TOP ACTIVATIONS
MAX = 4.970

. He drops the ash tr ay . It breaks .
hit her mom 's ash tr ay . The ash tr
looked at the empty ash tr ay on Sara 's head
carefully picked up the ash tr ay and put it in
she could have the ash tr ay to put her rocks
cleaned up the broken ash tr ay and Lily learned to
accidentally knocked over the ash tr ay and it broke into
and fell . The ash tr ay flew out of her
show her an expensive ash tr ay he got as a
and saw the broken ash tr ay . She was upset
on top of the ash tr ay . The
around town on his ash tr ay , z ipping everywhere
it came across an ash tr ay . It wanted to
Lily accidentally dropped the ash tr ay and it broke into
putting it in the ash tr ay . Lily didn 't
and accidentally dropped her ash tr ay on the ground .
so hard on the ash tr ay , and now it
notice how slippery the ash tr ay was . In no
and spotted a wide ash tr ay on the table .
, it caused the ash tr ay to scatter all over

MIN ACTIVATIONS
MIN = -2.626

they do it . He imag ines he is one of
, because you have wonderful imag inations ." The boy and
of the animals in the me adow stopped and watched .
a great time using their imag inations . <|endoftext|> Once upon
new world . Using their imag inations , they played with
. She lived in a me adow near a tall mountain
He lived in a sunny me adow near a large bucket
he could be and never mis beh aved . <|endoftext|> Once
. They had used their imag inations and their net to
of oranges in the whole me adow ! <|endoftext|> Bob was
bright blue berry in a me adow . One day ,
a rabbit lived in a me adow . They were good
warm , and the shore line was ancient .
rabbit that lived in a me adow . One day while
. Daisy lived in the me adow and she loved to
of a hill in a me adow . One day
da isy living in a me adow . She was waving
, if they used their imag inations . So the children
see her flower . She imag ines it will be red
many wonderful things in the me adow . The animals let

INTERVAL 3.071 - 4.970
CONTAINS 0.000%

hit her mom 's ash tr ay . The ash tr
. He drops the ash tr ay . It breaks .
carefully picked up the ash tr ay and put it in
looked at the empty ash tr ay on Sara 's head
she could have the ash tr ay to put her rocks

INTERVAL 1.172 - 3.071
CONTAINS 0.104%

the most interesting thing she had ever seen . <|endoftext|> Once
and played together with the shiny mineral . And from that
," their mom said . " I 'm glad you liked
the bird found something it had never seen before - poison
it look like a real spaceship . One day

INTERVAL -0.727 - 1.172
CONTAINS 97.004%

Every night Lily would dream about luxury . She dreamed of
She sat down next to Lily and hugged her .
<|endoftext|> Once upon a time there was a puppy . He
crazy . Then one day , the infant started
talked about their adventures . And the harbor was always happy

INTERVAL -2.626 - -0.727
CONTAINS 2.892%

patch to find the perfect pumpkin . L ily
up . It became the biggest balloon she had ever seen
. He had a big , yellow tractor
!" Tom and Lily felt sad . They did
. He thought about it for a long time .
Token.
Token ID13
Feature activation-2.06e-01

Pos logit contributions
 polar+0.019
 tow+0.018
 ranger+0.018
 gn+0.017
 chimpan+0.017
Neg logit contributions
ivated-0.022
 tant-0.021
our-0.021
 hey-0.021
arre-0.021
Token He
Token ID679
Feature activation-1.94e-01

Pos logit contributions
ivated+0.004
 Def+0.004
icker+0.004
our+0.004
 hey+0.004
Neg logit contributions
 polar-0.006
 ranger-0.005
 tow-0.005
 gn-0.005
 chimpan-0.005
Token drops
Token ID10532
Feature activation+3.74e-01

Pos logit contributions
 tant+0.004
ivated+0.004
our+0.004
 hey+0.004
arre+0.004
Neg logit contributions
 polar-0.005
 tow-0.005
 ranger-0.005
 chimpan-0.005
 gn-0.005
Token the
Token ID262
Feature activation+1.10e-02

Pos logit contributions
 polar+0.010
 gn+0.010
 ranger+0.009
 chimpan+0.009
 trove+0.009
Neg logit contributions
 tant-0.009
 Blood-0.008
ivated-0.008
bs-0.008
 Ow-0.008
Token ash
Token ID12530
Feature activation+1.06e-01

Pos logit contributions
 polar+0.000
 ranger+0.000
 chimpan+0.000
 tow+0.000
 gn+0.000
Neg logit contributions
 tant-0.000
nam-0.000
icker-0.000
ivated-0.000
obb-0.000
Tokentr
Token ID2213
Feature activation+3.59e+00

Pos logit contributions
 polar+0.003
 tow+0.002
 ranger+0.002
 chimpan+0.002
 gn+0.002
Neg logit contributions
our-0.003
 tant-0.003
icker-0.002
ivated-0.002
obb-0.002
Tokenay
Token ID323
Feature activation+7.80e-01

Pos logit contributions
 polar+0.058
 tow+0.053
 ranger+0.050
 gn+0.045
!+0.043
Neg logit contributions
ivated-0.121
nam-0.115
gging-0.111
 Def-0.111
 hey-0.111
Token.
Token ID13
Feature activation-1.53e-01

Pos logit contributions
 polar+0.015
 ranger+0.014
 gn+0.013
 tow+0.013
 chimpan+0.013
Neg logit contributions
ivated-0.023
our-0.023
icker-0.023
 tant-0.022
 hey-0.022
Token It
Token ID632
Feature activation+2.51e-02

Pos logit contributions
ivated+0.004
icker+0.003
our+0.003
nam+0.003
 hey+0.003
Neg logit contributions
 polar-0.004
 ranger-0.004
 tow-0.004
 gn-0.004
 chimpan-0.004
Token breaks
Token ID9457
Feature activation+6.50e-02

Pos logit contributions
 polar+0.001
 ranger+0.001
 tow+0.001
 gn+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.001
 tant-0.001
our-0.001
icker-0.001
 hey-0.001
Token.
Token ID13
Feature activation-2.17e-01

Pos logit contributions
 ranger+0.001
 polar+0.001
 chimpan+0.001
 tow+0.001
 gn+0.001
Neg logit contributions
 Ow-0.002
 Blood-0.002
our-0.002
 tant-0.002
obb-0.002
Token hit
Token ID2277
Feature activation+6.10e-01

Pos logit contributions
 polar+0.000
 ranger+0.000
 chimpan+0.000
 tow+0.000
glers+0.000
Neg logit contributions
 Blood-0.000
bs-0.000
ivated-0.000
 hey-0.000
our-0.000
Token her
Token ID607
Feature activation+5.60e-01

Pos logit contributions
 polar+0.017
 ranger+0.016
 tow+0.015
 gn+0.015
 chimpan+0.015
Neg logit contributions
ivated-0.013
nam-0.013
 tant-0.013
 Def-0.012
 hey-0.012
Token mom
Token ID1995
Feature activation+3.19e-01

Pos logit contributions
 polar+0.016
 tow+0.016
 chimpan+0.016
 ranger+0.015
 gn+0.015
Neg logit contributions
 tant-0.011
our-0.011
ivated-0.010
nam-0.010
icker-0.010
Token's
Token ID338
Feature activation-4.00e-01

Pos logit contributions
 polar+0.009
 chimpan+0.008
 ranger+0.008
 waterfall+0.008
 tow+0.008
Neg logit contributions
our-0.007
ivated-0.007
iable-0.006
nam-0.006
ivery-0.006
Token ash
Token ID12530
Feature activation+4.34e-01

Pos logit contributions
 tant+0.007
nam+0.007
ivated+0.007
our+0.007
icker+0.007
Neg logit contributions
 polar-0.012
 ranger-0.011
 chimpan-0.011
 tow-0.011
 gn-0.011
Tokentr
Token ID2213
Feature activation+3.35e+00

Pos logit contributions
 polar+0.013
 tow+0.012
 chimpan+0.012
 ranger+0.011
 gn+0.011
Neg logit contributions
our-0.009
 tant-0.008
obb-0.008
icker-0.008
ivated-0.008
Tokenay
Token ID323
Feature activation+5.22e-01

Pos logit contributions
 polar+0.064
 ranger+0.058
 tow+0.057
 gn+0.054
 chimpan+0.051
Neg logit contributions
ivated-0.102
nam-0.097
icker-0.096
 hey-0.095
 Def-0.095
Token.
Token ID13
Feature activation-3.27e-01

Pos logit contributions
 polar+0.011
 chimpan+0.010
 tow+0.010
 ranger+0.010
 gn+0.009
Neg logit contributions
our-0.015
ivated-0.015
arre-0.014
 tant-0.014
iable-0.014
Token The
Token ID383
Feature activation+1.15e-01

Pos logit contributions
ivated+0.008
our+0.008
icker+0.008
 hey+0.008
unct+0.007
Neg logit contributions
 ranger-0.008
 polar-0.008
 gn-0.008
 tow-0.008
 chimpan-0.007
Token ash
Token ID12530
Feature activation-2.75e-01

Pos logit contributions
 polar+0.003
 ranger+0.003
 chimpan+0.003
 tow+0.003
 gn+0.003
Neg logit contributions
 tant-0.002
 hey-0.002
nam-0.002
icker-0.002
ivated-0.002
Tokentr
Token ID2213
Feature activation+2.85e+00

Pos logit contributions
ivated+0.006
our+0.006
 tant+0.005
icker+0.005
 hey+0.005
Neg logit contributions
 polar-0.008
 ranger-0.007
 tow-0.007
 gn-0.007
 chimpan-0.007
Token looked
Token ID3114
Feature activation-7.23e-01

Pos logit contributions
 polar+0.001
 ranger+0.001
 gn+0.001
 tow+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.001
our-0.001
icker-0.001
 hey-0.001
 Def-0.001
Token at
Token ID379
Feature activation+1.23e+00

Pos logit contributions
ivated+0.015
icker+0.015
 hey+0.014
 Def+0.014
our+0.014
Neg logit contributions
 polar-0.021
 ranger-0.020
 tow-0.018
 gn-0.018
 chimpan-0.018
Token the
Token ID262
Feature activation-1.48e-01

Pos logit contributions
 polar+0.031
 ranger+0.030
 gn+0.030
 chimpan+0.029
 tow+0.028
Neg logit contributions
ivated-0.028
 hey-0.028
 tant-0.028
icker-0.027
our-0.027
Token empty
Token ID6565
Feature activation+4.70e-01

Pos logit contributions
ivated+0.004
icker+0.003
our+0.003
 Def+0.003
nam+0.003
Neg logit contributions
 polar-0.004
 ranger-0.004
 tow-0.003
 gn-0.003
 chimpan-0.003
Token ash
Token ID12530
Feature activation+2.39e-01

Pos logit contributions
 polar+0.014
 ranger+0.014
 chimpan+0.013
 gn+0.013
 tow+0.013
Neg logit contributions
 tant-0.008
our-0.008
nam-0.008
icker-0.008
 Def-0.008
Tokentr
Token ID2213
Feature activation+3.13e+00

Pos logit contributions
 polar+0.007
 tow+0.007
 chimpan+0.006
 ranger+0.006
 gn+0.006
Neg logit contributions
our-0.005
icker-0.004
 tant-0.004
 hey-0.004
ivated-0.004
Tokenay
Token ID323
Feature activation+2.84e-01

Pos logit contributions
 polar+0.057
 ranger+0.052
 tow+0.052
 gn+0.047
 chimpan+0.045
Neg logit contributions
ivated-0.099
nam-0.094
 Def-0.090
 hey-0.090
icker-0.090
Token on
Token ID319
Feature activation+3.18e-01

Pos logit contributions
 polar+0.006
 gn+0.005
 tow+0.005
 chimpan+0.005
 ranger+0.005
Neg logit contributions
our-0.009
ivated-0.008
icker-0.008
 tant-0.008
 hey-0.008
Token Sara
Token ID24799
Feature activation-6.17e-01

Pos logit contributions
 polar+0.009
 gn+0.009
 ranger+0.009
 chimpan+0.009
glers+0.008
Neg logit contributions
 Ow-0.006
 tant-0.006
 hey-0.005
 Blood-0.005
obb-0.005
Token's
Token ID338
Feature activation+2.55e-01

Pos logit contributions
ivated+0.014
our+0.014
icker+0.013
nam+0.013
 Def+0.013
Neg logit contributions
 polar-0.017
 ranger-0.015
 tow-0.015
 gn-0.015
 chimpan-0.015
Token head
Token ID1182
Feature activation+1.13e-01

Pos logit contributions
 polar+0.007
 ranger+0.007
 tow+0.007
 gn+0.007
 chimpan+0.007
Neg logit contributions
ivated-0.005
our-0.005
icker-0.005
 tant-0.005
nam-0.005
Token carefully
Token ID7773
Feature activation-2.92e-01

Pos logit contributions
 polar+0.007
 ranger+0.007
 tow+0.007
 chimpan+0.007
 waterfall+0.007
Neg logit contributions
our-0.005
ivated-0.005
bs-0.005
int-0.005
cient-0.004
Token picked
Token ID6497
Feature activation+5.28e-01

Pos logit contributions
our+0.006
bs+0.006
ivated+0.006
int+0.005
 Def+0.005
Neg logit contributions
 polar-0.008
 ranger-0.008
 waterfall-0.008
 chimpan-0.007
 tow-0.007
Token up
Token ID510
Feature activation+2.27e-01

Pos logit contributions
 polar+0.015
 ranger+0.015
 tow+0.014
 gn+0.014
 chimpan+0.013
Neg logit contributions
ivated-0.010
 tant-0.010
 Def-0.010
our-0.010
nam-0.010
Token the
Token ID262
Feature activation-1.02e-01

Pos logit contributions
 polar+0.007
 ranger+0.006
 tow+0.006
 gn+0.006
 chimpan+0.006
Neg logit contributions
 tant-0.005
nam-0.005
ivated-0.004
bs-0.004
 however-0.004
Token ash
Token ID12530
Feature activation+2.39e-01

Pos logit contributions
nam+0.002
 tant+0.002
ivated+0.002
our+0.002
 Def+0.002
Neg logit contributions
 polar-0.003
 ranger-0.002
 tow-0.002
 chimpan-0.002
 gn-0.002
Tokentr
Token ID2213
Feature activation+3.11e+00

Pos logit contributions
 polar+0.007
 tow+0.006
 chimpan+0.006
 amusement+0.006
 ranger+0.005
Neg logit contributions
our-0.005
 tant-0.005
 spine-0.005
cient-0.005
icker-0.004
Tokenay
Token ID323
Feature activation+8.24e-01

Pos logit contributions
 polar+0.055
 ranger+0.051
 tow+0.051
 gn+0.046
 chimpan+0.044
Neg logit contributions
ivated-0.099
nam-0.093
 hey-0.092
 Def-0.091
icker-0.091
Token and
Token ID290
Feature activation+1.75e-01

Pos logit contributions
 polar+0.019
 ranger+0.017
 tow+0.017
 chimpan+0.017
 gn+0.017
Neg logit contributions
our-0.022
ivated-0.021
iable-0.021
oney-0.021
bs-0.021
Token put
Token ID1234
Feature activation-9.33e-02

Pos logit contributions
 polar+0.005
 ranger+0.004
 tow+0.004
 chimpan+0.004
 gn+0.004
Neg logit contributions
nam-0.004
ivated-0.004
our-0.004
bs-0.004
 Def-0.004
Token it
Token ID340
Feature activation-3.03e-01

Pos logit contributions
nam+0.002
 tant+0.002
ivated+0.002
 Def+0.002
our+0.002
Neg logit contributions
 polar-0.003
 ranger-0.003
 gn-0.003
 chimpan-0.003
glers-0.003
Token in
Token ID287
Feature activation-8.94e-02

Pos logit contributions
ivated+0.007
nam+0.007
our+0.006
icker+0.006
 tant+0.006
Neg logit contributions
 polar-0.008
 ranger-0.008
 tow-0.008
 chimpan-0.008
 gn-0.007
Token she
Token ID673
Feature activation+2.58e-01

Pos logit contributions
 polar+0.019
 tow+0.017
 chimpan+0.017
 ranger+0.017
 waterfall+0.016
Neg logit contributions
nam-0.007
 hey-0.007
our-0.006
ivated-0.006
 Him-0.006
Token could
Token ID714
Feature activation+3.49e-01

Pos logit contributions
 polar+0.008
 ranger+0.007
 tow+0.007
 chimpan+0.007
 gn+0.007
Neg logit contributions
our-0.005
ivated-0.005
 hey-0.004
 Def-0.004
icker-0.004
Token have
Token ID423
Feature activation-5.92e-01

Pos logit contributions
 ranger+0.011
 polar+0.011
 chimpan+0.011
 MacDonald+0.010
 ze+0.010
Neg logit contributions
our-0.007
icker-0.006
ivated-0.005
bs-0.005
 hey-0.005
Token the
Token ID262
Feature activation-3.29e-02

Pos logit contributions
nam+0.013
ivated+0.013
 tant+0.012
 Def+0.012
iable+0.012
Neg logit contributions
 polar-0.016
 ranger-0.015
 gn-0.015
 chimpan-0.015
 tow-0.014
Token ash
Token ID12530
Feature activation+1.13e-01

Pos logit contributions
nam+0.001
 tant+0.001
ivated+0.001
our+0.001
 hey+0.001
Neg logit contributions
 polar-0.001
 ranger-0.001
 tow-0.001
 chimpan-0.001
 gn-0.001
Tokentr
Token ID2213
Feature activation+3.09e+00

Pos logit contributions
 polar+0.003
 tow+0.003
 chimpan+0.003
 gn+0.003
 ranger+0.003
Neg logit contributions
our-0.002
 tant-0.002
icker-0.002
 spine-0.002
 hey-0.002
Tokenay
Token ID323
Feature activation+4.75e-01

Pos logit contributions
 polar+0.050
 tow+0.046
 ranger+0.046
 gn+0.040
glers+0.037
Neg logit contributions
ivated-0.104
nam-0.098
gging-0.097
 hey-0.096
 Def-0.095
Token to
Token ID284
Feature activation-7.98e-02

Pos logit contributions
 polar+0.012
 chimpan+0.011
 gn+0.011
 ranger+0.011
 tow+0.011
Neg logit contributions
our-0.012
iable-0.011
 hey-0.011
cient-0.011
bs-0.011
Token put
Token ID1234
Feature activation+1.14e-02

Pos logit contributions
ivated+0.002
our+0.002
icker+0.002
nam+0.002
 hey+0.002
Neg logit contributions
 polar-0.002
 ranger-0.002
 gn-0.002
 tow-0.002
 chimpan-0.002
Token her
Token ID607
Feature activation+2.95e-01

Pos logit contributions
 polar+0.000
 ranger+0.000
 chimpan+0.000
 tow+0.000
 gn+0.000
Neg logit contributions
nam-0.000
 tant-0.000
our-0.000
ivated-0.000
bs-0.000
Token rocks
Token ID12586
Feature activation-5.45e-01

Pos logit contributions
 polar+0.008
 ranger+0.007
 chimpan+0.007
 tow+0.007
 gn+0.007
Neg logit contributions
nam-0.007
 tant-0.007
ivated-0.006
our-0.006
icker-0.006
Token cleaned
Token ID20750
Feature activation+4.58e-02

Pos logit contributions
ivated+0.004
our+0.004
icker+0.004
 tant+0.004
 hey+0.004
Neg logit contributions
 polar-0.003
 ranger-0.003
 tow-0.003
 gn-0.003
 chimpan-0.003
Token up
Token ID510
Feature activation+5.63e-02

Pos logit contributions
 polar+0.001
 ranger+0.001
 tow+0.001
 gn+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.001
nam-0.001
our-0.001
icker-0.001
ivery-0.001
Token the
Token ID262
Feature activation+3.07e-01

Pos logit contributions
 polar+0.001
 ranger+0.001
 gn+0.001
 tow+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.002
icker-0.002
our-0.002
nam-0.002
 tant-0.002
Token broken
Token ID5445
Feature activation+9.73e-01

Pos logit contributions
 polar+0.006
 ranger+0.006
 gn+0.006
 tow+0.005
 chimpan+0.005
Neg logit contributions
ivated-0.010
icker-0.009
our-0.009
nam-0.009
oney-0.009
Token ash
Token ID12530
Feature activation+3.92e-01

Pos logit contributions
 polar+0.022
 ranger+0.021
 tow+0.020
 gn+0.020
 chimpan+0.019
Neg logit contributions
ivated-0.026
our-0.025
icker-0.025
nam-0.024
 tant-0.024
Tokentr
Token ID2213
Feature activation+3.01e+00

Pos logit contributions
 ranger+0.008
 polar+0.008
 gn+0.007
 tow+0.007
 chimpan+0.007
Neg logit contributions
ivated-0.012
nam-0.011
icker-0.011
 hey-0.011
arre-0.010
Tokenay
Token ID323
Feature activation+8.53e-01

Pos logit contributions
 polar+0.040
 tow+0.040
 ranger+0.038
!+0.032
 gn+0.030
Neg logit contributions
ivated-0.109
nam-0.103
gging-0.102
 ent-0.098
 hey-0.098
Token and
Token ID290
Feature activation+4.09e-01

Pos logit contributions
 ranger+0.009
 polar+0.009
 tow+0.007
!+0.007
 gn+0.006
Neg logit contributions
ivated-0.033
nam-0.031
 hey-0.031
icker-0.031
 ent-0.030
Token Lily
Token ID20037
Feature activation-3.15e-01

Pos logit contributions
 polar+0.009
 ranger+0.008
 tow+0.008
 gn+0.008
 chimpan+0.008
Neg logit contributions
ivated-0.011
our-0.011
icker-0.011
nam-0.011
 hey-0.010
Token learned
Token ID4499
Feature activation-2.43e-01

Pos logit contributions
ivated+0.008
icker+0.008
our+0.008
nam+0.008
 hey+0.008
Neg logit contributions
 polar-0.007
 ranger-0.007
 tow-0.007
 gn-0.007
 chimpan-0.006
Token to
Token ID284
Feature activation-2.79e-01

Pos logit contributions
ivated+0.005
nam+0.005
 tant+0.005
icker+0.005
arre+0.005
Neg logit contributions
 polar-0.007
 tow-0.006
 chimpan-0.006
 gn-0.006
 ranger-0.006
Token accidentally
Token ID14716
Feature activation-2.15e-01

Pos logit contributions
 polar+0.005
 ranger+0.004
 tow+0.004
 gn+0.004
 chimpan+0.004
Neg logit contributions
ivated-0.004
icker-0.004
our-0.004
nam-0.004
 hey-0.004
Token knocked
Token ID13642
Feature activation+6.82e-01

Pos logit contributions
our+0.003
nam+0.003
bs+0.003
 hey+0.003
 accidentally+0.003
Neg logit contributions
 ranger-0.007
 polar-0.007
 MacDonald-0.007
 waterfall-0.007
 chimpan-0.007
Token over
Token ID625
Feature activation+6.69e-01

Pos logit contributions
 polar+0.015
 ranger+0.013
 gn+0.013
 tow+0.013
 chimpan+0.012
Neg logit contributions
ivated-0.019
icker-0.018
our-0.018
 tant-0.018
nam-0.018
Token the
Token ID262
Feature activation+1.19e-01

Pos logit contributions
 polar+0.018
 ranger+0.017
 chimpan+0.017
 gn+0.016
 waterfall+0.016
Neg logit contributions
nam-0.015
 tant-0.014
ivated-0.013
 hey-0.012
icker-0.012
Token ash
Token ID12530
Feature activation+3.02e-01

Pos logit contributions
 polar+0.003
 ranger+0.003
 gn+0.003
 chimpan+0.003
 tow+0.003
Neg logit contributions
 tant-0.003
nam-0.003
 hey-0.003
ivated-0.003
our-0.002
Tokentr
Token ID2213
Feature activation+3.00e+00

