TOP ACTIVATIONS
MAX = 3.893

nodded and put on their rain co ats and boots .
and his dog and his sunset . He says he does
him and Joe and his brick were best friends ! <|endoftext|>
and his dog and his sunset . He writes happy and
shining and it 's not raining , okay ?"
her siblings and loved to trem ble and make them laugh
structure and ran to their structures . But they were gone
his stomach was starting to trem ble . His
and his phone and the fake mustache . <|endoftext|> L ily
sit down and do her math exercises . She loved finishing
cave started to shake and trem ble . Suddenly , the
to stay and finish his math . So Tim my stayed
and quickly put on his rain coat . When he was
the hive and started to trem ble with excitement . But
make her mom angry or sad . She realized that she
mom and dad angry and sad . She wanted to make
excited about r aking and r aked the small piles too
came and blew away their structures . The sticks , stones
made him and his mom sad . You made me and
<|endoftext|> Jim was tired and frustrated . He had been walking

MIN ACTIVATIONS
MIN = -5.478

. She used a m itt to take out the pan
the shore . They collected seas hell s and built sand
thought they looked like ac rob ats . She enjoyed the
learn more about rh in oc er oses and respect them
didn 't like wet av oc ados , so he decided
the waves . They gathered seas hell s and filled their
They heard the rh in oc eros roar . They heard
they could grow more av oc ados and share them with
had discovered the rh in oc eros , but they had
They heard the rh in oc eros sn ore .
They get a m itt and a spat ula .
that boss y rh in oc eros . <|endoftext|> D ee
, " I love av oc ados ! They are so
It was the rh in oc eros . It lifted its
have stopped the rh in oc eros . He is sleeping
She saw the rh in oc eros coming . It was
I will buy more av oc ados tomorrow . You can
vegetables ! All the b unn ies were over joy ed
He had taught the b unn ies to be friendly .
the top . The b unn ies settled in and soon

INTERVAL 1.551 - 3.893
CONTAINS 1.454%

one day it started to rain . The little girl started
boy . He liked to climb . He climbed on his
's not safe ," replied her mom . " You need
and Ben smiled and looked at it with wonder . They
family , with Mom and Dad and his two brothers ,

INTERVAL -0.792 - 1.551
CONTAINS 88.298%

quickly took out the shining coal from her pocket and placed
Thank you , now I can work again !"
my smiled and felt much better . Lily learned that sometimes
" Hi ! My name is Sue . This is Fl
was very dark inside , but they didn 't mind .

INTERVAL -3.135 - -0.792
CONTAINS 10.238%

They looked at each other and saw their wide
her eyes . She heard a crash . She felt a
down the street . He saw a flag that was waving
got scared . She ran away , leaving her toys behind
day , she found a card with a yellow fruit .

INTERVAL -5.478 - -3.135
CONTAINS 0.011%

she saw another rh in oc eros coming towards her .
fun in the sky . Enjoy the season ," Tom says
He saw some lovely sa us ages on the shelf ,
a very clever rh in oc eros ." <|endoftext|> Once upon
the tree . Both b unn ies agreed that it had
Token nodded
Token ID14464
Feature activation+3.84e-01

Pos logit contributions
flower+0.055
ble+0.048
els+0.046
cking+0.046
ric+0.045
Neg logit contributions
ives-0.041
 Enjoy-0.037
 Welcome-0.036
ury-0.036
 Happy-0.034
Token and
Token ID290
Feature activation+6.09e-01

Pos logit contributions
ric+0.024
flower+0.024
cks+0.023
cking+0.023
els+0.022
Neg logit contributions
 Max-0.007
 And-0.007
 Happy-0.006
 hide-0.005
ives-0.005
Token put
Token ID1234
Feature activation+5.93e-01

Pos logit contributions
flower+0.026
ble+0.022
cking+0.021
eled+0.021
bery+0.021
Neg logit contributions
ives-0.026
 Enjoy-0.022
 Welcome-0.021
ury-0.021
 These-0.021
Token on
Token ID319
Feature activation+2.02e+00

Pos logit contributions
flower+0.030
ric+0.028
ble+0.027
cking+0.027
mill+0.025
Neg logit contributions
ives-0.018
 Max-0.017
 Enjoy-0.016
 Happy-0.016
 Now-0.015
Token their
Token ID511
Feature activation+7.17e-01

Pos logit contributions
flower+0.096
ble+0.086
ric+0.079
mill+0.078
cker+0.077
Neg logit contributions
 Max-0.074
 Enjoy-0.067
 Happy-0.067
ives-0.067
 And-0.066
Token rain
Token ID6290
Feature activation+3.89e+00

Pos logit contributions
flower+0.029
ble+0.026
ric+0.026
cking+0.025
els+0.024
Neg logit contributions
ives-0.029
ury-0.026
 Welcome-0.026
 Happy-0.026
 Max-0.026
Tokenco
Token ID1073
Feature activation+3.13e-01

Pos logit contributions
flower+0.193
ble+0.183
ric+0.180
cking+0.179
els+0.174
Neg logit contributions
ives-0.129
ury-0.111
 Max-0.101
 hide-0.100
and-0.095
Tokenats
Token ID1381
Feature activation+7.03e-02

Pos logit contributions
flower+0.014
ble+0.012
ric+0.012
els+0.012
cking+0.012
Neg logit contributions
ives-0.012
ury-0.011
 Enjoy-0.011
 Welcome-0.010
 Follow-0.010
Token and
Token ID290
Feature activation+1.08e+00

Pos logit contributions
flower+0.003
ble+0.003
els+0.003
ric+0.002
cking+0.002
Neg logit contributions
ives-0.003
 Enjoy-0.003
ury-0.003
 Welcome-0.003
 Follow-0.002
Token boots
Token ID14412
Feature activation+1.53e+00

Pos logit contributions
flower+0.039
ble+0.034
ric+0.033
els+0.033
cking+0.033
Neg logit contributions
ives-0.051
ury-0.046
 Enjoy-0.045
 Welcome-0.044
 Follow-0.043
Token.
Token ID13
Feature activation+1.20e-01

Pos logit contributions
flower+0.058
ble+0.051
els+0.048
ric+0.048
cking+0.048
Neg logit contributions
ives-0.067
 Enjoy-0.064
ury-0.062
 Welcome-0.062
 Follow-0.061
Token and
Token ID290
Feature activation-4.73e-02

Pos logit contributions
ives+0.000
ury+0.000
 Enjoy+0.000
 Welcome+0.000
 Follow+0.000
Neg logit contributions
flower-0.000
ble-0.000
ric-0.000
els-0.000
cking-0.000
Token his
Token ID465
Feature activation+6.35e-01

Pos logit contributions
ives+0.002
ury+0.002
 Enjoy+0.002
 Max+0.002
 Welcome+0.002
Neg logit contributions
flower-0.002
ble-0.002
cking-0.002
ric-0.002
els-0.002
Token dog
Token ID3290
Feature activation+6.20e-01

Pos logit contributions
flower+0.032
ble+0.028
ric+0.028
els+0.027
cking+0.027
Neg logit contributions
ives-0.022
ury-0.019
 Enjoy-0.018
 Welcome-0.018
 Follow-0.017
Token and
Token ID290
Feature activation+5.17e-01

Pos logit contributions
flower+0.026
ble+0.023
ric+0.023
els+0.023
cking+0.023
Neg logit contributions
ives-0.025
ury-0.022
 Enjoy-0.022
 Welcome-0.021
 Follow-0.021
Token his
Token ID465
Feature activation+1.24e+00

Pos logit contributions
flower+0.022
ble+0.019
ric+0.019
cking+0.019
els+0.019
Neg logit contributions
ives-0.021
ury-0.019
 Enjoy-0.019
 Welcome-0.018
 Max-0.018
Token sunset
Token ID26428
Feature activation+3.88e+00

Pos logit contributions
flower+0.062
ble+0.055
ric+0.054
els+0.053
cking+0.052
Neg logit contributions
ives-0.043
ury-0.037
 Enjoy-0.036
 Follow-0.034
 Welcome-0.034
Token.
Token ID13
Feature activation-2.90e-01

Pos logit contributions
flower+0.164
ble+0.145
ric+0.141
cking+0.140
els+0.140
Neg logit contributions
ives-0.158
ury-0.143
 Enjoy-0.140
 Welcome-0.136
 Follow-0.133
Token He
Token ID679
Feature activation-1.95e-01

Pos logit contributions
ives+0.009
ury+0.008
 Enjoy+0.007
 Welcome+0.007
 Follow+0.007
Neg logit contributions
flower-0.014
ric-0.013
ble-0.013
cks-0.012
mill-0.012
Token says
Token ID1139
Feature activation-1.03e+00

Pos logit contributions
ives+0.005
 Enjoy+0.004
ury+0.004
 Welcome+0.003
 Happy+0.003
Neg logit contributions
flower-0.012
ble-0.011
ric-0.011
cking-0.011
els-0.010
Token he
Token ID339
Feature activation-7.23e-01

Pos logit contributions
ives+0.038
ury+0.033
 Enjoy+0.031
 Follow+0.031
 Welcome+0.030
Neg logit contributions
flower-0.048
ble-0.044
ric-0.042
els-0.042
cking-0.042
Token does
Token ID857
Feature activation-5.64e-01

Pos logit contributions
ives+0.024
ury+0.023
 Welcome+0.023
 Happy+0.023
and+0.023
Neg logit contributions
flower-0.032
ric-0.029
els-0.029
ble-0.028
cks-0.027
Token him
Token ID683
Feature activation+3.99e-01

Pos logit contributions
ives+0.010
ury+0.009
 Enjoy+0.008
 Welcome+0.008
 Follow+0.008
Neg logit contributions
flower-0.011
ble-0.010
els-0.009
cking-0.009
ric-0.009
Token and
Token ID290
Feature activation+8.15e-01

Pos logit contributions
flower+0.020
ble+0.018
ric+0.018
cking+0.018
els+0.018
Neg logit contributions
ives-0.013
ury-0.011
 Enjoy-0.011
 Max-0.011
 Welcome-0.011
Token Joe
Token ID5689
Feature activation+2.14e+00

Pos logit contributions
flower+0.038
ble+0.035
ric+0.034
cking+0.033
els+0.033
Neg logit contributions
ives-0.030
ury-0.026
 Enjoy-0.025
 Welcome-0.024
 Follow-0.024
Token and
Token ID290
Feature activation+1.05e+00

Pos logit contributions
flower+0.118
ble+0.112
cking+0.109
els+0.108
ric+0.108
Neg logit contributions
ives-0.057
ury-0.047
 Max-0.046
 Enjoy-0.045
 Welcome-0.045
Token his
Token ID465
Feature activation+1.66e+00

Pos logit contributions
flower+0.050
ble+0.046
ric+0.045
cking+0.045
els+0.044
Neg logit contributions
ives-0.036
ury-0.032
 Enjoy-0.032
 Welcome-0.031
 Happy-0.030
Token brick
Token ID17214
Feature activation+3.86e+00

Pos logit contributions
flower+0.075
ble+0.068
ric+0.066
cking+0.066
els+0.065
Neg logit contributions
ives-0.062
ury-0.056
 Enjoy-0.054
 Welcome-0.053
 Happy-0.051
Token were
Token ID547
Feature activation+8.59e-01

Pos logit contributions
cking+0.191
cks+0.190
flower+0.190
ble+0.190
ric+0.185
Neg logit contributions
ives-0.101
 Sadly-0.091
 Max-0.088
 And-0.086
 People-0.083
Token best
Token ID1266
Feature activation-2.95e-01

Pos logit contributions
flower+0.049
ric+0.046
els+0.045
ble+0.045
bery+0.044
Neg logit contributions
ives-0.017
 Max-0.017
 Enjoy-0.017
 Happy-0.016
 Welcome-0.016
Token friends
Token ID2460
Feature activation-2.67e-01

Pos logit contributions
ives+0.009
ury+0.007
 Enjoy+0.007
 Welcome+0.007
 Follow+0.007
Neg logit contributions
flower-0.016
ble-0.015
ric-0.014
els-0.014
cking-0.014
Token!
Token ID0
Feature activation+7.14e-01

Pos logit contributions
ives+0.011
ury+0.010
 Enjoy+0.010
 Follow+0.010
 Welcome+0.010
Neg logit contributions
flower-0.011
ble-0.009
ric-0.009
cking-0.009
els-0.009
Token<|endoftext|>
Token ID50256
Feature activation-2.00e-01

Pos logit contributions
flower+0.045
ble+0.042
cking+0.042
els+0.041
ric+0.041
Neg logit contributions
ives-0.014
 Enjoy-0.011
ury-0.011
 Welcome-0.011
 Happy-0.010
Token and
Token ID290
Feature activation+2.76e-01

Pos logit contributions
flower+0.029
ble+0.025
ric+0.025
els+0.025
cking+0.025
Neg logit contributions
ives-0.021
ury-0.019
 Enjoy-0.019
 Welcome-0.018
 Follow-0.018
Token his
Token ID465
Feature activation+1.14e+00

Pos logit contributions
flower+0.013
ble+0.011
cking+0.011
ric+0.011
els+0.011
Neg logit contributions
ives-0.010
ury-0.009
 Enjoy-0.009
 Max-0.009
 Welcome-0.009
Token dog
Token ID3290
Feature activation+1.05e+00

Pos logit contributions
flower+0.054
ble+0.049
ric+0.048
els+0.047
cking+0.047
Neg logit contributions
ives-0.041
ury-0.036
 Enjoy-0.035
 Welcome-0.034
 Follow-0.033
Token and
Token ID290
Feature activation+7.56e-01

Pos logit contributions
flower+0.045
ble+0.039
ric+0.039
els+0.039
cking+0.038
Neg logit contributions
ives-0.042
ury-0.038
 Enjoy-0.037
 Welcome-0.036
 Follow-0.036
Token his
Token ID465
Feature activation+1.56e+00

Pos logit contributions
flower+0.030
ble+0.027
ric+0.026
els+0.026
cking+0.026
Neg logit contributions
ives-0.032
ury-0.029
 Enjoy-0.029
 Welcome-0.028
 Follow-0.027
Token sunset
Token ID26428
Feature activation+3.80e+00

Pos logit contributions
flower+0.075
ble+0.066
ric+0.066
els+0.065
cking+0.063
Neg logit contributions
ives-0.057
ury-0.050
 Enjoy-0.048
 Follow-0.047
 Welcome-0.046
Token.
Token ID13
Feature activation+1.52e-01

Pos logit contributions
flower+0.167
ble+0.151
ric+0.149
cking+0.148
els+0.146
Neg logit contributions
ives-0.147
ury-0.131
 Enjoy-0.127
 Welcome-0.124
 Happy-0.122
Token He
Token ID679
Feature activation+1.86e-01

Pos logit contributions
flower+0.008
ric+0.008
ble+0.008
els+0.007
cks+0.007
Neg logit contributions
ives-0.004
ury-0.004
 Enjoy-0.003
 Follow-0.003
 Welcome-0.003
Token writes
Token ID6797
Feature activation-1.29e+00

Pos logit contributions
flower+0.010
ble+0.009
cking+0.009
ric+0.009
els+0.009
Neg logit contributions
ives-0.005
ury-0.005
 Enjoy-0.005
 Welcome-0.004
 Happy-0.004
Token happy
Token ID3772
Feature activation+4.93e-01

Pos logit contributions
ives+0.055
ury+0.049
 Enjoy+0.048
 Welcome+0.047
 Follow+0.047
Neg logit contributions
flower-0.052
ble-0.048
els-0.046
ric-0.045
cking-0.044
Token and
Token ID290
Feature activation+4.53e-02

Pos logit contributions
flower+0.023
ble+0.021
ric+0.020
els+0.020
cking+0.020
Neg logit contributions
ives-0.018
ury-0.016
 Enjoy-0.016
 Welcome-0.015
 Follow-0.015
Token shining
Token ID22751
Feature activation+1.56e+00

Pos logit contributions
flower+0.026
els+0.025
ric+0.024
bery+0.024
cks+0.024
Neg logit contributions
 Enjoy-0.013
 Max-0.013
 Happy-0.013
 Welcome-0.013
ives-0.013
Token and
Token ID290
Feature activation+8.22e-01

Pos logit contributions
flower+0.079
ric+0.074
cking+0.072
ble+0.072
els+0.071
Neg logit contributions
ives-0.048
ury-0.041
 Happy-0.041
 Welcome-0.040
 Enjoy-0.040
Token it
Token ID340
Feature activation+9.32e-01

Pos logit contributions
flower+0.037
ble+0.034
ric+0.033
cking+0.033
els+0.032
Neg logit contributions
ives-0.031
ury-0.028
 Enjoy-0.027
 Welcome-0.026
 Follow-0.025
Token's
Token ID338
Feature activation+5.03e-01

Pos logit contributions
flower+0.049
ble+0.044
ric+0.044
cking+0.043
els+0.043
Neg logit contributions
ives-0.028
ury-0.025
 Enjoy-0.025
 Welcome-0.022
 Happy-0.022
Token not
Token ID407
Feature activation+1.46e+00

Pos logit contributions
flower+0.025
els+0.023
ble+0.023
ric+0.022
cking+0.022
Neg logit contributions
ives-0.015
 Enjoy-0.014
 Welcome-0.014
ury-0.013
 Happy-0.013
Token raining
Token ID43079
Feature activation+3.76e+00

Pos logit contributions
flower+0.082
els+0.076
ble+0.074
ric+0.074
cking+0.072
Neg logit contributions
ives-0.035
ury-0.032
 Max-0.031
 Welcome-0.031
 Enjoy-0.031
Token,
Token ID11
Feature activation+5.79e-01

Pos logit contributions
flower+0.172
ble+0.155
ric+0.151
cking+0.149
els+0.148
Neg logit contributions
ives-0.138
ury-0.123
 Enjoy-0.122
 Welcome-0.116
 Follow-0.115
Token okay
Token ID8788
Feature activation+1.05e+00

Pos logit contributions
flower+0.028
ble+0.026
ric+0.025
cking+0.025
els+0.025
Neg logit contributions
ives-0.020
ury-0.017
 Enjoy-0.017
 Welcome-0.016
 Follow-0.016
Token?"
Token ID1701
Feature activation+6.84e-01

Pos logit contributions
cking+0.049
flower+0.049
cks+0.048
els+0.047
eled+0.045
Neg logit contributions
 Max-0.031
 Enjoy-0.029
 Welcome-0.029
ury-0.029
 Happy-0.028
Token
Token ID220
Feature activation+1.75e+00

Pos logit contributions
flower+0.035
ble+0.032
ric+0.031
els+0.031
cking+0.031
Neg logit contributions
ives-0.021
ury-0.017
 Enjoy-0.017
 Follow-0.016
 villains-0.016
Token
Token ID198
Feature activation+1.29e+00

Pos logit contributions
flower+0.103
ble+0.095
ric+0.093
cking+0.093
els+0.092
Neg logit contributions
ives-0.042
ury-0.035
 Enjoy-0.034
 Welcome-0.032
 Follow-0.030
Token her
Token ID607
Feature activation+7.94e-01

Pos logit contributions
flower+0.046
ble+0.041
ric+0.040
els+0.040
cking+0.040
Neg logit contributions
ives-0.049
ury-0.044
 Enjoy-0.043
 Welcome-0.042
 Follow-0.041
Token siblings
Token ID20569
Feature activation+5.19e-01

Pos logit contributions
flower+0.038
ble+0.035
els+0.033
ric+0.033
cking+0.032
Neg logit contributions
ives-0.029
ury-0.026
 Enjoy-0.025
 Follow-0.024
 Welcome-0.024
Token and
Token ID290
Feature activation+7.72e-01

Pos logit contributions
flower+0.025
ble+0.022
ric+0.022
cking+0.022
els+0.021
Neg logit contributions
ives-0.018
ury-0.016
 Enjoy-0.016
 Welcome-0.015
 Happy-0.015
Token loved
Token ID6151
Feature activation-1.39e-01

Pos logit contributions
flower+0.038
ble+0.034
ric+0.033
els+0.033
cking+0.032
Neg logit contributions
ives-0.027
ury-0.023
 Enjoy-0.022
 Welcome-0.022
 Follow-0.022
Token to
Token ID284
Feature activation+2.95e-01

Pos logit contributions
ives+0.003
ury+0.003
 Follow+0.002
 Enjoy+0.002
 Welcome+0.002
Neg logit contributions
flower-0.008
ric-0.008
ble-0.008
els-0.008
cking-0.008
Token trem
Token ID10023
Feature activation+3.69e+00

Pos logit contributions
flower+0.017
ble+0.016
cking+0.015
els+0.015
ric+0.015
Neg logit contributions
ives-0.007
 Enjoy-0.006
ury-0.006
 Welcome-0.006
 Happy-0.006
Tokenble
Token ID903
Feature activation+1.70e+00

Pos logit contributions
flower+0.051
ric+0.035
els+0.027
eled+0.026
cking+0.026
Neg logit contributions
ives-0.228
ury-0.219
 People-0.218
and-0.217
 hide-0.216
Token and
Token ID290
Feature activation+9.51e-01

Pos logit contributions
flower+0.074
ble+0.067
els+0.065
cking+0.065
ric+0.064
Neg logit contributions
ives-0.066
ury-0.060
 Enjoy-0.059
 Welcome-0.057
 Follow-0.056
Token make
Token ID787
Feature activation+1.85e+00

Pos logit contributions
flower+0.047
ric+0.042
ble+0.042
cking+0.041
els+0.040
Neg logit contributions
ives-0.034
ury-0.029
 Enjoy-0.027
 Welcome-0.026
 Follow-0.026
Token them
Token ID606
Feature activation+1.17e+00

Pos logit contributions
flower+0.081
ble+0.072
ric+0.071
els+0.069
cking+0.069
Neg logit contributions
ives-0.073
ury-0.065
 Enjoy-0.064
 Welcome-0.063
 Happy-0.062
Token laugh
Token ID6487
Feature activation+2.12e+00

Pos logit contributions
flower+0.067
els+0.064
eled+0.062
ries+0.060
ric+0.060
Neg logit contributions
ives-0.026
 hide-0.024
 Welcome-0.022
 Happy-0.021
 Max-0.021
Token structure
Token ID4645
Feature activation+2.63e+00

Pos logit contributions
ives+0.003
ury+0.003
 Enjoy+0.003
 Welcome+0.003
 Follow+0.003
Neg logit contributions
flower-0.003
ble-0.003
ric-0.003
els-0.003
cking-0.003
Token and
Token ID290
Feature activation-4.85e-02

Pos logit contributions
flower+0.104
ble+0.090
cking+0.089
els+0.089
ric+0.087
Neg logit contributions
ives-0.111
 Enjoy-0.104
ury-0.103
 Welcome-0.098
 Happy-0.097
Token ran
Token ID4966
Feature activation+1.42e-01

Pos logit contributions
ives+0.002
ury+0.002
 Enjoy+0.002
 Welcome+0.002
 These+0.002
Neg logit contributions
flower-0.002
ble-0.002
cking-0.002
els-0.002
ric-0.002
Token to
Token ID284
Feature activation+1.27e-01

Pos logit contributions
flower+0.007
ble+0.006
cking+0.006
els+0.006
mill+0.006
Neg logit contributions
ives-0.004
ury-0.004
 Enjoy-0.004
 Welcome-0.004
 People-0.004
Token their
Token ID511
Feature activation-6.86e-02

Pos logit contributions
flower+0.004
ble+0.003
cking+0.003
ric+0.003
els+0.003
Neg logit contributions
ives-0.007
ury-0.006
 Follow-0.006
ave-0.006
 Enjoy-0.006
Token structures
Token ID8573
Feature activation+3.68e+00

Pos logit contributions
ives+0.003
ury+0.002
 Enjoy+0.002
 Welcome+0.002
 Happy+0.002
Neg logit contributions
flower-0.003
ble-0.003
ric-0.003
els-0.003
cking-0.003
Token.
Token ID13
Feature activation-4.22e-01

Pos logit contributions
flower+0.159
ble+0.142
ric+0.140
cking+0.138
els+0.137
Neg logit contributions
ives-0.146
ury-0.131
 Enjoy-0.128
 Welcome-0.124
 Happy-0.121
Token But
Token ID887
Feature activation+2.22e-01

