 raining-0.001
elly-0.001
 shadows-0.001
umbles-0.001
Token Sam
Token ID3409
Feature activation-1.28e-02

Pos logit contributions
pron+0.093
 saddle+0.085
quet+0.085
 medal+0.084
 ceremony+0.081
Neg logit contributions
 Sam-0.032
 L-0.031
 Jen-0.026
 J-0.025
oky-0.024
Token and
Token ID290
Feature activation-6.04e-02

Pos logit contributions
pron+0.032
 yes+0.030
quet+0.030
 ceremony+0.030
 medal+0.029
Neg logit contributions
 finds-0.013
 wonders-0.012
elly-0.012
oky-0.012
urious-0.012
Token Mia
Token ID32189
Feature activation-1.31e-02

Pos logit contributions
pron+0.179
 yes+0.175
 ceremony+0.171
quet+0.170
 saddle+0.167
Neg logit contributions
 Sam-0.034
oky-0.032
ases-0.032
angs-0.032
 trash-0.031
Token say
Token ID910
Feature activation-3.03e-02

Pos logit contributions
pron+0.033
quet+0.030
ves+0.028
 therapist+0.028
 medal+0.028
Neg logit contributions
 finds-0.015
my-0.014
 hears-0.014
 sees-0.014
 wonders-0.013
Token.
Token ID13
Feature activation+1.22e-02

Pos logit contributions
pron+0.099
 ceremony+0.093
 medal+0.092
 saddle+0.091
 therapist+0.090
Neg logit contributions
 apart-0.006
 because-0.004
umbles-0.004
ases-0.004
.-0.002
Token
Token ID198
Feature activation-1.13e-02

Pos logit contributions
oky+0.013
elly+0.013
angs+0.012
umbles+0.012
ases+0.011
Neg logit contributions
 yes-0.031
pron-0.030
 ceremony-0.030
 medal-0.029
 therapist-0.028
Token
Token ID198
Feature activation-1.21e-02

Pos logit contributions
 yes+0.028
pron+0.027
 ceremony+0.027
 medal+0.026
 therapist+0.025
Neg logit contributions
oky-0.013
elly-0.012
umbles-0.012
angs-0.012
ases-0.011
Token
Token ID198
Feature activation-2.73e-02

Pos logit contributions
 yes+0.064
pron+0.064
 ceremony+0.063
 medal+0.060
 therapist+0.058
Neg logit contributions
elly-0.025
oky-0.024
umbles-0.022
angs-0.021
ubs-0.021
TokenG
Token ID38
Feature activation+2.40e-03

Pos logit contributions
 yes+0.055
pron+0.053
 ceremony+0.052
 medal+0.050
 goodbye+0.049
Neg logit contributions
elly-0.043
oky-0.042
urious-0.039
angs-0.038
ubs-0.038
Tokenina
Token ID1437
Feature activation-1.32e-02

Pos logit contributions
oky+0.004
angs+0.004
 gaps+0.004
 trash+0.004
 shadows+0.004
Neg logit contributions
pron-0.005
 yes-0.005
 ceremony-0.004
 therapist-0.004
 couple-0.004
Token promised
Token ID8072
Feature activation-1.91e-02

Pos logit contributions
pron+0.033
 yes+0.031
 ceremony+0.030
quet+0.030
 medal+0.030
Neg logit contributions
 finds-0.013
urious-0.012
umbles-0.012
en-0.012
elly-0.012
Token,
Token ID11
Feature activation-3.62e-02

Pos logit contributions
pron+0.045
 ceremony+0.040
 yes+0.040
 Amen+0.039
 medal+0.038
Neg logit contributions
 shadows-0.023
elly-0.023
umbles-0.022
oky-0.022
 raining-0.022
Token and
Token ID290
Feature activation-6.15e-02

Pos logit contributions
pron+0.084
 ceremony+0.077
 medal+0.075
 yes+0.075
quet+0.074
Neg logit contributions
elly-0.039
 raining-0.038
oky-0.037
 Maybe-0.036
 shadows-0.036
Token so
Token ID523
Feature activation-4.93e-02

Pos logit contributions
pron+0.137
 yes+0.122
 Amen+0.118
 medal+0.116
 ceremony+0.115
Neg logit contributions
 L-0.077
 finds-0.076
 shadows-0.076
elly-0.074
en-0.074
Token the
Token ID262
Feature activation-2.30e-02

Pos logit contributions
pron+0.092
 yes+0.090
 medal+0.084
 ceremony+0.083
 saddle+0.081
Neg logit contributions
elly-0.080
oky-0.078
 shadows-0.076
umbles-0.075
ubs-0.074
Token old
Token ID1468
Feature activation-3.15e-02

Pos logit contributions
pron+0.063
 yes+0.062
ves+0.061
quet+0.058
nes+0.057
Neg logit contributions
 trash-0.021
 wonders-0.021
 shadows-0.020
 ways-0.017
 raining-0.017
Token man
Token ID582
Feature activation-1.74e-02

Pos logit contributions
pron+0.066
 yes+0.064
quet+0.060
nes+0.059
fs+0.059
Neg logit contributions
 wonders-0.042
 sees-0.038
 trash-0.036
 wants-0.036
 woods-0.035
Token took
Token ID1718
Feature activation-2.71e-02

Pos logit contributions
pron+0.040
 ceremony+0.035
 yes+0.035
 Amen+0.035
quet+0.035
Neg logit contributions
 finds-0.020
en-0.019
ases-0.018
urious-0.018
 hears-0.018