Pos logit contributions
 polar+0.010
 chimpan+0.009
 tow+0.009
 gn+0.009
 ranger+0.008
Neg logit contributions
our-0.005
 tant-0.005
icker-0.005
obb-0.004
 spine-0.004
Tokenay
Token ID323
Feature activation+5.78e-01

Pos logit contributions
 polar+0.058
 ranger+0.054
 tow+0.053
 gn+0.049
 chimpan+0.047
Neg logit contributions
ivated-0.091
nam-0.086
icker-0.085
 hey-0.085
our-0.084
Token and
Token ID290
Feature activation-1.64e-02

Pos logit contributions
 polar+0.014
 chimpan+0.013
 gn+0.012
 ranger+0.012
 tow+0.012
Neg logit contributions
our-0.015
she-0.014
ivated-0.013
 tant-0.013
bs-0.013
Token it
Token ID340
Feature activation-5.73e-02

Pos logit contributions
ivated+0.000
icker+0.000
our+0.000
nam+0.000
 hey+0.000
Neg logit contributions
 polar-0.000
 ranger-0.000
 tow-0.000
 gn-0.000
 chimpan-0.000
Token broke
Token ID6265
Feature activation+4.42e-01

Pos logit contributions
ivated+0.001
our+0.001
icker+0.001
 tant+0.001
 Def+0.001
Neg logit contributions
 polar-0.002
 ranger-0.001
 tow-0.001
 gn-0.001
 chimpan-0.001
Token into
Token ID656
Feature activation+6.92e-02

Pos logit contributions
 ranger+0.012
 polar+0.011
 chimpan+0.011
 gn+0.011
 tow+0.011
Neg logit contributions
nam-0.009
our-0.009
 Ow-0.009
 tant-0.009
icker-0.009
Token and
Token ID290
Feature activation-2.94e-01

Pos logit contributions
 polar+0.012
 ranger+0.011
 tow+0.010
 gn+0.010
 chimpan+0.010
Neg logit contributions
ivated-0.016
 tant-0.015
 Def-0.015
our-0.015
arre-0.015
Token fell
Token ID3214
Feature activation+2.47e-01

Pos logit contributions
ivated+0.008
icker+0.008
arre+0.008
our+0.008
 Him+0.008
Neg logit contributions
 polar-0.006
 gn-0.006
 ranger-0.006
 tow-0.005
 chimpan-0.005
Token.
Token ID13
Feature activation-2.15e-01

Pos logit contributions
 polar+0.005
 ranger+0.005
 tow+0.005
 gn+0.004
 chimpan+0.004
Neg logit contributions
ivated-0.007
our-0.007
 tant-0.007
icker-0.007
nam-0.007
Token The
Token ID383
Feature activation+1.96e-01

Pos logit contributions
ivated+0.005
iable+0.005
cient+0.005
arre+0.005
 hey+0.005
Neg logit contributions
 polar-0.005
 gn-0.005
 tow-0.005
 ranger-0.005
 chimpan-0.004
Token ash
Token ID12530
Feature activation-2.08e-01

Pos logit contributions
 polar+0.005
 ranger+0.005
 tow+0.005
 chimpan+0.005
 gn+0.005
Neg logit contributions
 tant-0.004
nam-0.004
ivated-0.004
icker-0.004
 hey-0.004
Tokentr
Token ID2213
Feature activation+3.00e+00

Pos logit contributions
ivated+0.004
our+0.004
 tant+0.004
icker+0.004
 hey+0.004
Neg logit contributions
 polar-0.006
 ranger-0.006
 tow-0.005
 gn-0.005
 chimpan-0.005
Tokenay
Token ID323
Feature activation+2.60e-01

Pos logit contributions
 polar+0.046
 tow+0.041
 ranger+0.039
 gn+0.036
!+0.034
Neg logit contributions
ivated-0.102
nam-0.099
gging-0.095
 hey-0.094
 Def-0.094
Token flew
Token ID13112
Feature activation+2.41e-01

Pos logit contributions
 polar+0.006
 ranger+0.006
 tow+0.005
 gn+0.005
 chimpan+0.005
Neg logit contributions
ivated-0.007
our-0.007
icker-0.007
 tant-0.006
 hey-0.006
Token out
Token ID503
Feature activation+8.20e-01

Pos logit contributions
 polar+0.008
 ranger+0.008
 gn+0.008
 tow+0.008
 chimpan+0.008
Neg logit contributions
ivated-0.003
 tant-0.003
obb-0.003
nam-0.003
 hey-0.003
Token of
Token ID286
Feature activation-3.41e-01

Pos logit contributions
 polar+0.020
 ranger+0.019
 chimpan+0.019
 carn+0.018
 gn+0.017
Neg logit contributions
ivated-0.019
 tant-0.019
 Blood-0.019
icker-0.019
our-0.018
Token her
Token ID607
Feature activation+4.39e-01

Pos logit contributions
nam+0.008
ivated+0.007
 tant+0.007
 hey+0.007
 Def+0.007
Neg logit contributions
 polar-0.009
 ranger-0.008
 chimpan-0.008
 gn-0.008
 tow-0.008
Token show
Token ID905
Feature activation+4.55e-01

Pos logit contributions
 polar+0.003
 ranger+0.003
 chimpan+0.003
 gn+0.003
 tow+0.003
Neg logit contributions
ivated-0.002
our-0.002
 hey-0.002
 Def-0.002
nam-0.002
Token her
Token ID607
Feature activation+5.69e-01

Pos logit contributions
 polar+0.013
 ranger+0.013
 gn+0.012
 chimpan+0.012
 tow+0.012
Neg logit contributions
nam-0.009
ivated-0.009
 hey-0.009
 tant-0.008
our-0.008
Token an
Token ID281
Feature activation+2.98e-01

Pos logit contributions
 polar+0.017
 chimpan+0.017
 tow+0.016
 ranger+0.016
 gn+0.016
Neg logit contributions
nam-0.011
 tant-0.010
ivated-0.009
 Def-0.009
bs-0.009
Token expensive
Token ID5789
Feature activation+1.03e-01

Pos logit contributions
 polar+0.008
 ranger+0.008
 tow+0.008
 chimpan+0.008
 gn+0.008
Neg logit contributions
nam-0.006
ivated-0.006
 tant-0.005
 ent-0.005
our-0.005
Token ash
Token ID12530
Feature activation+3.45e-01

Pos logit contributions
 polar+0.003
 chimpan+0.003
glers+0.003
 ranger+0.003
 tow+0.002
Neg logit contributions
 tant-0.002
nam-0.002
our-0.002
 exam-0.002
 boo-0.002
Tokentr
Token ID2213
Feature activation+2.99e+00

Pos logit contributions
 polar+0.010
 tow+0.009
 chimpan+0.008
 ranger+0.008
 amusement+0.008
Neg logit contributions
our-0.007
cient-0.007
 spine-0.007
 tant-0.006
ong-0.006
Tokenay
Token ID323
Feature activation+5.50e-01

Pos logit contributions
 polar+0.055
 ranger+0.051
 tow+0.050
 gn+0.047
 chimpan+0.044
Neg logit contributions
ivated-0.093
nam-0.087
 hey-0.087
icker-0.086
 Def-0.086
Token he
Token ID339
Feature activation+7.58e-02

Pos logit contributions
 polar+0.013
 tow+0.012
 chimpan+0.012
 ranger+0.011
 gn+0.011
Neg logit contributions
our-0.014
she-0.014
oney-0.014
iable-0.014
osing-0.013
Token got
Token ID1392
Feature activation+2.71e-02

Pos logit contributions
 polar+0.002
 ranger+0.002
 tow+0.002
 chimpan+0.002
 gn+0.002
Neg logit contributions
ivated-0.002
our-0.002
nam-0.002
 Def-0.002
 hey-0.002
Token as
Token ID355
Feature activation+3.36e-01

Pos logit contributions
 polar+0.001
 ranger+0.001
 chimpan+0.001
 tow+0.001
 waterfall+0.001
Neg logit contributions
nam-0.001
ivated-0.001
 tant-0.000
iable-0.000
bs-0.000
Token a
Token ID257
Feature activation-9.69e-02

Pos logit contributions
 polar+0.010
 ranger+0.010
 tow+0.009
 chimpan+0.009
 waterfall+0.009
Neg logit contributions
nam-0.007
obb-0.006
 tant-0.006
bs-0.006
 ent-0.006
Token and
Token ID290
Feature activation+2.61e-01

Pos logit contributions
 polar+0.010
 ranger+0.008
 tow+0.008
 gn+0.008
 chimpan+0.008
Neg logit contributions
ivated-0.017
our-0.016
icker-0.016
 hey-0.016
arre-0.016
Token saw
Token ID2497
Feature activation+3.51e-02

Pos logit contributions
 polar+0.006
 ranger+0.006
 gn+0.006
 tow+0.005
 chimpan+0.005
Neg logit contributions
ivated-0.007
icker-0.007
our-0.007
obb-0.006
arre-0.006
Token the
Token ID262
Feature activation-8.29e-02

Pos logit contributions
 polar+0.001
 ranger+0.001
 gn+0.001
 tow+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.001
our-0.001
icker-0.001
 Def-0.001
nam-0.001
Token broken
Token ID5445
Feature activation+6.42e-01

Pos logit contributions
ivated+0.002
icker+0.002
our+0.002
 hey+0.002
 tant+0.002
Neg logit contributions
 polar-0.002
 ranger-0.002
 tow-0.002
 gn-0.002
 chimpan-0.002
Token ash
Token ID12530
Feature activation+2.97e-01

Pos logit contributions
 polar+0.017
 ranger+0.017
 chimpan+0.016
 tow+0.016
 gn+0.015
Neg logit contributions
 tant-0.013
our-0.013
icker-0.012
 hey-0.012
 Blood-0.012
Tokentr
Token ID2213
Feature activation+2.98e+00

Pos logit contributions
 polar+0.009
 ranger+0.008
 tow+0.008
 chimpan+0.008
 gn+0.008
Neg logit contributions
our-0.006
ivated-0.005
icker-0.005
 tant-0.005
 hey-0.005
Tokenay
Token ID323
Feature activation+5.87e-01

Pos logit contributions
 polar+0.050
 tow+0.046
 ranger+0.045
 gn+0.041
 chimpan+0.038
Neg logit contributions
ivated-0.098
nam-0.094
gging-0.090
 Def-0.090
 hey-0.090
Token.
Token ID13
Feature activation-1.39e-01

Pos logit contributions
 polar+0.011
 ranger+0.010
 tow+0.010
 gn+0.010
 chimpan+0.009
Neg logit contributions
our-0.018
ivated-0.018
 hey-0.017
icker-0.017
 Def-0.017
Token She
Token ID1375
Feature activation+4.27e-01

Pos logit contributions
 unnecessary+0.004
unct+0.004
ivated+0.004
int+0.004
iable+0.004
Neg logit contributions
 ranger-0.003
 gn-0.003
 polar-0.002
 tow-0.002
 chimpan-0.002
Token was
Token ID373
Feature activation-1.46e-01

Pos logit contributions
 polar+0.009
 ranger+0.008
 gn+0.008
 tow+0.008
 chimpan+0.007
Neg logit contributions
ivated-0.013
icker-0.012
our-0.012
 tant-0.012
nam-0.012
Token upset
Token ID9247
Feature activation+5.50e-01

Pos logit contributions
our+0.003
ivated+0.003
icker+0.003
 tant+0.003
 Def+0.003
Neg logit contributions
 polar-0.004
 ranger-0.004
 tow-0.004
 gn-0.003
 chimpan-0.003
Token on
Token ID319
Feature activation+2.88e-01

Pos logit contributions
 polar+0.006
 chimpan+0.006
 ranger+0.006
 tow+0.006
glers+0.005
Neg logit contributions
ivated-0.005
our-0.005
onel-0.004
nam-0.004
obb-0.004
Token top
Token ID1353
Feature activation+2.18e-01

Pos logit contributions
 polar+0.008
 ranger+0.007
 chimpan+0.007
glers+0.007
 tow+0.006
Neg logit contributions
ivated-0.006
nam-0.006
 Def-0.006
our-0.006
 tant-0.006
Token of
Token ID286
Feature activation-4.04e-01

Pos logit contributions
 polar+0.005
 chimpan+0.005
 ranger+0.004
 gn+0.004
 tow+0.004
Neg logit contributions
our-0.006
ivated-0.006
ong-0.005
icker-0.005
 tant-0.005
Token the
Token ID262
Feature activation+2.28e-01

Pos logit contributions
nam+0.010
ivated+0.009
 hey+0.009
 Def+0.009
icker+0.009
Neg logit contributions
 polar-0.010
 ranger-0.010
 chimpan-0.009
 gn-0.009
 tow-0.009
Token ash
Token ID12530
Feature activation+3.88e-01

Pos logit contributions
 polar+0.005
 ranger+0.005
 gn+0.005
 tow+0.005
 chimpan+0.005
Neg logit contributions
ivated-0.006
icker-0.006
our-0.006
nam-0.006
 Def-0.006
Tokentr
Token ID2213
Feature activation+2.97e+00

Pos logit contributions
 polar+0.011
 tow+0.010
 chimpan+0.010
 ranger+0.010
 gn+0.010
Neg logit contributions
our-0.008
icker-0.007
 spine-0.007
ivated-0.007
cient-0.007
Tokenay
Token ID323
Feature activation+3.59e-01

Pos logit contributions
 polar+0.057
 ranger+0.053
 tow+0.052
 gn+0.049
 chimpan+0.047
Neg logit contributions
ivated-0.090
nam-0.086
 hey-0.084
icker-0.084
 Def-0.083
Token.
Token ID13
Feature activation-1.23e-01

Pos logit contributions
 polar+0.008
 chimpan+0.007
 ranger+0.007
 tow+0.007
 gn+0.007
Neg logit contributions
our-0.011
ivated-0.010
icker-0.010
bs-0.010
oney-0.010
Token
Token ID198
Feature activation+7.49e-02

Pos logit contributions
ivated+0.003
 tant+0.003
ivery+0.003
our+0.003
iable+0.003
Neg logit contributions
 tow-0.003
 ranger-0.003
 gn-0.003
 polar-0.003
 chimpan-0.003
Token
Token ID198
Feature activation+3.11e-02

Pos logit contributions
 tow+0.001
 ranger+0.001
 polar+0.001
 gn+0.001
!+0.001
Neg logit contributions
nam-0.002
our-0.002
 tant-0.002
ivated-0.002
 spine-0.002
TokenThe
Token ID464
Feature activation+3.42e-01

Pos logit contributions
 ranger+0.001
 tow+0.001
 gn+0.001
 polar+0.001
 chimpan+0.001
Neg logit contributions
our-0.001
 tant-0.001
 spine-0.001
icker-0.001
nam-0.001
Token around
Token ID1088
Feature activation-2.32e-01

Pos logit contributions
ivated+0.002
 tant+0.002
 ent+0.002
nam+0.002
icker+0.002
Neg logit contributions
 polar-0.005
 gn-0.005
 tow-0.005
 chimpan-0.005
 ranger-0.005
Token town
Token ID3240
Feature activation-2.95e-01

Pos logit contributions
ivated+0.005
 hey+0.005
 tant+0.005
 Def+0.005
 ent+0.005
Neg logit contributions
 polar-0.006
 ranger-0.005
 tow-0.005
glers-0.005
 chimpan-0.005
Token on
Token ID319
Feature activation-2.25e-03

Pos logit contributions
ivated+0.008
our+0.008
 ent+0.008
icker+0.008
nam+0.008
Neg logit contributions
 polar-0.007
 tow-0.006
 ranger-0.006
 chimpan-0.006
 gn-0.006
Token his
Token ID465
Feature activation-1.90e-01

Pos logit contributions
 tant+0.000
 Def+0.000
ivated+0.000
nam+0.000
icker+0.000
Neg logit contributions
 polar-0.000
 ranger-0.000
glers-0.000
 gn-0.000
 chimpan-0.000
Token ash
Token ID12530
Feature activation+4.64e-01

Pos logit contributions
ivated+0.005
our+0.005
icker+0.005
nam+0.004
 Def+0.004
Neg logit contributions
 polar-0.005
 ranger-0.004
 tow-0.004
 gn-0.004
 chimpan-0.004
Tokentr
Token ID2213
Feature activation+2.91e+00

Pos logit contributions
 polar+0.014
 tow+0.012
 ranger+0.012
 chimpan+0.012
 gn+0.012
Neg logit contributions
our-0.009
icker-0.008
ivated-0.008
 tant-0.008
 Def-0.008
Tokenay
Token ID323
Feature activation+1.33e-01

Pos logit contributions
 polar+0.055
 ranger+0.050
 tow+0.050
 gn+0.046
 chimpan+0.044
Neg logit contributions
ivated-0.090
nam-0.086
 hey-0.084
our-0.083
icker-0.083
Token,
Token ID11
Feature activation+2.30e-01

Pos logit contributions
 polar+0.003
 ranger+0.003
 chimpan+0.003
 gn+0.003
 tow+0.002
Neg logit contributions
our-0.004
ivated-0.004
 Def-0.004
icker-0.004
arre-0.003
Token z
Token ID1976
Feature activation+3.80e-01

Pos logit contributions
 polar+0.006
 ranger+0.005
 tow+0.005
 chimpan+0.005
 gn+0.005
Neg logit contributions
ivated-0.006
nam-0.005
 ent-0.005
our-0.005
 hey-0.005
Tokenipping
Token ID4501
Feature activation+5.71e-01

Pos logit contributions
 polar+0.012
 ranger+0.012
 tow+0.011
 gn+0.011
 chimpan+0.011
Neg logit contributions
ivated-0.007
our-0.007
icker-0.007
 hey-0.006
arre-0.006
Token everywhere
Token ID8347
Feature activation+3.35e-01

Pos logit contributions
 polar+0.019
 gn+0.018
 tow+0.018
 ranger+0.018
 chimpan+0.018
Neg logit contributions
 tant-0.009
ivated-0.007
bs-0.007
 ent-0.007
ong-0.007
Token it
Token ID340
Feature activation-2.71e-01

Pos logit contributions
 polar+0.009
 ranger+0.009
 tow+0.008
 gn+0.008
 chimpan+0.008
Neg logit contributions
ivated-0.011
icker-0.011
nam-0.011
our-0.011
 hey-0.011
Token came
Token ID1625
Feature activation+3.44e-01

Pos logit contributions
ivated+0.006
our+0.006
icker+0.006
 Def+0.006
 hey+0.006
Neg logit contributions
 polar-0.007
 ranger-0.007
 tow-0.007
 gn-0.006
 chimpan-0.006
Token across
Token ID1973
Feature activation-7.76e-02

Pos logit contributions
 polar+0.010
 ranger+0.009
 tow+0.009
 gn+0.009
 chimpan+0.009
Neg logit contributions
ivated-0.007
 ent-0.007
icker-0.007
our-0.007
 Def-0.006
Token an
Token ID281
Feature activation-1.92e-01

Pos logit contributions
 ent+0.001
icker+0.001
 hey+0.001
ivated+0.001
 Def+0.001
Neg logit contributions
 polar-0.002
glers-0.002
 ranger-0.002
 tow-0.002
 chimpan-0.002
Token ash
Token ID12530
Feature activation+4.80e-01

Pos logit contributions
ivated+0.005
icker+0.005
our+0.005
 hey+0.005
nam+0.005
Neg logit contributions
 polar-0.005
 ranger-0.004
 gn-0.004
 tow-0.004
 chimpan-0.004
Tokentr
Token ID2213
Feature activation+2.91e+00

Pos logit contributions
 polar+0.015
 tow+0.014
 ranger+0.013
 chimpan+0.013
 gn+0.013
Neg logit contributions
our-0.009
 spine-0.008
icker-0.008
ivated-0.008
 hey-0.008
Tokenay
Token ID323
Feature activation+2.87e-01

Pos logit contributions
 polar+0.054
 tow+0.049
 ranger+0.049
 gn+0.045
 chimpan+0.043
Neg logit contributions
ivated-0.090
nam-0.087
 hey-0.084
 Def-0.084
icker-0.084
Token.
Token ID13
Feature activation-1.96e-01

Pos logit contributions
 polar+0.007
 tow+0.006
 chimpan+0.006
 ranger+0.006
 gn+0.006
Neg logit contributions
our-0.008
ivated-0.008
osing-0.007
 hey-0.007
icker-0.007
Token It
Token ID632
Feature activation+2.00e-02

Pos logit contributions
ivated+0.004
our+0.004
nam+0.004
icker+0.004
 tant+0.004
Neg logit contributions
 polar-0.006
 ranger-0.005
 tow-0.005
 gn-0.005
 chimpan-0.005
Token wanted
Token ID2227
Feature activation+2.02e-01

Pos logit contributions
 polar+0.000
 ranger+0.000
 tow+0.000
 gn+0.000
 chimpan+0.000
Neg logit contributions
ivated-0.001
our-0.001
icker-0.001
 tant-0.001
 Def-0.001
Token to
Token ID284
Feature activation+3.60e-02

Pos logit contributions
 polar+0.006
 ranger+0.006
glers+0.006
 gn+0.006
 chimpan+0.006
Neg logit contributions
 Def-0.003
 hey-0.003
 Blood-0.003
 anybody-0.003
 anyone-0.003
Token Lily
Token ID20037
Feature activation+4.08e-02

Pos logit contributions
ivated+0.001
our+0.000
icker+0.000
arre+0.000
 Def+0.000
Neg logit contributions
 polar-0.000
 ranger-0.000
 tow-0.000
 gn-0.000
 chimpan-0.000
Token accidentally
Token ID14716
Feature activation-1.86e-01

Pos logit contributions
 polar+0.001
 ranger+0.001
 tow+0.001
 waterfall+0.001
 chimpan+0.001
Neg logit contributions
arre-0.001
our-0.001
ivated-0.001
 hey-0.001
 Def-0.001
Token dropped
Token ID5710
Feature activation+3.90e-01

Pos logit contributions
bs+0.003
nam+0.002
our+0.002
 hey+0.002
 Blood+0.002
Neg logit contributions
 ranger-0.006
 polar-0.006
 tow-0.006
 chimpan-0.006
 waterfall-0.006
Token the
Token ID262
Feature activation+3.72e-01

Pos logit contributions
 polar+0.009
 ranger+0.009
 tow+0.008
 chimpan+0.008
 gn+0.008
Neg logit contributions
 tant-0.010
ivated-0.010
nam-0.010
our-0.009
icker-0.009
Token ash
Token ID12530
Feature activation-1.76e-02

Pos logit contributions
 polar+0.009
 ranger+0.008
 tow+0.008
 gn+0.008
 chimpan+0.008
Neg logit contributions
ivated-0.009
our-0.009
icker-0.009
 tant-0.009
 hey-0.009
Tokentr
Token ID2213
Feature activation+2.91e+00

Pos logit contributions
ivated+0.000
our+0.000
icker+0.000
 tant+0.000
 hey+0.000
Neg logit contributions
 polar-0.000
 ranger-0.000
 tow-0.000
 gn-0.000
 chimpan-0.000
Tokenay
Token ID323
Feature activation+4.64e-01

Pos logit contributions
 polar+0.050
 tow+0.047
 ranger+0.046
 gn+0.042
 chimpan+0.039
Neg logit contributions
ivated-0.094
nam-0.089
 hey-0.087
 Def-0.086
gging-0.086
Token and
Token ID290
Feature activation+5.47e-02

Pos logit contributions
 polar+0.010
 ranger+0.009
 chimpan+0.009
 gn+0.009
 tow+0.009
Neg logit contributions
our-0.013
ivated-0.012
bs-0.012
 tant-0.012
icker-0.012
Token it
Token ID340
Feature activation-2.74e-01

Pos logit contributions
 polar+0.001
 ranger+0.001
 tow+0.001
 gn+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.001
nam-0.001
our-0.001
 tant-0.001
icker-0.001
Token broke
Token ID6265
Feature activation+4.27e-01

Pos logit contributions
ivated+0.006
icker+0.006
our+0.006
nam+0.006
 hey+0.006
Neg logit contributions
 polar-0.007
 ranger-0.007
 gn-0.007
 tow-0.007
 chimpan-0.007
Token into
Token ID656
Feature activation+1.24e-01