Pos logit contributions
ives+0.015
ury+0.014
 Enjoy+0.013
 Follow+0.012
itt+0.012
Neg logit contributions
flower-0.015
ric-0.015
cks-0.015
mill-0.014
els-0.014
Token they
Token ID484
Feature activation-1.23e+00

Pos logit contributions
flower+0.008
ble+0.007
cking+0.006
els+0.006
mill+0.006
Neg logit contributions
ives-0.011
ury-0.010
 Enjoy-0.010
 Welcome-0.009
 Follow-0.009
Token were
Token ID547
Feature activation+5.59e-03

Pos logit contributions
ives+0.042
 Enjoy+0.038
ury+0.037
 Welcome+0.037
 Happy+0.037
Neg logit contributions
flower-0.059
ble-0.055
ric-0.053
cking-0.051
els-0.051
Token gone
Token ID3750
Feature activation+6.02e-01

Pos logit contributions
flower+0.000
ble+0.000
ric+0.000
cking+0.000
els+0.000
Neg logit contributions
ives-0.000
ury-0.000
 Enjoy-0.000
 Welcome-0.000
 Happy-0.000
Token his
Token ID465
Feature activation+1.22e+00

Pos logit contributions
flower+0.014
ble+0.012
ric+0.012
cking+0.012
els+0.012
Neg logit contributions
ives-0.009
ury-0.008
 Enjoy-0.008
 Welcome-0.008
 Follow-0.007
Token stomach
Token ID11384
Feature activation+1.44e+00

Pos logit contributions
flower+0.057
ble+0.051
ric+0.050
els+0.049
cking+0.049
Neg logit contributions
ives-0.045
ury-0.040
 Enjoy-0.039
 Welcome-0.038
 Follow-0.037
Token was
Token ID373
Feature activation+7.61e-01

Pos logit contributions
flower+0.067
ric+0.063
els+0.062
cking+0.061
ble+0.060
Neg logit contributions
ives-0.049
ury-0.044
 Max-0.040
 Enjoy-0.039
 Welcome-0.038
Token starting
Token ID3599
Feature activation+1.46e+00

Pos logit contributions
flower+0.040
els+0.036
ble+0.035
ric+0.035
cking+0.034
Neg logit contributions
ives-0.021
 Enjoy-0.019
 Max-0.018
 Welcome-0.018
ury-0.017
Token to
Token ID284
Feature activation+1.76e-01

Pos logit contributions
flower+0.103
ble+0.096
ric+0.096
els+0.095
cking+0.095
Neg logit contributions
ives-0.014
 Enjoy-0.008
 Welcome-0.008
 Sadly-0.006
ury-0.006
Token trem
Token ID10023
Feature activation+3.65e+00

Pos logit contributions
els+0.009
flower+0.009
lights+0.008
ries+0.008
cks+0.008
Neg logit contributions
 hide-0.005
ives-0.005
 Enjoy-0.004
 Welcome-0.004
 Max-0.004
Tokenble
Token ID903
Feature activation+1.74e+00

Pos logit contributions
flower+0.055
ric+0.052
cks+0.041
els+0.037
cking+0.037
Neg logit contributions
ives-0.205
ury-0.201
and-0.200
 hide-0.198
 Give-0.197
Token.
Token ID13
Feature activation+4.71e-02

Pos logit contributions
flower+0.083
ric+0.077
els+0.074
ble+0.073
cking+0.073
Neg logit contributions
ives-0.060
ury-0.053
 Enjoy-0.051
 Welcome-0.050
 Max-0.049
Token
Token ID198
Feature activation+4.43e-02

Pos logit contributions
flower+0.002
ble+0.002
ric+0.002
eled+0.002
els+0.002
Neg logit contributions
ives-0.002
ury-0.001
 villains-0.001
 Enjoy-0.001
 hide-0.001
Token
Token ID198
Feature activation+3.08e-01

Pos logit contributions
flower+0.002
ble+0.002
ric+0.002
cking+0.002
els+0.002
Neg logit contributions
ives-0.001
ury-0.001
 Enjoy-0.001
 Welcome-0.001
 Happy-0.001
TokenHis
Token ID6653
Feature activation+5.90e-01

Pos logit contributions
flower+0.013
ble+0.011
ric+0.011
els+0.011
cking+0.011
Neg logit contributions
ives-0.013
ury-0.012
 Enjoy-0.011
 Welcome-0.011
 Follow-0.011
Token and
Token ID290
Feature activation+2.23e-01

Pos logit contributions
flower+0.002
ble+0.002
ric+0.002
cking+0.002
els+0.002
Neg logit contributions
ives-0.001
ury-0.001
 Enjoy-0.001
 Welcome-0.001
 Happy-0.001
Token his
Token ID465
Feature activation+7.45e-01

Pos logit contributions
flower+0.011
ble+0.009
ric+0.009
cking+0.009
els+0.009
Neg logit contributions
ives-0.008
ury-0.007
 Enjoy-0.007
 Welcome-0.007
 Follow-0.006
Token phone
Token ID3072
Feature activation+9.45e-01

Pos logit contributions
flower+0.036
ble+0.033
ric+0.032
cking+0.032
els+0.032
Neg logit contributions
ives-0.026
ury-0.023
 Enjoy-0.022
 Welcome-0.021
 Follow-0.021
Token and
Token ID290
Feature activation+4.57e-01

Pos logit contributions
flower+0.043
ble+0.039
cking+0.038
ric+0.038
els+0.037
Neg logit contributions
ives-0.035
ury-0.031
 Enjoy-0.030
 Welcome-0.030
 Happy-0.029
Token the
Token ID262
Feature activation+8.43e-01

Pos logit contributions
flower+0.020
ble+0.018
ric+0.017
cking+0.017
els+0.017
Neg logit contributions
ives-0.018
ury-0.016
 Enjoy-0.016
 Welcome-0.016
 Happy-0.015
Token fake
Token ID8390
Feature activation+3.63e+00

Pos logit contributions
flower+0.040
ble+0.037
cking+0.036
els+0.036
ric+0.036
Neg logit contributions
ives-0.028
 Enjoy-0.025
 Welcome-0.025
ury-0.024
 Max-0.024
Token mustache
Token ID49303
Feature activation+1.24e+00

Pos logit contributions
flower+0.177
ble+0.164
cking+0.163
ric+0.161
cks+0.157
Neg logit contributions
ives-0.118
ury-0.103
 Welcome-0.099
 Enjoy-0.099
 Happy-0.097
Token.
Token ID13
Feature activation+1.97e-02

Pos logit contributions
flower+0.056
ble+0.051
ric+0.050
cking+0.050
els+0.049
Neg logit contributions
ives-0.046
ury-0.041
 Enjoy-0.039
 Welcome-0.039
 Happy-0.038
Token<|endoftext|>
Token ID50256
Feature activation-5.62e-01

Pos logit contributions
flower+0.001
ble+0.001
ric+0.001
els+0.001
cking+0.001
Neg logit contributions
ives-0.000
ury-0.000
 Enjoy-0.000
 Welcome-0.000
 Follow-0.000
TokenL
Token ID43
Feature activation-1.61e+00

Pos logit contributions
ives+0.023
ury+0.021
 Enjoy+0.020
 Welcome+0.020
 Follow+0.020
Neg logit contributions
flower-0.023
ble-0.021
ric-0.020
els-0.020
cking-0.019
Tokenily
Token ID813
Feature activation-8.17e-01

Pos logit contributions
ives+0.051
 Enjoy+0.042
ury+0.042
 Happy+0.040
 Welcome+0.040
Neg logit contributions
flower-0.085
ble-0.076
ric-0.076
cking-0.076
els-0.072
Token sit
Token ID1650
Feature activation-8.71e-01

Pos logit contributions
ives+0.055
ury+0.048
 Enjoy+0.047
 Welcome+0.045
 Happy+0.043
Neg logit contributions
flower-0.093
ble-0.085
ric-0.083
cking-0.083
els-0.082
Token down
Token ID866
Feature activation+6.10e-01

Pos logit contributions
ives+0.025
 Max+0.023
 Enjoy+0.022
ury+0.022
 Happy+0.022
Neg logit contributions
flower-0.042
ric-0.041
cking-0.040
cks-0.039
els-0.038
Token and
Token ID290
Feature activation+8.02e-02

Pos logit contributions
flower+0.029
ble+0.026
els+0.025
ric+0.025
cking+0.025
Neg logit contributions
ives-0.022
ury-0.020
 Enjoy-0.019
 Welcome-0.018
 Follow-0.018
Token do
Token ID466
Feature activation+1.61e+00

Pos logit contributions
flower+0.004
ric+0.003
ble+0.003
cking+0.003
els+0.003
Neg logit contributions
ives-0.003
ury-0.003
 Enjoy-0.002
and-0.002
 Follow-0.002
Token her
Token ID607
Feature activation+1.20e+00

Pos logit contributions
flower+0.081
ble+0.072
ric+0.070
cking+0.069
els+0.068
Neg logit contributions
ives-0.054
ury-0.048
 Enjoy-0.047
 Welcome-0.045
 People-0.045
Token math
Token ID10688
Feature activation+3.62e+00

Pos logit contributions
flower+0.055
ble+0.051
ric+0.049
els+0.049
cking+0.047
Neg logit contributions
ives-0.044
ury-0.039
 Enjoy-0.037
 Welcome-0.035
 Follow-0.035
Token exercises
Token ID13565
Feature activation+2.67e+00

Pos logit contributions
flower+0.187
ble+0.170
ric+0.167
cking+0.166
els+0.165
Neg logit contributions
ives-0.113
ury-0.098
 Enjoy-0.096
 Welcome-0.092
 Follow-0.089
Token.
Token ID13
Feature activation-2.69e-01

Pos logit contributions
flower+0.131
ble+0.119
ric+0.118
cking+0.116
els+0.116
Neg logit contributions
ives-0.090
ury-0.079
 Enjoy-0.077
 Welcome-0.074
 Happy-0.073
Token She
Token ID1375
Feature activation+5.03e-01

Pos logit contributions
ives+0.008
ury+0.008
 Enjoy+0.007
 villains+0.007
 Cop+0.007
Neg logit contributions
flower-0.013
els-0.011
ric-0.011
ble-0.011
cks-0.011
Token loved
Token ID6151
Feature activation-1.49e+00

Pos logit contributions
flower+0.025
ble+0.022
ric+0.022
els+0.022
cking+0.022
Neg logit contributions
ives-0.017
ury-0.015
 Enjoy-0.014
 Welcome-0.014
 Follow-0.013
Token finishing
Token ID12848
Feature activation+8.61e-02

Pos logit contributions
ives+0.048
ury+0.041
 Follow+0.040
 Enjoy+0.040
 Sadly+0.038
Neg logit contributions
flower-0.074
els-0.068
ric-0.068
ble-0.067
cking-0.066
Token cave
Token ID11527
Feature activation+3.50e-02

Pos logit contributions
flower+0.013
ble+0.012
ric+0.010
els+0.010
cking+0.010
Neg logit contributions
ives-0.016
ury-0.015
 Enjoy-0.014
enny-0.013
and-0.012
Token started
Token ID2067
Feature activation-1.47e-01

Pos logit contributions
flower+0.002
ble+0.001
els+0.001
cking+0.001
ric+0.001
Neg logit contributions
ives-0.001
 Enjoy-0.001
ury-0.001
 Welcome-0.001
 Happy-0.001
Token to
Token ID284
Feature activation-4.53e-01

Pos logit contributions
ives+0.003
ury+0.002
 Welcome+0.002
 Enjoy+0.002
 Happy+0.002
Neg logit contributions
flower-0.010
ble-0.009
ric-0.009
cking-0.009
els-0.009
Token shake
Token ID13279
Feature activation+1.52e+00

Pos logit contributions
 hide+0.015
ives+0.014
 Welcome+0.013
 Max+0.013
 Happy+0.013
Neg logit contributions
flower-0.021
els-0.020
ric-0.019
ries-0.019
cks-0.019
Token and
Token ID290
Feature activation+3.24e-01

Pos logit contributions
flower+0.074
ric+0.067
ble+0.066
cking+0.065
els+0.064
Neg logit contributions
ives-0.051
ury-0.046
 Max-0.044
 Happy-0.043
 Welcome-0.043
Token trem
Token ID10023
Feature activation+3.61e+00

Pos logit contributions
flower+0.014
ble+0.013
ric+0.012
cking+0.012
els+0.012
Neg logit contributions
ives-0.013
ury-0.011
 Enjoy-0.011
 Welcome-0.011
 Happy-0.011
Tokenble
Token ID903
Feature activation+1.79e+00

Pos logit contributions
flower+0.055
ric+0.045
cking+0.031
els+0.030
ries+0.030
Neg logit contributions
ives-0.213
ury-0.211
 hide-0.207
 Follow-0.205
 Max-0.205
Token.
Token ID13
Feature activation+1.38e-01

Pos logit contributions
flower+0.082
ric+0.073
ble+0.072
els+0.070
cking+0.070
Neg logit contributions
ives-0.067
ury-0.060
 Enjoy-0.057
 Welcome-0.057
 Max-0.055
Token Suddenly
Token ID24975
Feature activation+7.56e-01

Pos logit contributions
ble+0.005
flower+0.005
ric+0.005
esh+0.005
neath+0.004
Neg logit contributions
ives-0.005
ury-0.004
 Bye-0.004
 Enjoy-0.004
and-0.004
Token,
Token ID11
Feature activation-4.52e-01

Pos logit contributions
flower+0.031
ble+0.030
els+0.027
cking+0.027
bery+0.026
Neg logit contributions
ives-0.031
 Enjoy-0.026
ury-0.026
 Welcome-0.026
and-0.025
Token the
Token ID262
Feature activation-1.70e-01

Pos logit contributions
ives+0.017
ury+0.015
 Enjoy+0.014
 Welcome+0.014
 Follow+0.014
Neg logit contributions
flower-0.020
ble-0.020
cking-0.018
ric-0.018
els-0.017
Token to
Token ID284
Feature activation-1.69e-01

Pos logit contributions
flower+0.017
ric+0.016
ble+0.016
els+0.015
cking+0.015
Neg logit contributions
ives-0.008
ury-0.007
 Follow-0.006
 Welcome-0.006
 Enjoy-0.006
Token stay
Token ID2652
Feature activation+2.27e-01

Pos logit contributions
ives+0.006
ury+0.005
 Enjoy+0.005
 Welcome+0.005
 Happy+0.005
Neg logit contributions
flower-0.008
ble-0.007
ric-0.007
cking-0.007
els-0.007
Token and
Token ID290
Feature activation+5.06e-01

Pos logit contributions
flower+0.013
ric+0.012
els+0.011
ble+0.011
ries+0.011
Neg logit contributions
ives-0.006
 Max-0.005
 hide-0.005
ury-0.005
 Enjoy-0.005
Token finish
Token ID5461
Feature activation+1.92e+00

Pos logit contributions
flower+0.022
ble+0.021
ric+0.020
cking+0.019
mill+0.019
Neg logit contributions
ives-0.020
ury-0.017
 Enjoy-0.016
 Welcome-0.016
 Happy-0.016
Token his
Token ID465
Feature activation+4.67e-01

Pos logit contributions
flower+0.095
ric+0.081
ble+0.080
cking+0.079
els+0.078
Neg logit contributions
ives-0.063
 Enjoy-0.059
ury-0.058
 Max-0.058
 Happy-0.057
Token math
Token ID10688
Feature activation+3.61e+00

Pos logit contributions
flower+0.020
ble+0.019
els+0.018
ric+0.018
cking+0.018
Neg logit contributions
ives-0.018
ury-0.016
 Enjoy-0.015
 Welcome-0.015
 Follow-0.014
Token.
Token ID13
Feature activation-1.61e-02

Pos logit contributions
flower+0.169
ble+0.155
cking+0.150
els+0.150
ric+0.148
Neg logit contributions
ives-0.124
 Enjoy-0.112
ury-0.110
 Welcome-0.106
 Follow-0.103
Token So
Token ID1406
Feature activation-2.22e-01

Pos logit contributions
ives+0.000
ury+0.000
 Enjoy+0.000
 Welcome+0.000
 villains+0.000
Neg logit contributions
flower-0.001
ric-0.001
els-0.001
ble-0.001
ries-0.001
Token Tim
Token ID5045
Feature activation-8.30e-01

Pos logit contributions
ives+0.006
ury+0.005
 Enjoy+0.005
 Welcome+0.005
 Happy+0.005
Neg logit contributions
flower-0.012
ble-0.011
ric-0.011
cking-0.011
els-0.011
Tokenmy
Token ID1820
Feature activation-8.24e-01

Pos logit contributions
ives+0.032
ury+0.029
 Enjoy+0.028
 Welcome+0.028
 Happy+0.027
Neg logit contributions
flower-0.038
ble-0.033
ric-0.032
els-0.032
cking-0.032
Token stayed
Token ID9658
Feature activation-3.08e-01

Pos logit contributions
ives+0.030
 Enjoy+0.027
 Welcome+0.027
ury+0.027
 Happy+0.025
Neg logit contributions
flower-0.037
ble-0.034
els-0.032
cking-0.032
ric-0.032
Token and
Token ID290
Feature activation+4.58e-01

Pos logit contributions
flower+0.002
ric+0.001
cking+0.001
cks+0.001
els+0.001
Neg logit contributions
ives-0.001
 Max-0.001
ury-0.001
 Welcome-0.001
 Happy-0.001
Token quickly
Token ID2952
Feature activation-3.50e-01

Pos logit contributions
flower+0.021
ble+0.019
ric+0.019
els+0.019
cking+0.019
Neg logit contributions
ives-0.017
ury-0.015
 Enjoy-0.014
 Welcome-0.014
 Happy-0.014
Token put
Token ID1234
Feature activation+3.10e-01

Pos logit contributions
ives+0.012
ury+0.010
 Enjoy+0.010
 Welcome+0.009
 Max+0.009
Neg logit contributions
flower-0.018
ric-0.016
ble-0.016
els-0.015
cking-0.015
Token on
Token ID319
Feature activation+1.87e+00

Pos logit contributions
flower+0.013
ric+0.012
ble+0.012
cking+0.011
els+0.011
Neg logit contributions
ives-0.012
 Enjoy-0.011
 Max-0.011
 Happy-0.011
ury-0.011
Token his
Token ID465
Feature activation+7.24e-01

Pos logit contributions
flower+0.085
ble+0.074
ric+0.071
cking+0.069
els+0.067
Neg logit contributions
ives-0.071
 Enjoy-0.065
 Max-0.065
 Happy-0.064
ury-0.063
Token rain
Token ID6290
Feature activation+3.61e+00

Pos logit contributions
flower+0.032
ric+0.029
cking+0.028
ble+0.028
els+0.027
Neg logit contributions
ives-0.027
ury-0.025
 Enjoy-0.024
 Welcome-0.024
 Happy-0.024
Tokencoat
Token ID31434
Feature activation+1.14e-01

Pos logit contributions
flower+0.181
ble+0.173
cking+0.170
ric+0.169
els+0.166
Neg logit contributions
ives-0.119
ury-0.100
 Max-0.091
 hide-0.091
and-0.084
Token.
Token ID13
Feature activation+2.93e-02

Pos logit contributions
flower+0.005
ble+0.005
ric+0.005
cking+0.005
els+0.005
Neg logit contributions
ives-0.004
ury-0.004
 Enjoy-0.004
 Welcome-0.003
 Max-0.003
Token When
Token ID1649
Feature activation+9.54e-01

Pos logit contributions
flower+0.001
mill+0.001
ric+0.001
lights+0.001
ble+0.001
Neg logit contributions
ives-0.001
ury-0.001
 Enjoy-0.001
unn-0.001
 Follow-0.001
Token he
Token ID339
Feature activation-6.85e-01

Pos logit contributions
flower+0.045
ble+0.041
cking+0.040
ric+0.040
els+0.040
Neg logit contributions
ives-0.035
ury-0.030
 Enjoy-0.028
 Follow-0.027
 Welcome-0.027
Token was
Token ID373
Feature activation+1.33e-01

Pos logit contributions
ives+0.024
ury+0.022
 Enjoy+0.021
 Welcome+0.020
 Follow+0.020
Neg logit contributions
flower-0.033
ble-0.029
els-0.028
ric-0.028
cking-0.028
Token the
Token ID262
Feature activation+1.77e-01

Pos logit contributions
flower+0.016
ble+0.015
ric+0.015
cking+0.014
els+0.014
Neg logit contributions
ives-0.022
ury-0.019
 Follow-0.018
 Welcome-0.018
 Thank-0.017
Token hive
Token ID35881
Feature activation+7.74e-01

Pos logit contributions
flower+0.006
ble+0.005
cking+0.005
ric+0.005
els+0.004
Neg logit contributions
ives-0.009
ury-0.008
 Enjoy-0.008
 Welcome-0.008
 Happy-0.008
Token and
Token ID290
Feature activation+3.64e-01

Pos logit contributions
flower+0.036
ble+0.032
ric+0.031
els+0.030
cking+0.030
Neg logit contributions
ives-0.028
 Enjoy-0.026
ury-0.025
 Welcome-0.024
 Happy-0.023
Token started
Token ID2067
Feature activation+7.77e-01

Pos logit contributions
flower+0.015
ble+0.014
cking+0.013
ric+0.013
 perched+0.012
Neg logit contributions
ives-0.015
 Enjoy-0.013
 These-0.012
ury-0.012
 People-0.012
Token to
Token ID284
Feature activation+1.49e-02

Pos logit contributions
flower+0.051
ble+0.048
ric+0.047
els+0.047
cking+0.046
Neg logit contributions
ives-0.013
ury-0.010
 Enjoy-0.009
 Welcome-0.009
 Happy-0.008
Token trem
Token ID10023
Feature activation+3.60e+00

Pos logit contributions
flower+0.001
ble+0.001
ric+0.001
cking+0.001
els+0.001
Neg logit contributions
ives-0.001
ury-0.000
 Enjoy-0.000
 Welcome-0.000
 Happy-0.000
Tokenble
Token ID903
Feature activation+1.76e+00

Pos logit contributions
flower+0.053
ric+0.044
ries+0.029
mill+0.029
cking+0.028
Neg logit contributions
ives-0.211
 hide-0.210
ury-0.210
 Follow-0.205
 Max-0.202
Token with
Token ID351
Feature activation+2.55e-01

Pos logit contributions
flower+0.079
ble+0.070
ric+0.070
cking+0.068
els+0.068
Neg logit contributions
ives-0.067
ury-0.059
 Enjoy-0.057
 Welcome-0.057
 Happy-0.055
Token excitement
Token ID14067
Feature activation+8.73e-01

Pos logit contributions
flower+0.009
ble+0.009
cking+0.008
els+0.008
ric+0.008
Neg logit contributions
ives-0.012
ury-0.011
 Enjoy-0.010
 Welcome-0.010
 Follow-0.010
Token.
Token ID13
Feature activation+1.77e-01

Pos logit contributions
flower+0.042
ric+0.038
cking+0.037
ble+0.037
els+0.036
Neg logit contributions
ives-0.030
ury-0.027
 Max-0.025
 Happy-0.025
 Welcome-0.025
Token But
Token ID887
Feature activation+5.40e-01

Pos logit contributions
flower+0.007
ble+0.007
ric+0.007
esh+0.006
mill+0.006
Neg logit contributions
ives-0.007
 Enjoy-0.005
itt-0.005
ury-0.005
and-0.005
Token make
Token ID787
Feature activation+1.05e+00

Pos logit contributions
ives+0.015
ury+0.013
 Enjoy+0.013
 Welcome+0.013
 Happy+0.012
Neg logit contributions
flower-0.023
ble-0.021
ric-0.021
cking-0.020
els-0.020
Token her
Token ID607
Feature activation+1.34e+00

Pos logit contributions
flower+0.043
ble+0.038
ric+0.037
cking+0.037
els+0.036
Neg logit contributions
ives-0.045
ury-0.040
 Enjoy-0.040
 Welcome-0.039
 Happy-0.038
Token mom
Token ID1995
Feature activation+1.25e+00

Pos logit contributions
flower+0.066
ble+0.061
ric+0.060
cking+0.059
els+0.058
Neg logit contributions
ives-0.045
ury-0.038
 Enjoy-0.037
 Welcome-0.037
 Max-0.037
Token angry
Token ID7954
Feature activation+2.37e+00

Pos logit contributions
flower+0.063
ble+0.061
ric+0.058
els+0.057
cking+0.055
Neg logit contributions
ives-0.039
ury-0.031
 Max-0.031
 Welcome-0.030
 Many-0.030
Token or
Token ID393
Feature activation+7.42e-01

Pos logit contributions
flower+0.103
ble+0.093
els+0.089
ric+0.089
cking+0.088
Neg logit contributions
ives-0.094
ury-0.084
 Enjoy-0.084
 Welcome-0.080
 Follow-0.079
Token sad
Token ID6507
Feature activation+3.56e+00

Pos logit contributions
flower+0.037
ble+0.034
ric+0.033
cking+0.033
els+0.033
Neg logit contributions
ives-0.024
ury-0.021
 Enjoy-0.021
 Welcome-0.020
 Follow-0.019
Token.
Token ID13
Feature activation-1.85e-01

Pos logit contributions
flower+0.168
ric+0.151
ble+0.150
cking+0.148
els+0.144
Neg logit contributions
ives-0.129
ury-0.113
 Max-0.108
 Enjoy-0.108
 Welcome-0.108
Token She
Token ID1375
Feature activation+5.40e-01

Pos logit contributions
ives+0.006
ury+0.005
 Enjoy+0.005
 Follow+0.004
 Welcome+0.004
Neg logit contributions
flower-0.009
ble-0.008
ric-0.008
els-0.008
mill-0.008
Token realized
Token ID6939
Feature activation-1.15e-01

Pos logit contributions
flower+0.023
ble+0.021
els+0.021
cking+0.021
eled+0.020
Neg logit contributions
ives-0.021
 Enjoy-0.018
 Welcome-0.018
ury-0.017
and-0.017
Token that
Token ID326
Feature activation-8.21e-01

Pos logit contributions
 Max+0.002
ives+0.001
 Jack+0.001
 Happy+0.001
 Miss+0.001
Neg logit contributions
flower-0.008
ric-0.007
cking-0.007
eled-0.007
cker-0.007
Token she
Token ID673
Feature activation+4.40e-02

Pos logit contributions
ives+0.033
ury+0.029
 Enjoy+0.028
 Follow+0.027
 Welcome+0.027
Neg logit contributions
flower-0.036
ble-0.032
els-0.031
ric-0.031
cking-0.031
Token mom
Token ID1995
Feature activation+9.89e-01

Pos logit contributions
flower+0.063
cking+0.059
ric+0.059
ble+0.058
els+0.057
Neg logit contributions
ives-0.031
 Max-0.030
 Happy-0.026
 Sadly-0.025
 And-0.025
Token and
Token ID290
Feature activation+2.03e-02

Pos logit contributions
flower+0.049
ble+0.049
ric+0.046
els+0.045
cking+0.043
Neg logit contributions
ives-0.031
 Max-0.025
and-0.025
ury-0.023
 Many-0.023
Token dad
Token ID9955
Feature activation+1.27e+00

Pos logit contributions
flower+0.001
ble+0.001
ric+0.001
cking+0.001
els+0.001
Neg logit contributions
ives-0.001
ury-0.001
 Enjoy-0.001
 Welcome-0.001
 Happy-0.001
Token angry
Token ID7954
Feature activation+2.88e+00

Pos logit contributions
flower+0.064
ble+0.059
ric+0.058
els+0.057
cking+0.056
Neg logit contributions
ives-0.042
ury-0.036
 Enjoy-0.034
 Welcome-0.034
 Max-0.033
Token and
Token ID290
Feature activation+5.61e-01

Pos logit contributions
flower+0.122
ble+0.108
ric+0.105
els+0.104
cking+0.104
Neg logit contributions
ives-0.118
ury-0.106
 Enjoy-0.104
 Welcome-0.101
 Follow-0.099
Token sad
Token ID6507
Feature activation+3.55e+00

Pos logit contributions
flower+0.025
ble+0.024
cking+0.023
mill+0.022
ric+0.022
Neg logit contributions
ives-0.020
ury-0.017
 Welcome-0.016
 Enjoy-0.016
 People-0.016
Token.
Token ID13
Feature activation-7.24e-02

Pos logit contributions
flower+0.157
ble+0.140
ric+0.138
cking+0.136
els+0.135
Neg logit contributions
ives-0.139
ury-0.124
 Enjoy-0.121
 Welcome-0.118
 Happy-0.116
Token She
Token ID1375
Feature activation+4.60e-01

Pos logit contributions
ives+0.002
ury+0.002
 Enjoy+0.002
ival+0.002
 Follow+0.002
Neg logit contributions
flower-0.004
ble-0.003
ric-0.003
els-0.003
mill-0.003
Token wanted
Token ID2227
Feature activation+8.72e-02

Pos logit contributions
flower+0.021
ble+0.019
cking+0.019
ric+0.018
els+0.018
Neg logit contributions
ives-0.017
 Welcome-0.014
 Enjoy-0.014
ury-0.014
and-0.014
Token to
Token ID284
Feature activation-5.61e-01

Pos logit contributions
flower+0.004
els+0.004
ble+0.004
ric+0.004
mill+0.004
Neg logit contributions
ives-0.003
ury-0.002
 Follow-0.002
 Welcome-0.002
 Enjoy-0.002
Token make
Token ID787
Feature activation+1.02e+00

Pos logit contributions
ives+0.016
ury+0.014
 Enjoy+0.014
 Welcome+0.013
 Happy+0.013
Neg logit contributions
flower-0.030
ble-0.028
ric-0.027
cking-0.027
els-0.027
Token excited
Token ID6568
Feature activation+2.86e-01

Pos logit contributions
ives+0.009
ury+0.007
 Enjoy+0.007
 Welcome+0.007
 Happy+0.007
Neg logit contributions
flower-0.017
ric-0.015
ble-0.015
els-0.015
cking-0.015
Token about
Token ID546
Feature activation-5.16e-01

Pos logit contributions
flower+0.015
ble+0.014
ric+0.013
els+0.013
cking+0.013
Neg logit contributions
ives-0.008
 Enjoy-0.007
ury-0.007
 Welcome-0.007
 Follow-0.007
Token r
Token ID374
Feature activation+2.45e+00

Pos logit contributions
 Max+0.016
 Jack+0.015
 Enjoy+0.015
 hide+0.014
ives+0.014
Neg logit contributions
flower-0.026
ric-0.022
bery-0.022
cking-0.022
ble-0.022
Tokenaking
Token ID868
Feature activation+5.27e-01

Pos logit contributions
flower+0.104
ric+0.094
cking+0.093
ble+0.093
cks+0.090
Neg logit contributions
ives-0.097
ury-0.081
 Enjoy-0.078
and-0.077
 People-0.075
Token and
Token ID290
Feature activation+3.90e-01

Pos logit contributions
flower+0.026
ric+0.023
ble+0.023
cking+0.023
eled+0.022
Neg logit contributions
ives-0.017
 Max-0.015
 People-0.014
 hide-0.014
ury-0.014
Token r
Token ID374
Feature activation+3.54e+00

Pos logit contributions
flower+0.018
ble+0.017
ric+0.016
cking+0.016
els+0.016
Neg logit contributions
ives-0.014
ury-0.013
 Enjoy-0.012
 Welcome-0.012
 Follow-0.012
Tokenaked
Token ID4335
Feature activation+1.46e+00

Pos logit contributions
flower+0.141
ble+0.125
ric+0.124
cking+0.123
bery+0.119
Neg logit contributions
ives-0.149
ury-0.125
 Enjoy-0.122
and-0.121
 Now-0.119
Token the
Token ID262
Feature activation+3.99e-01

Pos logit contributions
flower+0.068
ric+0.061
ble+0.061
cking+0.058
els+0.056
Neg logit contributions
ives-0.054
ury-0.047
 Max-0.046
 Enjoy-0.046
 Happy-0.045
Token small
Token ID1402
Feature activation+9.59e-01

Pos logit contributions
flower+0.016
ble+0.015
ric+0.014
cking+0.014
els+0.014
Neg logit contributions
ives-0.017
ury-0.015
 Enjoy-0.015
 Welcome-0.014
 Follow-0.014
Token piles
Token ID30935
Feature activation+1.88e+00

Pos logit contributions
flower+0.040
ble+0.037
cking+0.037
ric+0.037
cks+0.036
Neg logit contributions
ives-0.037
ury-0.034
 Enjoy-0.032
 Welcome-0.032
 Max-0.032
Token too
Token ID1165
Feature activation+8.22e-01

Pos logit contributions
flower+0.104
ble+0.096
ric+0.095
cking+0.094
els+0.093
Neg logit contributions
ives-0.051
ury-0.043
 Enjoy-0.042
 Welcome-0.040
 Happy-0.039
Token came
Token ID1625
Feature activation-1.14e+00

Pos logit contributions
ives+0.011
 helped+0.009
 Welcome+0.009
t+0.009
 Give+0.009
Neg logit contributions
els-0.032
ric-0.031
flower-0.031
cking-0.031
bery-0.031
Token and
Token ID290
Feature activation-1.36e+00

Pos logit contributions
ives+0.029
ury+0.025
 Welcome+0.024
 Max+0.024
 Enjoy+0.023
Neg logit contributions
flower-0.063
ric-0.058
cking-0.058
ble-0.057
els-0.056
Token blew
Token ID17948
Feature activation+3.30e-01

Pos logit contributions
ives+0.053
 Max+0.052
 Happy+0.049
 Enjoy+0.049
 Welcome+0.048
Neg logit contributions
flower-0.053
ric-0.049
ble-0.048
els-0.046
cking-0.046
Token away
Token ID1497
Feature activation+2.41e-01

Pos logit contributions
flower+0.014
ble+0.013
els+0.012
ric+0.012
cking+0.012
Neg logit contributions
ives-0.013
ury-0.012
 Enjoy-0.012
 Welcome-0.011
 Follow-0.011
Token their
Token ID511
Feature activation-1.75e-01

Pos logit contributions
flower+0.011
cking+0.010
ric+0.010
eled+0.009
ble+0.009
Neg logit contributions
 Max-0.008
ives-0.008
 Happy-0.008
 Enjoy-0.008
 And-0.008
Token structures
Token ID8573
Feature activation+3.53e+00

Pos logit contributions
ives+0.007
ury+0.006
 Enjoy+0.006
 Welcome+0.006
 Happy+0.006
Neg logit contributions
flower-0.008
ble-0.007
ric-0.007
cking-0.007
els-0.007
Token.
Token ID13
Feature activation-3.98e-01

Pos logit contributions
flower+0.175
ric+0.161
ble+0.156
els+0.153
cking+0.153
Neg logit contributions
ives-0.121
ury-0.100
 Max-0.095
 hide-0.094
 Welcome-0.094
Token The
Token ID383
Feature activation-8.03e-01

Pos logit contributions
ives+0.011
ury+0.010
 Follow+0.009
 Welcome+0.009
 Enjoy+0.009
Neg logit contributions
flower-0.020
ble-0.020
ric-0.019
els-0.019
mill-0.018
Token sticks
Token ID16461
Feature activation-7.00e-01

Pos logit contributions
ives+0.031
ury+0.028
 Enjoy+0.027
 Welcome+0.026
 Happy+0.026
Neg logit contributions
flower-0.036
ble-0.032
ric-0.031
cking-0.031
els-0.031
Token,
Token ID11
Feature activation-2.40e-01

Pos logit contributions
ives+0.024
ury+0.019
 hide+0.019
 Max+0.019
 Welcome+0.018
Neg logit contributions
flower-0.034
ric-0.031
els-0.029
cking-0.029
ble-0.029
Token stones
Token ID14966
Feature activation-6.51e-01

Pos logit contributions
ives+0.009
ury+0.008
 Enjoy+0.008
 Welcome+0.008
 Max+0.008
Neg logit contributions
flower-0.010
ble-0.009
ric-0.009
cking-0.009
els-0.009
Token made
Token ID925
Feature activation-7.29e-02

Pos logit contributions
flower+0.031
ble+0.028
ric+0.028
els+0.028
cking+0.027
Neg logit contributions
ives-0.022
ury-0.021
 Welcome-0.021
 Enjoy-0.021
 Happy-0.020
Token him
Token ID683
Feature activation-2.97e-01

Pos logit contributions
ives+0.003
ury+0.003
 Follow+0.003
 Welcome+0.003
 Enjoy+0.003
Neg logit contributions
flower-0.003
ble-0.003
els-0.003
cking-0.002
ric-0.002
Token and
Token ID290
Feature activation-4.13e-01

Pos logit contributions
ives+0.008
 hide+0.007
 Max+0.006
ury+0.006
 Enjoy+0.006
Neg logit contributions
flower-0.017
els-0.015
ric-0.015
eled-0.015
cking-0.014
Token his
Token ID465
Feature activation+6.03e-01

Pos logit contributions
ives+0.012
ury+0.011
 Enjoy+0.010
 Welcome+0.010
 Happy+0.009
Neg logit contributions
flower-0.022
ble-0.020
ric-0.020
els-0.020
cking-0.020
Token mom
Token ID1995
Feature activation+1.29e+00

Pos logit contributions
flower+0.030
ble+0.028
cking+0.027
ric+0.027
els+0.026
Neg logit contributions
ives-0.019
 Max-0.016
 Enjoy-0.016
ury-0.016
 Welcome-0.016
Token sad
Token ID6507
Feature activation+3.52e+00

Pos logit contributions
flower+0.067
ble+0.061
ric+0.060
els+0.059
cking+0.059
Neg logit contributions
ives-0.040
ury-0.034
 Enjoy-0.033
 Welcome-0.032
 Follow-0.031
Token.
Token ID13
Feature activation-5.12e-02

Pos logit contributions
flower+0.174
cking+0.160
ric+0.158
ble+0.157
els+0.155
Neg logit contributions
ives-0.117
ury-0.100
 Enjoy-0.097
 Max-0.095
 Thank-0.094
Token You
Token ID921
Feature activation+8.71e-01

Pos logit contributions
ives+0.001
ury+0.001
ival+0.001
 hide+0.001
 Enjoy+0.001
Neg logit contributions
flower-0.003
ric-0.002
els-0.002
ble-0.002
cks-0.002
Token made
Token ID925
Feature activation+9.56e-02

Pos logit contributions
flower+0.039
ric+0.035
ble+0.035
els+0.034
cking+0.033
Neg logit contributions
ury-0.029
ives-0.029
 Welcome-0.028
 Enjoy-0.028
 Bye-0.027
Token me
Token ID502
Feature activation-1.07e+00

Pos logit contributions
flower+0.004
ble+0.004
els+0.004
ric+0.004
cking+0.003
Neg logit contributions
ives-0.004
ury-0.004
 Follow-0.003
 Welcome-0.003
 Enjoy-0.003
Token and
Token ID290
Feature activation-4.42e-01

Pos logit contributions
ives+0.032
 Enjoy+0.027
ury+0.026
 Max+0.026
 hide+0.024
Neg logit contributions
flower-0.056
els-0.051
ric-0.051
ble-0.049
eled-0.049
Token<|endoftext|>
Token ID50256
Feature activation+1.23e-01

Pos logit contributions
ives+0.006
ury+0.006
 Enjoy+0.005
 Welcome+0.005
 Follow+0.005
Neg logit contributions
flower-0.013
ble-0.012
ric-0.012
els-0.011
cking-0.011
TokenJim
Token ID18050
Feature activation+8.66e-02

Pos logit contributions
flower+0.006
ble+0.005
ric+0.005
els+0.005
cks+0.004
Neg logit contributions
ives-0.005
ury-0.004
 Enjoy-0.004
 Follow-0.004
 Thank-0.004
Token was
Token ID373
Feature activation+5.11e-01

Pos logit contributions
cking+0.005
flower+0.005
ble+0.005
ric+0.005
cks+0.005
Neg logit contributions
ives-0.002
ury-0.002
 Enjoy-0.002
 Max-0.002
 Now-0.001
Token tired
Token ID10032
Feature activation+1.55e-01

Pos logit contributions
flower+0.026
ble+0.023
ric+0.023
cking+0.023
els+0.022
Neg logit contributions
ives-0.017
ury-0.015
 Enjoy-0.014
 Welcome-0.014
 Follow-0.013
Token and
Token ID290
Feature activation+2.86e-01

Pos logit contributions
flower+0.007
ble+0.006
ric+0.006
cking+0.006
els+0.006
Neg logit contributions
ives-0.006
ury-0.005
 Enjoy-0.005
 Follow-0.005
 Welcome-0.005
Token frustrated
Token ID14718
Feature activation+3.52e+00

Pos logit contributions
flower+0.014
ble+0.013
ric+0.012
cking+0.012
els+0.012
Neg logit contributions
ives-0.010
ury-0.009
 Enjoy-0.008
 Welcome-0.008
 Follow-0.008
Token.
Token ID13
Feature activation-9.65e-02

Pos logit contributions
flower+0.159
ble+0.144
ric+0.140
els+0.139
cking+0.139
Neg logit contributions
ives-0.132
ury-0.117
 Enjoy-0.115
 Welcome-0.111
 Follow-0.109
Token He
Token ID679
Feature activation+3.36e-01

Pos logit contributions
ives+0.002
ury+0.002
 Enjoy+0.002
 Welcome+0.002
 Follow+0.001
Neg logit contributions
flower-0.006
ble-0.005
ric-0.005
els-0.005
cking-0.005
Token had
Token ID550
Feature activation+1.57e-01

Pos logit contributions
flower+0.015
ble+0.014
ric+0.014
els+0.014
cking+0.013
Neg logit contributions
ives-0.013
ury-0.011
 Enjoy-0.011
 Welcome-0.010
 Follow-0.010
Token been
Token ID587
Feature activation-2.14e-01

Pos logit contributions
flower+0.009
ble+0.008
els+0.008
ric+0.008
cking+0.008
Neg logit contributions
ives-0.004
ury-0.004
 Enjoy-0.003
 Welcome-0.003
 Max-0.003
Token walking
Token ID6155
Feature activation-2.41e-01

Pos logit contributions
ives+0.008
ury+0.007
 Enjoy+0.006
 Follow+0.006
 Welcome+0.006
Neg logit contributions
flower-0.010
ble-0.009
cking-0.009
ric-0.009
els-0.009
Token.
Token ID13
Feature activation-4.27e-02

Pos logit contributions
flower+0.018
ble+0.016
els+0.015
ric+0.015
cking+0.015
Neg logit contributions
ives-0.017
ury-0.015
 Enjoy-0.015
 Welcome-0.014
 Follow-0.014
Token She
Token ID1375
Feature activation+5.25e-01

Pos logit contributions
ives+0.001
 villains+0.001
ury+0.001
ave+0.001
 traitor+0.001
Neg logit contributions
flower-0.002
ric-0.002
els-0.002
ble-0.002
ries-0.001
Token used
Token ID973
Feature activation-2.08e+00

Pos logit contributions
flower+0.023
els+0.021
ble+0.021
cking+0.020
ric+0.020
Neg logit contributions
ives-0.020
 Enjoy-0.018
ury-0.017
 Welcome-0.017
 People-0.017
Token a
Token ID257
Feature activation-1.05e+00

Pos logit contributions
ives+0.076
 Enjoy+0.066
ury+0.065
 Max+0.065
 Happy+0.064
Neg logit contributions
flower-0.097
ble-0.087
ric-0.086
cking-0.084
els-0.081
Token m
Token ID285
Feature activation-1.74e+00

Pos logit contributions
ives+0.034
ury+0.030
 Enjoy+0.029
 Welcome+0.029
 Happy+0.028
Neg logit contributions
flower-0.052
ble-0.048
ric-0.047
els-0.047
cking-0.047
Tokenitt
Token ID715
Feature activation-5.05e+00

Pos logit contributions
ives+0.060
ury+0.053
 Enjoy+0.052
 Welcome+0.051
 Happy+0.050
Neg logit contributions
flower-0.084
ble-0.077
ric-0.075
els-0.074
cking-0.074
Token to
Token ID284
Feature activation-6.99e-01

Pos logit contributions
ives+0.157
ury+0.139
 Enjoy+0.137
 Welcome+0.132
 Follow+0.129
Neg logit contributions
flower-0.259
ble-0.236
ric-0.231
cking-0.231
els-0.230
Token take
Token ID1011
Feature activation-3.31e-01

Pos logit contributions
ives+0.025
ury+0.022
 Enjoy+0.022
 Max+0.021
 Welcome+0.021
Neg logit contributions
flower-0.033
ric-0.029
ble-0.029
cking-0.028
els-0.028
Token out
Token ID503
Feature activation-6.17e-01

Pos logit contributions
ives+0.015
ury+0.014
 Follow+0.013
 villains+0.013
 Bye+0.013
Neg logit contributions
flower-0.011
els-0.011
ble-0.010
ries-0.010
cking-0.010
Token the
Token ID262
Feature activation-3.77e-01

Pos logit contributions
ives+0.021
ury+0.018
 Enjoy+0.017
 Happy+0.017
 Welcome+0.017
Neg logit contributions
flower-0.031
ble-0.028
ric-0.028
cking-0.027
els-0.026
Token pan
Token ID3425
Feature activation-1.29e+00

Pos logit contributions
ives+0.014
 Enjoy+0.012
ury+0.012
 Welcome+0.012
 Happy+0.012
Neg logit contributions
flower-0.017
ble-0.016
ric-0.016
cking-0.015
els-0.015
Token the
Token ID262
Feature activation-7.76e-01

Pos logit contributions
ives+0.037
ury+0.033
 Enjoy+0.033
 Welcome+0.032
 Happy+0.032
Neg logit contributions
flower-0.036
ble-0.031
ric-0.031
els-0.030
cking-0.030
Token shore
Token ID15191
Feature activation-8.58e-01

Pos logit contributions
ives+0.028
ury+0.025
 Enjoy+0.024
 Welcome+0.024
 Follow+0.023
Neg logit contributions
flower-0.036
ble-0.033
ric-0.032
cking-0.032
els-0.031
Token.
Token ID13
Feature activation+1.85e-01

Pos logit contributions
ives+0.027
ury+0.023
 Enjoy+0.022
 Welcome+0.021
 Happy+0.021
Neg logit contributions
flower-0.044
ble-0.040
ric-0.040
cking-0.039
els-0.039
Token They
Token ID1119
Feature activation-1.42e-01

Pos logit contributions
flower+0.010
ric+0.010
ble+0.009
els+0.009
mill+0.009
Neg logit contributions
ives-0.005
ury-0.004
 Enjoy-0.003
 Follow-0.003
 villains-0.003
Token collected
Token ID7723
Feature activation-1.03e+00

Pos logit contributions
ives+0.004
ury+0.003
 Enjoy+0.003
 Welcome+0.003
 Happy+0.003
Neg logit contributions
flower-0.008
ble-0.007
els-0.007
ric-0.007
cking-0.007
Token seas
Token ID21547
Feature activation-4.79e+00

Pos logit contributions
ives+0.034
 Enjoy+0.029
 Happy+0.029
 hide+0.029
 Max+0.028
Neg logit contributions
flower-0.052
ric-0.046
ble-0.046
cker-0.044
cking-0.044
Tokenhell
Token ID12758
Feature activation-3.49e-01

Pos logit contributions
ives+0.169
ury+0.144
 Enjoy+0.136
 Welcome+0.130
 Happy+0.129
Neg logit contributions
flower-0.235
ble-0.211
ric-0.207
cking-0.205
els-0.204
Tokens
Token ID82
Feature activation-1.03e+00

Pos logit contributions
ives+0.010
ury+0.009
 Enjoy+0.008
 Welcome+0.008
 Max+0.008
Neg logit contributions
flower-0.018
ric-0.017
ble-0.017
cking-0.017
els-0.017
Token and
Token ID290
Feature activation+3.84e-02

Pos logit contributions
ives+0.030
ury+0.024
 Enjoy+0.024
 Welcome+0.022
 Happy+0.021
Neg logit contributions
flower-0.055
ble-0.051
cking-0.051
ric-0.049
els-0.049
Token built
Token ID3170
Feature activation+3.18e-01

Pos logit contributions
flower+0.002
ble+0.002
ric+0.002
els+0.002
cking+0.002
Neg logit contributions
ives-0.001
ury-0.001
 Enjoy-0.001
 Welcome-0.001
 Follow-0.001
Token sand
Token ID6450
Feature activation-5.65e-01