Pos logit contributions
 polar+0.011
 ranger+0.011
 tow+0.010
 chimpan+0.010
 gn+0.010
Neg logit contributions
nam-0.010
our-0.009
 tant-0.009
ivated-0.009
icker-0.009
Token putting
Token ID5137
Feature activation-2.96e-01

Pos logit contributions
 polar+0.005
 ranger+0.005
 gn+0.005
 tow+0.005
 chimpan+0.005
Neg logit contributions
ivated-0.006
icker-0.006
our-0.006
arre-0.006
 tant-0.006
Token it
Token ID340
Feature activation-2.22e-01

Pos logit contributions
ivated+0.010
our+0.009
icker+0.009
arre+0.009
 Def+0.009
Neg logit contributions
 polar-0.005
 ranger-0.005
 tow-0.005
 gn-0.004
 chimpan-0.004
Token in
Token ID287
Feature activation-1.56e-01

Pos logit contributions
ivated+0.007
our+0.006
icker+0.006
 Def+0.006
 hey+0.006
Neg logit contributions
 polar-0.004
 ranger-0.004
 gn-0.004
 tow-0.004
 chimpan-0.003
Token the
Token ID262
Feature activation-2.36e-01

Pos logit contributions
 tant+0.003
nam+0.003
ivated+0.003
 Ow+0.003
 Def+0.003
Neg logit contributions
 polar-0.004
 ranger-0.004
 chimpan-0.004
glers-0.004
 gn-0.004
Token ash
Token ID12530
Feature activation+4.12e-01

Pos logit contributions
ivated+0.007
osing+0.006
icker+0.006
nam+0.006
our+0.006
Neg logit contributions
 polar-0.005
 ranger-0.005
 tow-0.005
 gn-0.005
 chimpan-0.005
Tokentr
Token ID2213
Feature activation+2.90e+00

Pos logit contributions
 polar+0.011
 ranger+0.010
 tow+0.009
 gn+0.009
 chimpan+0.009
Neg logit contributions
ivated-0.010
icker-0.009
our-0.009
nam-0.009
 hey-0.009
Tokenay
Token ID323
Feature activation+3.57e-01

Pos logit contributions
 polar+0.046
 tow+0.044
 ranger+0.041
 gn+0.037
glers+0.034
Neg logit contributions
ivated-0.098
nam-0.094
 hey-0.091
gging-0.091
 ent-0.089
Token.
Token ID13
Feature activation-5.22e-02

Pos logit contributions
 polar+0.007
 ranger+0.006
 chimpan+0.006
 gn+0.006
 tow+0.006
Neg logit contributions
our-0.011
 tant-0.011
ivated-0.010
icker-0.010
nam-0.010
Token Lily
Token ID20037
Feature activation+1.77e-01

Pos logit contributions
onel+0.002
 unnecessary+0.002
obb+0.002
unct+0.002
 hey+0.002
Neg logit contributions
 ranger-0.001
 gn-0.001
 tow-0.001
 polar-0.001
 C-0.001
Token didn
Token ID1422
Feature activation-1.23e-01

Pos logit contributions
 polar+0.003
 gn+0.003
 ranger+0.003
!+0.002
 was+0.002
Neg logit contributions
icker-0.006
ivated-0.006
 unnecessary-0.006
obb-0.006
 tant-0.006
Token't
Token ID470
Feature activation+2.37e-01

Pos logit contributions
ivated+0.002
icker+0.002
our+0.002
 Def+0.002
 hey+0.002
Neg logit contributions
 polar-0.004
 ranger-0.004
 gn-0.004
 tow-0.004
 chimpan-0.004
Token and
Token ID290
Feature activation+1.97e-01

Pos logit contributions
 polar+0.015
 tow+0.015
 ranger+0.015
 gn+0.014
 chimpan+0.013
Neg logit contributions
our-0.022
ivated-0.021
icker-0.020
cient-0.020
arre-0.020
Token accidentally
Token ID14716
Feature activation-1.57e-01

Pos logit contributions
 polar+0.005
 ranger+0.004
 tow+0.004
 gn+0.004
 chimpan+0.004
Neg logit contributions
ivated-0.005
nam-0.005
icker-0.005
 hey-0.005
 tant-0.005
Token dropped
Token ID5710
Feature activation+5.25e-01

Pos logit contributions
 Blood+0.002
bs+0.002
 hey+0.002
our+0.002
 Ow+0.002
Neg logit contributions
 ranger-0.005
 polar-0.005
 tow-0.005
glers-0.005
 chimpan-0.005
Token her
Token ID607
Feature activation-7.74e-02

Pos logit contributions
 polar+0.012
 ranger+0.011
 gn+0.010
 tow+0.010
 chimpan+0.010
Neg logit contributions
ivated-0.014
 tant-0.014
nam-0.014
icker-0.013
 Def-0.013
Token ash
Token ID12530
Feature activation+3.97e-01

Pos logit contributions
ivated+0.002
icker+0.002
nam+0.002
our+0.002
 Def+0.002
Neg logit contributions
 polar-0.002
 ranger-0.002
 tow-0.002
 gn-0.002
 chimpan-0.002
Tokentr
Token ID2213
Feature activation+2.90e+00

Pos logit contributions
 polar+0.011
 ranger+0.010
 tow+0.010
 gn+0.009
 chimpan+0.009
Neg logit contributions
ivated-0.009
our-0.009
icker-0.009
 tant-0.008
 hey-0.008
Tokenay
Token ID323
Feature activation+4.77e-01

Pos logit contributions
 polar+0.052
 tow+0.048
 ranger+0.047
 gn+0.044
 chimpan+0.041
Neg logit contributions
ivated-0.092
nam-0.087
 hey-0.086
icker-0.085
 Def-0.085
Token on
Token ID319
Feature activation+1.16e-01

Pos logit contributions
 polar+0.009
 ranger+0.008
 tow+0.008
 chimpan+0.008
 gn+0.008
Neg logit contributions
our-0.015
ivated-0.014
 tant-0.014
nam-0.014
 Def-0.014
Token the
Token ID262
Feature activation+2.55e-02

Pos logit contributions
 polar+0.003
 ranger+0.003
 chimpan+0.002
 gn+0.002
 tow+0.002
Neg logit contributions
 tant-0.003
ivated-0.003
nam-0.003
 Def-0.003
 Ow-0.003
Token ground
Token ID2323
Feature activation+3.36e-01

Pos logit contributions
 polar+0.001
 ranger+0.001
 tow+0.001
 gn+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.000
icker-0.000
our-0.000
nam-0.000
 tant-0.000
Token.
Token ID13
Feature activation-4.46e-01

Pos logit contributions
 polar+0.009
 chimpan+0.008
 tow+0.008
 ranger+0.007
 gn+0.007
Neg logit contributions
our-0.008
ivated-0.007
 spine-0.007
 tant-0.007
ong-0.007
Token so
Token ID523
Feature activation+2.55e-01

Pos logit contributions
ivated+0.008
 tant+0.008
arre+0.008
iable+0.007
obb+0.007
Neg logit contributions
 polar-0.016
 tow-0.014
 gn-0.014
 chimpan-0.014
 ranger-0.014
Token hard
Token ID1327
Feature activation-1.04e-01

Pos logit contributions
 polar+0.006
 ranger+0.006
 tow+0.005
 gn+0.005
 chimpan+0.005
Neg logit contributions
ivated-0.007
our-0.007
 Def-0.006
arre-0.006
 hey-0.006
Token on
Token ID319
Feature activation-7.87e-02

Pos logit contributions
ivated+0.003
our+0.003
icker+0.003
arre+0.003
 tant+0.003
Neg logit contributions
 polar-0.002
 ranger-0.002
 tow-0.002
 gn-0.002
 chimpan-0.002
Token the
Token ID262
Feature activation+4.72e-01

Pos logit contributions
nam+0.002
ivated+0.002
our+0.002
icker+0.002
 tant+0.002
Neg logit contributions
 polar-0.002
 ranger-0.002
 chimpan-0.002
 gn-0.002
 tow-0.002
Token ash
Token ID12530
Feature activation+4.49e-01

Pos logit contributions
 polar+0.012
 ranger+0.011
 gn+0.011
 tow+0.011
 chimpan+0.010
Neg logit contributions
ivated-0.012
icker-0.011
our-0.011
arre-0.011
 Def-0.011
Tokentr
Token ID2213
Feature activation+2.90e+00

Pos logit contributions
 polar+0.013
 ranger+0.011
 tow+0.011
 gn+0.011
 chimpan+0.011
Neg logit contributions
ivated-0.009
our-0.009
icker-0.009
 tant-0.009
 Def-0.009
Tokenay
Token ID323
Feature activation+6.63e-01

Pos logit contributions
 polar+0.046
 tow+0.044
 ranger+0.042
 gn+0.037
 chimpan+0.035
Neg logit contributions
ivated-0.098
nam-0.094
gging-0.090
 hey-0.090
 Def-0.088
Token,
Token ID11
Feature activation+5.31e-01

Pos logit contributions
 polar+0.015
 ranger+0.014
 gn+0.014
 chimpan+0.013
 tow+0.013
Neg logit contributions
our-0.018
ivated-0.017
icker-0.017
 Def-0.017
 tant-0.017
Token and
Token ID290
Feature activation+4.37e-03

Pos logit contributions
 polar+0.013
 ranger+0.012
 tow+0.012
 chimpan+0.012
 gn+0.012
Neg logit contributions
ivated-0.013
nam-0.012
 tant-0.012
our-0.012
 Def-0.012
Token now
Token ID783
Feature activation+3.46e-01

Pos logit contributions
 polar+0.000
 ranger+0.000
 tow+0.000
 chimpan+0.000
 gn+0.000
Neg logit contributions
ivated-0.000
nam-0.000
 hey-0.000
 Def-0.000
 tant-0.000
Token it
Token ID340
Feature activation-2.77e-01

Pos logit contributions
 polar+0.010
 chimpan+0.009
 ranger+0.009
 tow+0.009
glers+0.009
Neg logit contributions
nam-0.007
our-0.007
 hey-0.007
 Def-0.006
ivated-0.006
Token notice
Token ID4003
Feature activation-2.94e-01

Pos logit contributions
 polar+0.003
 ranger+0.003
 chimpan+0.003
 gn+0.003
 tow+0.003
Neg logit contributions
ivated-0.002
 hey-0.002
our-0.002
icker-0.002
 Def-0.002
Token how
Token ID703
Feature activation+7.22e-01

Pos logit contributions
 tant+0.007
 hey+0.007
nam+0.007
ivated+0.007
our+0.007
Neg logit contributions
 polar-0.007
 ranger-0.007
 chimpan-0.007
 tow-0.007
 gn-0.006
Token slippery
Token ID32911
Feature activation+4.05e-01

Pos logit contributions
 polar+0.020
 ranger+0.019
 tow+0.018
 gn+0.018
 chimpan+0.018
Neg logit contributions
ivated-0.016
icker-0.015
our-0.015
 tant-0.014
nam-0.014
Token the
Token ID262
Feature activation+1.35e-02

Pos logit contributions
 polar+0.012
 tow+0.011
 gn+0.011
 ranger+0.011
 chimpan+0.011
Neg logit contributions
our-0.007
 hey-0.007
obb-0.007
iable-0.007
ivated-0.007
Token ash
Token ID12530
Feature activation+3.25e-02

Pos logit contributions
 polar+0.000
 ranger+0.000
 tow+0.000
 chimpan+0.000
 gn+0.000
Neg logit contributions
 tant-0.000
ivated-0.000
nam-0.000
 hey-0.000
icker-0.000
Tokentr
Token ID2213
Feature activation+2.89e+00

Pos logit contributions
 polar+0.001
 tow+0.001
 chimpan+0.001
 ranger+0.001
 gn+0.001
Neg logit contributions
our-0.001
 hey-0.001
icker-0.001
ivated-0.001
 tant-0.001
Tokenay
Token ID323
Feature activation+5.04e-01

Pos logit contributions
 polar+0.047
 tow+0.044
 ranger+0.044
 gn+0.039
 chimpan+0.036
Neg logit contributions
ivated-0.095
nam-0.091
gging-0.088
 hey-0.087
 Def-0.087
Token was
Token ID373
Feature activation-2.74e-01

Pos logit contributions
 polar+0.011
 ranger+0.010
 tow+0.009
 gn+0.009
 chimpan+0.009
Neg logit contributions
our-0.014
ivated-0.014
 hey-0.013
 Def-0.013
iable-0.013
Token.
Token ID13
Feature activation+2.55e-02

Pos logit contributions
iable+0.005
obb+0.005
our+0.005
 tant+0.005
ivated+0.005
Neg logit contributions
 polar-0.008
 chimpan-0.007
 ranger-0.007
 tow-0.007
 gn-0.007
Token In
Token ID554
Feature activation-2.94e-02

Pos logit contributions
 polar+0.001
 ranger+0.001
 tow+0.001
 gn+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.001
icker-0.001
our-0.001
nam-0.001
 Def-0.001
Token no
Token ID645
Feature activation+5.62e-01

Pos logit contributions
 tant+0.001
nam+0.001
ivated+0.001
 Def+0.001
 hey+0.001
Neg logit contributions
 polar-0.001
 ranger-0.001
 chimpan-0.001
 gn-0.001
glers-0.001
Token and
Token ID290
Feature activation+2.23e-02

Pos logit contributions
 polar+0.001
 tow+0.001
 ranger+0.001
 chimpan+0.001
 gn+0.001
Neg logit contributions
our-0.001
icker-0.001
ivated-0.001
nam-0.001
 spine-0.001
Token spotted
Token ID13489
Feature activation-1.83e-01

Pos logit contributions
 polar+0.001
 ranger+0.001
 gn+0.000
 tow+0.000
 chimpan+0.000
Neg logit contributions
 tant-0.001
ivated-0.001
icker-0.001
obb-0.001
arre-0.001
Token a
Token ID257
Feature activation-1.38e-01

Pos logit contributions
nam+0.004
ivated+0.004
 hey+0.004
icker+0.004
 Def+0.004
Neg logit contributions
 polar-0.005
 ranger-0.005
 tow-0.005
 chimpan-0.005
 gn-0.004
Token wide
Token ID3094
Feature activation-2.22e-01

Pos logit contributions
 tant+0.003
nam+0.003
icker+0.003
ivated+0.003
 miserable+0.002
Neg logit contributions
 polar-0.004
 ranger-0.003
 tow-0.003
 chimpan-0.003
esh-0.003
Token ash
Token ID12530
Feature activation+4.87e-01

Pos logit contributions
 tant+0.004
our+0.004
icker+0.004
ivated+0.004
 spine+0.004
Neg logit contributions
 ranger-0.006
 polar-0.005
girls-0.005
glers-0.005
 chimpan-0.005
Tokentr
Token ID2213
Feature activation+2.88e+00

Pos logit contributions
 polar+0.016
 tow+0.015
 ranger+0.014
 chimpan+0.014
 gn+0.013
Neg logit contributions
our-0.009
icker-0.008
 spine-0.008
 hey-0.007
obb-0.007
Tokenay
Token ID323
Feature activation+4.15e-01

Pos logit contributions
 polar+0.058
 ranger+0.053
 tow+0.052
 gn+0.049
 chimpan+0.047
Neg logit contributions
ivated-0.085
nam-0.081
icker-0.080
 hey-0.079
our-0.079
Token on
Token ID319
Feature activation+2.02e-01

Pos logit contributions
 polar+0.011
 ranger+0.010
 chimpan+0.010
 tow+0.010
 gn+0.009
Neg logit contributions
our-0.011
ivated-0.010
iable-0.009
 hey-0.009
osing-0.009
Token the
Token ID262
Feature activation-2.55e-01

Pos logit contributions
 polar+0.005
 ranger+0.005
 gn+0.004
 chimpan+0.004
 tow+0.004
Neg logit contributions
ivated-0.005
nam-0.005
 tant-0.005
 Ow-0.004
icker-0.004
Token table
Token ID3084
Feature activation-5.45e-02

Pos logit contributions
ivated+0.004
nam+0.004
icker+0.004
 hey+0.004
our+0.004
Neg logit contributions
 polar-0.008
 ranger-0.007
 tow-0.007
 gn-0.007
 chimpan-0.007
Token.
Token ID13
Feature activation-2.16e-01

Pos logit contributions
our+0.001
 spine+0.001
icker+0.001
ivated+0.001
care+0.001
Neg logit contributions
 polar-0.002
 chimpan-0.001
 tow-0.001
 coy-0.001
 ranger-0.001
Token,
Token ID11
Feature activation+1.83e-01

Pos logit contributions
 polar+0.006
 ranger+0.006
 gn+0.006
 tow+0.006
 chimpan+0.005
Neg logit contributions
ivated-0.007
 tant-0.007
our-0.006
arre-0.006
 hey-0.006
Token it
Token ID340
Feature activation-3.06e-01

Pos logit contributions
 polar+0.004
 ranger+0.004
 chimpan+0.004
 gn+0.004
 tow+0.004
Neg logit contributions
nam-0.004
ivated-0.004
 hey-0.004
 Def-0.004
 tant-0.004
Token caused
Token ID4073
Feature activation+4.31e-01

Pos logit contributions
ivated+0.008
our+0.008
icker+0.008
 tant+0.008
 Def+0.008
Neg logit contributions
 polar-0.007
 ranger-0.007
 tow-0.006
 gn-0.006
 chimpan-0.006
Token the
Token ID262
Feature activation+8.48e-02

Pos logit contributions
 polar+0.011
 ranger+0.010
 gn+0.010
 chimpan+0.009
 tow+0.009
Neg logit contributions
ivated-0.010
 Def-0.010
 tant-0.010
 hey-0.010
arre-0.010
Token ash
Token ID12530
Feature activation-1.28e-01

Pos logit contributions
 polar+0.002
 ranger+0.002
 gn+0.002
 tow+0.002
 chimpan+0.002
Neg logit contributions
ivated-0.002
icker-0.002
 hey-0.002
our-0.002
 tant-0.002
Tokentr
Token ID2213
Feature activation+2.87e+00

Pos logit contributions
ivated+0.003
our+0.003
icker+0.003
 tant+0.003
 hey+0.003
Neg logit contributions
 polar-0.003
 ranger-0.003
 tow-0.003
 gn-0.003
 chimpan-0.003
Tokenay
Token ID323
Feature activation+4.73e-01

Pos logit contributions
 polar+0.046
 tow+0.043
 ranger+0.041
 gn+0.036
 chimpan+0.034
Neg logit contributions
ivated-0.096
nam-0.093
gging-0.089
 hey-0.089
 Def-0.088
Token to
Token ID284
Feature activation-3.75e-01

Pos logit contributions
 polar+0.010
 ranger+0.009
 gn+0.009
 tow+0.009
 chimpan+0.009
Neg logit contributions
our-0.013
arre-0.013
ivated-0.013
icker-0.012
 tant-0.012
Token scatter
Token ID41058
Feature activation+3.77e-01

Pos logit contributions
ivated+0.010
icker+0.010
our+0.010
 hey+0.010
 Def+0.010
Neg logit contributions
 polar-0.008
 ranger-0.008
 gn-0.007
 tow-0.007
 chimpan-0.007
Token all
Token ID477
Feature activation-5.48e-01

Pos logit contributions
 polar+0.012
 chimpan+0.011
 gn+0.011
 ranger+0.011
 tow+0.010
Neg logit contributions
 tant-0.007
ivated-0.006
obb-0.006
nam-0.006
arre-0.006
Token over
Token ID625
Feature activation+3.02e-01

Pos logit contributions
ivated+0.011
 tant+0.010
arre+0.010
 Def+0.010
icker+0.009
Neg logit contributions
 polar-0.016
 chimpan-0.016
 gn-0.015
 ranger-0.015
 tow-0.014
Token they
Token ID484
Feature activation+1.62e-01

Pos logit contributions
 polar+0.018
 gn+0.016
 ranger+0.016
 chimpan+0.016
 tow+0.016
Neg logit contributions
icker-0.014
nam-0.014
bs-0.014
 tant-0.013
 Him-0.013
Token do
Token ID466
Feature activation-2.02e-01

Pos logit contributions
 polar+0.004
 ranger+0.004
 gn+0.004
 tow+0.004
 chimpan+0.003
Neg logit contributions
ivated-0.004
icker-0.004
nam-0.004
 Def-0.004
 tant-0.004
Token it
Token ID340
Feature activation+2.25e-02

Pos logit contributions
our+0.005
osing+0.004
ivated+0.004
bs+0.004
icker+0.004
Neg logit contributions
 polar-0.006
 ranger-0.005
 chimpan-0.005
 gn-0.005
glers-0.005
Token.
Token ID13
Feature activation-4.61e-02

Pos logit contributions
 polar+0.000
 tow+0.000
 ranger+0.000
 chimpan+0.000
 gn+0.000
Neg logit contributions
our-0.001
ivated-0.001
icker-0.001
 Def-0.001
bs-0.001
Token He
Token ID679
Feature activation+1.87e-01

Pos logit contributions
ivated+0.001
icker+0.001
our+0.001
 Def+0.001
nam+0.001
Neg logit contributions
 polar-0.001
 ranger-0.001
 gn-0.001
 tow-0.001
 chimpan-0.001
Token imag
Token ID3590
Feature activation-2.63e+00

Pos logit contributions
 polar+0.006
 ranger+0.005
 tow+0.005
 chimpan+0.005
 gn+0.005
Neg logit contributions
our-0.003
ivated-0.003
arre-0.003
obb-0.003
 hey-0.003
Tokenines
Token ID1127
Feature activation+2.33e-01

Pos logit contributions
ivated+0.067
nam+0.066
 Def+0.064
 tant+0.064
icker+0.063
Neg logit contributions
 polar-0.061
 tow-0.054
 ranger-0.054
 gn-0.053
 chimpan-0.049
Token he
Token ID339
Feature activation+7.74e-02

Pos logit contributions
 polar+0.007
 chimpan+0.006
 ranger+0.006
 gn+0.006
 bisc+0.006
Neg logit contributions
 hey-0.004
ivated-0.004
osing-0.004
she-0.004
our-0.004
Token is
Token ID318
Feature activation+9.92e-02

Pos logit contributions
 polar+0.002
 ranger+0.002
 tow+0.002
 chimpan+0.002
 gn+0.002
Neg logit contributions
our-0.002
ivated-0.002
arre-0.002
 hey-0.002
icker-0.002
Token one
Token ID530
Feature activation-3.42e-01

Pos logit contributions
 polar+0.003
 ranger+0.003
 bisc+0.003
 tow+0.003
 chimpan+0.003
Neg logit contributions
 bored-0.002
 ent-0.002
ivated-0.002
nam-0.002
 miserable-0.002
Token of
Token ID286
Feature activation+9.46e-02

Pos logit contributions
our+0.006
icker+0.006
bs+0.006
 hey+0.006
oney+0.006
Neg logit contributions
 polar-0.010
 gn-0.009
 ranger-0.009
 chimpan-0.009
 tow-0.009
Token,
Token ID11
Feature activation+7.32e-01

Pos logit contributions
 polar+0.000
 ranger+0.000
 gn+0.000
 tow+0.000
 chimpan+0.000
Neg logit contributions
ivated-0.000
our-0.000
icker-0.000
oney-0.000
nam-0.000
Token because
Token ID780
Feature activation-3.07e-01

Pos logit contributions
 polar+0.019
 tow+0.018
 ranger+0.018
 chimpan+0.018
 gn+0.018
Neg logit contributions
ivated-0.016
nam-0.016
 tant-0.015
our-0.015
 hey-0.015
Token you
Token ID345
Feature activation-4.71e-02

Pos logit contributions
ivated+0.006
nam+0.005
our+0.005
icker+0.005
 hey+0.005
Neg logit contributions
 polar-0.010
 ranger-0.009
 gn-0.009
 tow-0.009
 chimpan-0.009
Token have
Token ID423
Feature activation-1.10e-01