Pos logit contributions
flower+0.016
ble+0.014
ric+0.014
els+0.013
cker+0.013
Neg logit contributions
ives-0.010
 hide-0.009
 Happy-0.009
 Enjoy-0.009
 Max-0.009
Token thought
Token ID1807
Feature activation+1.44e-01

Pos logit contributions
ives+0.020
 Enjoy+0.019
 Welcome+0.018
ury+0.017
 Follow+0.017
Neg logit contributions
flower-0.025
ble-0.022
els-0.021
ric-0.021
cking-0.021
Token they
Token ID484
Feature activation-4.66e-01

Pos logit contributions
flower+0.006
ble+0.005
els+0.005
cking+0.005
ric+0.005
Neg logit contributions
ives-0.006
 Enjoy-0.005
 Follow-0.005
ury-0.005
 Sadly-0.005
Token looked
Token ID3114
Feature activation-2.05e-01

Pos logit contributions
ives+0.015
ury+0.013
 Enjoy+0.013
 Welcome+0.012
 Follow+0.012
Neg logit contributions
flower-0.024
ble-0.022
ric-0.021
els-0.021
cking-0.021
Token like
Token ID588
Feature activation-1.94e-01

Pos logit contributions
ives+0.006
ury+0.005
 Enjoy+0.005
 Welcome+0.005
 Happy+0.005
Neg logit contributions
flower-0.011
ble-0.010
ric-0.010
els-0.010
cking-0.010
Token ac
Token ID936
Feature activation-6.85e-01

Pos logit contributions
ives+0.008
ury+0.007
 Enjoy+0.006
 Follow+0.006
 Sadly+0.006
Neg logit contributions
flower-0.008
ble-0.007
els-0.007
ric-0.007
mill-0.007
Tokenrob
Token ID22609
Feature activation-4.57e+00

Pos logit contributions
 Welcome+0.029
 Enjoy+0.029
ives+0.028
 Follow+0.028
 Thank+0.027
Neg logit contributions
flower-0.027
ble-0.024
cking-0.023
els-0.022
ric-0.022
Tokenats
Token ID1381
Feature activation-1.96e+00

Pos logit contributions
ives+0.182
ury+0.171
 Welcome+0.170
 Enjoy+0.166
 Follow+0.165
Neg logit contributions
flower-0.186
els-0.177
cking-0.171
cks-0.166
ble-0.166
Token.
Token ID13
Feature activation-6.85e-02

Pos logit contributions
ives+0.064
ury+0.056
 Enjoy+0.054
 Welcome+0.052
 Happy+0.051
Neg logit contributions
flower-0.098
ble-0.089
ric-0.088
cking-0.088
els-0.087
Token She
Token ID1375
Feature activation+3.13e-01

Pos logit contributions
ives+0.003
 villains+0.002
 Enjoy+0.002
 traitor+0.002
 Cop+0.002
Neg logit contributions
flower-0.003
els-0.002
ric-0.002
mill-0.002
ries-0.002
Token enjoyed
Token ID8359
Feature activation-1.11e+00

Pos logit contributions
flower+0.016
ble+0.014
ric+0.014
els+0.014
cking+0.014
Neg logit contributions
ives-0.011
 Enjoy-0.009
ury-0.009
 Welcome-0.009
 Follow-0.008
Token the
Token ID262
Feature activation-1.29e+00

Pos logit contributions
ives+0.038
ury+0.033
 Enjoy+0.032
 Welcome+0.031
 Follow+0.030
Neg logit contributions
flower-0.055
ble-0.050
ric-0.049
cking-0.049
els-0.048
Token learn
Token ID2193
Feature activation-1.10e-01

Pos logit contributions
ives+0.022
ury+0.020
 Enjoy+0.019
 Welcome+0.019
 Happy+0.018
Neg logit contributions
flower-0.028
ble-0.026
ric-0.025
cking-0.025
els-0.024
Token more
Token ID517
Feature activation-1.05e+00

Pos logit contributions
ives+0.004
ury+0.003
 Enjoy+0.003
 Welcome+0.003
 Happy+0.003
Neg logit contributions
flower-0.006
ble-0.005
ric-0.005
cking-0.005
els-0.005
Token about
Token ID546
Feature activation-6.81e-01

Pos logit contributions
ives+0.029
ury+0.025
 Enjoy+0.024
 Welcome+0.023
 Sadly+0.022
Neg logit contributions
flower-0.055
ble-0.054
els-0.052
ric-0.051
cking-0.051
Token rh
Token ID9529
Feature activation-2.05e+00

Pos logit contributions
ives+0.031
ury+0.027
 Enjoy+0.026
 Follow+0.026
 Welcome+0.025
Neg logit contributions
flower-0.027
ric-0.024
ble-0.024
els-0.023
cking-0.023
Tokenin
Token ID259
Feature activation-8.16e-01

Pos logit contributions
ives+0.112
ury+0.105
 Enjoy+0.104
 Welcome+0.104
 Thank+0.103
Neg logit contributions
flower-0.056
ble-0.050
cking-0.050
els-0.050
ric-0.047
Tokenoc
Token ID420
Feature activation-4.47e+00

Pos logit contributions
ives+0.030
 Enjoy+0.027
ury+0.027
 Sadly+0.026
 Welcome+0.026
Neg logit contributions
flower-0.036
ble-0.032
cking-0.032
ric-0.032
els-0.032
Tokener
Token ID263
Feature activation-2.93e+00

Pos logit contributions
ives+0.221
 Welcome+0.212
ury+0.211
 Sadly+0.203
 Happy+0.203
Neg logit contributions
els-0.139
flower-0.138
ries-0.129
ric-0.125
ble-0.124
Tokenoses
Token ID4629
Feature activation-1.34e+00

Pos logit contributions
ives+0.098
ury+0.086
 Enjoy+0.082
 Welcome+0.080
 Max+0.078
Neg logit contributions
flower-0.142
ble-0.130
cking-0.128
ric-0.127
els-0.126
Token and
Token ID290
Feature activation+2.56e-01

Pos logit contributions
ives+0.048
ury+0.044
 Enjoy+0.043
 Welcome+0.042
 Follow+0.041
Neg logit contributions
flower-0.062
ble-0.055
ric-0.054
els-0.053
cking-0.052
Token respect
Token ID2461
Feature activation-4.22e-01

Pos logit contributions
flower+0.012
ric+0.011
ble+0.010
els+0.010
cking+0.010
Neg logit contributions
ives-0.009
ury-0.008
 Enjoy-0.008
 Welcome-0.008
 Follow-0.008
Token them
Token ID606
Feature activation+4.77e-01

Pos logit contributions
ives+0.018
ury+0.016
 Enjoy+0.016
 Welcome+0.015
 Follow+0.015
Neg logit contributions
flower-0.017
ble-0.015
els-0.015
ric-0.015
cking-0.015
Token didn
Token ID1422
Feature activation+6.36e-02

Pos logit contributions
ives+0.066
 Enjoy+0.058
ury+0.057
 Welcome+0.056
 Happy+0.054
Neg logit contributions
flower-0.088
ble-0.081
cking-0.078
els-0.077
ric-0.077
Token't
Token ID470
Feature activation-5.21e-01

Pos logit contributions
flower+0.005
cking+0.004
ric+0.004
els+0.004
eled+0.004
Neg logit contributions
ives-0.001
ury-0.001
 Enjoy-0.001
 Max-0.001
 People-0.000
Token like
Token ID588
Feature activation-6.67e-01

Pos logit contributions
ives+0.014
ury+0.012
 Enjoy+0.011
 Welcome+0.011
 Happy+0.010
Neg logit contributions
flower-0.030
ble-0.027
ric-0.027
cking-0.027
els-0.027
Token wet
Token ID9583
Feature activation-1.64e-01

Pos logit contributions
ives+0.024
ury+0.022
 Enjoy+0.021
 Welcome+0.021
 Happy+0.020
Neg logit contributions
flower-0.031
ble-0.028
ric-0.027
cking-0.027
els-0.027
Token av
Token ID1196
Feature activation-2.84e+00

Pos logit contributions
ives+0.006
 Max+0.005
 Enjoy+0.005
ury+0.005
 Happy+0.005
Neg logit contributions
flower-0.008
ric-0.007
ble-0.007
cking-0.007
cks-0.007
Tokenoc
Token ID420
Feature activation-4.40e+00

Pos logit contributions
ives+0.100
 Welcome+0.099
 Enjoy+0.095
ury+0.094
 People+0.094
Neg logit contributions
flower-0.131
cking-0.117
els-0.115
ric-0.112
cks-0.112
Tokenados
Token ID22484
Feature activation+5.63e-01

Pos logit contributions
ives+0.219
ury+0.217
 Welcome+0.216
 Follow+0.209
 Happy+0.205
Neg logit contributions
flower-0.130
els-0.125
ries-0.120
ble-0.117
cking-0.105
Token,
Token ID11
Feature activation-2.58e-01

Pos logit contributions
flower+0.024
ble+0.022
cking+0.021
els+0.021
ric+0.021
Neg logit contributions
ives-0.022
 Enjoy-0.021
 Follow-0.020
ury-0.020
 Welcome-0.020
Token so
Token ID523
Feature activation+2.78e-01

Pos logit contributions
ives+0.005
 Max+0.005
ury+0.004
 People+0.004
 Welcome+0.004
Neg logit contributions
flower-0.016
ble-0.015
els-0.014
cking-0.014
ric-0.014
Token he
Token ID339
Feature activation-7.63e-01

Pos logit contributions
flower+0.017
ric+0.016
els+0.016
cks+0.016
cking+0.016
Neg logit contributions
 Max-0.005
ury-0.004
 Sadly-0.004
 Enjoy-0.004
 People-0.004
Token decided
Token ID3066
Feature activation-4.92e-01

Pos logit contributions
ives+0.029
ury+0.025
 Enjoy+0.025
 Welcome+0.024
 Happy+0.023
Neg logit contributions
flower-0.035
ble-0.032
cking-0.031
els-0.031
ric-0.030
Token the
Token ID262
Feature activation-6.35e-01

Pos logit contributions
flower+0.020
cker+0.018
ble+0.017
ric+0.017
immer+0.017
Neg logit contributions
 hide-0.008
 Happy-0.007
 Max-0.007
 Welcome-0.007
 many-0.006
Token waves
Token ID9813
Feature activation-6.34e-01

Pos logit contributions
ives+0.026
 Enjoy+0.023
ury+0.023
 Welcome+0.022
 Happy+0.022
Neg logit contributions
flower-0.027
ble-0.024
ric-0.024
cking-0.023
els-0.023
Token.
Token ID13
Feature activation-9.51e-02

Pos logit contributions
ives+0.024
ury+0.022
 Enjoy+0.021
 Welcome+0.021
 Happy+0.020
Neg logit contributions
flower-0.028
ble-0.025
ric-0.025
cking-0.025
els-0.025
Token They
Token ID1119
Feature activation+5.23e-03

Pos logit contributions
ives+0.003
ury+0.003
 traitor+0.002
 villains+0.002
 Enjoy+0.002
Neg logit contributions
flower-0.004
ric-0.004
els-0.004
mill-0.004
ble-0.004
Token gathered
Token ID9272
Feature activation-1.02e+00

Pos logit contributions
flower+0.000
ble+0.000
ric+0.000
cking+0.000
els+0.000
Neg logit contributions
ives-0.000
ury-0.000
 Enjoy-0.000
 Welcome-0.000
 Follow-0.000
Token seas
Token ID21547
Feature activation-4.39e+00

Pos logit contributions
ives+0.038
 Enjoy+0.034
ury+0.033
 Happy+0.032
 Welcome+0.032
Neg logit contributions
flower-0.047
ric-0.042
ble-0.042
cking-0.040
els-0.039
Tokenhell
Token ID12758
Feature activation-4.23e-01

Pos logit contributions
ives+0.160
ury+0.140
 Enjoy+0.133
 Welcome+0.128
 Happy+0.126
Neg logit contributions
flower-0.209
ble-0.186
ric-0.183
cking-0.180
els-0.180
Tokens
Token ID82
Feature activation-1.13e+00

Pos logit contributions
ives+0.014
ury+0.012
 Enjoy+0.012
 Welcome+0.012
 Follow+0.011
Neg logit contributions
flower-0.021
ble-0.019
ric-0.019
cking-0.018
els-0.018
Token and
Token ID290
Feature activation-1.18e-01

Pos logit contributions
ives+0.029
ury+0.023
 Enjoy+0.022
 Welcome+0.020
 Follow+0.020
Neg logit contributions
flower-0.064
cking-0.059
ble-0.059
ric-0.058
els-0.057
Token filled
Token ID5901
Feature activation+3.62e-01

Pos logit contributions
ives+0.005
ury+0.004
 Enjoy+0.004
 Welcome+0.004
 Happy+0.004
Neg logit contributions
flower-0.005
ble-0.004
ric-0.004
cking-0.004
els-0.004
Token their
Token ID511
Feature activation-2.70e-01

Pos logit contributions
flower+0.018
ric+0.015
ble+0.015
els+0.015
cking+0.015
Neg logit contributions
ives-0.011
 Enjoy-0.011
 Happy-0.011
 Welcome-0.010
ury-0.010
Token They
Token ID1119
Feature activation-4.76e-01

Pos logit contributions
ives+0.015
ury+0.013
ave+0.012
 Follow+0.011
 Enjoy+0.011
Neg logit contributions
flower-0.018
ric-0.017
ble-0.016
els-0.016
lights-0.016
Token heard
Token ID2982
Feature activation-1.78e+00

Pos logit contributions
ives+0.018
ury+0.016
 Enjoy+0.016
 Welcome+0.015
 Follow+0.015
Neg logit contributions
flower-0.022
ble-0.020
els-0.019
ric-0.019
cking-0.019
Token the
Token ID262
Feature activation-1.31e+00

Pos logit contributions
ives+0.073
ury+0.066
 Enjoy+0.064
 Follow+0.062
 Welcome+0.061
Neg logit contributions
flower-0.073
ble-0.066
ric-0.065
els-0.064
cking-0.064
Token rh
Token ID9529
Feature activation-2.13e+00

Pos logit contributions
ives+0.051
ury+0.047
 Enjoy+0.046
 Follow+0.043
 Welcome+0.042
Neg logit contributions
flower-0.059
ble-0.052
ric-0.051
cking-0.049
els-0.049
Tokenin
Token ID259
Feature activation-1.02e+00

Pos logit contributions
ives+0.114
ury+0.105
 Enjoy+0.103
 Welcome+0.102
 Happy+0.100
Neg logit contributions
flower-0.064
ble-0.054
ric-0.052
cking-0.052
els-0.051
Tokenoc
Token ID420
Feature activation-4.39e+00

Pos logit contributions
ives+0.034
ury+0.031
 Enjoy+0.030
 Welcome+0.028
 Follow+0.028
Neg logit contributions
flower-0.051
ric-0.046
ble-0.046
cking-0.045
els-0.044
Tokeneros
Token ID27498
Feature activation-8.68e-01

Pos logit contributions
ives+0.228
ury+0.212
 Welcome+0.207
 Enjoy+0.203
 Follow+0.200
Neg logit contributions
flower-0.144
ble-0.123
els-0.120
ric-0.118
cking-0.112
Token roar
Token ID34532
Feature activation-3.59e-01

Pos logit contributions
ives+0.030
ury+0.026
 Enjoy+0.025
 Welcome+0.025
 Happy+0.024
Neg logit contributions
flower-0.042
ble-0.038
ric-0.037
els-0.037
cking-0.037
Token.
Token ID13
Feature activation-4.85e-01

Pos logit contributions
ives+0.012
ury+0.011
 Welcome+0.010
 Happy+0.010
 Enjoy+0.010
Neg logit contributions
flower-0.018
ric-0.016
ble-0.016
els-0.016
cking-0.016
Token They
Token ID1119
Feature activation-5.16e-01

Pos logit contributions
ives+0.014
ury+0.011
 Enjoy+0.010
 Follow+0.010
 Welcome+0.010
Neg logit contributions
flower-0.026
ble-0.024
ric-0.024
els-0.023
cks-0.023
Token heard
Token ID2982
Feature activation-1.91e+00

Pos logit contributions
ives+0.017
ury+0.015
 Enjoy+0.015
 Welcome+0.014
 Follow+0.014
Neg logit contributions
flower-0.026
ble-0.023
ric-0.023
cking-0.023
els-0.022
Token they
Token ID484
Feature activation-8.86e-01

Pos logit contributions
ives+0.024
ury+0.021
 Enjoy+0.021
 Welcome+0.020
 Follow+0.020
Neg logit contributions
flower-0.027
ble-0.024
els-0.023
cking-0.023
ric-0.023
Token could
Token ID714
Feature activation-7.38e-01

Pos logit contributions
ives+0.025
ury+0.021
 Enjoy+0.020
 Welcome+0.020
 Happy+0.019
Neg logit contributions
flower-0.049
ble-0.045
ric-0.044
els-0.044
cking-0.044
Token grow
Token ID1663
Feature activation+3.92e-01

Pos logit contributions
ives+0.017
 Enjoy+0.016
 hide+0.016
 Welcome+0.013
 Max+0.013
Neg logit contributions
flower-0.042
els-0.038
ric-0.038
eled-0.038
cking-0.038
Token more
Token ID517
Feature activation-1.08e+00

Pos logit contributions
flower+0.021
ric+0.020
cking+0.018
eled+0.018
els+0.018
Neg logit contributions
ives-0.011
 Enjoy-0.010
 Happy-0.009
 People-0.009
 Welcome-0.009
Token av
Token ID1196
Feature activation-2.71e+00

Pos logit contributions
ives+0.045
ury+0.041
 Enjoy+0.040
 Welcome+0.039
 Follow+0.038
Neg logit contributions
flower-0.045
ble-0.040
els-0.039
cking-0.038
ric-0.038
Tokenoc
Token ID420
Feature activation-4.38e+00

Pos logit contributions
 Welcome+0.099
ives+0.099
 People+0.095
ury+0.094
 Enjoy+0.093
Neg logit contributions
flower-0.123
cking-0.107
els-0.106
cker-0.102
cks-0.102
Tokenados
Token ID22484
Feature activation+1.31e+00

Pos logit contributions
ives+0.217
 Welcome+0.213
ury+0.212
 Happy+0.202
 Sadly+0.202
Neg logit contributions
flower-0.134
els-0.129
ries-0.123
ble-0.122
cking-0.113
Token and
Token ID290
Feature activation-3.47e-02

Pos logit contributions
flower+0.059
ble+0.053
els+0.050
cking+0.050
ric+0.049
Neg logit contributions
ives-0.049
 Enjoy-0.045
ury-0.045
 Welcome-0.043
 Sadly-0.043
Token share
Token ID2648
Feature activation+2.66e-01

Pos logit contributions
ives+0.001
ury+0.001
 Enjoy+0.001
 Welcome+0.001
 Happy+0.001
Neg logit contributions
flower-0.002
ble-0.001
ric-0.001
cking-0.001
els-0.001
Token them
Token ID606
Feature activation+9.17e-01

Pos logit contributions
flower+0.012
ric+0.011
ble+0.011
cking+0.010
els+0.010
Neg logit contributions
ives-0.010
 Enjoy-0.009
ury-0.009
 Happy-0.008
 Welcome-0.008
Token with
Token ID351
Feature activation+3.60e-01

Pos logit contributions
flower+0.052
ric+0.048
ble+0.046
cking+0.046
els+0.046
Neg logit contributions
ives-0.024
ury-0.020
 Enjoy-0.020
 Happy-0.019
 Welcome-0.018
Token had
Token ID550
Feature activation-2.56e-01

Pos logit contributions
ives+0.016
ury+0.014
 Enjoy+0.014
 Welcome+0.013
 Happy+0.013
Neg logit contributions
flower-0.027
ble-0.024
ric-0.023
cking-0.023
els-0.023
Token discovered
Token ID5071
Feature activation-1.45e+00

Pos logit contributions
ives+0.008
ury+0.007
 Enjoy+0.007
 Welcome+0.007
 Follow+0.007
Neg logit contributions
flower-0.013
ric-0.012
ble-0.012
cking-0.011
els-0.011
Token the
Token ID262
Feature activation-9.64e-01

Pos logit contributions
ives+0.047
 Enjoy+0.042
ury+0.041
 Max+0.040
 Welcome+0.040
Neg logit contributions
flower-0.072
ble-0.064
ric-0.063
cking-0.063
els-0.062
Token rh
Token ID9529
Feature activation-2.12e+00

Pos logit contributions
ives+0.038
ury+0.034
 Enjoy+0.032
 Follow+0.031
 Welcome+0.031
Neg logit contributions
flower-0.044
ric-0.039
ble-0.039
cking-0.037
els-0.037
Tokenin
Token ID259
Feature activation-1.20e+00

Pos logit contributions
ives+0.114
ury+0.106
 Enjoy+0.105
 Welcome+0.103
 Happy+0.102
Neg logit contributions
flower-0.063
ble-0.054
els-0.051
ric-0.051
cking-0.051
Tokenoc
Token ID420
Feature activation-4.37e+00

Pos logit contributions
ives+0.041
ury+0.036
 Enjoy+0.035
 Welcome+0.034
 Happy+0.033
Neg logit contributions
flower-0.060
ric-0.054
ble-0.053
els-0.052
cking-0.052
Tokeneros
Token ID27498
Feature activation-9.94e-01

Pos logit contributions
ives+0.228
ury+0.213
 Welcome+0.206
 Max+0.203
 Enjoy+0.203
Neg logit contributions
flower-0.143
els-0.122
ble-0.120
ric-0.120
cking-0.111
Token,
Token ID11
Feature activation-1.33e-01

Pos logit contributions
ives+0.033
ury+0.029
 Enjoy+0.029
 Welcome+0.028
 Happy+0.027
Neg logit contributions
flower-0.049
ble-0.044
ric-0.044
cking-0.043
els-0.043
Token but
Token ID475
Feature activation+1.33e-01

Pos logit contributions
ives+0.004
ury+0.004
 Enjoy+0.004
 Welcome+0.004
 Happy+0.003
Neg logit contributions
flower-0.007
ble-0.006
ric-0.006
cking-0.006
els-0.006
Token they
Token ID484
Feature activation-7.39e-01

Pos logit contributions
flower+0.006
ble+0.005
ric+0.005
els+0.005
cking+0.005
Neg logit contributions
ives-0.006
ury-0.005
 Enjoy-0.005
 Follow-0.005
 Welcome-0.005
Token had
Token ID550
Feature activation+1.09e-01

Pos logit contributions
ives+0.022
ury+0.019
 Enjoy+0.019
 Welcome+0.018
 Happy+0.017
Neg logit contributions
flower-0.039
ble-0.036
ric-0.035
cking-0.035
els-0.035
Token They
Token ID1119
Feature activation-5.76e-01

Pos logit contributions
ives+0.019
ury+0.016
 Enjoy+0.015
 Follow+0.014
ave+0.014
Neg logit contributions
flower-0.028
ble-0.026
ric-0.025
els-0.024
cks-0.024
Token heard
Token ID2982
Feature activation-1.84e+00

Pos logit contributions
ives+0.021
ury+0.018
 Enjoy+0.018
 Welcome+0.017
 Follow+0.017
Neg logit contributions
flower-0.028
ble-0.025
ric-0.024
cking-0.024
els-0.024
Token the
Token ID262
Feature activation-1.31e+00

Pos logit contributions
ives+0.077
ury+0.069
 Enjoy+0.067
 Follow+0.065
 Welcome+0.065
Neg logit contributions
flower-0.076
ble-0.068
ric-0.067
els-0.066
cking-0.066
Token rh
Token ID9529
Feature activation-2.15e+00

Pos logit contributions
ives+0.056
ury+0.051
 Enjoy+0.049
 Follow+0.047
enny+0.046
Neg logit contributions
flower-0.055
ric-0.050
ble-0.049
cking-0.048
els-0.046
Tokenin
Token ID259
Feature activation-1.01e+00

Pos logit contributions
ives+0.113
ury+0.104
 Enjoy+0.102
 Welcome+0.100
 Happy+0.098
Neg logit contributions
flower-0.066
ble-0.055
ric-0.054
cking-0.053
els-0.053
Tokenoc
Token ID420
Feature activation-4.37e+00

Pos logit contributions
ives+0.031
ury+0.027
 Enjoy+0.026
 Welcome+0.025
 Follow+0.024
Neg logit contributions
flower-0.053
ble-0.048
ric-0.048
cking-0.047
els-0.047
Tokeneros
Token ID27498
Feature activation-8.63e-01

Pos logit contributions
ives+0.227
ury+0.209
 Welcome+0.204
 Enjoy+0.202
 Follow+0.198
Neg logit contributions
flower-0.144
ble-0.123
els-0.120
ric-0.119
cking-0.114
Token sn
Token ID3013
Feature activation-1.62e+00

Pos logit contributions
ives+0.030
ury+0.027
 Welcome+0.026
 Enjoy+0.026
 Happy+0.025
Neg logit contributions
flower-0.041
ble-0.037
ric-0.036
els-0.036
cking-0.036
Tokenore
Token ID382
Feature activation-2.57e+00

Pos logit contributions
ives+0.057
 Welcome+0.054
ury+0.053
 Happy+0.053
 villains+0.050
Neg logit contributions
flower-0.076
ble-0.070
ric-0.069
els-0.068
cking-0.066
Token.
Token ID13
Feature activation-5.96e-01

Pos logit contributions
ives+0.106
ury+0.096
 Enjoy+0.095
 Welcome+0.092
 Follow+0.090
Neg logit contributions
flower-0.107
ble-0.097
ric-0.094
cking-0.093
els-0.093
Token
Token ID198
Feature activation-1.15e+00

Pos logit contributions
ives+0.018
ury+0.015
 Enjoy+0.013
 Follow+0.013
 Welcome+0.012
Neg logit contributions
flower-0.031
ble-0.028
ric-0.028
els-0.027
cks-0.026
Token
Token ID198
Feature activation-6.54e-01

Pos logit contributions
ives+0.020
ury+0.016
 Enjoy+0.016
 Welcome+0.015
 Max+0.014
Neg logit contributions
flower-0.065
ble-0.059
els-0.058
ric-0.058
cking-0.058
TokenThey
Token ID2990
Feature activation+6.89e-01

Pos logit contributions
ives+0.025
ury+0.024
 Enjoy+0.023
 Follow+0.022
 Welcome+0.022
Neg logit contributions
flower-0.030
ric-0.026
els-0.025
ble-0.025
cking-0.024
Token get
Token ID651
Feature activation+1.31e-01

Pos logit contributions
flower+0.035
ble+0.032
ric+0.032
cking+0.031
els+0.031
Neg logit contributions
ives-0.022
 Enjoy-0.019
ury-0.019
 Welcome-0.018
 Happy-0.017
Token a
Token ID257
Feature activation-9.49e-01

Pos logit contributions
flower+0.007
ric+0.006
ble+0.006
cking+0.006
els+0.006
Neg logit contributions
ives-0.004
 Enjoy-0.004
 Happy-0.003
 Welcome-0.003
 Max-0.003
Token m
Token ID285
Feature activation-1.31e+00

Pos logit contributions
ives+0.036
ury+0.032
 Enjoy+0.032
 Welcome+0.031
 Happy+0.030
Neg logit contributions
flower-0.042
ble-0.038
ric-0.038
els-0.038
cking-0.038
Tokenitt
Token ID715
Feature activation-4.34e+00

Pos logit contributions
ives+0.052
ury+0.046
 Enjoy+0.045
 Welcome+0.043
 Follow+0.042
Neg logit contributions
flower-0.057
ble-0.050
ric-0.050
cking-0.049
els-0.049
Token and
Token ID290
Feature activation-3.86e-01

Pos logit contributions
ives+0.154
ury+0.133
 Enjoy+0.128
 Welcome+0.124
 Happy+0.121
Neg logit contributions
flower-0.208
ble-0.187
ric-0.186
els-0.181
cking-0.180
Token a
Token ID257
Feature activation-6.18e-02

Pos logit contributions
ives+0.013
 Enjoy+0.011
ury+0.011
 Happy+0.011
 Welcome+0.011
Neg logit contributions
flower-0.020
ble-0.018
ric-0.017
cking-0.017
els-0.017
Token spat
Token ID15246
Feature activation+3.76e-01

Pos logit contributions
ives+0.002
ury+0.002
 Enjoy+0.002
 Welcome+0.002
 Happy+0.002
Neg logit contributions
flower-0.003
ble-0.002
els-0.002
ric-0.002
cking-0.002
Tokenula
Token ID4712
Feature activation+1.20e+00

Pos logit contributions
flower+0.019
ric+0.017
cking+0.017
els+0.017
ble+0.016
Neg logit contributions
ives-0.013
ury-0.011
 Enjoy-0.011
 Welcome-0.010
 Happy-0.010
Token.
Token ID13
Feature activation-2.39e-01

Pos logit contributions
flower+0.060
ric+0.056
cking+0.056
ble+0.054
els+0.054
Neg logit contributions
ives-0.041
ury-0.035
 Enjoy-0.034
 Thank-0.031
 Welcome-0.031
Token that
Token ID326
Feature activation-1.17e+00

Pos logit contributions
ives+0.039
 Enjoy+0.035
ury+0.035
 Welcome+0.033
 Max+0.033
Neg logit contributions
flower-0.051
ble-0.045
cking-0.044
ric-0.044
els-0.044
Token boss
Token ID6478
Feature activation-5.26e-01

Pos logit contributions
ives+0.046
ury+0.040
 Enjoy+0.037
 Follow+0.035
 Welcome+0.035
Neg logit contributions
flower-0.054
ble-0.049
cking-0.047
ric-0.047
els-0.045
Tokeny
Token ID88
Feature activation-2.67e-01

Pos logit contributions
ives+0.024
ury+0.022
 Enjoy+0.022
 Welcome+0.021
 Happy+0.021
Neg logit contributions
flower-0.019
ble-0.017
ric-0.016
cking-0.016
els-0.016
Token rh
Token ID9529
Feature activation-1.99e+00

Pos logit contributions
ives+0.009
ury+0.008
 Enjoy+0.008
 Welcome+0.007
 Happy+0.007
Neg logit contributions
flower-0.013
ble-0.012
ric-0.012
cking-0.012
els-0.012
Tokenin
Token ID259
Feature activation-1.19e+00

Pos logit contributions
ives+0.110
ury+0.102
 Enjoy+0.101
 Welcome+0.099
 Happy+0.098
Neg logit contributions
flower-0.056
ble-0.048
ric-0.045
cking-0.045
els-0.045
Tokenoc
Token ID420
Feature activation-4.34e+00

Pos logit contributions
ives+0.038
ury+0.034
 Enjoy+0.033
 Welcome+0.032
 Happy+0.031
Neg logit contributions
flower-0.060
ble-0.055
ric-0.054
cking-0.053
els-0.053
Tokeneros
Token ID27498
Feature activation-1.26e+00

Pos logit contributions
ives+0.229
ury+0.215
 Welcome+0.212
 Sadly+0.207
 Enjoy+0.205
Neg logit contributions
flower-0.129
els-0.120
ble-0.115
ries-0.109
ric-0.109
Token.
Token ID13
Feature activation-1.26e-02

Pos logit contributions
ives+0.040
ury+0.035
 Enjoy+0.034
 Welcome+0.033
 Follow+0.031
Neg logit contributions
flower-0.064
ble-0.058
ric-0.057
cking-0.057
els-0.057
Token<|endoftext|>
Token ID50256
Feature activation-4.00e-01

Pos logit contributions
ives+0.000
ury+0.000
 hide+0.000
 villains+0.000
 Welcome+0.000
Neg logit contributions
flower-0.001
ric-0.001
ble-0.001
els-0.001
mill-0.000
TokenD
Token ID35
Feature activation-1.41e+00

Pos logit contributions
ives+0.016
ury+0.015
 Enjoy+0.014
 Follow+0.013
 Welcome+0.013
Neg logit contributions
flower-0.017
ble-0.015
ric-0.015
els-0.014
cks-0.014
Tokenee
Token ID1453
Feature activation-2.11e+00

Pos logit contributions
ives+0.052
 Enjoy+0.046
ury+0.045
 Welcome+0.042
 People+0.041
Neg logit contributions
flower-0.066
cking-0.059
ble-0.059
els-0.058
ric-0.057
Token,
Token ID11
Feature activation-2.13e-01

Pos logit contributions
ives+0.007
ury+0.006
 Enjoy+0.006
 Welcome+0.006
 Follow+0.006
Neg logit contributions
flower-0.009
ble-0.009
cking-0.008
els-0.008
ric-0.008
Token "
Token ID366
Feature activation-1.38e-01

Pos logit contributions
ives+0.007
 Enjoy+0.006
ury+0.006
 Follow+0.006
 Welcome+0.006
Neg logit contributions
flower-0.010
ble-0.009
mill-0.009
ric-0.009
cking-0.009
TokenI
Token ID40
Feature activation+4.82e-01

Pos logit contributions
ives+0.004
ury+0.004
 Enjoy+0.004
 Welcome+0.004
 Follow+0.004
Neg logit contributions
flower-0.007
ric-0.006
ble-0.006
els-0.006
cking-0.006
Token love
Token ID1842
Feature activation-1.28e+00

Pos logit contributions
flower+0.023
ble+0.020
ric+0.020
els+0.019
cking+0.019
Neg logit contributions
ives-0.016
ury-0.014
 Welcome-0.014
 Happy-0.014
 People-0.014
Token av
Token ID1196
Feature activation-2.88e+00

Pos logit contributions
ives+0.047
ury+0.041
 Follow+0.039
 Welcome+0.038
 Enjoy+0.038
Neg logit contributions
flower-0.061
ble-0.055
ric-0.054
els-0.054
cking-0.053
Tokenoc
Token ID420
Feature activation-4.33e+00

Pos logit contributions
 Welcome+0.108
ives+0.107
ury+0.103
 People+0.102
 Bye+0.101
Neg logit contributions
flower-0.127
els-0.111
cking-0.109
ric-0.104
cks-0.103
Tokenados
Token ID22484
Feature activation+7.65e-01

Pos logit contributions
ives+0.220
ury+0.218
 Welcome+0.216
 Happy+0.204
 Follow+0.203
Neg logit contributions
flower-0.131
els-0.123
ries-0.119
ble-0.110
cking-0.102
Token!
Token ID0
Feature activation+5.82e-01

Pos logit contributions
flower+0.035
ble+0.031
ric+0.030
els+0.030
mill+0.029
Neg logit contributions
ives-0.028
ury-0.025
 Enjoy-0.025
 Welcome-0.025
 Sadly-0.025
Token They
Token ID1119
Feature activation+2.97e-01

Pos logit contributions
flower+0.032
ric+0.028
ble+0.028
mill+0.027
els+0.026
Neg logit contributions
ives-0.015
ury-0.012
 villains-0.011
 hide-0.011
and-0.011
Token are
Token ID389
Feature activation-4.00e-01

Pos logit contributions
flower+0.015
ble+0.014
ric+0.014
cking+0.014
els+0.014
Neg logit contributions
ives-0.009
ury-0.008
 Enjoy-0.008
 Welcome-0.008
 Happy-0.007
Token so
Token ID523
Feature activation-1.24e-01

Pos logit contributions
ives+0.011
 Enjoy+0.010
ury+0.010
 Welcome+0.009
 Happy+0.009
Neg logit contributions
flower-0.022
ble-0.020
ric-0.019
cking-0.019
els-0.019
Token It
Token ID632
Feature activation-6.63e-01

Pos logit contributions
ives+0.017
ury+0.015
ave+0.014
 Cop+0.014
 villains+0.014
Neg logit contributions
ble-0.021
flower-0.020
ric-0.019
cks-0.019
els-0.018
Token was
Token ID373
Feature activation-8.03e-01

Pos logit contributions
ives+0.015
 Max+0.014
ury+0.014
 Welcome+0.014
 hide+0.013
Neg logit contributions
flower-0.037
ric-0.035
ble-0.035
els-0.034
cking-0.034
Token the
Token ID262
Feature activation-9.66e-01

Pos logit contributions
ives+0.022
 Max+0.021
 Enjoy+0.020
 Welcome+0.020
ury+0.020
Neg logit contributions
flower-0.042
ric-0.037
els-0.037
ble-0.037
cking-0.036
Token rh
Token ID9529
Feature activation-1.86e+00

Pos logit contributions
ives+0.035
 Enjoy+0.031
ury+0.031
 Welcome+0.030
 Happy+0.029
Neg logit contributions
flower-0.043
cking-0.039
els-0.039
ble-0.039
ric-0.038
Tokenin
Token ID259
Feature activation-9.24e-01

Pos logit contributions
ives+0.099
ury+0.091
 Enjoy+0.089
 Welcome+0.088
 Happy+0.086
Neg logit contributions
flower-0.055
ble-0.047
ric-0.046
cking-0.045
els-0.044
Tokenoc
Token ID420
Feature activation-4.32e+00

Pos logit contributions
ives+0.033
ury+0.030
 Welcome+0.028
 Enjoy+0.028
 Follow+0.027
Neg logit contributions
flower-0.042
els-0.037
ric-0.037
ble-0.037
cking-0.037
Tokeneros
Token ID27498
Feature activation-8.16e-01

Pos logit contributions
ives+0.222
ury+0.206
 Welcome+0.200
 Enjoy+0.198
 Max+0.194
Neg logit contributions
flower-0.144
ble-0.129
els-0.122
ric-0.119
cking-0.114
Token.
Token ID13
Feature activation-5.14e-01

Pos logit contributions
ives+0.029
ury+0.026
 Enjoy+0.025
 Welcome+0.024
 Happy+0.023
Neg logit contributions
flower-0.039
ble-0.035
ric-0.035
els-0.034
cking-0.034
Token It
Token ID632
Feature activation-6.79e-01

Pos logit contributions
ives+0.018
ury+0.015
ave+0.014
 Cop+0.013
 villains+0.013
Neg logit contributions
flower-0.022
ble-0.022
ric-0.021
cks-0.020
els-0.019
Token lifted
Token ID13663
Feature activation-8.55e-01

Pos logit contributions
ives+0.016
ury+0.014
 Welcome+0.014
 Max+0.014
 Follow+0.014
Neg logit contributions
flower-0.038
ble-0.035
ric-0.035
els-0.035
cking-0.034
Token its
Token ID663
Feature activation-7.83e-01

Pos logit contributions
ives+0.042
ury+0.038
 Enjoy+0.037
 Welcome+0.036
 Follow+0.035
Neg logit contributions
flower-0.030
ble-0.027
els-0.026
ric-0.025
cking-0.025
Token have
Token ID423
Feature activation-1.20e-01

Pos logit contributions
flower+0.008
ble+0.008
ric+0.007
cking+0.007
els+0.007
Neg logit contributions
ives-0.005
ury-0.005
 Enjoy-0.005
 Welcome-0.004
 Follow-0.004
Token stopped
Token ID5025
Feature activation-3.70e-01

Pos logit contributions
ives+0.004
ury+0.004
 Enjoy+0.004
 Follow+0.004
 Welcome+0.004
Neg logit contributions
flower-0.006
ric-0.005
ble-0.005
cking-0.005
els-0.005
Token the
Token ID262
Feature activation-1.04e+00

Pos logit contributions
ives+0.011
ury+0.010
 Enjoy+0.010
 Welcome+0.010
 Happy+0.009
Neg logit contributions
flower-0.019
ble-0.017
ric-0.017
cking-0.017
els-0.017
Token rh
Token ID9529
Feature activation-1.99e+00

Pos logit contributions
ives+0.046
ury+0.041
 Enjoy+0.038
 Follow+0.037
enny+0.037
Neg logit contributions
flower-0.043
ric-0.037
ble-0.036
cking-0.035
els-0.034
Tokenin
Token ID259
Feature activation-6.67e-01

Pos logit contributions
ives+0.105
ury+0.097
 Enjoy+0.095
 Welcome+0.093
 Happy+0.091
Neg logit contributions
flower-0.061
ble-0.051
ric-0.050
cking-0.049
els-0.049
Tokenoc
Token ID420
Feature activation-4.27e+00

Pos logit contributions
ives+0.022
ury+0.019
 Enjoy+0.019
 Welcome+0.018
 Follow+0.017
Neg logit contributions
flower-0.034
ric-0.030
ble-0.030
cking-0.029
els-0.029
Tokeneros
Token ID27498
Feature activation-6.62e-01

Pos logit contributions
ives+0.217
ury+0.200
 Welcome+0.195
 Enjoy+0.193
 Follow+0.190
Neg logit contributions
flower-0.143
ble-0.121
els-0.120
ric-0.119
cking-0.113
Token.
Token ID13
Feature activation-3.99e-01

Pos logit contributions
ives+0.028
ury+0.025
 Enjoy+0.025
 Welcome+0.024
 People+0.023
Neg logit contributions
flower-0.027
ble-0.024
ric-0.023
cking-0.023
els-0.023
Token He
Token ID679
Feature activation-1.99e-01

Pos logit contributions
ives+0.012
ury+0.010
and+0.009
enny+0.009
 hide+0.009
Neg logit contributions
flower-0.019
ric-0.018
ble-0.017
els-0.016
cks-0.016
Token is
Token ID318
Feature activation-8.81e-01

Pos logit contributions
ives+0.007
ury+0.006
 Enjoy+0.006
and+0.006
 Welcome+0.006
Neg logit contributions
flower-0.009
ric-0.008
els-0.008
ble-0.008
cking-0.008
Token sleeping
Token ID11029
Feature activation-8.34e-01

Pos logit contributions
ives+0.031
ury+0.027
 Enjoy+0.026
 Welcome+0.025
 Follow+0.024
Neg logit contributions
flower-0.043
ble-0.039
ric-0.038
cking-0.038
els-0.038
Token She
Token ID1375
Feature activation+1.20e-01

Pos logit contributions
ives+0.016
ury+0.014
 Enjoy+0.013
 Follow+0.013
 Welcome+0.012
Neg logit contributions
flower-0.025
ble-0.023
ric-0.022
els-0.022
mill-0.022
Token saw
Token ID2497
Feature activation-1.61e+00

Pos logit contributions
flower+0.006
ble+0.005
els+0.005
cking+0.005
ric+0.005
Neg logit contributions
ives-0.004
 Enjoy-0.004
ury-0.004
 Welcome-0.004
 Happy-0.004
Token the
Token ID262
Feature activation-1.27e+00

Pos logit contributions
ives+0.058
ury+0.051
 Enjoy+0.051
 Max+0.049
 Welcome+0.049
Neg logit contributions
flower-0.075
ble-0.067
ric-0.066
cking-0.065
els-0.064
Token rh
Token ID9529
Feature activation-2.12e+00

Pos logit contributions
ives+0.049
ury+0.044
 Enjoy+0.042
 Welcome+0.041
 Follow+0.040
Neg logit contributions
flower-0.058
ble-0.052
ric-0.051
cking-0.050
els-0.050
Tokenin
Token ID259
Feature activation-1.23e+00

Pos logit contributions
ives+0.112
ury+0.103
 Enjoy+0.102
 Welcome+0.100
 Happy+0.098
Neg logit contributions
flower-0.064
ble-0.054
ric-0.052
cking-0.051
els-0.051
Tokenoc
Token ID420
Feature activation-4.27e+00

Pos logit contributions
ives+0.030
ury+0.025
 Enjoy+0.024
 Welcome+0.023
 Follow+0.022
Neg logit contributions
flower-0.070
ble-0.065
els-0.064
ric-0.064
cking-0.064
Tokeneros
Token ID27498
Feature activation-1.06e+00

Pos logit contributions
ives+0.222
ury+0.205
 Welcome+0.199
 Enjoy+0.197
 Happy+0.193
Neg logit contributions
flower-0.141
ble-0.120
els-0.119
ric-0.116
cking-0.112
Token coming
Token ID2406
Feature activation-8.18e-02

Pos logit contributions
ives+0.031
ury+0.027
 Welcome+0.026
 Max+0.026
 hide+0.025
Neg logit contributions
flower-0.054
ble-0.050
ric-0.050
els-0.048
cking-0.048
Token.
Token ID13
Feature activation-3.75e-01

Pos logit contributions
ives+0.003
ury+0.003
 Welcome+0.003
 Enjoy+0.003
 Max+0.003
Neg logit contributions
flower-0.004
ric-0.003
ble-0.003
cking-0.003
els-0.003
Token It
Token ID632
Feature activation-7.89e-01

Pos logit contributions
ives+0.011
ury+0.009
 Enjoy+0.009
 Follow+0.008
 Welcome+0.008
Neg logit contributions
flower-0.019
ble-0.018
ric-0.017
els-0.017
mill-0.016
Token was
Token ID373
Feature activation-7.94e-01

Pos logit contributions
ives+0.022
ury+0.020
 Welcome+0.019
 Max+0.019
 Enjoy+0.019
Neg logit contributions
flower-0.041
ble-0.038
ric-0.038
els-0.037
cking-0.037
TokenI
Token ID40
Feature activation+4.14e-01

Pos logit contributions
ives+0.003
ury+0.003
 Enjoy+0.003
 Welcome+0.002
 Follow+0.002
Neg logit contributions
flower-0.004
ble-0.003
ric-0.003
cking-0.003
els-0.003
Token will
Token ID481
Feature activation-1.50e+00

Pos logit contributions
flower+0.019
ric+0.016
ble+0.016
els+0.015
cking+0.015
Neg logit contributions
ives-0.015
 People-0.013
ury-0.013
 Welcome-0.012
 Happy-0.012
Token buy
Token ID2822
Feature activation+3.11e-01

Pos logit contributions
ives+0.042
ury+0.036
 Enjoy+0.035
 Welcome+0.034
 Happy+0.032
Neg logit contributions
flower-0.083
ble-0.075
ric-0.075
cking-0.074
els-0.074
Token more
Token ID517
Feature activation-7.99e-01

Pos logit contributions
flower+0.015
els+0.014
ble+0.014
ries+0.014
cking+0.013
Neg logit contributions
ives-0.011
ury-0.010
 Follow-0.009
 Welcome-0.009
 Sadly-0.009
Token av
Token ID1196
Feature activation-2.45e+00

Pos logit contributions
ives+0.026
ury+0.022
 Enjoy+0.022
 Welcome+0.021
 Happy+0.021
Neg logit contributions
flower-0.041
ble-0.037
ric-0.037
cking-0.036
els-0.036
Tokenoc
Token ID420
Feature activation-4.27e+00

Pos logit contributions
 Welcome+0.087
ives+0.087
ury+0.084
 People+0.082
 Bye+0.081
Neg logit contributions
flower-0.109
els-0.097
cking-0.094
cks-0.090
cker-0.090
Tokenados
Token ID22484
Feature activation+1.46e+00

Pos logit contributions
ives+0.216
 Welcome+0.216
ury+0.214
 Sadly+0.205
 Max+0.204
Neg logit contributions
els-0.123
flower-0.121
ries-0.117
ble-0.104
cking-0.100
Token tomorrow
Token ID9439
Feature activation-4.57e-01

Pos logit contributions
flower+0.072
ble+0.065
ric+0.063
els+0.063
cking+0.062
Neg logit contributions
ives-0.049
ury-0.044
 Enjoy-0.043
 Welcome-0.041
 Follow-0.040
Token.
Token ID13
Feature activation+4.22e-02

Pos logit contributions
ives+0.018
 Enjoy+0.016
ury+0.016
 Welcome+0.016
 Sadly+0.016
Neg logit contributions
flower-0.019
ble-0.017
els-0.016
ric-0.016
mill-0.016
Token You
Token ID921
Feature activation+6.83e-01

Pos logit contributions
flower+0.002
ric+0.002
els+0.002
ble+0.002
mill+0.002
Neg logit contributions
ives-0.001
and-0.001
ave-0.001
 villains-0.001
ury-0.001
Token can
Token ID460
Feature activation-8.03e-01

Pos logit contributions
flower+0.034
ble+0.030
ric+0.030
els+0.029
cking+0.028
Neg logit contributions
ives-0.021
ury-0.019
and-0.018
 Welcome-0.017
 Bye-0.017
Token vegetables
Token ID13701
Feature activation-1.06e-01

Pos logit contributions
ives+0.009
ury+0.009
 Enjoy+0.008
 Welcome+0.008
 Follow+0.008
Neg logit contributions
flower-0.010
ble-0.009
els-0.009
ric-0.009
cking-0.009
Token!
Token ID0
Feature activation+3.45e-01