Pos logit contributions
ivated+0.001
icker+0.001
our+0.001
nam+0.001
 hey+0.001
Neg logit contributions
 polar-0.001
 ranger-0.001
 tow-0.001
 gn-0.001
 chimpan-0.001
Token wonderful
Token ID7932
Feature activation-7.20e-01

Pos logit contributions
ivated+0.003
nam+0.003
 Def+0.002
our+0.002
 tant+0.002
Neg logit contributions
 polar-0.003
 ranger-0.003
 tow-0.003
 gn-0.002
 chimpan-0.002
Token imag
Token ID3590
Feature activation-2.52e+00

Pos logit contributions
our+0.014
 tant+0.014
nam+0.013
bs+0.012
 hey+0.012
Neg logit contributions
 ranger-0.021
 polar-0.021
 tow-0.021
 chimpan-0.020
glers-0.020
Tokeninations
Token ID7352
Feature activation+3.40e-01

Pos logit contributions
ivated+0.053
icker+0.049
our+0.049
nam+0.048
 hey+0.048
Neg logit contributions
 polar-0.072
 ranger-0.068
 tow-0.066
 gn-0.065
 chimpan-0.063
Token."
Token ID526
Feature activation-4.79e-01

Pos logit contributions
 polar+0.010
 chimpan+0.009
 tow+0.008
 ranger+0.008
 gn+0.008
Neg logit contributions
our-0.008
bs-0.007
ivated-0.007
 hey-0.007
nam-0.007
Token The
Token ID383
Feature activation-2.57e-02

Pos logit contributions
ivated+0.013
arre+0.013
 tant+0.013
obb+0.013
our+0.012
Neg logit contributions
 polar-0.011
 ranger-0.010
 tow-0.010
 gn-0.010
 chimpan-0.009
Token boy
Token ID2933
Feature activation-1.53e-01

Pos logit contributions
 tant+0.000
icker+0.000
nam+0.000
ivated+0.000
 hey+0.000
Neg logit contributions
 polar-0.001
 gn-0.001
 ranger-0.001
 chimpan-0.001
 tow-0.001
Token and
Token ID290
Feature activation-1.36e+00

Pos logit contributions
our+0.004
ivated+0.003
 Def+0.003
arre+0.003
 ent+0.003
Neg logit contributions
 polar-0.004
 tow-0.004
 ranger-0.003
 chimpan-0.003
 gn-0.003
Token of
Token ID286
Feature activation-2.58e-01

Pos logit contributions
ivated+0.002
icker+0.002
 tant+0.002
our+0.002
 hey+0.002
Neg logit contributions
 polar-0.002
 ranger-0.002
 gn-0.002
 tow-0.002
 chimpan-0.002
Token the
Token ID262
Feature activation-1.17e-01

Pos logit contributions
ivated+0.006
nam+0.006
 tant+0.006
 Def+0.006
 hey+0.006
Neg logit contributions
 ranger-0.006
 polar-0.006
 gn-0.006
 chimpan-0.005
 tow-0.005
Token animals
Token ID4695
Feature activation-3.62e-01

Pos logit contributions
ivated+0.003
our+0.003
icker+0.003
 hey+0.003
nam+0.003
Neg logit contributions
 polar-0.003
 ranger-0.003
 tow-0.003
 gn-0.003
 chimpan-0.003
Token in
Token ID287
Feature activation-3.07e-01

Pos logit contributions
ivated+0.009
our+0.008
icker+0.008
 hey+0.008
nam+0.008
Neg logit contributions
 polar-0.010
 ranger-0.009
 tow-0.009
 gn-0.009
 chimpan-0.008
Token the
Token ID262
Feature activation-3.86e-01

Pos logit contributions
 tant+0.006
 Many+0.005
 Def+0.005
 anyone+0.005
ivated+0.005
Neg logit contributions
 ranger-0.009
 gn-0.009
glers-0.008
 bisc-0.008
 chimpan-0.008
Token me
Token ID502
Feature activation-2.47e+00

Pos logit contributions
ivated+0.006
our+0.006
icker+0.006
 hey+0.006
 Def+0.006
Neg logit contributions
 polar-0.013
 ranger-0.012
 tow-0.012
 gn-0.012
 chimpan-0.011
Tokenadow
Token ID4584
Feature activation-6.16e-01

Pos logit contributions
ivated+0.037
our+0.037
icker+0.036
 hey+0.033
arre+0.033
Neg logit contributions
 polar-0.086
 ranger-0.081
 tow-0.080
 gn-0.078
 chimpan-0.078
Token stopped
Token ID5025
Feature activation+1.89e-01

Pos logit contributions
our+0.015
icker+0.015
ivated+0.015
 hey+0.015
arre+0.015
Neg logit contributions
 polar-0.014
 tow-0.013
 ranger-0.013
 chimpan-0.013
 gn-0.013
Token and
Token ID290
Feature activation+4.13e-01

Pos logit contributions
 polar+0.004
 ranger+0.004
 tow+0.004
 gn+0.004
 chimpan+0.004
Neg logit contributions
ivated-0.005
our-0.005
icker-0.005
 hey-0.005
arre-0.005
Token watched
Token ID7342
Feature activation+6.00e-02

Pos logit contributions
 polar+0.010
 ranger+0.009
 tow+0.009
 gn+0.008
 chimpan+0.008
Neg logit contributions
ivated-0.011
our-0.010
icker-0.010
 hey-0.010
nam-0.010
Token.
Token ID13
Feature activation+2.83e-01

Pos logit contributions
 polar+0.002
 ranger+0.002
 gn+0.002
 tow+0.002
 chimpan+0.002
Neg logit contributions
ivated-0.001
icker-0.001
our-0.001
 hey-0.001
nam-0.001
Token a
Token ID257
Feature activation-8.81e-02

Pos logit contributions
 Def+0.004
nam+0.004
 ent+0.004
arre+0.004
ivated+0.004
Neg logit contributions
 polar-0.007
 ranger-0.006
 gn-0.006
 tow-0.006
 chimpan-0.006
Token great
Token ID1049
Feature activation-8.57e-01

Pos logit contributions
 tant+0.002
 hey+0.002
Finally+0.002
nam+0.002
icker+0.002
Neg logit contributions
 polar-0.003
glers-0.002
 ranger-0.002
 chimpan-0.002
falls-0.002
Token time
Token ID640
Feature activation+5.78e-01

Pos logit contributions
our+0.015
icker+0.015
 tant+0.015
 Def+0.014
arre+0.014
Neg logit contributions
 polar-0.027
 ranger-0.025
glers-0.025
 chimpan-0.024
 tow-0.024
Token using
Token ID1262
Feature activation-7.45e-02

Pos logit contributions
 polar+0.017
 ranger+0.017
 tow+0.016
 chimpan+0.016
 gn+0.016
Neg logit contributions
our-0.011
bs-0.011
ivated-0.011
 ent-0.010
osing-0.010
Token their
Token ID511
Feature activation+3.57e-01

Pos logit contributions
bs+0.001
nam+0.001
 tant+0.001
 unnecessary+0.001
our+0.001
Neg logit contributions
 polar-0.002
 ranger-0.002
 gn-0.002
 chimpan-0.002
glers-0.002
Token imag
Token ID3590
Feature activation-2.46e+00

Pos logit contributions
 polar+0.010
 ranger+0.009
 tow+0.009
 gn+0.009
 chimpan+0.008
Neg logit contributions
ivated-0.008
our-0.008
icker-0.008
nam-0.007
 tant-0.007
Tokeninations
Token ID7352
Feature activation+2.30e-01

Pos logit contributions
ivated+0.052
icker+0.048
our+0.048
nam+0.048
 hey+0.047
Neg logit contributions
 polar-0.070
 ranger-0.066
 tow-0.064
 gn-0.064
 chimpan-0.062
Token.
Token ID13
Feature activation-2.28e-01

Pos logit contributions
 polar+0.006
 chimpan+0.005
 tow+0.005
 gn+0.005
 ranger+0.005
Neg logit contributions
our-0.006
ivated-0.005
bs-0.005
 tant-0.005
arre-0.005
Token<|endoftext|>
Token ID50256
Feature activation-1.03e-01

Pos logit contributions
ivated+0.004
 Def+0.004
icker+0.004
arre+0.004
our+0.004
Neg logit contributions
 polar-0.007
 ranger-0.007
 gn-0.007
 tow-0.006
 chimpan-0.006
TokenOnce
Token ID7454
Feature activation-9.87e-02

Pos logit contributions
 Def+0.001
 Ow+0.001
upon+0.001
 Blood+0.001
 Finally+0.001
Neg logit contributions
 polar-0.004
 ranger-0.004
 gn-0.004
 chimpan-0.004
 tow-0.003
Token upon
Token ID2402
Feature activation-6.12e-01

Pos logit contributions
ivated+0.002
 hey+0.002
nam+0.002
arre+0.002
ivery+0.002
Neg logit contributions
 polar-0.002
 tow-0.002
 ranger-0.002
 gn-0.002
!-0.002
Token new
Token ID649
Feature activation-4.56e-01

Pos logit contributions
ivated+0.000
icker+0.000
our+0.000
 hey+0.000
 Def+0.000
Neg logit contributions
 polar-0.000
 ranger-0.000
 gn-0.000
 tow-0.000
 chimpan-0.000
Token world
Token ID995
Feature activation-3.81e-02

Pos logit contributions
ivated+0.009
our+0.009
 ent+0.009
 Def+0.009
 tant+0.009
Neg logit contributions
 polar-0.013
 ranger-0.012
 gn-0.012
 tow-0.011
 chimpan-0.011
Token.
Token ID13
Feature activation+1.67e-01

Pos logit contributions
ivated+0.001
our+0.001
bs+0.001
osing+0.001
 ent+0.001
Neg logit contributions
 polar-0.001
 tow-0.001
 gn-0.001
 chimpan-0.001
 bisc-0.001
Token Using
Token ID8554
Feature activation+3.43e-01

Pos logit contributions
 polar+0.005
 ranger+0.005
 gn+0.004
 tow+0.004
 chimpan+0.004
Neg logit contributions
ivated-0.003
icker-0.003
 Def-0.003
arre-0.003
our-0.003
Token their
Token ID511
Feature activation+7.71e-02

Pos logit contributions
 polar+0.010
 ranger+0.010
 gn+0.010
 bisc+0.009
 chimpan+0.009
Neg logit contributions
nam-0.007
 tant-0.007
ivated-0.006
bs-0.006
 Def-0.006
Token imag
Token ID3590
Feature activation-2.44e+00

Pos logit contributions
 polar+0.002
 ranger+0.002
 tow+0.002
 gn+0.002
 chimpan+0.002
Neg logit contributions
ivated-0.002
icker-0.002
our-0.002
nam-0.002
 hey-0.002
Tokeninations
Token ID7352
Feature activation+2.63e-01

Pos logit contributions
ivated+0.051
icker+0.048
our+0.048
nam+0.046
 hey+0.046
Neg logit contributions
 polar-0.070
 ranger-0.066
 tow-0.064
 gn-0.064
 chimpan-0.062
Token,
Token ID11
Feature activation+4.62e-01

Pos logit contributions
 polar+0.007
 ranger+0.006
 chimpan+0.006
 gn+0.006
 tow+0.006
Neg logit contributions
our-0.006
bs-0.006
ivated-0.006
 Def-0.006
 ent-0.006
Token they
Token ID484
Feature activation+3.52e-01

Pos logit contributions
 polar+0.013
 ranger+0.012
 tow+0.011
 gn+0.011
 chimpan+0.011
Neg logit contributions
ivated-0.010
nam-0.010
bs-0.009
 hey-0.009
 Def-0.009
Token played
Token ID2826
Feature activation+3.19e-01

Pos logit contributions
 polar+0.009
 ranger+0.009
 chimpan+0.008
 gn+0.008
 tow+0.008
Neg logit contributions
ivated-0.008
our-0.008
nam-0.007
icker-0.007
 ent-0.007
Token with
Token ID351
Feature activation-1.73e-01

Pos logit contributions
 polar+0.010
 tow+0.009
 ranger+0.009
 gn+0.009
 chimpan+0.008
Neg logit contributions
ivated-0.006
icker-0.005
Eventually-0.005
 ent-0.005
 Def-0.005
Token.
Token ID13
Feature activation+2.25e-01

Pos logit contributions
ivated+0.022
our+0.021
icker+0.021
nam+0.021
 hey+0.020
Neg logit contributions
 polar-0.018
 ranger-0.017
 tow-0.016
 gn-0.016
 chimpan-0.015
Token She
Token ID1375
Feature activation+3.90e-02

Pos logit contributions
 polar+0.007
 ranger+0.006
 tow+0.006
 gn+0.006
 chimpan+0.006
Neg logit contributions
ivated-0.005
icker-0.004
 hey-0.004
our-0.004
 tant-0.004
Token lived
Token ID5615
Feature activation-1.45e-01

Pos logit contributions
 polar+0.001
 ranger+0.001
 tow+0.001
 gn+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.001
our-0.001
icker-0.001
nam-0.001
 Def-0.001
Token in
Token ID287
Feature activation-6.46e-01

Pos logit contributions
ivated+0.004
icker+0.003
our+0.003
nam+0.003
 hey+0.003
Neg logit contributions
 polar-0.004
 ranger-0.003
 tow-0.003
 gn-0.003
 chimpan-0.003
Token a
Token ID257
Feature activation-3.19e-01

Pos logit contributions
ivated+0.016
nam+0.016
 Def+0.015
icker+0.015
 hey+0.015
Neg logit contributions
 polar-0.015
 ranger-0.015
 tow-0.013
 gn-0.013
 chimpan-0.013
Token me
Token ID502
Feature activation-2.43e+00

Pos logit contributions
our+0.010
ivated+0.010
 hey+0.010
osing+0.010
nam+0.010
Neg logit contributions
 polar-0.006
 ranger-0.006
 tow-0.005
 gn-0.005
 waterfall-0.005
Tokenadow
Token ID4584
Feature activation-7.80e-01

Pos logit contributions
ivated+0.050
nam+0.046
 hey+0.046
 tant+0.046
icker+0.045
Neg logit contributions
 polar-0.071
 ranger-0.067
 gn-0.065
 tow-0.065
 chimpan-0.062
Token near
Token ID1474
Feature activation-2.62e-01

Pos logit contributions
ivated+0.022
icker+0.021
our+0.021
nam+0.020
 Def+0.020
Neg logit contributions
 polar-0.018
 ranger-0.016
 tow-0.016
 chimpan-0.015
 gn-0.015
Token a
Token ID257
Feature activation+2.15e-01

Pos logit contributions
ivated+0.007
nam+0.007
icker+0.007
 Def+0.007
our+0.006
Neg logit contributions
 polar-0.006
 ranger-0.006
 tow-0.005
 gn-0.005
 chimpan-0.005
Token tall
Token ID7331
Feature activation-4.17e-01

Pos logit contributions
 polar+0.005
 ranger+0.004
 gn+0.004
 tow+0.004
 chimpan+0.004
Neg logit contributions
ivated-0.006
our-0.006
 tant-0.006
nam-0.006
icker-0.006
Token mountain
Token ID8598
Feature activation-9.01e-01

Pos logit contributions
ivated+0.010
our+0.009
cient+0.009
icker+0.009
 tant+0.009
Neg logit contributions
 polar-0.010
 tow-0.010
 ranger-0.009
 chimpan-0.009
 gn-0.009
Token He
Token ID679
Feature activation+4.52e-01

Pos logit contributions
 polar+0.004
 ranger+0.004
 tow+0.004
 gn+0.004
 chimpan+0.003
Neg logit contributions
ivated-0.003
our-0.003
icker-0.003
nam-0.003
 Def-0.003
Token lived
Token ID5615
Feature activation-2.46e-01

Pos logit contributions
 tow+0.014
 polar+0.013
 ranger+0.013
glers+0.012
 amusement+0.012
Neg logit contributions
 Blood-0.007
 Amid-0.007
ivated-0.007
 Def-0.007
cient-0.007
Token in
Token ID287
Feature activation-8.51e-01

Pos logit contributions
ivated+0.006
our+0.006
icker+0.006
 hey+0.006
 tant+0.006
Neg logit contributions
 polar-0.006
 ranger-0.006
 gn-0.005
 tow-0.005
 chimpan-0.005
Token a
Token ID257
Feature activation-4.39e-01

Pos logit contributions
ivated+0.021
 Def+0.021
nam+0.021
 hey+0.020
icker+0.020
Neg logit contributions
 polar-0.019
 ranger-0.019
glers-0.017
 gn-0.017
 tow-0.017
Token sunny
Token ID27737
Feature activation-1.28e+00

Pos logit contributions
ivated+0.013
our+0.013
 tant+0.012
 hey+0.012
nam+0.012
Neg logit contributions
 polar-0.010
 ranger-0.009
 gn-0.009
 tow-0.009
 chimpan-0.008
Token me
Token ID502
Feature activation-2.43e+00

Pos logit contributions
icker+0.024
ivated+0.023
 Def+0.023
arre+0.022
our+0.022
Neg logit contributions
 polar-0.034
 ranger-0.033
 chimpan-0.033
 gn-0.032
 tow-0.031
Tokenadow
Token ID4584
Feature activation-7.99e-01

Pos logit contributions
ivated+0.040
our+0.038
icker+0.038
 Def+0.036
 hey+0.036
Neg logit contributions
 polar-0.080
 ranger-0.076
 tow-0.074
 gn-0.073
 chimpan-0.072
Token near
Token ID1474
Feature activation-3.72e-01

Pos logit contributions
ivated+0.021
icker+0.021
our+0.020
 Blood+0.019
nam+0.019
Neg logit contributions
 polar-0.018
 tow-0.017
 ranger-0.016
 chimpan-0.016
 gn-0.015
Token a
Token ID257
Feature activation+2.20e-01

Pos logit contributions
 Def+0.009
nam+0.009
ivated+0.009
icker+0.008
 Ow+0.008
Neg logit contributions
 ranger-0.009
 polar-0.009
 gn-0.008
 tow-0.008
glers-0.008
Token large
Token ID1588
Feature activation-6.83e-02

Pos logit contributions
 polar+0.005
 ranger+0.004
 gn+0.004
 tow+0.004
 chimpan+0.004
Neg logit contributions
ivated-0.006
our-0.006
 tant-0.006
nam-0.006
icker-0.006
Token bucket
Token ID19236
Feature activation-1.13e+00

Pos logit contributions
cient+0.001
ivated+0.001
our+0.001
icker+0.001
nam+0.001
Neg logit contributions
 polar-0.002
 tow-0.002
 ranger-0.002
 chimpan-0.002
 gn-0.002
Token he
Token ID339
Feature activation+5.38e-01

Pos logit contributions
 tant+0.004
 hey+0.004
icker+0.004
arre+0.004
 Def+0.004
Neg logit contributions
 polar-0.006
glers-0.005
 ranger-0.005
 chimpan-0.005
 tow-0.005
Token could
Token ID714
Feature activation+5.48e-01

Pos logit contributions
 polar+0.013
 tow+0.012
 ranger+0.011
 gn+0.011
 chimpan+0.011
Neg logit contributions
ivated-0.014
our-0.013
 hey-0.013
 Def-0.013
osing-0.013
Token be
Token ID307
Feature activation+6.19e-02

Pos logit contributions
 polar+0.015
 ranger+0.014
 chimpan+0.013
 gn+0.013
 tow+0.013
Neg logit contributions
ivated-0.013
our-0.012
 hey-0.012
icker-0.012
 Def-0.011
Token and
Token ID290
Feature activation+6.66e-01

Pos logit contributions
 polar+0.002
 ranger+0.002
 chimpan+0.002
 gn+0.002
 tow+0.002
Neg logit contributions
ivated-0.001
arre-0.001
icker-0.001
 hey-0.001
 tant-0.001
Token never
Token ID1239
Feature activation-2.34e-01

Pos logit contributions
 polar+0.017
 ranger+0.016
 chimpan+0.015
 tow+0.015
 gn+0.015
Neg logit contributions
ivated-0.015
nam-0.015
 hey-0.015
our-0.015
 Def-0.014
Token mis
Token ID2984
Feature activation-2.42e+00

Pos logit contributions
ivated+0.005
our+0.005
icker+0.005
nam+0.005
 hey+0.005
Neg logit contributions
 polar-0.007
 ranger-0.006
 tow-0.006
 gn-0.006
 chimpan-0.006
Tokenbeh
Token ID20709
Feature activation+9.17e-02

Pos logit contributions
obb+0.055
oney+0.054
icker+0.052
ivated+0.052
 Him+0.052
Neg logit contributions
 polar-0.059
 ranger-0.055
 tow-0.053
 gn-0.051
 chimpan-0.051
Tokenaved
Token ID9586
Feature activation-7.00e-01

Pos logit contributions
 polar+0.003
 ranger+0.003
 tow+0.003
 gn+0.003
 chimpan+0.003
Neg logit contributions
ivated-0.002
icker-0.001
our-0.001
nam-0.001
 hey-0.001
Token.
Token ID13
Feature activation+2.62e-01

Pos logit contributions
 tant+0.015
ivated+0.015
arre+0.014
 hey+0.014
 Def+0.013
Neg logit contributions
 polar-0.020
 chimpan-0.018
 tow-0.018
 bisc-0.017
 ranger-0.017
Token<|endoftext|>
Token ID50256
Feature activation-5.30e-02

Pos logit contributions
 polar+0.007
 ranger+0.006
 tow+0.006
 gn+0.006
 chimpan+0.006
Neg logit contributions
ivated-0.007
our-0.006
icker-0.006
nam-0.006
 hey-0.006
TokenOnce
Token ID7454
Feature activation-1.77e-01

Pos logit contributions
 Def+0.001
 Ow+0.001
upon+0.001
ivated+0.001
 Finally+0.001
Neg logit contributions
 polar-0.002
 ranger-0.002
 gn-0.002
 chimpan-0.002
 tow-0.002
Token.
Token ID13
Feature activation-1.26e-01

Pos logit contributions
bs+0.004
our+0.004
 else+0.004
she+0.004
icker+0.004
Neg logit contributions
 polar-0.007
 gn-0.006
 chimpan-0.006
 grizz-0.005
 tow-0.005
Token They
Token ID1119
Feature activation+5.60e-01

Pos logit contributions
ivated+0.003
 Def+0.002
icker+0.002
our+0.002
arre+0.002
Neg logit contributions
 polar-0.004
 gn-0.003
 ranger-0.003
 tow-0.003
 chimpan-0.003
Token had
Token ID550
Feature activation+1.76e-02

Pos logit contributions
 polar+0.016
 chimpan+0.015
 ranger+0.015
 gn+0.015
 tow+0.014
Neg logit contributions
ivated-0.011
bs-0.010
 ent-0.010
nam-0.010
iable-0.010
Token used
Token ID973
Feature activation+4.22e-01

Pos logit contributions
 polar+0.001
 gn+0.001
 ranger+0.001
 chimpan+0.000
glers+0.000
Neg logit contributions
arre-0.000
 Def-0.000
Eventually-0.000
 ent-0.000
 both-0.000
Token their
Token ID511
Feature activation+7.92e-01

Pos logit contributions
 polar+0.013
 gn+0.011
 chimpan+0.011
 ranger+0.011
glers+0.010
Neg logit contributions
 tant-0.009
nam-0.009
bs-0.008
ivated-0.008
 Def-0.008
Token imag
Token ID3590
Feature activation-2.41e+00

Pos logit contributions
 polar+0.019
 ranger+0.017
 tow+0.017
 gn+0.017
 chimpan+0.016
Neg logit contributions
ivated-0.021
icker-0.020
our-0.020
nam-0.019
 hey-0.019
Tokeninations
Token ID7352
Feature activation+1.51e-01

Pos logit contributions
ivated+0.044
icker+0.042
our+0.041
arre+0.039
 tant+0.039
Neg logit contributions
 polar-0.078
 ranger-0.075
 gn-0.072
 tow-0.071
 chimpan-0.070
Token and
Token ID290
Feature activation+3.55e-01