Pos logit contributions
ives+0.003
ury+0.003
 Enjoy+0.003
 Welcome+0.003
 Max+0.003
Neg logit contributions
flower-0.005
ric-0.005
ble-0.005
els-0.005
cking-0.005
Token All
Token ID1439
Feature activation+1.78e-01

Pos logit contributions
flower+0.018
ric+0.016
ble+0.016
els+0.016
cks+0.015
Neg logit contributions
ives-0.010
ury-0.009
 Enjoy-0.008
 villains-0.007
 Welcome-0.007
Token the
Token ID262
Feature activation-1.40e+00

Pos logit contributions
flower+0.010
ble+0.009
ric+0.009
cking+0.009
els+0.008
Neg logit contributions
ives-0.005
 Max-0.004
 Happy-0.004
 Welcome-0.004
ury-0.004
Token b
Token ID275
Feature activation-1.97e+00

Pos logit contributions
ives+0.057
ury+0.051
 Enjoy+0.049
 Follow+0.048
 Welcome+0.047
Neg logit contributions
flower-0.062
els-0.055
ble-0.053
cking-0.053
ric-0.052
Tokenunn
Token ID20935
Feature activation-4.26e+00

Pos logit contributions
ives+0.043
 Welcome+0.042
 Happy+0.042
 Max+0.041
 Cop+0.041
Neg logit contributions
flower-0.114
els-0.106
ble-0.105
cking-0.104
ric-0.104
Tokenies
Token ID444
Feature activation-5.46e-01

Pos logit contributions
ives+0.287
ury+0.269
 Enjoy+0.269
 Welcome+0.264
 Follow+0.261
Neg logit contributions
flower-0.068
ble-0.047
ric-0.043
cking-0.042
els-0.042
Token were
Token ID547
Feature activation-4.77e-01

Pos logit contributions
ives+0.016
ury+0.014
 Enjoy+0.013
 Welcome+0.013
 Happy+0.013
Neg logit contributions
flower-0.029
ric-0.026
ble-0.026
els-0.026
cking-0.026
Token over
Token ID625
Feature activation+3.32e-01

Pos logit contributions
ives+0.013
ury+0.011
 Enjoy+0.010
 Welcome+0.010
 Happy+0.010
Neg logit contributions
flower-0.026
ric-0.024
ble-0.024
els-0.023
cking-0.023
Tokenjoy
Token ID2633
Feature activation-2.41e+00

Pos logit contributions
flower+0.017
ble+0.016
ric+0.016
cking+0.015
els+0.015
Neg logit contributions
ives-0.010
ury-0.009
 Enjoy-0.009
 Welcome-0.009
 Happy-0.008
Tokened
Token ID276
Feature activation-1.34e+00

Pos logit contributions
ives+0.073
 Enjoy+0.070
ury+0.067
 Sadly+0.066
 Welcome+0.064
Neg logit contributions
flower-0.122
els-0.105
ble-0.104
ric-0.102
cking-0.101
Token He
Token ID679
Feature activation+3.39e-01

Pos logit contributions
flower+0.007
ric+0.007
ble+0.007
mill+0.006
els+0.006
Neg logit contributions
ives-0.004
ury-0.003
 Enjoy-0.003
 hide-0.003
 Follow-0.003
Token had
Token ID550
Feature activation+1.38e-01

Pos logit contributions
flower+0.018
ble+0.016
ric+0.016
cking+0.016
els+0.016
Neg logit contributions
ives-0.010
ury-0.009
 Enjoy-0.009
 Welcome-0.008
 Follow-0.008
Token taught
Token ID7817
Feature activation-1.49e+00

Pos logit contributions
flower+0.007
ble+0.006
ric+0.006
cking+0.006
els+0.006
Neg logit contributions
ives-0.005
ury-0.004
 Enjoy-0.004
 Welcome-0.004
 Follow-0.004
Token the
Token ID262
Feature activation-2.81e-01

Pos logit contributions
ives+0.062
ury+0.056
 Enjoy+0.053
 Follow+0.053
 Welcome+0.052
Neg logit contributions
flower-0.061
ric-0.056
ble-0.056
els-0.055
cking-0.053
Token b
Token ID275
Feature activation-1.97e+00

Pos logit contributions
ives+0.010
ury+0.009
 Enjoy+0.008
 Welcome+0.008
 Follow+0.008
Neg logit contributions
flower-0.014
ble-0.013
ric-0.012
cking-0.012
els-0.012
Tokenunn
Token ID20935
Feature activation-4.26e+00

Pos logit contributions
ives+0.044
ury+0.038
 Max+0.037
 Happy+0.037
 Enjoy+0.037
Neg logit contributions
flower-0.116
ble-0.107
ric-0.105
els-0.105
cking-0.103
Tokenies
Token ID444
Feature activation-4.56e-01

Pos logit contributions
ives+0.264
ury+0.245
 Enjoy+0.239
 Welcome+0.237
 Happy+0.233
Neg logit contributions
flower-0.088
ble-0.071
ric-0.068
cking-0.067
els-0.065
Token to
Token ID284
Feature activation-2.82e-01

Pos logit contributions
ives+0.014
 Enjoy+0.012
ury+0.012
 Welcome+0.011
 Happy+0.011
Neg logit contributions
flower-0.024
cking-0.022
ble-0.022
els-0.021
eled-0.021
Token be
Token ID307
Feature activation+9.07e-01

Pos logit contributions
ives+0.010
ury+0.009
 Enjoy+0.008
 Welcome+0.008
 Follow+0.008
Neg logit contributions
flower-0.014
ble-0.012
ric-0.012
cking-0.012
els-0.012
Token friendly
Token ID8030
Feature activation-8.11e-01

Pos logit contributions
flower+0.052
ric+0.049
ble+0.049
els+0.047
cking+0.046
Neg logit contributions
ives-0.022
 Enjoy-0.018
ury-0.018
 Max-0.018
 Happy-0.017
Token.
Token ID13
Feature activation+1.12e-01

Pos logit contributions
ives+0.030
ury+0.027
 Enjoy+0.026
 Welcome+0.025
 Follow+0.025
Neg logit contributions
flower-0.037
ble-0.033
ric-0.032
els-0.032
cking-0.031
Token the
Token ID262
Feature activation-3.92e-02

Pos logit contributions
ives+0.002
 Enjoy+0.002
 Max+0.002
 hide+0.001
ury+0.001
Neg logit contributions
flower-0.002
els-0.002
ble-0.002
cking-0.002
ric-0.002
Token top
Token ID1353
Feature activation+8.32e-01

Pos logit contributions
ives+0.001
 Enjoy+0.001
 Welcome+0.001
 hide+0.001
ury+0.001
Neg logit contributions
flower-0.002
els-0.002
cks-0.002
cking-0.002
ric-0.001
Token.
Token ID13
Feature activation+2.15e-01

Pos logit contributions
flower+0.047
ble+0.045
els+0.044
ric+0.044
cking+0.044
Neg logit contributions
ives-0.020
ury-0.017
 Welcome-0.015
 Max-0.015
 Enjoy-0.015
Token The
Token ID383
Feature activation-4.55e-01

Pos logit contributions
flower+0.011
ric+0.011
ble+0.010
els+0.010
eled+0.010
Neg logit contributions
ives-0.006
ury-0.005
 Enjoy-0.004
 villains-0.004
 Welcome-0.004
Token b
Token ID275
Feature activation-1.77e+00

Pos logit contributions
ives+0.014
 Enjoy+0.013
 Welcome+0.013
 Happy+0.012
ury+0.012
Neg logit contributions
flower-0.022
cks-0.021
ric-0.020
els-0.020
cking-0.020
Tokenunn
Token ID20935
Feature activation-4.25e+00

Pos logit contributions
ives+0.037
ury+0.030
 Enjoy+0.028
 Welcome+0.027
 Happy+0.026
Neg logit contributions
flower-0.111
ble-0.103
ric-0.101
els-0.100
cking-0.100
Tokenies
Token ID444
Feature activation-1.80e-01

Pos logit contributions
ives+0.260
ury+0.241
 Enjoy+0.235
 Welcome+0.232
 Follow+0.229
Neg logit contributions
flower-0.085
ble-0.070
ric-0.069
cking-0.067
els-0.065
Token settled
Token ID10282
Feature activation-1.49e+00

Pos logit contributions
ives+0.005
ury+0.004
 Welcome+0.004
 Enjoy+0.004
 Follow+0.004
Neg logit contributions
flower-0.010
ric-0.009
ble-0.009
els-0.009
cking-0.009
Token in
Token ID287
Feature activation-5.87e-01

Pos logit contributions
ives+0.049
ury+0.044
 Max+0.043
 Enjoy+0.043
 Happy+0.042
Neg logit contributions
flower-0.068
ric-0.063
cking-0.062
els-0.062
ble-0.061
Token and
Token ID290
Feature activation-1.99e-01

Pos logit contributions
 Enjoy+0.016
ives+0.015
 Happy+0.015
 Max+0.015
 Welcome+0.015
Neg logit contributions
flower-0.031
ble-0.029
ric-0.028
els-0.028
cking-0.028
Token soon
Token ID2582
Feature activation-1.07e-02

Pos logit contributions
ives+0.008
ury+0.007
 Enjoy+0.007
 People+0.007
 Welcome+0.007
Neg logit contributions
flower-0.009
ble-0.007
cking-0.007
ric-0.007
mill-0.007
Token one
Token ID530
Feature activation-5.49e-01

Pos logit contributions
flower+0.023
ble+0.022
cking+0.021
cks+0.021
ric+0.021
Neg logit contributions
 Max-0.015
ives-0.015
 Enjoy-0.014
ury-0.014
 Welcome-0.014
Token day
Token ID1110
Feature activation-3.04e-01

Pos logit contributions
ives+0.014
ury+0.012
 Enjoy+0.012
 Welcome+0.012
 Happy+0.011
Neg logit contributions
flower-0.031
ble-0.029
ric-0.028
els-0.028
cking-0.028
Token it
Token ID340
Feature activation-1.00e+00

Pos logit contributions
ives+0.008
ury+0.007
 Enjoy+0.007
 Max+0.007
 Welcome+0.007
Neg logit contributions
flower-0.017
ric-0.016
ble-0.015
cking-0.015
els-0.015
Token started
Token ID2067
Feature activation-3.66e-01

Pos logit contributions
ives+0.031
ury+0.027
 Max+0.026
 Sadly+0.025
 Welcome+0.025
Neg logit contributions
flower-0.050
ric-0.047
els-0.046
cking-0.046
cks-0.045
Token to
Token ID284
Feature activation-4.83e-01

Pos logit contributions
ives+0.005
ury+0.003
 Max+0.003
 Welcome+0.003
 Sadly+0.003
Neg logit contributions
flower-0.025
ble-0.023
els-0.023
cks-0.023
cking-0.023
Token rain
Token ID6290
Feature activation+1.59e+00

Pos logit contributions
 hide+0.012
 Max+0.011
 rest+0.010
 you+0.009
 Sadly+0.009
Neg logit contributions
els-0.027
cks-0.026
eled-0.026
flower-0.026
ries-0.024
Token.
Token ID13
Feature activation-8.82e-02

Pos logit contributions
flower+0.080
els+0.076
ble+0.074
cking+0.074
eled+0.073
Neg logit contributions
ives-0.048
ury-0.042
 Max-0.040
 hide-0.039
t-0.037
Token The
Token ID383
Feature activation-2.95e-01

Pos logit contributions
ives+0.003
ury+0.003
 villains+0.003
 Enjoy+0.002
 Cop+0.002
Neg logit contributions
flower-0.004
ric-0.004
ble-0.003
els-0.003
ries-0.003
Token little
Token ID1310
Feature activation-4.39e-01

Pos logit contributions
ives+0.010
ury+0.009
 Enjoy+0.009
 Welcome+0.009
 Happy+0.008
Neg logit contributions
flower-0.014
ble-0.013
ric-0.013
cking-0.013
els-0.012
Token girl
Token ID2576
Feature activation-3.67e-01

Pos logit contributions
ives+0.013
ury+0.012
 Welcome+0.011
 Max+0.011
 Happy+0.011
Neg logit contributions
flower-0.022
ric-0.021
cking-0.021
cks-0.021
ble-0.021
Token started
Token ID2067
Feature activation-1.60e-01

Pos logit contributions
ives+0.014
 Enjoy+0.013
ury+0.012
 Welcome+0.012
 Happy+0.012
Neg logit contributions
flower-0.017
ble-0.014
cking-0.014
ric-0.014
els-0.014
Token boy
Token ID2933
Feature activation-1.08e-01

Pos logit contributions
flower+0.005
ble+0.004
ric+0.004
mill+0.004
els+0.004
Neg logit contributions
ives-0.005
ury-0.005
 Enjoy-0.005
 Sadly-0.004
 People-0.004
Token.
Token ID13
Feature activation-1.15e-01

Pos logit contributions
ives+0.003
ury+0.003
 Enjoy+0.003
 Welcome+0.003
 Follow+0.002
Neg logit contributions
flower-0.006
ble-0.005
ric-0.005
els-0.005
cking-0.005
Token He
Token ID679
Feature activation+7.58e-01

Pos logit contributions
ives+0.003
ury+0.003
 Enjoy+0.002
 Follow+0.002
 Welcome+0.002
Neg logit contributions
flower-0.006
ric-0.006
ble-0.006
els-0.006
mill-0.006
Token liked
Token ID8288
Feature activation-6.19e-01

Pos logit contributions
flower+0.044
ble+0.040
ric+0.040
cking+0.039
els+0.039
Neg logit contributions
ives-0.019
ury-0.016
 Enjoy-0.016
 Welcome-0.015
 Happy-0.014
Token to
Token ID284
Feature activation-5.19e-01

Pos logit contributions
ives+0.013
ury+0.011
 Enjoy+0.010
 Welcome+0.009
 Follow+0.009
Neg logit contributions
flower-0.038
ble-0.035
ric-0.035
cking-0.035
els-0.035
Token climb
Token ID12080
Feature activation+1.68e+00

Pos logit contributions
ives+0.013
 Enjoy+0.012
 hide+0.011
ury+0.011
 Welcome+0.011
Neg logit contributions
flower-0.029
cking-0.026
ble-0.026
ric-0.026
els-0.026
Token.
Token ID13
Feature activation-1.64e-01

Pos logit contributions
flower+0.093
cking+0.083
ble+0.082
eled+0.081
ric+0.081
Neg logit contributions
 Max-0.044
ives-0.041
 Happy-0.039
 hide-0.039
 People-0.039
Token He
Token ID679
Feature activation+3.91e-01

Pos logit contributions
ives+0.005
ury+0.005
 Enjoy+0.004
 Follow+0.004
 Welcome+0.004
Neg logit contributions
flower-0.008
ric-0.008
ble-0.008
els-0.007
cks-0.007
Token climbed
Token ID19952
Feature activation+6.74e-01

Pos logit contributions
flower+0.021
ble+0.020
ric+0.019
cking+0.019
els+0.019
Neg logit contributions
ives-0.011
ury-0.009
 Enjoy-0.009
 Welcome-0.009
 Follow-0.009
Token on
Token ID319
Feature activation-5.00e-01

Pos logit contributions
flower+0.037
cking+0.034
ric+0.033
eled+0.033
els+0.032
Neg logit contributions
 Max-0.016
ives-0.016
 Happy-0.015
 hide-0.015
 Now-0.015
Token his
Token ID465
Feature activation-9.03e-01

Pos logit contributions
ives+0.020
ury+0.018
 Enjoy+0.017
 Welcome+0.017
 Follow+0.016
Neg logit contributions
flower-0.022
ble-0.020
ric-0.019
cking-0.019
els-0.019
Token's
Token ID338
Feature activation-3.02e-03

Pos logit contributions
flower+0.002
ble+0.002
ric+0.002
cking+0.002
els+0.002
Neg logit contributions
ives-0.001
ury-0.001
 Enjoy-0.001
 Welcome-0.001
 Follow-0.001
Token not
Token ID407
Feature activation+8.36e-01

Pos logit contributions
 Max+0.000
ives+0.000
ury+0.000
 Enjoy+0.000
 hide+0.000
Neg logit contributions
flower-0.000
ble-0.000
els-0.000
ric-0.000
eled-0.000
Token safe
Token ID3338
Feature activation-6.01e-01

Pos logit contributions
flower+0.046
els+0.042
ble+0.041
ric+0.041
cking+0.041
Neg logit contributions
ives-0.023
ury-0.021
 Max-0.020
 Enjoy-0.020
 Welcome-0.019
Token,"
Token ID553
Feature activation+1.22e-01

Pos logit contributions
ives+0.020
ury+0.018
 Enjoy+0.017
 Welcome+0.016
 Max+0.016
Neg logit contributions
flower-0.030
ric-0.027
ble-0.027
cking-0.027
els-0.026
Token replied
Token ID8712
Feature activation+1.31e+00

Pos logit contributions
flower+0.007
ble+0.006
ric+0.006
els+0.006
cking+0.006
Neg logit contributions
ives-0.003
ury-0.003
 Enjoy-0.003
 Welcome-0.002
 Follow-0.002
Token her
Token ID607
Feature activation+1.81e+00

Pos logit contributions
flower+0.070
ble+0.064
ric+0.063
cking+0.063
els+0.062
Neg logit contributions
ives-0.038
ury-0.033
 Enjoy-0.032
 Welcome-0.031
 Happy-0.030
Token mom
Token ID1995
Feature activation+1.53e+00

Pos logit contributions
flower+0.086
ric+0.078
cking+0.078
ble+0.077
els+0.076
Neg logit contributions
ives-0.062
ury-0.056
 Max-0.053
 Enjoy-0.053
 Welcome-0.053
Token.
Token ID13
Feature activation+9.51e-01

Pos logit contributions
flower+0.060
ble+0.050
els+0.050
cking+0.049
ric+0.048
Neg logit contributions
ives-0.069
 Enjoy-0.065
ury-0.062
 Welcome-0.061
 People-0.060
Token "
Token ID366
Feature activation+2.15e-01

Pos logit contributions
flower+0.045
ric+0.039
ble+0.038
mill+0.038
els+0.036
Neg logit contributions
ives-0.033
 Enjoy-0.028
ury-0.027
 villains-0.027
 Follow-0.025
TokenYou
Token ID1639
Feature activation+1.29e+00

Pos logit contributions
flower+0.009
ble+0.008
ric+0.008
cking+0.008
els+0.008
Neg logit contributions
ives-0.009
ury-0.008
 Enjoy-0.008
 Welcome-0.007
 Happy-0.007
Token need
Token ID761
Feature activation+1.74e-01

Pos logit contributions
flower+0.062
ble+0.058
ric+0.056
els+0.055
cking+0.053
Neg logit contributions
ives-0.040
and-0.037
ury-0.037
 Enjoy-0.036
 Welcome-0.036
Token and
Token ID290
Feature activation-3.48e-01

Pos logit contributions
ives+0.026
 Enjoy+0.024
ury+0.023
 Welcome+0.022
 People+0.022
Neg logit contributions
flower-0.035
ble-0.030
ric-0.030
els-0.029
cking-0.029
Token Ben
Token ID3932
Feature activation+3.70e-02

Pos logit contributions
ives+0.008
ury+0.007
 Enjoy+0.006
 Welcome+0.006
 Follow+0.006
Neg logit contributions
flower-0.021
ble-0.019
els-0.019
ric-0.019
cking-0.019
Token smiled
Token ID13541
Feature activation-5.17e-01

Pos logit contributions
flower+0.002
ble+0.002
ric+0.002
els+0.002
cking+0.002
Neg logit contributions
ives-0.001
ury-0.001
 Enjoy-0.001
 Welcome-0.001
 Happy-0.001
Token and
Token ID290
Feature activation+2.64e-01

Pos logit contributions
ives+0.012
 Happy+0.010
 Max+0.010
 And+0.010
ury+0.010
Neg logit contributions
flower-0.030
ric-0.029
cking-0.029
els-0.029
cks-0.028
Token looked
Token ID3114
Feature activation+4.50e-01

Pos logit contributions
flower+0.012
ble+0.010
cking+0.010
ric+0.010
cks+0.010
Neg logit contributions
ives-0.010
ury-0.009
 Enjoy-0.009
 These-0.008
 People-0.008
Token at
Token ID379
Feature activation+1.56e+00

Pos logit contributions
flower+0.024
ble+0.022
ric+0.022
els+0.021
cking+0.021
Neg logit contributions
ives-0.013
ury-0.012
 Enjoy-0.011
 Welcome-0.011
 Happy-0.011
Token it
Token ID340
Feature activation+3.40e-01

Pos logit contributions
flower+0.069
ble+0.061
ric+0.060
cking+0.059
els+0.057
Neg logit contributions
ives-0.061
 Enjoy-0.055
ury-0.054
 Max-0.054
 Welcome-0.053
Token with
Token ID351
Feature activation-1.82e-01

Pos logit contributions
flower+0.017
ric+0.016
ble+0.015
els+0.015
cking+0.015
Neg logit contributions
ives-0.011
ury-0.009
 Welcome-0.009
 Max-0.009
 Happy-0.009
Token wonder
Token ID4240
Feature activation-1.66e-01

Pos logit contributions
ives+0.006
 Enjoy+0.006
ury+0.006
 Welcome+0.006
 Happy+0.005
Neg logit contributions
flower-0.009
ble-0.008
ric-0.008
cking-0.008
els-0.008
Token.
Token ID13
Feature activation-2.37e-01

Pos logit contributions
ives+0.005
ury+0.004
 Happy+0.004
 Enjoy+0.004
 Max+0.004
Neg logit contributions
flower-0.009
ric-0.008
ble-0.008
cking-0.008
eled-0.008
Token They
Token ID1119
Feature activation-2.39e-01

Pos logit contributions
ives+0.008
ury+0.007
 villains+0.006
 Cop+0.006
 Enjoy+0.006
Neg logit contributions
flower-0.010
ric-0.010
ble-0.009
cks-0.009
els-0.009
Token family
Token ID1641
Feature activation-6.68e-01

Pos logit contributions
ives+0.029
ury+0.025
 Enjoy+0.025
 Welcome+0.024
 Happy+0.023
Neg logit contributions
flower-0.042
ble-0.038
cking-0.038
ric-0.038
els-0.037
Token,
Token ID11
Feature activation+3.44e-01

Pos logit contributions
ives+0.018
ury+0.015
 Welcome+0.015
 Enjoy+0.015
 Happy+0.015
Neg logit contributions
flower-0.035
ble-0.033
cking-0.033
ric-0.033
cks-0.032
Token with
Token ID351
Feature activation-3.26e-01

Pos logit contributions
flower+0.019
ble+0.018
cking+0.017
ric+0.017
els+0.017
Neg logit contributions
ives-0.009
ury-0.008
 Enjoy-0.008
 Welcome-0.007
 Max-0.007
Token Mom
Token ID11254
Feature activation+1.37e+00

Pos logit contributions
ives+0.012
ury+0.011
 Enjoy+0.011
 Welcome+0.010
 Follow+0.010
Neg logit contributions
flower-0.015
ble-0.013
ric-0.013
els-0.013
cking-0.013
Token and
Token ID290
Feature activation+3.28e-01

Pos logit contributions
flower+0.070
ble+0.067
cking+0.065
ric+0.064
els+0.063
Neg logit contributions
ives-0.040
ury-0.035
 Max-0.034
 Happy-0.033
 Enjoy-0.033
Token Dad
Token ID17415
Feature activation+2.21e+00

Pos logit contributions
flower+0.017
ble+0.016
ric+0.016
cking+0.015
els+0.015
Neg logit contributions
ives-0.010
 Enjoy-0.009
ury-0.009
 Happy-0.008
 Welcome-0.008
Token and
Token ID290
Feature activation+9.05e-01

Pos logit contributions
flower+0.107
ble+0.098
ric+0.096
cking+0.095
els+0.094
Neg logit contributions
ives-0.075
ury-0.066
 Enjoy-0.064
 Welcome-0.064
 Happy-0.062
Token his
Token ID465
Feature activation+1.40e+00

Pos logit contributions
flower+0.045
ble+0.041
ric+0.040
cking+0.040
els+0.040
Neg logit contributions
ives-0.030
ury-0.026
 Enjoy-0.025
 Welcome-0.025
 Follow-0.024
Token two
Token ID734
Feature activation+2.76e+00

Pos logit contributions
flower+0.067
ble+0.061
ric+0.060
els+0.059
cking+0.058
Neg logit contributions
ives-0.049
ury-0.043
 Enjoy-0.042
 Welcome-0.041
 Follow-0.040
Token brothers
Token ID9397
Feature activation+1.75e+00

Pos logit contributions
flower+0.126
ble+0.113
ric+0.111
els+0.111
cking+0.111
Neg logit contributions
ives-0.102
ury-0.091
 Enjoy-0.090
 Welcome-0.086
 Follow-0.085
Token,
Token ID11
Feature activation+1.07e+00

Pos logit contributions
flower+0.083
ble+0.076
ric+0.074
cking+0.074
els+0.073
Neg logit contributions
ives-0.062
ury-0.054
 Enjoy-0.053
 Welcome-0.052
 Happy-0.050
Token quickly
Token ID2952
Feature activation-1.35e+00

Pos logit contributions
flower+0.021
ble+0.019
ric+0.018
cking+0.018
els+0.018
Neg logit contributions
ives-0.013
ury-0.011
 Enjoy-0.011
 Welcome-0.011
 Happy-0.010
Token took
Token ID1718
Feature activation+1.74e-02

Pos logit contributions
ives+0.050
 Enjoy+0.045
ury+0.044
 Welcome+0.043
 Happy+0.042
Neg logit contributions
flower-0.060
ble-0.055
cking-0.054
els-0.053
ric-0.052
Token out
Token ID503
Feature activation-6.31e-01

Pos logit contributions
flower+0.001
els+0.001
ble+0.001
cking+0.000
eled+0.000
Neg logit contributions
ives-0.001
ury-0.001
 villains-0.001
 Welcome-0.001
 Bye-0.001
Token the
Token ID262
Feature activation-5.11e-01

Pos logit contributions
ives+0.023
 Enjoy+0.020
 Happy+0.020
 Max+0.019
 Welcome+0.019
Neg logit contributions
flower-0.030
ble-0.028
ric-0.027
cking-0.026
cks-0.025
Token shining
Token ID22751
Feature activation+7.10e-01

Pos logit contributions
ives+0.023
ury+0.021
 Enjoy+0.020
 Welcome+0.020
 Happy+0.019
Neg logit contributions
flower-0.020
ble-0.017
ric-0.017
cking-0.017
els-0.017
Token coal
Token ID5655
Feature activation-3.21e-01

Pos logit contributions
flower+0.031
cking+0.030
ric+0.029
cks+0.029
ble+0.028
Neg logit contributions
ives-0.025
 Enjoy-0.023
ury-0.022
 Welcome-0.021
 Happy-0.021
Token from
Token ID422
Feature activation+1.63e-01

Pos logit contributions
ives+0.010
ury+0.009
 Enjoy+0.008
 Welcome+0.008
 Max+0.008
Neg logit contributions
flower-0.016
ric-0.015
ble-0.015
cking-0.015
els-0.015
Token her
Token ID607
Feature activation+8.03e-01

Pos logit contributions
flower+0.007
ric+0.006
ble+0.006
cking+0.006
els+0.006
Neg logit contributions
ives-0.006
 Enjoy-0.006
 Max-0.005
 Welcome-0.005
ury-0.005
Token pocket
Token ID10000
Feature activation-1.23e-01

Pos logit contributions
flower+0.038
ble+0.034
ric+0.033
cking+0.033
els+0.033
Neg logit contributions
ives-0.029
ury-0.026
 Enjoy-0.025
 Welcome-0.025
 Happy-0.024
Token and
Token ID290
Feature activation+4.51e-01

Pos logit contributions
ives+0.005
 Enjoy+0.004
ury+0.004
 Welcome+0.004
 Happy+0.004
Neg logit contributions
flower-0.006
ble-0.005
els-0.005
ric-0.005
cking-0.005
Token placed
Token ID4624
Feature activation-5.26e-01

Pos logit contributions
flower+0.021
ble+0.019
els+0.018
cking+0.018
ric+0.017
Neg logit contributions
ives-0.017
ury-0.015
 Enjoy-0.015
 Welcome-0.014
 People-0.014
TokenThank
Token ID10449
Feature activation+6.88e-01

Pos logit contributions
flower+0.015
ble+0.013
ric+0.013
cking+0.013
els+0.013
Neg logit contributions
ives-0.011
ury-0.009
 Enjoy-0.009
 Welcome-0.009
 Happy-0.009
Token you
Token ID345
Feature activation+3.95e-02

Pos logit contributions
flower+0.033
ble+0.033
els+0.032
cks+0.031
ries+0.031
Neg logit contributions
ives-0.022
 Sadly-0.019
ury-0.018
ave-0.016
 Enjoy-0.015
Token,
Token ID11
Feature activation+1.95e-01

Pos logit contributions
flower+0.002
ble+0.001
ric+0.001
els+0.001
bery+0.001
Neg logit contributions
ives-0.002
ury-0.001
 Enjoy-0.001
 Welcome-0.001
 Follow-0.001
Token now
Token ID783
Feature activation-3.40e-02

Pos logit contributions
flower+0.008
ble+0.008
ric+0.007
mill+0.007
els+0.007
Neg logit contributions
ives-0.008
ury-0.006
ave-0.006
and-0.006
 Enjoy-0.006
Token I
Token ID314
Feature activation+5.76e-02

Pos logit contributions
ives+0.001
ury+0.001
and+0.001
 Enjoy+0.001
 Sadly+0.001
Neg logit contributions
flower-0.002
ble-0.002
cking-0.001
ric-0.001
els-0.001
Token can
Token ID460
Feature activation-8.81e-02

Pos logit contributions
flower+0.003
ble+0.002
ric+0.002
els+0.002
cking+0.002
Neg logit contributions
ives-0.002
ury-0.002
 Enjoy-0.002
 People-0.002
 Cop-0.002
Token work
Token ID670
Feature activation+5.86e-01

Pos logit contributions
ives+0.002
ury+0.002
 Enjoy+0.002
 Welcome+0.002
 Happy+0.002
Neg logit contributions
flower-0.005
ble-0.005
ric-0.004
cking-0.004
els-0.004
Token again
Token ID757
Feature activation-3.56e-01

Pos logit contributions
flower+0.026
ble+0.024
cking+0.023
els+0.023
ric+0.023
Neg logit contributions
ives-0.022
ury-0.020
 Enjoy-0.019
 Follow-0.018
 Welcome-0.018
Token!"
Token ID2474
Feature activation+1.32e-01

Pos logit contributions
ives+0.014
ury+0.012
 Enjoy+0.012
 Welcome+0.011
 Follow+0.011
Neg logit contributions
flower-0.016
ble-0.014
ric-0.014
cking-0.014
els-0.014
Token
Token ID220
Feature activation+1.03e+00

Pos logit contributions
flower+0.007
ric+0.007
ble+0.007
els+0.006
mill+0.006
Neg logit contributions
ives-0.003
ury-0.003
 Welcome-0.003
 Enjoy-0.003
 villains-0.002
Token
Token ID198
Feature activation+8.59e-01

Pos logit contributions
flower+0.056
ble+0.054
ric+0.052
cking+0.050
els+0.050
Neg logit contributions
ives-0.027
ury-0.024
 Enjoy-0.022
 Welcome-0.022
 Happy-0.021
Tokenmy
Token ID1820
Feature activation+1.05e-01

Pos logit contributions
flower+0.013
ble+0.012
ric+0.012
cking+0.012
els+0.012
Neg logit contributions
ives-0.009
ury-0.008
 Enjoy-0.008
 Welcome-0.008
 Happy-0.007
Token smiled
Token ID13541
Feature activation-9.15e-01

Pos logit contributions
flower+0.005
ble+0.005
ric+0.005
cking+0.005
els+0.005
Neg logit contributions
ives-0.003
ury-0.003
 Enjoy-0.003
 Welcome-0.003
 Happy-0.003
Token and
Token ID290
Feature activation+1.10e-01

Pos logit contributions
ives+0.017
 Max+0.016
ury+0.015
 And+0.015
 Happy+0.015
Neg logit contributions
ric-0.056
cks-0.055
flower-0.054
cking-0.054
els-0.053
Token felt
Token ID2936
Feature activation+1.04e+00

Pos logit contributions
flower+0.006
ble+0.005
cking+0.005
mill+0.005
els+0.005
Neg logit contributions
ives-0.004
ury-0.003
 Enjoy-0.003
 Welcome-0.003
 People-0.003
Token much
Token ID881
Feature activation+7.08e-01

Pos logit contributions
flower+0.063
ric+0.058
els+0.057
ble+0.056
cking+0.055
Neg logit contributions
ives-0.025
 Enjoy-0.022
 Happy-0.020
ury-0.020
 Welcome-0.020
Token better
Token ID1365
Feature activation+1.85e-01

Pos logit contributions
flower+0.033
ble+0.030
cking+0.029
els+0.029
ric+0.028
Neg logit contributions
ives-0.025
ury-0.023
 Enjoy-0.022
 Welcome-0.021
 Follow-0.020
Token.
Token ID13
Feature activation+2.31e-01

Pos logit contributions
flower+0.008
ble+0.007
cking+0.007
mill+0.006
els+0.006
Neg logit contributions
ives-0.008
 Enjoy-0.007
 People-0.007
ury-0.007
 Follow-0.007
Token Lily
Token ID20037
Feature activation-4.59e-01

Pos logit contributions
flower+0.011
ric+0.010
mill+0.009
eled+0.009
els+0.009
Neg logit contributions
ives-0.007
ury-0.006
 Cop-0.006
 villains-0.006
 Enjoy-0.006
Token learned
Token ID4499
Feature activation-7.83e-01

Pos logit contributions
ives+0.015
ury+0.013
 Enjoy+0.013
 Welcome+0.012
 Happy+0.012
Neg logit contributions
flower-0.023
ble-0.021
ric-0.020
els-0.020
cking-0.020
Token that
Token ID326
Feature activation-1.27e+00

Pos logit contributions
ives+0.026
ury+0.023
 Enjoy+0.023
 Welcome+0.022
 Happy+0.021
Neg logit contributions
flower-0.039
ble-0.035
ric-0.035
cking-0.034
els-0.034
Token sometimes
Token ID3360
Feature activation+2.11e-01

Pos logit contributions
ives+0.063
ury+0.057
 Follow+0.052
 Enjoy+0.051
ave+0.050
Neg logit contributions
flower-0.048
ble-0.043
els-0.039
mill-0.039
cking-0.039
Token "
Token ID366
Feature activation-3.38e-01

Pos logit contributions
flower+0.001
ble+0.001
ric+0.001
cking+0.001
els+0.001
Neg logit contributions
ives-0.000
ury-0.000
 Enjoy-0.000
 Follow-0.000
 Welcome-0.000
TokenHi
Token ID17250
Feature activation+4.01e-01

Pos logit contributions
ives+0.011
ury+0.010
 Enjoy+0.009
 Welcome+0.009
 Happy+0.009
Neg logit contributions
flower-0.017
ble-0.016
ric-0.016
els-0.016
cking-0.016
Token!
Token ID0
Feature activation+7.75e-01

Pos logit contributions
flower+0.018
ble+0.016
els+0.016
ric+0.015
ries+0.015
Neg logit contributions
ives-0.016
 Enjoy-0.014
ury-0.013
 Sadly-0.013
 Follow-0.013
Token My
Token ID2011
Feature activation-5.27e-01

Pos logit contributions
flower+0.043
ric+0.039
mill+0.036
ble+0.035
els+0.035
Neg logit contributions
ives-0.022
ury-0.016
 Sadly-0.015
 Enjoy-0.015
and-0.014
Token name
Token ID1438
Feature activation+8.74e-01

Pos logit contributions
ives+0.023
ury+0.020
 Enjoy+0.020
 Sadly+0.019
 Follow+0.019
Neg logit contributions
flower-0.022
ble-0.019
ric-0.019
els-0.018
mill-0.016
Token is
Token ID318
Feature activation+7.98e-01

Pos logit contributions
flower+0.046
ble+0.042
ric+0.042
cking+0.041
els+0.041
Neg logit contributions
ives-0.026
ury-0.023
 Enjoy-0.022
 Welcome-0.021
 Happy-0.021
Token Sue
Token ID26089
Feature activation+1.13e+00

Pos logit contributions
flower+0.046
ble+0.042
ric+0.042
els+0.041
cks+0.041
Neg logit contributions
ives-0.021
ury-0.016
 Enjoy-0.015
 Sadly-0.014
 Follow-0.014
Token.
Token ID13
Feature activation+2.88e-01

Pos logit contributions
flower+0.052
ble+0.048
cking+0.048
ric+0.047
els+0.047
Neg logit contributions
ives-0.040
ury-0.036
 Enjoy-0.034
 Welcome-0.034
 Happy-0.033
Token This
Token ID770
Feature activation+1.36e+00

Pos logit contributions
flower+0.016
ric+0.014
els+0.013
mill+0.013
ble+0.013
Neg logit contributions
ives-0.008
ury-0.006
 Sadly-0.005
ave-0.005
 Enjoy-0.005
Token is
Token ID318
Feature activation+1.12e-01

Pos logit contributions
flower+0.060
ble+0.052
ric+0.051
els+0.050
cks+0.047
Neg logit contributions
ives-0.053
ury-0.048
 Enjoy-0.046
 Sadly-0.046
and-0.045
Token Fl
Token ID1610
Feature activation-9.86e-01

Pos logit contributions
flower+0.006
ble+0.005
ric+0.005
cking+0.005
els+0.005
Neg logit contributions
ives-0.003
ury-0.003
 Enjoy-0.003
 Welcome-0.003
 Happy-0.003
Token was
Token ID373
Feature activation-8.36e-01

Pos logit contributions
ives+0.028
ury+0.024
 Welcome+0.023
 Follow+0.023
 Happy+0.023
Neg logit contributions
flower-0.048
ble-0.044
ric-0.044
cking-0.043
els-0.043
Token very
Token ID845
Feature activation-9.62e-01

Pos logit contributions
 Max+0.021
ives+0.019
 Happy+0.018
 hide+0.018
 Welcome+0.018
Neg logit contributions
flower-0.047
ric-0.042
ble-0.041
els-0.041
cking-0.041
Token dark
Token ID3223
Feature activation-5.55e-01

Pos logit contributions
ives+0.036
ury+0.031
 Enjoy+0.030
 Welcome+0.029
 Cop+0.028
Neg logit contributions
flower-0.044
ble-0.042
cking-0.040
els-0.039
ric-0.039
Token inside
Token ID2641
Feature activation-9.41e-01

Pos logit contributions
ives+0.018
ury+0.016
 Enjoy+0.016
 Welcome+0.015
 Follow+0.015
Neg logit contributions
flower-0.028
ble-0.025
ric-0.025
els-0.024
cking-0.024
Token,
Token ID11
Feature activation-2.70e-01

Pos logit contributions
ives+0.034
ury+0.030
 Enjoy+0.029
 Welcome+0.029
 Happy+0.028
Neg logit contributions
flower-0.044
ble-0.040
ric-0.039
cking-0.039
els-0.038
Token but
Token ID475
Feature activation+2.00e-01

Pos logit contributions
ives+0.009
ury+0.008
 Enjoy+0.008
 Welcome+0.007
 Follow+0.007
Neg logit contributions
flower-0.013
ble-0.012
ric-0.012
cking-0.012
els-0.012
Token they
Token ID484
Feature activation-6.55e-01

Pos logit contributions
flower+0.008
ble+0.007
cking+0.007
els+0.007
ric+0.007
Neg logit contributions
ives-0.009
ury-0.008
 Enjoy-0.008
 Welcome-0.007
 Follow-0.007
Token didn
Token ID1422
Feature activation+5.61e-01

Pos logit contributions
ives+0.018
ury+0.015
 Enjoy+0.015
 Welcome+0.014
 Follow+0.014
Neg logit contributions
flower-0.036
ble-0.033
ric-0.033
cking-0.033
els-0.032
Token't
Token ID470
Feature activation-1.35e-01

Pos logit contributions
flower+0.041
cking+0.037
ric+0.037
els+0.037
eled+0.036
Neg logit contributions
ives-0.006
 Max-0.004
 Welcome-0.004
ury-0.004
 Enjoy-0.004
Token mind
Token ID2000
Feature activation-3.64e-01

Pos logit contributions
ives+0.004
ury+0.003
 Enjoy+0.003
 Welcome+0.003
 Happy+0.003
Neg logit contributions
flower-0.008
ble-0.007
ric-0.007
cking-0.007
els-0.007
Token.
Token ID13
Feature activation-2.52e-01

Pos logit contributions
 Max+0.010
ives+0.008
ury+0.008
 Happy+0.008
 Welcome+0.008
Neg logit contributions
flower-0.020
ble-0.017
eled-0.017
cking-0.017
cker-0.017
Token
Token ID198
Feature activation+5.90e-01

Pos logit contributions
ives+0.001
ury+0.001
 Enjoy+0.001
 Welcome+0.001
 Follow+0.001
Neg logit contributions
flower-0.003
ble-0.002
ric-0.002
els-0.002
cking-0.002
Token
Token ID198
Feature activation+6.41e-01

Pos logit contributions
flower+0.031
ble+0.030
ric+0.029
els+0.029
cking+0.028
Neg logit contributions
ives-0.016
ury-0.014
 Enjoy-0.013
 Welcome-0.013
 Follow-0.013
TokenThey
Token ID2990
Feature activation+1.16e+00

Pos logit contributions
flower+0.030
ric+0.027
cking+0.026
els+0.026
ries+0.025
Neg logit contributions
ives-0.024
ury-0.022
 Enjoy-0.021
 Now-0.020
 Follow-0.020
Token looked
Token ID3114
Feature activation-1.88e-01

Pos logit contributions
flower+0.057
ble+0.051
ric+0.050
cking+0.050
els+0.050
Neg logit contributions
ives-0.040
ury-0.035
 Enjoy-0.034
 Welcome-0.033
 Happy-0.032
Token at
Token ID379
Feature activation+1.07e+00

Pos logit contributions
ives+0.006
ury+0.005
 Enjoy+0.005
 Welcome+0.005
 Happy+0.005
Neg logit contributions
flower-0.010
ble-0.009
ric-0.009
cking-0.009
els-0.009
Token each
Token ID1123
Feature activation-9.65e-01

Pos logit contributions
flower+0.054
ble+0.048
ric+0.047
cking+0.047
mill+0.045
Neg logit contributions
 Max-0.032
ives-0.032
 Enjoy-0.030
 Jack-0.029
 Happy-0.029
Token other
Token ID584
Feature activation-1.06e+00

Pos logit contributions
ives+0.022
ury+0.017
 Enjoy+0.017
 Welcome+0.016
 Happy+0.015
Neg logit contributions
flower-0.059
ble-0.054
ric-0.054
cking-0.053
els-0.053
Token and
Token ID290
Feature activation+4.72e-01

Pos logit contributions
ives+0.037
ury+0.033
 Enjoy+0.031
 Welcome+0.031
 Max+0.030
Neg logit contributions
flower-0.051
ble-0.046
ric-0.046
cking-0.045
els-0.044
Token saw
Token ID2497
Feature activation-2.54e-01

Pos logit contributions
flower+0.021
cking+0.018
ble+0.018
els+0.018
ric+0.017
Neg logit contributions
ives-0.020
 Enjoy-0.017
ury-0.017
 Welcome-0.016
 Follow-0.016
Token their
Token ID511
Feature activation-5.78e-01

Pos logit contributions
ives+0.007
 Max+0.006
 Enjoy+0.006
 Happy+0.005
 People+0.005
Neg logit contributions
flower-0.014
ric-0.013
cking-0.012
ble-0.012
cker-0.012
Token wide
Token ID3094
Feature activation+7.26e-01

Pos logit contributions
ives+0.022
ury+0.020
 Enjoy+0.019
 Welcome+0.019
 Happy+0.018
Neg logit contributions
flower-0.026
ble-0.023
ric-0.023
cking-0.023
els-0.022
Token her
Token ID607
Feature activation+1.71e-01

Pos logit contributions
 Max+0.020
 Happy+0.018
ives+0.017
 Jack+0.017
ury+0.016
Neg logit contributions
flower-0.030
ric-0.028
cking-0.026
ble-0.025
cker-0.024
Token eyes
Token ID2951
Feature activation-2.27e-01

Pos logit contributions
flower+0.008
ble+0.007
cking+0.007
ric+0.007
els+0.006
Neg logit contributions
ives-0.007
ury-0.006
 Enjoy-0.006
 Welcome-0.006
 Max-0.006
Token.
Token ID13
Feature activation-6.46e-01

Pos logit contributions
 Enjoy+0.010
ives+0.010
 Welcome+0.010
ury+0.010
 Cop+0.010
Neg logit contributions
flower-0.008
ble-0.007
els-0.007
cking-0.006
bery-0.006
Token She
Token ID1375
Feature activation+6.30e-02

Pos logit contributions
ives+0.021
ury+0.018
 Enjoy+0.017
 Welcome+0.016
 Follow+0.016
Neg logit contributions
flower-0.030
ble-0.029
els-0.028
ric-0.028
cks-0.026
Token heard
Token ID2982
Feature activation-2.04e+00

Pos logit contributions
flower+0.003
ble+0.003
els+0.002
ric+0.002
cking+0.002
Neg logit contributions
ives-0.002
 Enjoy-0.002
 Welcome-0.002
ury-0.002
 These-0.002
Token a
Token ID257
Feature activation-1.21e+00

Pos logit contributions
ives+0.076
ury+0.067
 Enjoy+0.066
 Welcome+0.064
 Follow+0.063
Neg logit contributions
flower-0.094
ble-0.085
ric-0.083
els-0.082
cking-0.082
Token crash
Token ID7014
Feature activation+9.10e-01

Pos logit contributions
ives+0.040
ury+0.036
 Enjoy+0.034
 Welcome+0.034
 Happy+0.033
Neg logit contributions
flower-0.060
ble-0.053
els-0.053
ric-0.053
cking-0.052
Token.
Token ID13
Feature activation-8.29e-01

Pos logit contributions
flower+0.047
ric+0.044
cking+0.042
ble+0.041
eled+0.041
Neg logit contributions
ives-0.028
 Max-0.024
ury-0.024
 Welcome-0.022
 Happy-0.022
Token She
Token ID1375
Feature activation-5.81e-02

Pos logit contributions
ives+0.026
ury+0.022
 Enjoy+0.022
 Follow+0.021
 Welcome+0.020
Neg logit contributions
flower-0.038
ble-0.037
els-0.035
ric-0.035
cks-0.033
Token felt
Token ID2936
Feature activation-2.73e-01

Pos logit contributions
ives+0.002
 Enjoy+0.002
ury+0.002
 Welcome+0.002
 Happy+0.002
Neg logit contributions
flower-0.003
ble-0.002
els-0.002
cking-0.002
ric-0.002
Token a
Token ID257
Feature activation-9.07e-01

Pos logit contributions
ives+0.008
 Max+0.007
 hide+0.007
 Enjoy+0.007
 People+0.006
Neg logit contributions
flower-0.015
ric-0.013
els-0.013
mill-0.013
cking-0.013
Token down
Token ID866
Feature activation+9.25e-01

Pos logit contributions
flower+0.005
ric+0.005
cking+0.005
els+0.005
ble+0.005
Neg logit contributions
ives-0.002
 Happy-0.002
 Welcome-0.002
 Enjoy-0.002
 Max-0.002
Token the
Token ID262
Feature activation-3.78e-01

Pos logit contributions
flower+0.044
cking+0.039
ble+0.039
ric+0.039
els+0.038
Neg logit contributions
ives-0.032
 Happy-0.030
 Enjoy-0.030
 Max-0.030
 Welcome-0.029
Token street
Token ID4675
Feature activation+3.49e-01

Pos logit contributions
ives+0.011
ury+0.010
 Enjoy+0.009
 Welcome+0.009
 Happy+0.009
Neg logit contributions
flower-0.020
ble-0.019
ric-0.018
els-0.018
cking-0.018
Token.
Token ID13
Feature activation-1.72e-01

Pos logit contributions
flower+0.016
ble+0.014
ric+0.014
cking+0.013
els+0.013
Neg logit contributions
ives-0.014
ury-0.012
 Enjoy-0.012
 Welcome-0.011
 Follow-0.011
Token He
Token ID679
Feature activation+2.99e-01