Pos logit contributions
 polar+0.004
 chimpan+0.004
 gn+0.004
 tow+0.004
 ranger+0.004
Neg logit contributions
ivated-0.003
arre-0.003
our-0.003
 tant-0.003
bs-0.003
Token their
Token ID511
Feature activation+1.03e+00

Pos logit contributions
 polar+0.010
 gn+0.009
 chimpan+0.009
 ranger+0.009
 tow+0.009
Neg logit contributions
bs-0.007
nam-0.007
arre-0.007
 hey-0.006
 tant-0.006
Token net
Token ID2010
Feature activation-9.42e-01

Pos logit contributions
 polar+0.029
 gn+0.026
 ranger+0.025
 tow+0.025
 chimpan+0.024
Neg logit contributions
ivated-0.023
icker-0.022
our-0.022
nam-0.021
 tant-0.021
Token to
Token ID284
Feature activation+6.77e-02

Pos logit contributions
bs+0.020
onel+0.019
icker+0.019
ivated+0.019
our+0.019
Neg logit contributions
 polar-0.026
 chimpan-0.023
 gn-0.021
 tow-0.021
 amusement-0.021
Token of
Token ID286
Feature activation+2.39e-02

Pos logit contributions
ivated+0.007
onel+0.007
 ent+0.007
bs+0.007
oney+0.007
Neg logit contributions
 polar-0.009
 gn-0.008
 ranger-0.007
 waterfall-0.007
 tow-0.007
Token oranges
Token ID48389
Feature activation-4.53e-01

Pos logit contributions
 polar+0.001
 ranger+0.001
 gn+0.001
 chimpan+0.001
 tow+0.001
Neg logit contributions
nam-0.000
ivated-0.000
 Def-0.000
 tant-0.000
 hey-0.000
Token in
Token ID287
Feature activation-4.43e-01

Pos logit contributions
our+0.011
ivated+0.010
iable+0.010
osing+0.010
onel+0.010
Neg logit contributions
 polar-0.012
 tow-0.011
 chimpan-0.010
 gn-0.010
 ranger-0.009
Token the
Token ID262
Feature activation-5.04e-01

Pos logit contributions
nam+0.010
ivated+0.010
 tant+0.010
 Def+0.009
icker+0.009
Neg logit contributions
 polar-0.012
 ranger-0.011
 gn-0.011
 chimpan-0.011
 bisc-0.010
Token whole
Token ID2187
Feature activation-7.79e-01

Pos logit contributions
ivated+0.010
icker+0.010
our+0.009
nam+0.009
arre+0.009
Neg logit contributions
 polar-0.015
 ranger-0.014
 tow-0.013
 gn-0.013
 chimpan-0.013
Token me
Token ID502
Feature activation-2.41e+00

Pos logit contributions
arre+0.013
ivated+0.013
 ent+0.012
 Def+0.012
urious+0.012
Neg logit contributions
 polar-0.024
 ranger-0.023
 gn-0.022
 chimpan-0.022
 tow-0.021
Tokenadow
Token ID4584
Feature activation-4.49e-01

Pos logit contributions
our+0.035
ivated+0.034
icker+0.033
oney+0.031
arre+0.030
Neg logit contributions
 polar-0.087
 ranger-0.082
 tow-0.080
 chimpan-0.079
 gn-0.079
Token!
Token ID0
Feature activation-7.89e-02

Pos logit contributions
our+0.011
ivated+0.011
icker+0.011
 ent+0.011
oney+0.010
Neg logit contributions
 polar-0.011
 chimpan-0.010
 tow-0.010
 gn-0.009
 ranger-0.009
Token<|endoftext|>
Token ID50256
Feature activation+4.45e-02

Pos logit contributions
ivated+0.002
icker+0.001
our+0.001
 Def+0.001
nam+0.001
Neg logit contributions
 polar-0.002
 ranger-0.002
 gn-0.002
 tow-0.002
 chimpan-0.002
TokenBob
Token ID18861
Feature activation+5.44e-02

Pos logit contributions
 polar+0.002
 ranger+0.002
 chimpan+0.002
 gn+0.002
 tow+0.002
Neg logit contributions
 Def-0.000
upon-0.000
 Ow-0.000
ivated-0.000
our-0.000
Token was
Token ID373
Feature activation-2.04e-01

Pos logit contributions
 ranger+0.001
 chimpan+0.001
 tow+0.001
 polar+0.001
 waterfall+0.001
Neg logit contributions
our-0.001
arre-0.001
bs-0.001
cient-0.001
oney-0.001
Token bright
Token ID6016
Feature activation-4.45e-01

Pos logit contributions
ivated+0.001
icker+0.001
nam+0.001
our+0.001
 hey+0.001
Neg logit contributions
 polar-0.002
 ranger-0.002
 tow-0.002
 gn-0.002
 chimpan-0.002
Token blue
Token ID4171
Feature activation-9.71e-02

Pos logit contributions
 tant+0.008
icker+0.008
our+0.008
ivated+0.008
 miserable+0.008
Neg logit contributions
 ranger-0.012
 chimpan-0.011
 tow-0.011
 gn-0.011
glers-0.011
Tokenberry
Token ID8396
Feature activation-1.04e+00

Pos logit contributions
our+0.002
icker+0.002
cient+0.002
 tant+0.002
 Ow+0.002
Neg logit contributions
 ranger-0.002
 polar-0.002
 tow-0.002
 gn-0.002
 chimpan-0.002
Token in
Token ID287
Feature activation-4.39e-01

Pos logit contributions
icker+0.027
cient+0.026
our+0.025
nam+0.025
ivated+0.025
Neg logit contributions
 polar-0.021
 tow-0.021
 ranger-0.020
 chimpan-0.020
 gn-0.019
Token a
Token ID257
Feature activation-2.89e-01

Pos logit contributions
nam+0.011
ivated+0.011
 Def+0.011
 Blood+0.010
 hey+0.010
Neg logit contributions
 polar-0.010
 ranger-0.010
 gn-0.009
glers-0.009
 tow-0.009
Token me
Token ID502
Feature activation-2.41e+00

Pos logit contributions
ivated+0.008
our+0.007
icker+0.007
 hey+0.007
nam+0.007
Neg logit contributions
 polar-0.007
 ranger-0.006
 gn-0.006
 tow-0.006
 chimpan-0.006
Tokenadow
Token ID4584
Feature activation-6.32e-01

Pos logit contributions
ivated+0.041
our+0.039
icker+0.039
 Def+0.036
 hey+0.036
Neg logit contributions
 polar-0.079
 ranger-0.075
 tow-0.073
 gn-0.072
 chimpan-0.071
Token.
Token ID13
Feature activation+1.63e-01

Pos logit contributions
icker+0.016
our+0.016
ivated+0.015
 Blood+0.015
oney+0.014
Neg logit contributions
 polar-0.015
 tow-0.014
 chimpan-0.014
 ranger-0.013
 amusement-0.013
Token One
Token ID1881
Feature activation+1.42e-01

Pos logit contributions
 polar+0.005
 ranger+0.005
 gn+0.005
 tow+0.005
 chimpan+0.005
Neg logit contributions
ivated-0.003
 Def-0.002
our-0.002
icker-0.002
nam-0.002
Token day
Token ID1110
Feature activation+1.25e-01

Pos logit contributions
 polar+0.004
 ranger+0.004
 gn+0.004
 tow+0.004
 chimpan+0.004
Neg logit contributions
icker-0.003
ivated-0.003
our-0.002
 Def-0.002
oney-0.002
Token,
Token ID11
Feature activation-2.57e-01

Pos logit contributions
 polar+0.003
 ranger+0.002
 tow+0.002
 gn+0.002
 chimpan+0.002
Neg logit contributions
ivated-0.004
our-0.004
icker-0.004
nam-0.003
 Def-0.003
Token a
Token ID257
Feature activation+5.28e-03

Pos logit contributions
nam+0.016
ivated+0.016
 Def+0.015
 hey+0.015
cient+0.015
Neg logit contributions
 polar-0.016
 ranger-0.016
 tow-0.015
 gn-0.015
 chimpan-0.014
Token rabbit
Token ID22746
Feature activation+2.38e-01

Pos logit contributions
 polar+0.000
 ranger+0.000
 tow+0.000
 gn+0.000
 chimpan+0.000
Neg logit contributions
ivated-0.000
icker-0.000
nam-0.000
 hey-0.000
our-0.000
Token lived
Token ID5615
Feature activation-2.46e-01

Pos logit contributions
 ranger+0.005
 polar+0.005
 gn+0.004
 chimpan+0.004
 tow+0.004
Neg logit contributions
cient-0.006
our-0.006
 hey-0.006
icker-0.006
ivated-0.006
Token in
Token ID287
Feature activation-6.03e-01

Pos logit contributions
ivated+0.006
icker+0.005
our+0.005
nam+0.005
 Def+0.005
Neg logit contributions
 polar-0.006
 ranger-0.006
 gn-0.006
 tow-0.006
 chimpan-0.006
Token a
Token ID257
Feature activation-2.25e-01

Pos logit contributions
ivated+0.011
 Many+0.010
 Def+0.010
nam+0.010
 Blood+0.010
Neg logit contributions
 ranger-0.018
glers-0.017
 polar-0.017
falls-0.016
 gn-0.016
Token me
Token ID502
Feature activation-2.37e+00

Pos logit contributions
ivated+0.006
icker+0.005
our+0.005
nam+0.005
 Def+0.005
Neg logit contributions
 polar-0.006
 ranger-0.005
 gn-0.005
 tow-0.005
 chimpan-0.005
Tokenadow
Token ID4584
Feature activation-7.47e-01

Pos logit contributions
icker+0.034
our+0.033
ivated+0.033
bs+0.030
oney+0.030
Neg logit contributions
 polar-0.082
 ranger-0.079
 gn-0.076
 tow-0.076
 chimpan-0.075
Token.
Token ID13
Feature activation+2.85e-01

Pos logit contributions
icker+0.021
ivated+0.021
our+0.020
nam+0.019
 Blood+0.019
Neg logit contributions
 polar-0.016
 ranger-0.014
 tow-0.014
 chimpan-0.014
 gn-0.014
Token They
Token ID1119
Feature activation+4.47e-01

Pos logit contributions
 polar+0.009
 ranger+0.008
 gn+0.008
 tow+0.008
 chimpan+0.008
Neg logit contributions
ivated-0.005
 Def-0.005
icker-0.005
our-0.004
nam-0.004
Token were
Token ID547
Feature activation-1.19e-01

Pos logit contributions
 polar+0.014
 ranger+0.013
 tow+0.013
 gn+0.012
 chimpan+0.012
Neg logit contributions
ivated-0.009
nam-0.008
icker-0.008
our-0.008
cient-0.007
Token good
Token ID922
Feature activation-4.76e-02

Pos logit contributions
ivated+0.002
nam+0.002
 Def+0.002
icker+0.002
 ent+0.002
Neg logit contributions
 ranger-0.003
 polar-0.003
 gn-0.003
 tow-0.003
 chimpan-0.003
Token warm
Token ID5814
Feature activation-2.57e-01

Pos logit contributions
nam+0.011
ivated+0.009
 Blood+0.009
 ent+0.009
 Def+0.008
Neg logit contributions
 polar-0.012
 tow-0.012
 ranger-0.012
 chimpan-0.011
 gn-0.011
Token,
Token ID11
Feature activation+4.51e-01

Pos logit contributions
our+0.006
ivated+0.006
icker+0.006
nam+0.005
 spine+0.005
Neg logit contributions
 polar-0.006
 tow-0.006
 gn-0.006
 chimpan-0.006
 ranger-0.006
Token and
Token ID290
Feature activation-1.50e-01

Pos logit contributions
 polar+0.012
 tow+0.012
 ranger+0.011
 chimpan+0.011
 gn+0.010
Neg logit contributions
ivated-0.010
our-0.009
nam-0.009
 ent-0.009
 Def-0.009
Token the
Token ID262
Feature activation-3.23e-01

Pos logit contributions
ivated+0.004
icker+0.004
our+0.004
 tant+0.004
arre+0.004
Neg logit contributions
 polar-0.003
 ranger-0.003
 gn-0.003
 tow-0.003
 chimpan-0.003
Token shore
Token ID15191
Feature activation-1.49e+00

Pos logit contributions
 hey+0.006
nam+0.006
ivated+0.006
icker+0.006
 tant+0.006
Neg logit contributions
 polar-0.008
 ranger-0.008
 tow-0.008
 gn-0.008
 chimpan-0.008
Tokenline
Token ID1370
Feature activation-2.37e+00

Pos logit contributions
our+0.029
icker+0.026
outed+0.025
bs+0.025
 bored+0.024
Neg logit contributions
 polar-0.042
 tow-0.040
 amusement-0.038
 grizz-0.037
 chimpan-0.037
Token was
Token ID373
Feature activation-1.40e-01

Pos logit contributions
ivated+0.063
our+0.062
icker+0.062
 Blood+0.060
 ent+0.060
Neg logit contributions
 polar-0.054
 ranger-0.047
 chimpan-0.047
 gn-0.045
 tow-0.045
Token ancient
Token ID6156
Feature activation-5.98e-01

Pos logit contributions
nam+0.003
ivated+0.003
 ent+0.002
 miserable+0.002
 bored+0.002
Neg logit contributions
 ranger-0.004
 chimpan-0.004
 polar-0.004
 gn-0.004
 tow-0.004
Token.
Token ID13
Feature activation+1.62e-01

Pos logit contributions
 bored+0.008
 at+0.008
 miserable+0.008
 favorite+0.007
our+0.007
Neg logit contributions
 tow-0.021
uit-0.018
 polar-0.018
 chimpan-0.018
Kim-0.018
Token
Token ID220
Feature activation-6.87e-01

Pos logit contributions
 ranger+0.003
 tow+0.002
 gn+0.002
 polar+0.002
 chimpan+0.002
Neg logit contributions
 tant-0.005
cient-0.005
unct-0.005
our-0.005
iable-0.005
Token
Token ID198
Feature activation+4.93e-01

Pos logit contributions
ivated+0.022
unct+0.022
nam+0.022
 tant+0.022
 hey+0.021
Neg logit contributions
 tow-0.011
 ranger-0.011
 polar-0.010
!-0.010
 gn-0.009
Token rabbit
Token ID22746
Feature activation-2.52e-02

Pos logit contributions
icker+0.010
our+0.010
cient+0.010
 tant+0.010
oney+0.009
Neg logit contributions
 ranger-0.012
 tow-0.012
 chimpan-0.011
 polar-0.011
 gn-0.011
Token that
Token ID326
Feature activation+2.31e-01

Pos logit contributions
cient+0.001
icker+0.001
our+0.001
bs+0.001
nam+0.001
Neg logit contributions
 tow-0.001
 chimpan-0.001
 polar-0.001
 amusement-0.001
 ranger-0.001
Token lived
Token ID5615
Feature activation-7.21e-03

Pos logit contributions
 polar+0.006
 ranger+0.006
 tow+0.006
 chimpan+0.005
 gn+0.005
Neg logit contributions
ivated-0.005
icker-0.005
nam-0.005
 Def-0.005
cient-0.005
Token in
Token ID287
Feature activation-5.23e-01

Pos logit contributions
ivated+0.000
icker+0.000
our+0.000
nam+0.000
 Def+0.000
Neg logit contributions
 polar-0.000
 ranger-0.000
 tow-0.000
 gn-0.000
 chimpan-0.000
Token a
Token ID257
Feature activation-2.27e-01

Pos logit contributions
ivated+0.012
nam+0.012
 Def+0.012
 Blood+0.012
icker+0.011
Neg logit contributions
 ranger-0.012
 polar-0.012
glers-0.011
 gn-0.011
 tow-0.011
Token me
Token ID502
Feature activation-2.36e+00

Pos logit contributions
ivated+0.006
our+0.006
 hey+0.006
icker+0.006
nam+0.006
Neg logit contributions
 polar-0.005
 ranger-0.005
 gn-0.005
 tow-0.005
 chimpan-0.005
Tokenadow
Token ID4584
Feature activation-7.43e-01

Pos logit contributions
ivated+0.040
icker+0.038
our+0.038
 Def+0.036
nam+0.036
Neg logit contributions
 polar-0.077
 ranger-0.073
 tow-0.071
 gn-0.070
 chimpan-0.069
Token.
Token ID13
Feature activation+2.80e-01

Pos logit contributions
icker+0.019
ivated+0.019
our+0.018
nam+0.018
 Blood+0.017
Neg logit contributions
 polar-0.017
 tow-0.016
 chimpan-0.016
 ranger-0.015
 bisc-0.015
Token One
Token ID1881
Feature activation+1.66e-01

Pos logit contributions
 polar+0.009
 ranger+0.008
 tow+0.008
 gn+0.008
 chimpan+0.008
Neg logit contributions
ivated-0.005
icker-0.005
our-0.005
nam-0.005
 hey-0.005
Token day
Token ID1110
Feature activation+2.91e-01

Pos logit contributions
 polar+0.005
 ranger+0.004
 tow+0.004
 gn+0.004
 chimpan+0.004
Neg logit contributions
ivated-0.003
icker-0.003
our-0.003
 Def-0.003
 tant-0.003
Token while
Token ID981
Feature activation+4.12e-01

Pos logit contributions
 polar+0.005
 ranger+0.005
 tow+0.005
 gn+0.005
 chimpan+0.004
Neg logit contributions
ivated-0.009
our-0.009
icker-0.009
nam-0.009
 hey-0.008
Token.
Token ID13
Feature activation+2.39e-01

Pos logit contributions
our+0.003
cient+0.003
bs+0.003
icker+0.003
nam+0.003
Neg logit contributions
 ranger-0.004
 chimpan-0.004
 tow-0.004
 polar-0.004
glers-0.004
Token Daisy
Token ID40355
Feature activation-5.66e-01

Pos logit contributions
 polar+0.005
 ranger+0.005
 gn+0.005
 tow+0.005
 chimpan+0.004
Neg logit contributions
ivated-0.007
our-0.006
icker-0.006
 tant-0.006
 hey-0.006
Token lived
Token ID5615
Feature activation-2.07e-01

Pos logit contributions
our+0.010
ivated+0.010
cient+0.009
icker+0.009
 Def+0.009
Neg logit contributions
 polar-0.017
 tow-0.016
 ranger-0.016
 waterfall-0.015
 chimpan-0.015
Token in
Token ID287
Feature activation-5.51e-01

Pos logit contributions
ivated+0.005
icker+0.005
our+0.005
nam+0.005
 hey+0.005
Neg logit contributions
 polar-0.005
 ranger-0.005
 tow-0.004
 gn-0.004
 chimpan-0.004
Token the
Token ID262
Feature activation-1.17e+00

Pos logit contributions
ivated+0.013
nam+0.013
 Def+0.013
icker+0.012
 hey+0.012
Neg logit contributions
 polar-0.013
 ranger-0.013
glers-0.012
 gn-0.012
 tow-0.012
Token me
Token ID502
Feature activation-2.36e+00

Pos logit contributions
ivated+0.037
nam+0.037
our+0.037
 tant+0.036
osing+0.035
Neg logit contributions
 polar-0.024
 ranger-0.021
 tow-0.020
 gn-0.020
 chimpan-0.019
Tokenadow
Token ID4584
Feature activation-7.86e-01

Pos logit contributions
ivated+0.051
nam+0.048
 tant+0.047
 hey+0.047
 Def+0.046
Neg logit contributions
 polar-0.067
 ranger-0.063
 gn-0.061
 tow-0.061
 chimpan-0.058
Token and
Token ID290
Feature activation+4.60e-01

Pos logit contributions
ivated+0.024
icker+0.023
our+0.023
nam+0.022
 Def+0.022
Neg logit contributions
 polar-0.016
 ranger-0.014
 tow-0.014
 gn-0.013
 chimpan-0.013
Token she
Token ID673
Feature activation-4.00e-01

Pos logit contributions
 polar+0.013
 ranger+0.013
 tow+0.012
 gn+0.012
 chimpan+0.012
Neg logit contributions
ivated-0.009
nam-0.009
our-0.009
icker-0.009
 Def-0.009
Token loved
Token ID6151
Feature activation-1.28e-01

Pos logit contributions
ivated+0.006
 ent+0.005
cient+0.005
our+0.005
nam+0.005
Neg logit contributions
 polar-0.014
 tow-0.013
 ranger-0.013
 chimpan-0.012
 waterfall-0.012
Token to
Token ID284
Feature activation-8.42e-02

Pos logit contributions
nam+0.003
ivated+0.003
 Def+0.002
 Him+0.002
 ent+0.002
Neg logit contributions
 polar-0.003
 tow-0.003
 ranger-0.003
 chimpan-0.003
 gn-0.003
Token of
Token ID286
Feature activation-3.20e-01

Pos logit contributions
ivated+0.004
icker+0.004
nam+0.004
 hey+0.004
our+0.004
Neg logit contributions
 polar-0.002
 ranger-0.002
 tow-0.002
 gn-0.002
 chimpan-0.001
Token a
Token ID257
Feature activation-1.06e-01

Pos logit contributions
ivated+0.010
icker+0.009
our+0.009
nam+0.009
 hey+0.009
Neg logit contributions
 polar-0.006
 ranger-0.006
 tow-0.005
 gn-0.005
 chimpan-0.005
Token hill
Token ID12788
Feature activation-5.83e-01

Pos logit contributions
ivated+0.003
our+0.003
arre+0.003
icker+0.003
 hey+0.003
Neg logit contributions
 polar-0.002
 ranger-0.002
 gn-0.002
 tow-0.002
 waterfall-0.002
Token in
Token ID287
Feature activation-7.81e-02

Pos logit contributions
our+0.015
ivated+0.014
icker+0.014
nam+0.013
cient+0.013
Neg logit contributions
 polar-0.015
 gn-0.013
 chimpan-0.013
 tow-0.013
 ranger-0.012
Token a
Token ID257
Feature activation+8.79e-02

Pos logit contributions
ivated+0.002
 Def+0.002
nam+0.002
 Blood+0.002
 hey+0.002
Neg logit contributions
 polar-0.002
 ranger-0.002
glers-0.002
 gn-0.002
 chimpan-0.002
Token me
Token ID502
Feature activation-2.35e+00

Pos logit contributions
 polar+0.002
 ranger+0.002
 tow+0.002
 gn+0.002
 chimpan+0.002
Neg logit contributions
ivated-0.003
our-0.003
icker-0.003
nam-0.002
arre-0.002
Tokenadow
Token ID4584
Feature activation-6.15e-01

Pos logit contributions
ivated+0.049
nam+0.046
 tant+0.045
icker+0.044
 hey+0.044
Neg logit contributions
 polar-0.068
 ranger-0.064
 gn-0.063
 tow-0.062
 chimpan-0.060
Token.
Token ID13
Feature activation-5.25e-02

Pos logit contributions
our+0.017
ivated+0.017
icker+0.017
 Blood+0.016
 ent+0.015
Neg logit contributions
 polar-0.014
 tow-0.012
 chimpan-0.012
 ranger-0.012
 gn-0.011
Token
Token ID198
Feature activation+6.29e-01

Pos logit contributions
ivated+0.001
icker+0.001
 tant+0.001
 hey+0.001
our+0.001
Neg logit contributions
 polar-0.001
 ranger-0.001
 tow-0.001
 gn-0.001
 chimpan-0.001
TokenOne
Token ID3198
Feature activation+1.94e-01

Pos logit contributions
 polar+0.017
 ranger+0.016
 tow+0.016
 gn+0.015
 chimpan+0.015
Neg logit contributions
ivated-0.014
our-0.014
icker-0.014
nam-0.013
 tant-0.013
Token day
Token ID1110
Feature activation+3.53e-01

Pos logit contributions
 polar+0.005
 ranger+0.004
 tow+0.004
 gn+0.004
 chimpan+0.004
Neg logit contributions
ivated-0.005
nam-0.005
 hey-0.005
our-0.005
arre-0.005
Token da
Token ID12379
Feature activation+5.34e-02

Pos logit contributions
icker+0.003
 tant+0.003
our+0.003
cient+0.003
ivated+0.003
Neg logit contributions
 ranger-0.005
 chimpan-0.005
 tow-0.005
 polar-0.005
glers-0.005
Tokenisy
Token ID13560
Feature activation+1.31e-02

Pos logit contributions
 polar+0.002
 ranger+0.002
 tow+0.002
 gn+0.002
 chimpan+0.002
Neg logit contributions
ivated-0.001
icker-0.001
our-0.001
 hey-0.001
cient-0.001
Token living
Token ID2877
Feature activation-1.19e-01

Pos logit contributions
 ranger+0.000
 tow+0.000
 polar+0.000
 chimpan+0.000
falls+0.000
Neg logit contributions
icker-0.000
our-0.000
cient-0.000
oney-0.000
nam-0.000
Token in
Token ID287
Feature activation-3.95e-01

Pos logit contributions
ivated+0.003
icker+0.003
our+0.003
 tant+0.003
nam+0.003
Neg logit contributions
 polar-0.003
 ranger-0.003
 tow-0.003
 gn-0.003
 chimpan-0.003
Token a
Token ID257
Feature activation-1.95e-01

Pos logit contributions
ivated+0.010
nam+0.010
 Def+0.009
 Blood+0.009
 hey+0.009
Neg logit contributions
 ranger-0.009
 polar-0.009
glers-0.008
 gn-0.008
 tow-0.008
Token me
Token ID502
Feature activation-2.35e+00

Pos logit contributions
ivated+0.005
our+0.005
icker+0.005
nam+0.005
 hey+0.005
Neg logit contributions
 polar-0.005
 ranger-0.004
 gn-0.004
 tow-0.004
 chimpan-0.004
Tokenadow
Token ID4584
Feature activation-6.21e-01

Pos logit contributions
ivated+0.040
our+0.038
icker+0.038
 Def+0.036
 hey+0.035
Neg logit contributions
 polar-0.076
 ranger-0.073
 tow-0.071
 gn-0.070
 chimpan-0.069
Token.
Token ID13
Feature activation+2.33e-01

Pos logit contributions
icker+0.015
our+0.014
ivated+0.014
 Blood+0.013
oney+0.013
Neg logit contributions
 polar-0.016
 tow-0.014
 chimpan-0.014
 bisc-0.013
 ranger-0.013
Token She
Token ID1375
Feature activation+2.51e-01

Pos logit contributions
 polar+0.007
 ranger+0.007
 tow+0.007
 gn+0.007
 chimpan+0.007
Neg logit contributions
ivated-0.004
icker-0.004
our-0.004
nam-0.004
 Def-0.004
Token was
Token ID373
Feature activation-4.13e-01

Pos logit contributions
 polar+0.007
 ranger+0.007
 tow+0.007
 gn+0.007
 chimpan+0.007
Neg logit contributions
ivated-0.005
our-0.005
icker-0.005
nam-0.005
 Def-0.004
Token waving
Token ID25849
Feature activation+4.35e-01

Pos logit contributions
ivated+0.010
icker+0.010
our+0.009
nam+0.009
 tant+0.009
Neg logit contributions
 polar-0.011
 ranger-0.010
 tow-0.009
 gn-0.009
 chimpan-0.009
Token,
Token ID11
Feature activation+8.62e-01

Pos logit contributions
our+0.001
nam+0.001
bs+0.001
ivated+0.001
iable+0.001
Neg logit contributions
 polar-0.001
 gn-0.001
 chimpan-0.001
 tow-0.001
 ranger-0.001
Token if
Token ID611
Feature activation-1.74e-01

Pos logit contributions
 polar+0.023
 ranger+0.021
 tow+0.021
 gn+0.021
 chimpan+0.020
Neg logit contributions
ivated-0.019
arre-0.019
nam-0.018
 ent-0.018
 Def-0.018
Token they
Token ID484
Feature activation+1.18e-01

Pos logit contributions
ivated+0.004
nam+0.004
 hey+0.004
icker+0.004
our+0.004
Neg logit contributions
 polar-0.004
 ranger-0.004
 gn-0.004
 tow-0.004
 chimpan-0.004
Token used
Token ID973
Feature activation-9.70e-03

Pos logit contributions
 polar+0.003
 ranger+0.003
 tow+0.003
 gn+0.003
 chimpan+0.003
Neg logit contributions
ivated-0.003
our-0.003
icker-0.002
 hey-0.002
nam-0.002
Token their
Token ID511
Feature activation+7.14e-01

Pos logit contributions
nam+0.000
 tant+0.000
ivated+0.000
 Def+0.000
bs+0.000
Neg logit contributions
 polar-0.000
 ranger-0.000
 gn-0.000
 chimpan-0.000
 tow-0.000
Token imag
Token ID3590
Feature activation-2.35e+00

Pos logit contributions
 polar+0.021
 ranger+0.020
 gn+0.019
 tow+0.019
 chimpan+0.019
Neg logit contributions
ivated-0.014
our-0.013
icker-0.013
 tant-0.013
nam-0.013
Tokeninations
Token ID7352
Feature activation+8.96e-02

Pos logit contributions
ivated+0.050
nam+0.047
icker+0.047
our+0.047
 hey+0.046
Neg logit contributions
 polar-0.066
 ranger-0.061
 tow-0.060
 gn-0.060
 chimpan-0.057
Token.
Token ID13
Feature activation-1.02e-01

Pos logit contributions
 polar+0.002
 chimpan+0.002
 ranger+0.002
 gn+0.002
 tow+0.002
Neg logit contributions
ivated-0.002
our-0.002
 tant-0.002
bs-0.002
icker-0.002
Token So
Token ID1406
Feature activation+2.09e-01

Pos logit contributions
ivated+0.003
nam+0.003
 tant+0.003
our+0.003
icker+0.002
Neg logit contributions
 ranger-0.002
 polar-0.002
 tow-0.002
 chimpan-0.002
 gn-0.002
Token the
Token ID262
Feature activation+5.18e-02

Pos logit contributions
 polar+0.005
 gn+0.004
 ranger+0.004
 tow+0.004
 chimpan+0.004
Neg logit contributions
ivated-0.006
our-0.006
icker-0.005
 hey-0.005
 Def-0.005
Token children
Token ID1751
Feature activation-1.15e-01

Pos logit contributions
 polar+0.002
 ranger+0.001
 gn+0.001
 tow+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.001
nam-0.001
 hey-0.001
our-0.001
icker-0.001
Token see
Token ID766
Feature activation-2.84e-02

Pos logit contributions
 polar+0.013
 ranger+0.012
 tow+0.012
 gn+0.012
 chimpan+0.011
Neg logit contributions
ivated-0.011
 tant-0.010
icker-0.010
nam-0.010
our-0.010
Token her
Token ID607
Feature activation+6.90e-01

Pos logit contributions
ivated+0.001
nam+0.001
icker+0.001
our+0.001
 hey+0.001
Neg logit contributions
 polar-0.001
 ranger-0.001
 chimpan-0.001
 gn-0.001
 tow-0.001
Token flower
Token ID15061
Feature activation-5.09e-01

Pos logit contributions
 polar+0.019
 ranger+0.018
 tow+0.017
 chimpan+0.017
 gn+0.017
Neg logit contributions
ivated-0.015
icker-0.015
our-0.015
 hey-0.014
nam-0.014
Token.
Token ID13
Feature activation+3.75e-01

Pos logit contributions
our+0.012
icker+0.011
ivated+0.011
bs+0.011
nam+0.010
Neg logit contributions
 polar-0.014
 chimpan-0.013
 tow-0.012
 ranger-0.012
 carn-0.011
Token She
Token ID1375
Feature activation+2.60e-01

Pos logit contributions
 polar+0.012
 ranger+0.012
 tow+0.011
 gn+0.011
 chimpan+0.011
Neg logit contributions
ivated-0.007
icker-0.006
our-0.006
 tant-0.006
 hey-0.006
Token imag
Token ID3590
Feature activation-2.35e+00

Pos logit contributions
 polar+0.007
 ranger+0.007
 tow+0.007
 chimpan+0.006
 gn+0.006
Neg logit contributions
ivated-0.005
our-0.005
arre-0.005
 hey-0.005
icker-0.005
Tokenines
Token ID1127
Feature activation+1.57e-01

Pos logit contributions
ivated+0.058
nam+0.058
 Def+0.056
 tant+0.055
our+0.055
Neg logit contributions
 polar-0.055
 tow-0.050
 ranger-0.050
 gn-0.049
 chimpan-0.046
Token it
Token ID340
Feature activation+3.52e-02

Pos logit contributions
 polar+0.005
 ranger+0.004
 chimpan+0.004
 tow+0.004
 gn+0.004
Neg logit contributions
ivated-0.003
bs-0.003
icker-0.003
our-0.003
nam-0.003
Token will
Token ID481
Feature activation+1.03e-01

Pos logit contributions
 polar+0.001
 ranger+0.001
 tow+0.001
 gn+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.001
our-0.001
icker-0.001
arre-0.001
 Def-0.001
Token be
Token ID307
Feature activation-2.06e-02

Pos logit contributions
 polar+0.003
 ranger+0.003
 chimpan+0.002
 tow+0.002
 gn+0.002
Neg logit contributions
ivated-0.002
icker-0.002
our-0.002
 hey-0.002
 tant-0.002
Token red
Token ID2266
Feature activation-3.15e-01

Pos logit contributions
ivated+0.000
nam+0.000
our+0.000
icker+0.000
obb+0.000
Neg logit contributions
 polar-0.001
 ranger-0.001
 tow-0.001
 chimpan-0.001
 gn-0.001
Token many
Token ID867
Feature activation+1.10e-01

Pos logit contributions
 polar+0.012
 ranger+0.012
 gn+0.011
 tow+0.011
 chimpan+0.011
Neg logit contributions
ivated-0.006
icker-0.006
nam-0.006
 tant-0.006
 Def-0.005
Token wonderful
Token ID7932
Feature activation-3.84e-01

Pos logit contributions
 ranger+0.003
 polar+0.003
 tow+0.003
man+0.003
 gn+0.003
Neg logit contributions
 unnecessary-0.002
 ent-0.002
 tant-0.002
bs-0.002
ivated-0.002
Token things
Token ID1243
Feature activation+4.86e-01

Pos logit contributions
 unnecessary+0.004
 tant+0.004
our+0.004
 ent+0.004
bs+0.004
Neg logit contributions
 ranger-0.014
 tow-0.014
 polar-0.013
glers-0.012
 gn-0.012
Token in
Token ID287
Feature activation-4.09e-01

Pos logit contributions
 polar+0.015
 tow+0.014
 chimpan+0.013
 gn+0.013
omo+0.012
Neg logit contributions
ivated-0.009
our-0.009
bs-0.009
osing-0.008
iable-0.008
Token the
Token ID262
Feature activation-4.12e-01

Pos logit contributions
 Def+0.006
 tant+0.006
nam+0.006
ivated+0.006
 Him+0.006
Neg logit contributions
 bisc-0.012
 ranger-0.012
 gn-0.011
 chimpan-0.011
 polar-0.011
Token me
Token ID502
Feature activation-2.35e+00

Pos logit contributions
ivated+0.005
our+0.005
Finally+0.005
Eventually+0.005
 Def+0.005
Neg logit contributions
 polar-0.015
 ranger-0.014
 tow-0.014
 gn-0.013
 chimpan-0.013
Tokenadow
Token ID4584
Feature activation-3.43e-01

Pos logit contributions
our+0.034
ivated+0.033
icker+0.033
oney+0.030
arre+0.029
Neg logit contributions
 polar-0.083
 ranger-0.078
 tow-0.077
 gn-0.075
 chimpan-0.075
Token.
Token ID13
Feature activation+1.28e-01

Pos logit contributions
our+0.009
icker+0.008
ivated+0.008
 ent+0.008
oney+0.008
Neg logit contributions
 polar-0.008
 chimpan-0.007
 tow-0.007
 ranger-0.007
 gn-0.007
Token The
Token ID383
Feature activation+1.60e-02

Pos logit contributions
 polar+0.004
 ranger+0.004
 gn+0.004
 tow+0.003
 chimpan+0.003
Neg logit contributions
ivated-0.002
 Def-0.002
our-0.002
icker-0.002
arre-0.002
Token animals
Token ID4695
Feature activation-2.38e-01

Pos logit contributions
 tow+0.000
 polar+0.000
glers+0.000
ull+0.000
 ranger+0.000
Neg logit contributions
Eventually-0.000
Finally-0.000
 hey-0.000
ivated-0.000
 tant-0.000
Token let
Token ID1309
Feature activation+4.02e-03

Pos logit contributions
ivated+0.005
bs+0.005
our+0.005
 ent+0.005
icker+0.005
Neg logit contributions
 polar-0.006
 ranger-0.006
 chimpan-0.006
 gn-0.006
 tow-0.006
Token hit
Token ID2277
Feature activation+6.10e-01

Pos logit contributions
 polar+0.000
 ranger+0.000
 chimpan+0.000
 tow+0.000
glers+0.000
Neg logit contributions
 Blood-0.000
bs-0.000
ivated-0.000
 hey-0.000
our-0.000
Token her
Token ID607
Feature activation+5.60e-01

Pos logit contributions
 polar+0.017
 ranger+0.016
 tow+0.015
 gn+0.015
 chimpan+0.015
Neg logit contributions
ivated-0.013
nam-0.013
 tant-0.013
 Def-0.012
 hey-0.012
Token mom
Token ID1995
Feature activation+3.19e-01

Pos logit contributions
 polar+0.016
 tow+0.016
 chimpan+0.016
 ranger+0.015
 gn+0.015
Neg logit contributions
 tant-0.011
our-0.011
ivated-0.010
nam-0.010
icker-0.010
Token's
Token ID338
Feature activation-4.00e-01

Pos logit contributions
 polar+0.009
 chimpan+0.008
 ranger+0.008
 waterfall+0.008
 tow+0.008
Neg logit contributions
our-0.007
ivated-0.007
iable-0.006
nam-0.006
ivery-0.006
Token ash
Token ID12530
Feature activation+4.34e-01

Pos logit contributions
 tant+0.007
nam+0.007
ivated+0.007
our+0.007
icker+0.007
Neg logit contributions
 polar-0.012
 ranger-0.011
 chimpan-0.011
 tow-0.011
 gn-0.011
Tokentr
Token ID2213
Feature activation+3.35e+00

Pos logit contributions
 polar+0.013
 tow+0.012
 chimpan+0.012
 ranger+0.011
 gn+0.011
Neg logit contributions
our-0.009
 tant-0.008
obb-0.008
icker-0.008
ivated-0.008
Tokenay
Token ID323
Feature activation+5.22e-01

Pos logit contributions
 polar+0.064
 ranger+0.058
 tow+0.057
 gn+0.054
 chimpan+0.051
Neg logit contributions
ivated-0.102
nam-0.097
icker-0.096
 hey-0.095
 Def-0.095
Token.
Token ID13
Feature activation-3.27e-01

Pos logit contributions
 polar+0.011
 chimpan+0.010
 tow+0.010
 ranger+0.010
 gn+0.009
Neg logit contributions
our-0.015
ivated-0.015
arre-0.014
 tant-0.014
iable-0.014
Token The
Token ID383
Feature activation+1.15e-01

Pos logit contributions
ivated+0.008
our+0.008
icker+0.008
 hey+0.008
unct+0.007
Neg logit contributions
 ranger-0.008
 polar-0.008
 gn-0.008
 tow-0.008
 chimpan-0.007
Token ash
Token ID12530
Feature activation-2.75e-01

Pos logit contributions
 polar+0.003
 ranger+0.003
 chimpan+0.003
 tow+0.003
 gn+0.003
Neg logit contributions
 tant-0.002
 hey-0.002
nam-0.002
icker-0.002
ivated-0.002
Tokentr
Token ID2213
Feature activation+2.85e+00

Pos logit contributions
ivated+0.006
our+0.006
 tant+0.005
icker+0.005
 hey+0.005
Neg logit contributions
 polar-0.008
 ranger-0.007
 tow-0.007
 gn-0.007
 chimpan-0.007
Token.
Token ID13
Feature activation-2.06e-01

Pos logit contributions
 polar+0.019
 tow+0.018
 ranger+0.018
 gn+0.017
 chimpan+0.017
Neg logit contributions
ivated-0.022
 tant-0.021
our-0.021
 hey-0.021
arre-0.021
Token He
Token ID679
Feature activation-1.94e-01

Pos logit contributions
ivated+0.004
 Def+0.004
icker+0.004
our+0.004
 hey+0.004
Neg logit contributions
 polar-0.006
 ranger-0.005
 tow-0.005
 gn-0.005
 chimpan-0.005
Token drops
Token ID10532
Feature activation+3.74e-01

Pos logit contributions
 tant+0.004
ivated+0.004
our+0.004
 hey+0.004
arre+0.004
Neg logit contributions
 polar-0.005
 tow-0.005
 ranger-0.005
 chimpan-0.005
 gn-0.005
Token the
Token ID262
Feature activation+1.10e-02

Pos logit contributions
 polar+0.010
 gn+0.010
 ranger+0.009
 chimpan+0.009
 trove+0.009
Neg logit contributions
 tant-0.009
 Blood-0.008
ivated-0.008
bs-0.008
 Ow-0.008
Token ash
Token ID12530
Feature activation+1.06e-01

Pos logit contributions
 polar+0.000
 ranger+0.000
 chimpan+0.000
 tow+0.000
 gn+0.000
Neg logit contributions
 tant-0.000
nam-0.000
icker-0.000
ivated-0.000
obb-0.000
Tokentr
Token ID2213
Feature activation+3.59e+00

Pos logit contributions
 polar+0.003
 tow+0.002
 ranger+0.002
 chimpan+0.002
 gn+0.002
Neg logit contributions
our-0.003
 tant-0.003
icker-0.002
ivated-0.002
obb-0.002
Tokenay
Token ID323
Feature activation+7.80e-01

Pos logit contributions
 polar+0.058
 tow+0.053
 ranger+0.050
 gn+0.045
!+0.043
Neg logit contributions
ivated-0.121
nam-0.115
gging-0.111
 Def-0.111
 hey-0.111
Token.
Token ID13
Feature activation-1.53e-01

Pos logit contributions
 polar+0.015
 ranger+0.014
 gn+0.013
 tow+0.013
 chimpan+0.013
Neg logit contributions
ivated-0.023
our-0.023
icker-0.023
 tant-0.022
 hey-0.022
Token It
Token ID632
Feature activation+2.51e-02

Pos logit contributions
ivated+0.004
icker+0.003
our+0.003
nam+0.003
 hey+0.003
Neg logit contributions
 polar-0.004
 ranger-0.004
 tow-0.004
 gn-0.004
 chimpan-0.004
Token breaks
Token ID9457
Feature activation+6.50e-02

Pos logit contributions
 polar+0.001
 ranger+0.001
 tow+0.001
 gn+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.001
 tant-0.001
our-0.001
icker-0.001
 hey-0.001
Token.
Token ID13
Feature activation-2.17e-01

Pos logit contributions
 ranger+0.001
 polar+0.001
 chimpan+0.001
 tow+0.001
 gn+0.001
Neg logit contributions
 Ow-0.002
 Blood-0.002
our-0.002
 tant-0.002
obb-0.002
Token carefully
Token ID7773
Feature activation-2.92e-01

Pos logit contributions
 polar+0.007
 ranger+0.007
 tow+0.007
 chimpan+0.007
 waterfall+0.007
Neg logit contributions
our-0.005
ivated-0.005
bs-0.005
int-0.005
cient-0.004
Token picked
Token ID6497
Feature activation+5.28e-01

Pos logit contributions
our+0.006
bs+0.006
ivated+0.006
int+0.005
 Def+0.005
Neg logit contributions
 polar-0.008
 ranger-0.008
 waterfall-0.008
 chimpan-0.007
 tow-0.007
Token up
Token ID510
Feature activation+2.27e-01

Pos logit contributions
 polar+0.015
 ranger+0.015
 tow+0.014
 gn+0.014
 chimpan+0.013
Neg logit contributions
ivated-0.010
 tant-0.010
 Def-0.010
our-0.010
nam-0.010
Token the
Token ID262
Feature activation-1.02e-01

Pos logit contributions
 polar+0.007
 ranger+0.006
 tow+0.006
 gn+0.006
 chimpan+0.006
Neg logit contributions
 tant-0.005
nam-0.005
ivated-0.004
bs-0.004
 however-0.004
Token ash
Token ID12530
Feature activation+2.39e-01

Pos logit contributions
nam+0.002
 tant+0.002
ivated+0.002
our+0.002
 Def+0.002
Neg logit contributions
 polar-0.003
 ranger-0.002
 tow-0.002
 chimpan-0.002
 gn-0.002
Tokentr
Token ID2213
Feature activation+3.11e+00

Pos logit contributions
 polar+0.007
 tow+0.006
 chimpan+0.006
 amusement+0.006
 ranger+0.005
Neg logit contributions
our-0.005
 tant-0.005
 spine-0.005
cient-0.005
icker-0.004
Tokenay
Token ID323
Feature activation+8.24e-01

Pos logit contributions
 polar+0.055
 ranger+0.051
 tow+0.051
 gn+0.046
 chimpan+0.044
Neg logit contributions
ivated-0.099
nam-0.093
 hey-0.092
 Def-0.091
icker-0.091
Token and
Token ID290
Feature activation+1.75e-01

Pos logit contributions
 polar+0.019
 ranger+0.017
 tow+0.017
 chimpan+0.017
 gn+0.017
Neg logit contributions
our-0.022
ivated-0.021
iable-0.021
oney-0.021
bs-0.021
Token put
Token ID1234
Feature activation-9.33e-02

Pos logit contributions
 polar+0.005
 ranger+0.004
 tow+0.004
 chimpan+0.004
 gn+0.004
Neg logit contributions
nam-0.004
ivated-0.004
our-0.004
bs-0.004
 Def-0.004
Token it
Token ID340
Feature activation-3.03e-01

Pos logit contributions
nam+0.002
 tant+0.002
ivated+0.002
 Def+0.002
our+0.002
Neg logit contributions
 polar-0.003
 ranger-0.003
 gn-0.003
 chimpan-0.003
glers-0.003
Token in
Token ID287
Feature activation-8.94e-02

Pos logit contributions
ivated+0.007
nam+0.007
our+0.006
icker+0.006
 tant+0.006
Neg logit contributions
 polar-0.008
 ranger-0.008
 tow-0.008
 chimpan-0.008
 gn-0.007
Token looked
Token ID3114
Feature activation-7.23e-01

Pos logit contributions
 polar+0.001
 ranger+0.001
 gn+0.001
 tow+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.001
our-0.001
icker-0.001
 hey-0.001
 Def-0.001
Token at
Token ID379
Feature activation+1.23e+00

Pos logit contributions
ivated+0.015
icker+0.015
 hey+0.014
 Def+0.014
our+0.014
Neg logit contributions
 polar-0.021
 ranger-0.020
 tow-0.018
 gn-0.018
 chimpan-0.018
Token the
Token ID262
Feature activation-1.48e-01

Pos logit contributions
 polar+0.031
 ranger+0.030
 gn+0.030
 chimpan+0.029
 tow+0.028
Neg logit contributions
ivated-0.028
 hey-0.028
 tant-0.028
icker-0.027
our-0.027
Token empty
Token ID6565
Feature activation+4.70e-01

Pos logit contributions
ivated+0.004
icker+0.003
our+0.003
 Def+0.003
nam+0.003
Neg logit contributions
 polar-0.004
 ranger-0.004
 tow-0.003
 gn-0.003
 chimpan-0.003
Token ash
Token ID12530
Feature activation+2.39e-01

Pos logit contributions
 polar+0.014
 ranger+0.014
 chimpan+0.013
 gn+0.013
 tow+0.013
Neg logit contributions
 tant-0.008
our-0.008
nam-0.008
icker-0.008
 Def-0.008
Tokentr
Token ID2213
Feature activation+3.13e+00