Pos logit contributions
ives+0.005
ury+0.004
 Enjoy+0.003
 Welcome+0.003
 Follow+0.003
Neg logit contributions
flower-0.010
ble-0.009
ric-0.009
els-0.009
cking-0.009
Token saw
Token ID2497
Feature activation-9.05e-01

Pos logit contributions
flower+0.015
ble+0.013
ric+0.013
cking+0.013
els+0.013
Neg logit contributions
ives-0.011
 Enjoy-0.009
ury-0.009
 Welcome-0.008
 Follow-0.008
Token a
Token ID257
Feature activation-6.89e-01

Pos logit contributions
ives+0.032
ury+0.028
 Enjoy+0.028
 Welcome+0.027
 Happy+0.026
Neg logit contributions
flower-0.043
ble-0.039
ric-0.038
cking-0.038
els-0.038
Token flag
Token ID6056
Feature activation-1.07e+00

Pos logit contributions
ives+0.024
ury+0.021
 Enjoy+0.021
 Welcome+0.020
 Follow+0.020
Neg logit contributions
flower-0.033
ble-0.030
ric-0.029
cking-0.029
els-0.029
Token that
Token ID326
Feature activation-8.86e-01

Pos logit contributions
 Max+0.023
 Welcome+0.022
 hide+0.021
ives+0.021
ury+0.020
Neg logit contributions
flower-0.053
ric-0.053
cking-0.053
els-0.053
eled-0.052
Token was
Token ID373
Feature activation+4.07e-01

Pos logit contributions
ives+0.036
 Enjoy+0.031
ury+0.031
 Follow+0.029
 Welcome+0.028
Neg logit contributions
flower-0.040
ble-0.036
ric-0.034
els-0.034
cking-0.033
Token waving
Token ID25849
Feature activation-5.94e-01

Pos logit contributions
flower+0.022
ric+0.020
els+0.020
bery+0.019
ries+0.019
Neg logit contributions
 hide-0.009
 Max-0.008
 long-0.008
 Welcome-0.008
 to-0.008
Token got
Token ID1392
Feature activation+8.64e-01

Pos logit contributions
flower+0.015
ble+0.013
cking+0.013
ric+0.013
els+0.013
Neg logit contributions
ives-0.010
ury-0.008
 Enjoy-0.008
 Welcome-0.007
 Follow-0.007
Token scared
Token ID12008
Feature activation+1.27e+00

Pos logit contributions
flower+0.040
ble+0.036
cking+0.036
els+0.035
ric+0.035
Neg logit contributions
ives-0.032
ury-0.029
 Enjoy-0.027
 Welcome-0.026
 Follow-0.026
Token.
Token ID13
Feature activation+2.07e-03

Pos logit contributions
flower+0.055
ble+0.049
ric+0.048
cking+0.048
els+0.047
Neg logit contributions
ives-0.051
ury-0.046
 Enjoy-0.045
 Welcome-0.043
 Follow-0.042
Token She
Token ID1375
Feature activation+4.87e-01

Pos logit contributions
flower+0.000
ble+0.000
ries+0.000
ric+0.000
els+0.000
Neg logit contributions
ives-0.000
 Enjoy-0.000
ury-0.000
 villains-0.000
ival-0.000
Token ran
Token ID4966
Feature activation-7.38e-01

Pos logit contributions
flower+0.021
ble+0.019
ric+0.018
els+0.018
cking+0.018
Neg logit contributions
ives-0.020
 Enjoy-0.018
ury-0.017
 Welcome-0.016
 These-0.016
Token away
Token ID1497
Feature activation-1.10e+00

Pos logit contributions
ives+0.025
ury+0.022
 Enjoy+0.021
 People+0.021
 Welcome+0.021
Neg logit contributions
flower-0.034
ble-0.030
cking-0.029
mill-0.029
els-0.029
Token,
Token ID11
Feature activation-5.53e-01

Pos logit contributions
ives+0.035
ury+0.031
 Enjoy+0.030
 Welcome+0.029
 Happy+0.028
Neg logit contributions
flower-0.056
ric-0.051
ble-0.051
els-0.050
cking-0.050
Token leaving
Token ID4305
Feature activation-9.89e-02

Pos logit contributions
ives+0.021
 Enjoy+0.018
ury+0.018
 People+0.017
 Follow+0.017
Neg logit contributions
flower-0.026
cking-0.023
ric-0.023
ble-0.023
cks-0.021
Token her
Token ID607
Feature activation+3.99e-02

Pos logit contributions
ives+0.005
ury+0.004
 Follow+0.004
 Enjoy+0.004
 Welcome+0.004
Neg logit contributions
flower-0.003
els-0.003
ble-0.003
ries-0.003
ric-0.003
Token toys
Token ID14958
Feature activation+9.47e-02

Pos logit contributions
flower+0.002
ble+0.002
ric+0.002
cking+0.002
els+0.002
Neg logit contributions
ives-0.001
ury-0.001
 Enjoy-0.001
 Welcome-0.001
 Max-0.001
Token behind
Token ID2157
Feature activation-2.86e-01

Pos logit contributions
flower+0.005
ble+0.004
cking+0.004
ric+0.004
els+0.004
Neg logit contributions
ives-0.003
ury-0.003
 Enjoy-0.003
 Welcome-0.003
 Happy-0.003
Token day
Token ID1110
Feature activation-7.09e-01

Pos logit contributions
flower+0.021
ble+0.019
ric+0.019
cking+0.019
els+0.019
Neg logit contributions
ives-0.011
ury-0.009
 Enjoy-0.009
 Welcome-0.008
 Happy-0.008
Token,
Token ID11
Feature activation-7.28e-01

Pos logit contributions
ives+0.021
ury+0.018
 Enjoy+0.017
 Welcome+0.017
 Happy+0.016
Neg logit contributions
flower-0.038
ble-0.035
ric-0.035
cking-0.035
els-0.034
Token she
Token ID673
Feature activation-3.94e-01

Pos logit contributions
ives+0.019
ury+0.017
 Enjoy+0.017
 Max+0.016
 Happy+0.016
Neg logit contributions
flower-0.040
ric-0.037
ble-0.037
cking-0.037
els-0.036
Token found
Token ID1043
Feature activation-9.90e-01

Pos logit contributions
ives+0.014
 Enjoy+0.012
ury+0.012
 Welcome+0.011
 Happy+0.011
Neg logit contributions
flower-0.019
ble-0.017
els-0.017
ric-0.016
cking-0.016
Token a
Token ID257
Feature activation-5.85e-01

Pos logit contributions
ives+0.034
ury+0.030
 Enjoy+0.029
 Welcome+0.028
 Max+0.028
Neg logit contributions
flower-0.048
ric-0.043
ble-0.043
cking-0.043
els-0.042
Token card
Token ID2657
Feature activation-8.80e-01

Pos logit contributions
ives+0.022
ury+0.019
 Enjoy+0.019
 Follow+0.018
 Welcome+0.018
Neg logit contributions
flower-0.027
ble-0.024
ric-0.024
cking-0.023
els-0.023
Token with
Token ID351
Feature activation-8.48e-01

Pos logit contributions
ives+0.023
ury+0.019
 Max+0.018
 Welcome+0.018
 Enjoy+0.018
Neg logit contributions
flower-0.048
ric-0.048
cking-0.047
els-0.045
eled-0.045
Token a
Token ID257
Feature activation-2.84e-01

Pos logit contributions
ives+0.032
ury+0.029
 Enjoy+0.028
 Welcome+0.027
 Follow+0.027
Neg logit contributions
flower-0.038
ble-0.034
els-0.034
ric-0.034
cking-0.034
Token yellow
Token ID7872
Feature activation+3.18e-01

Pos logit contributions
ives+0.011
ury+0.010
 Enjoy+0.010
 Welcome+0.009
 Follow+0.009
Neg logit contributions
flower-0.012
ble-0.011
ric-0.011
cking-0.011
els-0.011
Token fruit
Token ID8234
Feature activation+7.50e-01

Pos logit contributions
cking+0.015
flower+0.014
ric+0.014
ble+0.014
cks+0.013
Neg logit contributions
ives-0.011
 Enjoy-0.010
ury-0.009
 Thank-0.009
 Welcome-0.009
Token.
Token ID13
Feature activation-3.35e-01

Pos logit contributions
flower+0.036
ric+0.034
cking+0.033
ble+0.033
els+0.031
Neg logit contributions
ives-0.026
ury-0.022
 Enjoy-0.021
 Welcome-0.021
 Max-0.020
Token she
Token ID673
Feature activation-3.82e-01

Pos logit contributions
ives+0.005
ury+0.004
 Enjoy+0.004
 Welcome+0.004
 Happy+0.004
Neg logit contributions
flower-0.006
ble-0.005
ric-0.005
cking-0.005
els-0.005
Token saw
Token ID2497
Feature activation-8.71e-01

Pos logit contributions
ives+0.013
ury+0.012
 Enjoy+0.012
 Welcome+0.011
 Happy+0.011
Neg logit contributions
flower-0.019
ble-0.017
ric-0.016
els-0.016
cking-0.016
Token another
Token ID1194
Feature activation-2.03e-01

Pos logit contributions
ives+0.033
ury+0.030
 Enjoy+0.029
 Welcome+0.028
 Happy+0.028
Neg logit contributions
flower-0.039
ble-0.035
ric-0.034
cking-0.034
els-0.034
Token rh
Token ID9529
Feature activation-1.84e+00

Pos logit contributions
ives+0.007
ury+0.006
 Welcome+0.006
 Enjoy+0.006
 Max+0.006
Neg logit contributions
flower-0.009
ble-0.009
els-0.009
cking-0.009
ric-0.009
Tokenin
Token ID259
Feature activation-9.67e-01

Pos logit contributions
ives+0.100
ury+0.092
 Enjoy+0.091
 Welcome+0.090
 Happy+0.088
Neg logit contributions
flower-0.054
ble-0.045
ric-0.043
cking-0.043
els-0.043
Tokenoc
Token ID420
Feature activation-4.15e+00

Pos logit contributions
ives+0.026
ury+0.023
 Enjoy+0.022
 Welcome+0.021
 Follow+0.020
Neg logit contributions
flower-0.053
ble-0.049
ric-0.048
els-0.048
cking-0.048
Tokeneros
Token ID27498
Feature activation-7.67e-01

Pos logit contributions
ives+0.213
ury+0.199
 Welcome+0.195
 Enjoy+0.192
 Happy+0.190
Neg logit contributions
flower-0.135
els-0.115
ble-0.115
ric-0.109
cking-0.106
Token coming
Token ID2406
Feature activation+4.06e-01

Pos logit contributions
ives+0.028
ury+0.025
 Welcome+0.024
 Enjoy+0.024
 Max+0.023
Neg logit contributions
flower-0.035
ble-0.032
ric-0.032
els-0.031
cking-0.031
Token towards
Token ID3371
Feature activation+7.56e-01

Pos logit contributions
flower+0.020
ric+0.019
els+0.018
cking+0.018
ble+0.018
Neg logit contributions
ives-0.012
 Welcome-0.011
ury-0.011
 Max-0.011
 Enjoy-0.011
Token her
Token ID607
Feature activation+4.80e-01

Pos logit contributions
flower+0.029
ble+0.026
ric+0.025
cking+0.025
els+0.025
Neg logit contributions
ives-0.033
ury-0.030
 Enjoy-0.030
 Welcome-0.029
 Happy-0.029
Token.
Token ID13
Feature activation+1.86e-01

Pos logit contributions
flower+0.022
ble+0.020
cking+0.020
els+0.019
ric+0.019
Neg logit contributions
ives-0.018
ury-0.016
 Enjoy-0.015
 Welcome-0.015
 Max-0.014
Token fun
Token ID1257
Feature activation-1.61e+00

Pos logit contributions
ives+0.023
ury+0.020
 Follow+0.018
 Enjoy+0.018
 Welcome+0.018
Neg logit contributions
flower-0.025
ble-0.024
cking-0.023
ric-0.023
cks-0.022
Token in
Token ID287
Feature activation-6.03e-01

Pos logit contributions
ives+0.064
ury+0.057
 Enjoy+0.055
 Welcome+0.054
 Sadly+0.053
Neg logit contributions
flower-0.069
ble-0.063
cking-0.062
els-0.060
ric-0.059
Token the
Token ID262
Feature activation-6.07e-01

Pos logit contributions
ives+0.024
ury+0.022
 Enjoy+0.022
 Welcome+0.021
 Happy+0.021
Neg logit contributions
flower-0.026
ble-0.023
ric-0.022
els-0.022
cking-0.022
Token sky
Token ID6766
Feature activation-3.64e-01

Pos logit contributions
ives+0.023
ury+0.021
 Enjoy+0.020
 Welcome+0.019
 Happy+0.019
Neg logit contributions
flower-0.028
ble-0.025
ric-0.025
cking-0.024
els-0.024
Token.
Token ID13
Feature activation-4.82e-01

Pos logit contributions
ives+0.013
ury+0.012
 Enjoy+0.011
 Welcome+0.011
 Happy+0.011
Neg logit contributions
flower-0.017
ble-0.015
ric-0.015
cking-0.015
els-0.015
Token Enjoy
Token ID18179
Feature activation-3.32e+00

Pos logit contributions
ives+0.014
boards+0.012
and+0.011
ival+0.011
ury+0.011
Neg logit contributions
flower-0.025
ric-0.023
ble-0.020
esh-0.020
cks-0.020
Token the
Token ID262
Feature activation-1.50e+00

Pos logit contributions
ives+0.109
 Enjoy+0.097
ury+0.096
 Happy+0.091
 Welcome+0.090
Neg logit contributions
flower-0.166
ble-0.147
ric-0.146
cking-0.144
els-0.143
Token season
Token ID1622
Feature activation-5.73e-01

Pos logit contributions
ives+0.063
ury+0.057
 Enjoy+0.056
 Welcome+0.054
 Follow+0.053
Neg logit contributions
flower-0.063
ble-0.055
ric-0.054
cking-0.053
els-0.053
Token,"
Token ID553
Feature activation-4.23e-01

Pos logit contributions
ives+0.022
ury+0.020
 Enjoy+0.020
 Welcome+0.019
 Follow+0.018
Neg logit contributions
flower-0.026
ble-0.023
ric-0.022
els-0.022
cking-0.022
Token Tom
Token ID4186
Feature activation+8.15e-01

Pos logit contributions
ives+0.013
ury+0.011
 Enjoy+0.011
 Welcome+0.010
 Follow+0.010
Neg logit contributions
flower-0.022
ble-0.020
els-0.020
ric-0.020
cking-0.020
Token says
Token ID1139
Feature activation+1.11e+00

Pos logit contributions
flower+0.044
ble+0.040
els+0.039
ric+0.039
cking+0.039
Neg logit contributions
ives-0.023
ury-0.021
 Enjoy-0.020
 Welcome-0.019
 Happy-0.018
Token He
Token ID679
Feature activation+4.10e-01

Pos logit contributions
flower+0.022
ble+0.020
ric+0.019
els+0.019
eled+0.018
Neg logit contributions
ives-0.014
ury-0.012
 Enjoy-0.011
 Bye-0.010
and-0.010
Token saw
Token ID2497
Feature activation-1.12e+00

Pos logit contributions
flower+0.019
ble+0.017
eled+0.016
ric+0.016
els+0.016
Neg logit contributions
ives-0.016
ury-0.013
 Enjoy-0.013
 Welcome-0.013
 People-0.012
Token some
Token ID617
Feature activation-4.09e-01

Pos logit contributions
ives+0.046
ury+0.042
 Welcome+0.040
 Enjoy+0.039
 Follow+0.039
Neg logit contributions
flower-0.045
ble-0.042
els-0.040
cking-0.040
ric-0.039
Token lovely
Token ID14081
Feature activation-2.49e-01

Pos logit contributions
ives+0.014
ury+0.013
 Enjoy+0.012
 Welcome+0.012
 Follow+0.012
Neg logit contributions
flower-0.019
ble-0.017
els-0.017
cking-0.017
ric-0.017
Token sa
Token ID473
Feature activation-1.93e+00

Pos logit contributions
ives+0.008
ury+0.007
 Enjoy+0.007
 Happy+0.007
 Welcome+0.007
Neg logit contributions
flower-0.012
ble-0.011
ric-0.011
cking-0.011
cks-0.011
Tokenus
Token ID385
Feature activation-3.53e+00

Pos logit contributions
ives+0.068
ury+0.061
 Welcome+0.061
 Enjoy+0.059
 Follow+0.058
Neg logit contributions
flower-0.093
ble-0.085
ric-0.081
els-0.081
cking-0.080
Tokenages
Token ID1095
Feature activation-3.35e-01

Pos logit contributions
ives+0.112
 Enjoy+0.103
 Welcome+0.101
 Follow+0.098
ury+0.098
Neg logit contributions
flower-0.172
ble-0.161
cking-0.156
ric-0.156
els-0.153
Token on
Token ID319
Feature activation+6.03e-01

Pos logit contributions
ives+0.011
ury+0.009
 Enjoy+0.009
 Welcome+0.009
 Happy+0.009
Neg logit contributions
flower-0.017
ble-0.015
ric-0.015
cking-0.015
els-0.015
Token the
Token ID262
Feature activation-4.24e-01

Pos logit contributions
flower+0.028
ble+0.025
ric+0.025
cking+0.025
els+0.024
Neg logit contributions
ives-0.021
 Max-0.020
 Enjoy-0.020
 Happy-0.019
ury-0.019
Token shelf
Token ID18316
Feature activation+7.55e-01

Pos logit contributions
ives+0.016
ury+0.014
 Enjoy+0.014
 Follow+0.013
 Welcome+0.013
Neg logit contributions
flower-0.019
ble-0.017
ric-0.017
els-0.016
cking-0.016
Token,
Token ID11
Feature activation+4.25e-01

Pos logit contributions
flower+0.035
ble+0.031
els+0.030
ric+0.030
cking+0.029
Neg logit contributions
ives-0.028
 Enjoy-0.025
ury-0.025
 Welcome-0.024
 Follow-0.023
Token a
Token ID257
Feature activation-5.71e-01

Pos logit contributions
ives+0.015
 Enjoy+0.013
ury+0.013
 Welcome+0.012
 Happy+0.012
Neg logit contributions
flower-0.027
ble-0.024
els-0.024
ric-0.024
cking-0.024
Token very
Token ID845
Feature activation-7.49e-01

Pos logit contributions
ives+0.016
ury+0.014
 Enjoy+0.013
 Welcome+0.013
 Follow+0.012
Neg logit contributions
flower-0.032
ble-0.029
ric-0.028
cking-0.028
els-0.028
Token clever
Token ID14169
Feature activation-8.95e-01

Pos logit contributions
ives+0.033
boards+0.026
 Sadly+0.025
and+0.025
 Did+0.024
Neg logit contributions
ble-0.028
flower-0.027
cking-0.025
cker-0.024
cks-0.024
Token rh
Token ID9529
Feature activation-1.55e+00

Pos logit contributions
ives+0.033
ury+0.029
 Enjoy+0.028
 Welcome+0.027
 Follow+0.027
Neg logit contributions
flower-0.042
ble-0.037
els-0.035
ric-0.035
mill-0.035
Tokenin
Token ID259
Feature activation-7.19e-01

Pos logit contributions
ives+0.092
ury+0.086
 Sadly+0.086
 Enjoy+0.085
 Welcome+0.085
Neg logit contributions
flower-0.037
ble-0.031
cking-0.027
els-0.027
mill-0.026
Tokenoc
Token ID420
Feature activation-4.00e+00

Pos logit contributions
ives+0.026
ury+0.022
 Enjoy+0.022
 Sadly+0.022
 Welcome+0.021
Neg logit contributions
flower-0.034
ble-0.030
mill-0.028
ric-0.028
cker-0.027
Tokeneros
Token ID27498
Feature activation-7.74e-01

Pos logit contributions
ives+0.216
 Welcome+0.207
 Sadly+0.206
ury+0.203
 Enjoy+0.199
Neg logit contributions
flower-0.112
ble-0.097
els-0.094
mill-0.087
ries-0.086
Token."
Token ID526
Feature activation-4.57e-01

Pos logit contributions
ives+0.031
ury+0.027
 Enjoy+0.027
 Sadly+0.026
 Welcome+0.026
Neg logit contributions
flower-0.033
ble-0.029
ric-0.027
els-0.027
cking-0.027
Token<|endoftext|>
Token ID50256
Feature activation+5.86e-02

Pos logit contributions
ives+0.013
ury+0.011
 Enjoy+0.010
 Welcome+0.010
 Follow+0.010
Neg logit contributions
flower-0.024
ric-0.022
ble-0.021
mill-0.020
els-0.020
TokenOnce
Token ID7454
Feature activation+9.86e-01

Pos logit contributions
flower+0.003
ble+0.002
ric+0.002
els+0.002
cks+0.002
Neg logit contributions
ives-0.002
ury-0.002
 Enjoy-0.002
 Follow-0.002
 Welcome-0.002
Token upon
Token ID2402
Feature activation-3.73e-01

Pos logit contributions
flower+0.040
cking+0.035
ble+0.035
ric+0.034
els+0.034
Neg logit contributions
ives-0.040
 Max-0.037
ury-0.037
 Welcome-0.036
 Enjoy-0.036
Token the
Token ID262
Feature activation-1.22e-01

Pos logit contributions
flower+0.018
ble+0.017
cking+0.016
ric+0.016
els+0.015
Neg logit contributions
ives-0.013
 Happy-0.013
 Welcome-0.012
 Enjoy-0.012
 Max-0.012
Token tree
Token ID5509
Feature activation+1.18e-01

Pos logit contributions
ives+0.004
ury+0.004
 Enjoy+0.004
 Welcome+0.004
 Happy+0.003
Neg logit contributions
flower-0.006
ble-0.005
ric-0.005
cking-0.005
els-0.005
Token.
Token ID13
Feature activation+3.78e-01

Pos logit contributions
flower+0.005
ble+0.005
ric+0.005
els+0.005
cking+0.005
Neg logit contributions
ives-0.004
ury-0.004
 Enjoy-0.004
 Welcome-0.004
 Happy-0.004
Token Both
Token ID5747
Feature activation+1.14e+00

Pos logit contributions
flower+0.020
ric+0.018
ble+0.018
els+0.017
mill+0.017
Neg logit contributions
ives-0.011
ury-0.009
 Enjoy-0.008
 villains-0.008
 hide-0.008
Token b
Token ID275
Feature activation-1.66e+00

Pos logit contributions
flower+0.059
els+0.053
ble+0.053
ric+0.052
cking+0.052
Neg logit contributions
ives-0.035
ury-0.030
 Enjoy-0.030
 Follow-0.028
 Welcome-0.028
Tokenunn
Token ID20935
Feature activation-4.05e+00

Pos logit contributions
ives+0.035
 Max+0.032
ury+0.032
 Welcome+0.032
 Cop+0.032
Neg logit contributions
flower-0.097
els-0.089
ric-0.088
ble-0.088
cking-0.088
Tokenies
Token ID444
Feature activation-3.79e-01

Pos logit contributions
ives+0.264
ury+0.247
 Enjoy+0.244
 Welcome+0.240
 Happy+0.237
Neg logit contributions
flower-0.072
ble-0.054
ric-0.051
cking-0.049
els-0.048
Token agreed
Token ID4987
Feature activation-2.75e-01

Pos logit contributions
ives+0.011
ury+0.009
 Enjoy+0.009
 Welcome+0.009
 Happy+0.008
Neg logit contributions
flower-0.020
ble-0.019
ric-0.019
els-0.018
cking-0.018
Token that
Token ID326
Feature activation-3.45e-01

Pos logit contributions
ives+0.007
ury+0.006
 Enjoy+0.006
 Welcome+0.006
 Happy+0.006
Neg logit contributions
flower-0.015
ble-0.014
ric-0.014
els-0.014
cking-0.014
Token it
Token ID340
Feature activation-4.01e-01

Pos logit contributions
ives+0.014
ury+0.012
 Enjoy+0.012
 Follow+0.011
 Welcome+0.011
Neg logit contributions
flower-0.015
ble-0.013
els-0.013
ric-0.013
cking-0.013
Token had
Token ID550
Feature activation+3.58e-01

Pos logit contributions
ives+0.014
ury+0.012
 Enjoy+0.012
 Welcome+0.011
 Happy+0.011
Neg logit contributions
flower-0.019
ble-0.017
ric-0.017
els-0.017
cking-0.017