Pos logit contributions
 polar+0.007
 tow+0.007
 chimpan+0.006
 ranger+0.006
 gn+0.006
Neg logit contributions
our-0.005
icker-0.004
 tant-0.004
 hey-0.004
ivated-0.004
Tokenay
Token ID323
Feature activation+2.84e-01

Pos logit contributions
 polar+0.057
 ranger+0.052
 tow+0.052
 gn+0.047
 chimpan+0.045
Neg logit contributions
ivated-0.099
nam-0.094
 Def-0.090
 hey-0.090
icker-0.090
Token on
Token ID319
Feature activation+3.18e-01

Pos logit contributions
 polar+0.006
 gn+0.005
 tow+0.005
 chimpan+0.005
 ranger+0.005
Neg logit contributions
our-0.009
ivated-0.008
icker-0.008
 tant-0.008
 hey-0.008
Token Sara
Token ID24799
Feature activation-6.17e-01

Pos logit contributions
 polar+0.009
 gn+0.009
 ranger+0.009
 chimpan+0.009
glers+0.008
Neg logit contributions
 Ow-0.006
 tant-0.006
 hey-0.005
 Blood-0.005
obb-0.005
Token's
Token ID338
Feature activation+2.55e-01

Pos logit contributions
ivated+0.014
our+0.014
icker+0.013
nam+0.013
 Def+0.013
Neg logit contributions
 polar-0.017
 ranger-0.015
 tow-0.015
 gn-0.015
 chimpan-0.015
Token head
Token ID1182
Feature activation+1.13e-01

Pos logit contributions
 polar+0.007
 ranger+0.007
 tow+0.007
 gn+0.007
 chimpan+0.007
Neg logit contributions
ivated-0.005
our-0.005
icker-0.005
 tant-0.005
nam-0.005
Token she
Token ID673
Feature activation+2.58e-01

Pos logit contributions
 polar+0.019
 tow+0.017
 chimpan+0.017
 ranger+0.017
 waterfall+0.016
Neg logit contributions
nam-0.007
 hey-0.007
our-0.006
ivated-0.006
 Him-0.006
Token could
Token ID714
Feature activation+3.49e-01

Pos logit contributions
 polar+0.008
 ranger+0.007
 tow+0.007
 chimpan+0.007
 gn+0.007
Neg logit contributions
our-0.005
ivated-0.005
 hey-0.004
 Def-0.004
icker-0.004
Token have
Token ID423
Feature activation-5.92e-01

Pos logit contributions
 ranger+0.011
 polar+0.011
 chimpan+0.011
 MacDonald+0.010
 ze+0.010
Neg logit contributions
our-0.007
icker-0.006
ivated-0.005
bs-0.005
 hey-0.005
Token the
Token ID262
Feature activation-3.29e-02

Pos logit contributions
nam+0.013
ivated+0.013
 tant+0.012
 Def+0.012
iable+0.012
Neg logit contributions
 polar-0.016
 ranger-0.015
 gn-0.015
 chimpan-0.015
 tow-0.014
Token ash
Token ID12530
Feature activation+1.13e-01

Pos logit contributions
nam+0.001
 tant+0.001
ivated+0.001
our+0.001
 hey+0.001
Neg logit contributions
 polar-0.001
 ranger-0.001
 tow-0.001
 chimpan-0.001
 gn-0.001
Tokentr
Token ID2213
Feature activation+3.09e+00

Pos logit contributions
 polar+0.003
 tow+0.003
 chimpan+0.003
 gn+0.003
 ranger+0.003
Neg logit contributions
our-0.002
 tant-0.002
icker-0.002
 spine-0.002
 hey-0.002
Tokenay
Token ID323
Feature activation+4.75e-01

Pos logit contributions
 polar+0.050
 tow+0.046
 ranger+0.046
 gn+0.040
glers+0.037
Neg logit contributions
ivated-0.104
nam-0.098
gging-0.097
 hey-0.096
 Def-0.095
Token to
Token ID284
Feature activation-7.98e-02

Pos logit contributions
 polar+0.012
 chimpan+0.011
 gn+0.011
 ranger+0.011
 tow+0.011
Neg logit contributions
our-0.012
iable-0.011
 hey-0.011
cient-0.011
bs-0.011
Token put
Token ID1234
Feature activation+1.14e-02

Pos logit contributions
ivated+0.002
our+0.002
icker+0.002
nam+0.002
 hey+0.002
Neg logit contributions
 polar-0.002
 ranger-0.002
 gn-0.002
 tow-0.002
 chimpan-0.002
Token her
Token ID607
Feature activation+2.95e-01

Pos logit contributions
 polar+0.000
 ranger+0.000
 chimpan+0.000
 tow+0.000
 gn+0.000
Neg logit contributions
nam-0.000
 tant-0.000
our-0.000
ivated-0.000
bs-0.000
Token rocks
Token ID12586
Feature activation-5.45e-01

Pos logit contributions
 polar+0.008
 ranger+0.007
 chimpan+0.007
 tow+0.007
 gn+0.007
Neg logit contributions
nam-0.007
 tant-0.007
ivated-0.006
our-0.006
icker-0.006
Token the
Token ID262
Feature activation-6.78e-02

Pos logit contributions
 ent+0.000
ivated+0.000
 miserable+0.000
 sad+0.000
nam+0.000
Neg logit contributions
 polar-0.000
 chimpan-0.000
 ranger-0.000
 gn-0.000
glers-0.000
Token most
Token ID749
Feature activation-2.07e-01

Pos logit contributions
ivated+0.001
nam+0.001
 hey+0.001
 tant+0.001
icker+0.001
Neg logit contributions
 polar-0.002
 ranger-0.002
 gn-0.002
 chimpan-0.002
 tow-0.002
Token interesting
Token ID3499
Feature activation-4.01e-02

Pos logit contributions
ivated+0.004
 ent+0.004
icker+0.004
 tant+0.003
obb+0.003
Neg logit contributions
 polar-0.007
 ranger-0.006
 gn-0.006
 chimpan-0.006
 tow-0.006
Token thing
Token ID1517
Feature activation-6.01e-01

Pos logit contributions
 tant+0.001
 Def+0.001
ivated+0.001
our+0.001
 ent+0.001
Neg logit contributions
 polar-0.001
 gn-0.001
 chimpan-0.001
glers-0.001
 ranger-0.001
Token she
Token ID673
Feature activation-1.91e-01

Pos logit contributions
she+0.009
bs+0.009
ivated+0.008
osing+0.008
oney+0.008
Neg logit contributions
 polar-0.022
 chimpan-0.019
 tow-0.019
 gn-0.019
 waterfall-0.018
Token had
Token ID550
Feature activation+1.18e+00

Pos logit contributions
ivated+0.005
our+0.005
 hey+0.005
 Def+0.005
nam+0.005
Neg logit contributions
 polar-0.004
 tow-0.004
 ranger-0.004
 gn-0.004
 chimpan-0.004
Token ever
Token ID1683
Feature activation-2.04e-01

Pos logit contributions
 polar+0.029
 tow+0.025
 ranger+0.025
 gn+0.024
 chimpan+0.023
Neg logit contributions
ivated-0.032
our-0.031
 Def-0.029
osing-0.029
arre-0.029
Token seen
Token ID1775
Feature activation-2.22e-01

Pos logit contributions
ivated+0.003
our+0.003
arre+0.003
bs+0.003
nam+0.003
Neg logit contributions
 polar-0.006
 tow-0.006
 ranger-0.006
 chimpan-0.006
 gn-0.006
Token.
Token ID13
Feature activation-7.79e-02

Pos logit contributions
ivated+0.006
our+0.006
osing+0.006
iable+0.006
nam+0.006
Neg logit contributions
 polar-0.006
 tow-0.005
 chimpan-0.005
 ranger-0.005
 gn-0.004
Token<|endoftext|>
Token ID50256
Feature activation+3.36e-02

Pos logit contributions
ivated+0.002
our+0.002
icker+0.002
 tant+0.002
nam+0.002
Neg logit contributions
 polar-0.002
 ranger-0.002
 tow-0.002
 gn-0.002
 chimpan-0.002
TokenOnce
Token ID7454
Feature activation-1.73e-01

Pos logit contributions
 polar+0.001
 ranger+0.001
 gn+0.001
 chimpan+0.001
 tow+0.001
Neg logit contributions
 Def-0.000
upon-0.000
 Ow-0.000
arre-0.000
ivated-0.000
Token and
Token ID290
Feature activation+1.41e-01

Pos logit contributions
 polar+0.012
 tow+0.011
 gn+0.011
 ranger+0.011
 chimpan+0.011
Neg logit contributions
ivated-0.013
arre-0.012
our-0.012
icker-0.012
 hey-0.012
Token played
Token ID2826
Feature activation+3.40e-01

Pos logit contributions
 polar+0.004
 tow+0.004
 chimpan+0.004
 gn+0.004
 ranger+0.004
Neg logit contributions
nam-0.003
bs-0.003
ivated-0.003
 Def-0.003
 hey-0.002
Token together
Token ID1978
Feature activation-1.04e-01

Pos logit contributions
 polar+0.009
 ranger+0.008
 tow+0.008
 gn+0.008
 chimpan+0.008
Neg logit contributions
ivated-0.008
icker-0.008
our-0.008
 hey-0.008
 Def-0.008
Token with
Token ID351
Feature activation+1.58e-01

Pos logit contributions
ivated+0.003
our+0.003
icker+0.003
 tant+0.003
nam+0.003
Neg logit contributions
 polar-0.002
 ranger-0.002
 tow-0.002
 gn-0.002
 chimpan-0.002
Token the
Token ID262
Feature activation+5.09e-01

Pos logit contributions
 polar+0.004
 gn+0.004
 ranger+0.004
 chimpan+0.004
 waterfall+0.003
Neg logit contributions
 tant-0.004
 hey-0.003
nam-0.003
icker-0.003
ivated-0.003
Token shiny
Token ID22441
Feature activation+1.26e+00

Pos logit contributions
 polar+0.014
 ranger+0.013
 tow+0.013
 gn+0.013
 chimpan+0.013
Neg logit contributions
ivated-0.011
 tant-0.010
icker-0.010
nam-0.010
our-0.010
Token mineral
Token ID18352
Feature activation-3.46e-01

Pos logit contributions
 polar+0.027
 ranger+0.026
 tow+0.024
 chimpan+0.023
 gn+0.023
Neg logit contributions
 tant-0.035
our-0.034
ivated-0.034
nam-0.032
arre-0.032
Token.
Token ID13
Feature activation-3.28e-01

Pos logit contributions
ivated+0.010
our+0.010
 tant+0.009
icker+0.009
onel+0.009
Neg logit contributions
 polar-0.007
 tow-0.007
 gn-0.006
 chimpan-0.006
 ranger-0.006
Token And
Token ID843
Feature activation+3.37e-01

Pos logit contributions
ivated+0.008
nam+0.008
our+0.008
icker+0.008
 hey+0.008
Neg logit contributions
 polar-0.008
 ranger-0.008
 tow-0.008
 chimpan-0.007
 gn-0.007
Token from
Token ID422
Feature activation+5.05e-02

Pos logit contributions
 polar+0.009
 gn+0.008
 tow+0.008
 chimpan+0.008
 ranger+0.007
Neg logit contributions
ivated-0.008
nam-0.007
 Def-0.007
 hey-0.007
 tant-0.007
Token that
Token ID326
Feature activation+6.00e-01

Pos logit contributions
 polar+0.001
 gn+0.001
 tow+0.001
 chimpan+0.001
 ranger+0.001
Neg logit contributions
ivated-0.001
 hey-0.001
nam-0.001
icker-0.001
our-0.001
Token,"
Token ID553
Feature activation-8.18e-01

Pos logit contributions
 polar+0.010
 waterfall+0.010
 chimpan+0.010
 tow+0.010
 gn+0.010
Neg logit contributions
 hey-0.007
our-0.007
 Him-0.006
oney-0.006
ivated-0.006
Token their
Token ID511
Feature activation+4.60e-01

Pos logit contributions
nam+0.013
bs+0.012
 tant+0.011
 hey+0.011
 Him+0.011
Neg logit contributions
 polar-0.025
 chimpan-0.024
 gn-0.024
 waterfall-0.024
 ranger-0.023
Token mom
Token ID1995
Feature activation+1.44e+00

Pos logit contributions
 polar+0.014
 gn+0.013
 ranger+0.013
 chimpan+0.013
 tow+0.013
Neg logit contributions
icker-0.008
 tant-0.008
nam-0.008
our-0.008
 hey-0.007
Token said
Token ID531
Feature activation+2.40e-02

Pos logit contributions
 polar+0.046
 tow+0.042
 waterfall+0.042
 chimpan+0.042
 ranger+0.041
Neg logit contributions
our-0.023
ivated-0.023
 Def-0.022
int-0.022
 hey-0.021
Token.
Token ID13
Feature activation+1.15e+00

Pos logit contributions
 polar+0.000
 ranger+0.000
 chimpan+0.000
 tow+0.000
 gn+0.000
Neg logit contributions
ivated-0.001
our-0.001
icker-0.001
nam-0.001
 hey-0.001
Token "
Token ID366
Feature activation+1.61e+00

Pos logit contributions
 polar+0.031
 ranger+0.029
 tow+0.028
 gn+0.028
 chimpan+0.027
Neg logit contributions
ivated-0.026
icker-0.025
our-0.025
nam-0.024
 hey-0.024
TokenI
Token ID40
Feature activation+4.08e-01

Pos logit contributions
 polar+0.048
 ranger+0.045
 tow+0.044
 gn+0.044
 chimpan+0.042
Neg logit contributions
ivated-0.032
icker-0.030
our-0.030
nam-0.029
 hey-0.029
Token'm
Token ID1101
Feature activation-6.20e-02

Pos logit contributions
 polar+0.013
 ranger+0.013
 chimpan+0.012
 tow+0.012
glers+0.012
Neg logit contributions
 hey-0.006
our-0.006
bs-0.006
arre-0.006
ivated-0.006
Token glad
Token ID9675
Feature activation+3.17e-01

Pos logit contributions
ivated+0.001
 hey+0.001
icker+0.001
nam+0.001
our+0.001
Neg logit contributions
 polar-0.002
 ranger-0.002
 gn-0.002
 tow-0.002
 chimpan-0.002
Token you
Token ID345
Feature activation+4.82e-01

Pos logit contributions
 polar+0.013
 tow+0.013
 chimpan+0.013
 gn+0.013
 ranger+0.013
Neg logit contributions
 hey-0.002
 Him-0.002
our-0.002
nam-0.002
ivated-0.002
Token liked
Token ID8288
Feature activation+6.39e-02

Pos logit contributions
 polar+0.013
 ranger+0.012
 tow+0.012
 gn+0.012
 chimpan+0.011
Neg logit contributions
ivated-0.011
our-0.010
icker-0.010
nam-0.010
 hey-0.010
Token the
Token ID262
Feature activation+1.67e-01

Pos logit contributions
 polar+0.000
 ranger+0.000
 gn+0.000
 tow+0.000
 waterfall+0.000
Neg logit contributions
arre-0.003
anna-0.003
ivery-0.003
 tant-0.003
int-0.003
Token bird
Token ID6512
Feature activation-3.36e-01

Pos logit contributions
 polar+0.003
 ranger+0.002
 gn+0.002
 tow+0.002
 waterfall+0.002
Neg logit contributions
ivated-0.006
arre-0.006
iable-0.006
our-0.006
osing-0.006
Token found
Token ID1043
Feature activation-2.77e-01

Pos logit contributions
ivated+0.010
nam+0.010
icker+0.010
 tant+0.009
 hey+0.009
Neg logit contributions
 polar-0.007
 gn-0.007
 ranger-0.006
 tow-0.006
 chimpan-0.006
Token something
Token ID1223
Feature activation-5.96e-03

Pos logit contributions
ivated+0.010
our+0.010
arre+0.010
 tant+0.010
icker+0.010
Neg logit contributions
 polar-0.004
 gn-0.003
 ranger-0.003
 tow-0.003
 chimpan-0.003
Token it
Token ID340
Feature activation-1.84e-01

Pos logit contributions
nam+0.000
ivated+0.000
 miserable+0.000
bs+0.000
 else+0.000
Neg logit contributions
 polar-0.000
 tow-0.000
 ranger-0.000
 chimpan-0.000
 gn-0.000
Token had
Token ID550
Feature activation+1.27e+00

Pos logit contributions
ivated+0.005
our+0.005
nam+0.005
 Def+0.004
cient+0.004
Neg logit contributions
 polar-0.004
 tow-0.004
 ranger-0.004
 chimpan-0.004
 gn-0.003
Token never
Token ID1239
Feature activation-1.98e-01

Pos logit contributions
 polar+0.034
 ranger+0.031
 tow+0.030
 chimpan+0.029
 gn+0.029
Neg logit contributions
ivated-0.029
our-0.028
 Def-0.027
nam-0.027
 hey-0.027
Token seen
Token ID1775
Feature activation-5.30e-01

Pos logit contributions
ivated+0.005
icker+0.005
our+0.005
nam+0.005
 hey+0.005
Neg logit contributions
 polar-0.005
 ranger-0.005
 tow-0.004
 gn-0.004
 chimpan-0.004
Token before
Token ID878
Feature activation+2.66e-01

Pos logit contributions
ivated+0.014
our+0.014
nam+0.014
 Def+0.014
icker+0.013
Neg logit contributions
 polar-0.012
 ranger-0.011
 tow-0.011
 gn-0.010
 chimpan-0.010
Token -
Token ID532
Feature activation+9.78e-02

Pos logit contributions
 polar+0.006
 ranger+0.006
 tow+0.006
 chimpan+0.005
 gn+0.005
Neg logit contributions
our-0.007
ivated-0.007
oney-0.007
icker-0.007
 Blood-0.007
Token poison
Token ID8764
Feature activation+5.83e-01

Pos logit contributions
 polar+0.002
 ranger+0.002
 tow+0.002
 chimpan+0.002
 gn+0.002
Neg logit contributions
nam-0.002
ivated-0.002
 hey-0.002
 Def-0.002
 tant-0.002
Token it
Token ID340
Feature activation-3.97e-01

Pos logit contributions
 polar+0.014
 ranger+0.013
 tow+0.012
 gn+0.012
 chimpan+0.012
Neg logit contributions
ivated-0.013
icker-0.013
our-0.013
 hey-0.012
nam-0.012
Token look
Token ID804
Feature activation+3.64e-01

Pos logit contributions
ivated+0.009
our+0.009
icker+0.009
nam+0.009
 tant+0.009
Neg logit contributions
 polar-0.010
 ranger-0.010
 tow-0.010
 chimpan-0.009
 gn-0.009
Token like
Token ID588
Feature activation+1.27e-01

Pos logit contributions
 polar+0.010
 ranger+0.010
 tow+0.010
 gn+0.009
 chimpan+0.009
Neg logit contributions
ivated-0.008
 tant-0.007
nam-0.007
our-0.007
icker-0.007
Token a
Token ID257
Feature activation+1.41e-03

Pos logit contributions
 polar+0.004
 ranger+0.003
 tow+0.003
 chimpan+0.003
 gn+0.003
Neg logit contributions
nam-0.003
 tant-0.002
ivated-0.002
 hey-0.002
iable-0.002
Token real
Token ID1103
Feature activation+1.57e-01

Pos logit contributions
 polar+0.000
 ranger+0.000
 chimpan+0.000
 tow+0.000
 gn+0.000
Neg logit contributions
 tant-0.000
nam-0.000
icker-0.000
 hey-0.000
arre-0.000
Token spaceship
Token ID40663
Feature activation+1.24e+00

Pos logit contributions
 polar+0.004
 ranger+0.004
 chimpan+0.003
 tow+0.003
glers+0.003
Neg logit contributions
our-0.004
 tant-0.004
icker-0.004
 hey-0.003
ivated-0.003
Token.
Token ID13
Feature activation-4.66e-01

Pos logit contributions
 polar+0.029
 chimpan+0.027
 tow+0.027
 gn+0.026
 ranger+0.025
Neg logit contributions
our-0.030
ivated-0.029
 hey-0.028
cient-0.028
 tant-0.028
Token
Token ID198
Feature activation-1.26e-01

Pos logit contributions
ivated+0.008
 Def+0.008
our+0.008
nam+0.008
icker+0.007
Neg logit contributions
 polar-0.015
 ranger-0.014
 gn-0.013
 tow-0.013
 chimpan-0.013
Token
Token ID198
Feature activation-8.17e-02

Pos logit contributions
ivated+0.003
our+0.003
nam+0.003
icker+0.003
 hey+0.003
Neg logit contributions
 polar-0.003
 ranger-0.003
 tow-0.003
 gn-0.003
 chimpan-0.003
TokenOne
Token ID3198
Feature activation+2.69e-02

Pos logit contributions
ivated+0.002
our+0.002
icker+0.002
nam+0.002
 tant+0.002
Neg logit contributions
 polar-0.002
 ranger-0.002
 tow-0.002
 gn-0.002
 chimpan-0.002
Token day
Token ID1110
Feature activation+2.50e-01

Pos logit contributions
 ranger+0.001
 gn+0.001
 polar+0.001
 chimpan+0.001
 tow+0.001
Neg logit contributions
icker-0.000
bs-0.000
 tant-0.000
our-0.000
 Def-0.000
Token Every
Token ID3887
Feature activation+5.29e-01

Pos logit contributions
 polar+0.008
 ranger+0.008
 gn+0.008
 tow+0.008
 chimpan+0.007
Neg logit contributions
ivated-0.007
our-0.006
 hey-0.006
icker-0.006
unct-0.006
Token night
Token ID1755
Feature activation-2.98e-01

Pos logit contributions
 polar+0.016
 ranger+0.015
 gn+0.015
 tow+0.014
 chimpan+0.014
Neg logit contributions
ivated-0.010
icker-0.010
our-0.010
 Def-0.009
 tant-0.009
Token Lily
Token ID20037
Feature activation+6.64e-02

Pos logit contributions
ivated+0.009
nam+0.008
our+0.008
icker+0.008
arre+0.008
Neg logit contributions
 polar-0.006
 ranger-0.006
 tow-0.006
 gn-0.005
 chimpan-0.005
Token would
Token ID561
Feature activation+2.17e-01

Pos logit contributions
 polar+0.001
 gn+0.001
 ranger+0.001
 tow+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.002
nam-0.002
icker-0.002
 hey-0.002
 tant-0.002
Token dream
Token ID4320
Feature activation-5.22e-01

Pos logit contributions
 polar+0.005
 ranger+0.005
 gn+0.005
 tow+0.005
 chimpan+0.004
Neg logit contributions
ivated-0.006
icker-0.005
our-0.005
nam-0.005
 tant-0.005
Token about
Token ID546
Feature activation-2.46e-01

Pos logit contributions
ivated+0.016
nam+0.015
 hey+0.015
icker+0.015
our+0.015
Neg logit contributions
 polar-0.010
 ranger-0.009
 gn-0.009
 tow-0.009
 chimpan-0.008
Token luxury
Token ID13064
Feature activation+3.61e-01

Pos logit contributions
nam+0.006
ivated+0.006
 Def+0.005
our+0.005
 ent+0.005
Neg logit contributions
 polar-0.006
 ranger-0.006
 tow-0.006
 chimpan-0.006
glers-0.005
Token.
Token ID13
Feature activation+3.70e-01

Pos logit contributions
 polar+0.010
 tow+0.010
 ranger+0.009
 chimpan+0.009
 gn+0.009
Neg logit contributions
our-0.008
ivated-0.007
nam-0.007
 tant-0.007
icker-0.007
Token She
Token ID1375
Feature activation+6.68e-02

Pos logit contributions
 tow+0.009
 polar+0.009
 ranger+0.009
 gn+0.008
 thanks+0.008
Neg logit contributions
ivated-0.010
 hey-0.009
unct-0.009
nam-0.009
 tant-0.009
Token dreamed
Token ID27947
Feature activation-8.15e-01

Pos logit contributions
 polar+0.002
 ranger+0.001
 tow+0.001
 gn+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.002
icker-0.002
our-0.002
nam-0.002
 hey-0.002
Token of
Token ID286
Feature activation-9.75e-02

Pos logit contributions
ivated+0.028
nam+0.028
our+0.027
icker+0.027
arre+0.026
Neg logit contributions
 polar-0.012
 ranger-0.011
 tow-0.010
 gn-0.010
 chimpan-0.009
Token She
Token ID1375
Feature activation+6.36e-02

Pos logit contributions
ivated+0.008
onel+0.008
unct+0.008
icker+0.008
 hey+0.007
Neg logit contributions
 ranger-0.004
 polar-0.004
 tow-0.004
 gn-0.004
 chimpan-0.003
Token sat
Token ID3332
Feature activation+7.43e-02

Pos logit contributions
 polar+0.001
 ranger+0.001
 gn+0.001
 tow+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.002
icker-0.002
nam-0.002
 tant-0.002
our-0.002
Token down
Token ID866
Feature activation-1.58e-01

Pos logit contributions
 ranger+0.001
 polar+0.001
 gn+0.001
 tow+0.001
!+0.001
Neg logit contributions
 Def-0.002
ivated-0.002
icker-0.002
INK-0.002
oney-0.002
Token next
Token ID1306
Feature activation+2.17e-01

Pos logit contributions
ivated+0.005
our+0.005
icker+0.005
nam+0.005
 tant+0.005
Neg logit contributions
 polar-0.003
 ranger-0.003
 tow-0.003
 gn-0.003
 chimpan-0.002
Token to
Token ID284
Feature activation+7.35e-01

Pos logit contributions
 polar+0.005
 ranger+0.004
 tow+0.004
 gn+0.004
 chimpan+0.004
Neg logit contributions
ivated-0.006
icker-0.006
our-0.006
nam-0.006
 hey-0.006
Token Lily
Token ID20037
Feature activation-4.55e-01

Pos logit contributions
 polar+0.015
 tow+0.013
 ranger+0.013
 gn+0.013
 chimpan+0.011
Neg logit contributions
ivated-0.022
icker-0.021
 tant-0.021
arre-0.021
our-0.021
Token and
Token ID290
Feature activation+8.38e-02

Pos logit contributions
ivated+0.015
our+0.014
icker+0.014
nam+0.014
 hey+0.014
Neg logit contributions
 polar-0.008
 ranger-0.007
 tow-0.006
 gn-0.006
 chimpan-0.006
Token hugged
Token ID41130
Feature activation+7.35e-01

Pos logit contributions
 polar+0.002
 ranger+0.002
 gn+0.002
 tow+0.002
 chimpan+0.002
Neg logit contributions
ivated-0.002
icker-0.002
 tant-0.002
our-0.002
arre-0.002
Token her
Token ID607
Feature activation+2.11e-01

Pos logit contributions
 polar+0.022
 ranger+0.021
 tow+0.020
 gn+0.020
 chimpan+0.019
Neg logit contributions
ivated-0.015
icker-0.014
our-0.014
nam-0.013
 hey-0.013
Token.
Token ID13
Feature activation-1.41e-02

Pos logit contributions
 polar+0.005
 tow+0.004
 chimpan+0.004
 ranger+0.004
 gn+0.004
Neg logit contributions
nam-0.006
 tant-0.006
ivated-0.006
our-0.006
icker-0.006
Token
Token ID198
Feature activation+5.09e-01

Pos logit contributions
ivated+0.000
icker+0.000
onel+0.000
 hey+0.000
unct+0.000
Neg logit contributions
 ranger-0.000
 polar-0.000
 tow-0.000
 gn-0.000
 chimpan-0.000
Token<|endoftext|>
Token ID50256
Feature activation-9.86e-02

Pos logit contributions
 polar+0.012
 ranger+0.011
 tow+0.011
 gn+0.010
 chimpan+0.010
Neg logit contributions
ivated-0.013
our-0.012
nam-0.012
 tant-0.012
 hey-0.012
TokenOnce
Token ID7454
Feature activation-2.35e-01

Pos logit contributions
 Def+0.001
upon+0.001
 Ow+0.001
ivated+0.001
arre+0.001
Neg logit contributions
 polar-0.004
 ranger-0.003
 gn-0.003
 chimpan-0.003
 tow-0.003
Token upon
Token ID2402
Feature activation-6.83e-01

Pos logit contributions
ivated+0.006
 hey+0.006
nam+0.006
obb+0.006
arre+0.005
Neg logit contributions
 polar-0.006
 ranger-0.005
 tow-0.005
!-0.005
 gn-0.005
Token a
Token ID257
Feature activation+6.93e-01

Pos logit contributions
ivated+0.020
icker+0.019
nam+0.019
our+0.019
 Def+0.019
Neg logit contributions
 polar-0.014
 ranger-0.013
 tow-0.012
 gn-0.012
 chimpan-0.012
Token time
Token ID640
Feature activation+3.68e-01

Pos logit contributions
 polar+0.016
 ranger+0.015
 tow+0.015
 gn+0.014
 chimpan+0.014
Neg logit contributions
ivated-0.019
nam-0.018
our-0.017
 hey-0.017
cient-0.017
Token there
Token ID612
Feature activation+5.55e-02

Pos logit contributions
 polar+0.006
 ranger+0.006
 tow+0.006
 gn+0.006
 chimpan+0.005
Neg logit contributions
ivated-0.012
icker-0.011
our-0.011
nam-0.011
 hey-0.011
Token was
Token ID373
Feature activation-8.16e-02

Pos logit contributions
 polar+0.001
 ranger+0.001
 gn+0.001
 chimpan+0.001
 tow+0.001
Neg logit contributions
 Def-0.001
ivated-0.001
our-0.001
icker-0.001
 Ow-0.001
Token a
Token ID257
Feature activation-2.61e-02

Pos logit contributions
ivated+0.002
icker+0.002
nam+0.002
our+0.002
 Def+0.002
Neg logit contributions
 polar-0.002
 ranger-0.002
 tow-0.001
 gn-0.001
 chimpan-0.001
Token puppy
Token ID26188
Feature activation+2.08e-01

Pos logit contributions
ivated+0.000
icker+0.000
nam+0.000
 hey+0.000
our+0.000
Neg logit contributions
 polar-0.001
 ranger-0.001
 tow-0.001
 gn-0.001
 chimpan-0.001
Token.
Token ID13
Feature activation+2.05e-01

Pos logit contributions
 tow+0.004
 polar+0.004
falls+0.004
 chimpan+0.004
 waterfall+0.004
Neg logit contributions
cient-0.005
icker-0.005
our-0.005
nam-0.005
ivated-0.005
Token He
Token ID679
Feature activation+2.02e-01

Pos logit contributions
 polar+0.007
 ranger+0.007
 gn+0.007
 chimpan+0.006
 waterfall+0.006
Neg logit contributions
ivated-0.003
 Def-0.003
nam-0.003
 Blood-0.003
icker-0.003
Token crazy
Token ID7165
Feature activation-4.23e-02

Pos logit contributions
 polar+0.003
 tow+0.003
 ranger+0.003
 gn+0.003
 chimpan+0.003
Neg logit contributions
ivated-0.002
 ent-0.002
 tant-0.002
 Def-0.002
bs-0.002
Token.
Token ID13
Feature activation-1.15e-01

Pos logit contributions
our+0.001
ivated+0.001
 ent+0.001
onel+0.001
arre+0.001
Neg logit contributions
 polar-0.001
 tow-0.001
 chimpan-0.001
 ranger-0.001
 gn-0.001
Token
Token ID198
Feature activation-2.06e-02

Pos logit contributions
ivated+0.003
 tant+0.003
nam+0.003
 hey+0.003
our+0.003
Neg logit contributions
 polar-0.003
 tow-0.003
 ranger-0.003
 gn-0.003
 chimpan-0.002
Token
Token ID198
Feature activation+5.68e-02

Pos logit contributions
ivated+0.001
nam+0.001
our+0.001
 hey+0.001
 tant+0.001
Neg logit contributions
 polar-0.000
 tow-0.000
 ranger-0.000
 gn-0.000
 chimpan-0.000
TokenThen
Token ID6423
Feature activation+7.06e-02

Pos logit contributions
 polar+0.002
 ranger+0.002
 tow+0.002
 gn+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.001
our-0.001
nam-0.001
icker-0.001
 tant-0.001
Token one
Token ID530
Feature activation-5.62e-01

Pos logit contributions
 polar+0.001
 ranger+0.001
 gn+0.001
 tow+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.002
our-0.002
icker-0.002
 hey-0.002
nam-0.002
Token day
Token ID1110
Feature activation+1.63e-01

Pos logit contributions
ivated+0.011
icker+0.010
our+0.010
 tant+0.010
 Def+0.010
Neg logit contributions
 polar-0.016
 ranger-0.016
 gn-0.015
 tow-0.015
 chimpan-0.015
Token,
Token ID11
Feature activation+2.59e-01

Pos logit contributions
 polar+0.004
 ranger+0.004
 gn+0.004
 tow+0.003
glers+0.003
Neg logit contributions
our-0.004
bs-0.004
ivated-0.004
 hey-0.004
icker-0.004
Token the
Token ID262
Feature activation-1.65e-01

Pos logit contributions
 polar+0.006
 ranger+0.005
 gn+0.005
 tow+0.005
 chimpan+0.005
Neg logit contributions
ivated-0.007
nam-0.007
our-0.007
icker-0.007
 hey-0.007
Token infant
Token ID11212
Feature activation-8.61e-01

Pos logit contributions
ivated+0.003
icker+0.003
our+0.003
 hey+0.003
 Def+0.003
Neg logit contributions
 polar-0.005
 ranger-0.005
 tow-0.005
 gn-0.005
 chimpan-0.004
Token started
Token ID2067
Feature activation+1.99e-01

Pos logit contributions
our+0.017
 ent+0.017
arre+0.016
anna+0.016
bs+0.016
Neg logit contributions
 polar-0.022
 tow-0.021
 ranger-0.021
 chimpan-0.021
glers-0.020
Token talked
Token ID6619
Feature activation-1.98e-01

Pos logit contributions
 polar+0.002
 ranger+0.002
 tow+0.002
 chimpan+0.002
 gn+0.002
Neg logit contributions
ivated-0.002
nam-0.002
 ent-0.002
bs-0.002
 hey-0.002
Token about
Token ID546
Feature activation+2.83e-02

Pos logit contributions
ivated+0.004
icker+0.004
our+0.004
 tant+0.004
 Def+0.004
Neg logit contributions
 polar-0.006
 gn-0.005
 ranger-0.005
 chimpan-0.005
 tow-0.005
Token their
Token ID511
Feature activation+7.25e-02

Pos logit contributions
 polar+0.001
 ranger+0.001
 bisc+0.001
 chimpan+0.001
glers+0.001
Neg logit contributions
nam-0.001
 ent-0.001
ivated-0.001
 Him-0.000
 hey-0.000
Token adventures
Token ID17545
Feature activation-1.89e-01

Pos logit contributions
 polar+0.002
 gn+0.002
 ranger+0.002
 tow+0.002
 chimpan+0.002
Neg logit contributions
ivated-0.001
icker-0.001
 miserable-0.001
 unhappy-0.001
 tant-0.001
Token.
Token ID13
Feature activation-8.58e-02

Pos logit contributions
our+0.004
ivated+0.004
nam+0.004
icker+0.004
bs+0.004
Neg logit contributions
 polar-0.005
 gn-0.005
 chimpan-0.004
 tow-0.004
 bisc-0.004
Token And
Token ID843
Feature activation+4.00e-01

Pos logit contributions
ivated+0.002
nam+0.002
 tant+0.002
our+0.002
 hey+0.002
Neg logit contributions
 polar-0.002
 tow-0.002
 ranger-0.002
 gn-0.002
 chimpan-0.002
Token the
Token ID262
Feature activation+4.42e-01

Pos logit contributions
 polar+0.011
 ranger+0.010
 tow+0.010
 gn+0.010
 chimpan+0.010
Neg logit contributions
ivated-0.009
nam-0.009
 hey-0.008
our-0.008
 Def-0.008
Token harbor
Token ID25451
Feature activation-1.37e+00

Pos logit contributions
 ranger+0.013
 gn+0.013
 polar+0.013
 bisc+0.013
uit+0.013
Neg logit contributions
ivated-0.007
 miserable-0.007
 sad-0.007
 bored-0.007
 unhappy-0.006
Token was
Token ID373
Feature activation-4.39e-01

Pos logit contributions
ivated+0.032
arre+0.032
 ent+0.031
 Def+0.031
our+0.031
Neg logit contributions
 polar-0.035
 gn-0.030
 tow-0.029
 chimpan-0.029
 bisc-0.029
Token always
Token ID1464
Feature activation+3.40e-02

Pos logit contributions
 ent+0.008
ivated+0.007
 miserable+0.007
Eventually+0.007
 unhappy+0.007
Neg logit contributions
 polar-0.014
 ranger-0.014
 gn-0.014
 chimpan-0.013
 bisc-0.013
Token happy
Token ID3772
Feature activation-5.62e-01

Pos logit contributions
 polar+0.001
 gn+0.001
 ranger+0.001
 chimpan+0.001
 tow+0.001
Neg logit contributions
nam-0.001
ivated-0.001
 ent-0.001
 miserable-0.001
 bored-0.001
Token patch
Token ID8529
Feature activation-3.26e-01

Pos logit contributions
our+0.014
ivated+0.014
icker+0.014
 Def+0.013
nam+0.013
Neg logit contributions
 polar-0.014
 ranger-0.013
 tow-0.013
 gn-0.013
 chimpan-0.013
Token to
Token ID284
Feature activation+7.81e-02

Pos logit contributions
our+0.007
icker+0.007
ivated+0.007
bs+0.007
she+0.007
Neg logit contributions
 polar-0.009
 chimpan-0.008
 tow-0.008
 amusement-0.007
 coy-0.007
Token find
Token ID1064
Feature activation-7.53e-02

Pos logit contributions
 polar+0.002
 tow+0.002
 ranger+0.002
 gn+0.002
 chimpan+0.002
Neg logit contributions
ivated-0.002
arre-0.002
 tant-0.002
icker-0.002
 Def-0.002
Token the
Token ID262
Feature activation-1.48e-01

Pos logit contributions
ivated+0.002
icker+0.002
our+0.002
nam+0.002
 hey+0.002
Neg logit contributions
 polar-0.002
 ranger-0.001
 tow-0.001
 gn-0.001
 chimpan-0.001
Token perfect
Token ID2818
Feature activation-2.90e-01

Pos logit contributions
ivated+0.004
arre+0.004
icker+0.004
our+0.004
 tant+0.004
Neg logit contributions
 polar-0.004
 ranger-0.003
 tow-0.003
 gn-0.003
 chimpan-0.003
Token pumpkin
Token ID30089
Feature activation-7.31e-01

Pos logit contributions
our+0.006
ivated+0.005
icker+0.005
 tant+0.005
nam+0.005
Neg logit contributions
 polar-0.009
 ranger-0.008
 gn-0.008
 tow-0.008
 chimpan-0.008
Token.
Token ID13
Feature activation+2.56e-01

Pos logit contributions
our+0.018
nam+0.018
cient+0.017
oney+0.017
bs+0.017
Neg logit contributions
 polar-0.017
 tow-0.017
 chimpan-0.016
 gn-0.015
 amusement-0.015
Token
Token ID198
Feature activation+5.05e-01

Pos logit contributions
 ranger+0.004
 tow+0.004
 polar+0.004
 gn+0.003
 bisc+0.003
Neg logit contributions
unct-0.009
onel-0.009
nam-0.008
 unnecessary-0.008
ivated-0.008
Token
Token ID198
Feature activation+2.72e-01

Pos logit contributions
 polar+0.010
 tow+0.009
 ranger+0.009
!+0.008
 gn+0.008
Neg logit contributions
nam-0.016
ivated-0.015
our-0.015
 hey-0.015
unct-0.015
TokenL
Token ID43
Feature activation+4.14e-01

Pos logit contributions
 polar+0.007
 ranger+0.007
 tow+0.006
 gn+0.006
 chimpan+0.006
Neg logit contributions
our-0.006
unct-0.006
ivated-0.006
onel-0.006
icker-0.006
Tokenily
Token ID813
Feature activation+2.03e-01

Pos logit contributions
 polar+0.010
 ranger+0.009
 gn+0.009
 tow+0.009
 chimpan+0.008
Neg logit contributions
nam-0.010
ivated-0.010
cient-0.010
icker-0.010
our-0.010
Token up
Token ID510
Feature activation-3.38e-01

Pos logit contributions
ivated+0.005
our+0.004
icker+0.004
 tant+0.004
 Def+0.004
Neg logit contributions
 polar-0.007
 ranger-0.006
 chimpan-0.006
 tow-0.006
 gn-0.006
Token.
Token ID13
Feature activation-2.44e-01

Pos logit contributions
ivated+0.008
our+0.007
 tant+0.007
nam+0.007
icker+0.007
Neg logit contributions
 polar-0.009
 chimpan-0.009
 ranger-0.008
 tow-0.008
 gn-0.008
Token It
Token ID632
Feature activation+7.51e-02

Pos logit contributions
ivated+0.005
our+0.005
 tant+0.005
icker+0.005
nam+0.005
Neg logit contributions
 polar-0.007
 ranger-0.007
 tow-0.007
 gn-0.006
 chimpan-0.006
Token became
Token ID2627
Feature activation+3.78e-02

Pos logit contributions
 polar+0.002
 ranger+0.002
 tow+0.002
 chimpan+0.001
 gn+0.001
Neg logit contributions
ivated-0.002
 tant-0.002
 Def-0.002
arre-0.002
icker-0.002
Token the
Token ID262
Feature activation-1.72e-01

Pos logit contributions
 polar+0.001
 ranger+0.001
 chimpan+0.001
 gn+0.001
 tow+0.001
Neg logit contributions
nam-0.001
 tant-0.001
 ent-0.001
ivated-0.001
 unnecessary-0.001
Token biggest
Token ID4094
Feature activation-9.25e-01

Pos logit contributions
ivated+0.003
nam+0.003
our+0.003
 hey+0.003
icker+0.003
Neg logit contributions
 polar-0.006
 ranger-0.005
 gn-0.005
 tow-0.005
 chimpan-0.005
Token balloon
Token ID21190
Feature activation-3.63e-01

Pos logit contributions
 tant+0.021
our+0.020
ivated+0.020
arre+0.019
 ent+0.018
Neg logit contributions
 polar-0.024
 gn-0.023
 chimpan-0.022
 ranger-0.022
glers-0.020
Token she
Token ID673
Feature activation-3.41e-03

Pos logit contributions
our+0.007
bs+0.007
onel+0.007
ivated+0.007
she+0.007
Neg logit contributions
 polar-0.011
 tow-0.009
 chimpan-0.009
 gn-0.009
 amusement-0.009
Token had
Token ID550
Feature activation+9.40e-01

Pos logit contributions
ivated+0.000
our+0.000
nam+0.000
bs+0.000
 hey+0.000
Neg logit contributions
 polar-0.000
 tow-0.000
 ranger-0.000
 gn-0.000
 chimpan-0.000
Token ever
Token ID1683
Feature activation-3.35e-01

Pos logit contributions
 polar+0.028
 tow+0.024
 ranger+0.023
 chimpan+0.023
 gn+0.022
Neg logit contributions
our-0.021
ivated-0.021
osing-0.020
bs-0.019
 ent-0.019
Token seen
Token ID1775
Feature activation-2.46e-01

Pos logit contributions
ivated+0.006
our+0.006
arre+0.006
nam+0.006
 tant+0.006
Neg logit contributions
 polar-0.010
 tow-0.010
 ranger-0.009
 chimpan-0.009
 gn-0.009
Token.
Token ID13
Feature activation-1.88e-01

Pos logit contributions
 waterfall+0.002
 chimpan+0.002
 ranger+0.002
 tow+0.002
 polar+0.002
Neg logit contributions
our-0.002
anna-0.002
icker-0.002
 Him-0.002
cient-0.002
Token He
Token ID679
Feature activation+4.35e-01

Pos logit contributions
ivated+0.004
our+0.004
icker+0.004
 Def+0.004
arre+0.004
Neg logit contributions
 polar-0.005
 ranger-0.004
 gn-0.004
 tow-0.004
 chimpan-0.004
Token had
Token ID550
Feature activation+3.50e-01

Pos logit contributions
 tow+0.011
 waterfall+0.011
 polar+0.010
 amusement+0.010
 ranger+0.010
Neg logit contributions
 Blood-0.009
Finally-0.008
 Amid-0.008
Ax-0.008
icker-0.008
Token a
Token ID257
Feature activation-3.37e-01

Pos logit contributions
 polar+0.007
 ranger+0.007
 gn+0.007
 tow+0.007
 chimpan+0.006
Neg logit contributions
ivated-0.009
nam-0.009
icker-0.009
 Def-0.009
 hey-0.009
Token big
Token ID1263
Feature activation-8.94e-02

Pos logit contributions
ivated+0.010
our+0.009
icker+0.009
 hey+0.009
 Def+0.009
Neg logit contributions
 polar-0.008
 ranger-0.007
 gn-0.007
 tow-0.007
 chimpan-0.006
Token,
Token ID11
Feature activation-1.09e+00

Pos logit contributions
ivated+0.002
our+0.002
icker+0.002
 tant+0.002
nam+0.002
Neg logit contributions
 polar-0.002
 ranger-0.002
 tow-0.002
 gn-0.002
 chimpan-0.002
Token yellow
Token ID7872
Feature activation-9.39e-02

Pos logit contributions
ivated+0.025
nam+0.025
 tant+0.024
icker+0.024
our+0.024
Neg logit contributions
 polar-0.027
 ranger-0.025
 tow-0.025
 gn-0.024
 chimpan-0.023
Token tractor
Token ID38278
Feature activation+2.98e-02

Pos logit contributions
our+0.002
ivated+0.002
icker+0.002
 tant+0.002
nam+0.002
Neg logit contributions
 polar-0.002
 ranger-0.002
 tow-0.002
 gn-0.002
 chimpan-0.002
Token
Token ID6184
Feature activation+3.89e-01

Pos logit contributions
 polar+0.001
 waterfall+0.001
 chimpan+0.001
 coy+0.001
 amusement+0.001
Neg logit contributions
cient-0.000
our-0.000
 But-0.000
nam-0.000
 alone-0.000
Token
Token ID95
Feature activation+5.84e-01

Pos logit contributions
 polar+0.011
 ranger+0.010
 tow+0.010
 gn+0.010
 chimpan+0.010
Neg logit contributions
ivated-0.008
our-0.008
icker-0.008
 hey-0.008
nam-0.008
Token
Token ID26391
Feature activation+3.82e-01

Pos logit contributions
 polar+0.016
 ranger+0.016
 tow+0.015
 gn+0.015
 chimpan+0.015
Neg logit contributions
ivated-0.013
nam-0.012
 tant-0.012
icker-0.012
our-0.011
Token!"
Token ID2474
Feature activation-5.70e-01

Pos logit contributions
our+0.002
ivated+0.002
arre+0.002
oney+0.002
 tant+0.002
Neg logit contributions
 polar-0.002
 tow-0.001
 ranger-0.001
 chimpan-0.001
 gn-0.001
Token
Token ID198
Feature activation-1.31e-01

Pos logit contributions
cient+0.019
ivated+0.019
onel+0.019
iable+0.019
arre+0.019
Neg logit contributions
 ranger-0.009
 polar-0.008
 gn-0.008
 tow-0.008
!-0.007
Token
Token ID198
Feature activation-2.92e-01

Pos logit contributions
ivated+0.004
our+0.004
nam+0.004
arre+0.003
 tant+0.003
Neg logit contributions
 polar-0.003
 ranger-0.003
 tow-0.003
 gn-0.003
 chimpan-0.002
TokenTom
Token ID13787
Feature activation+9.62e-02

Pos logit contributions
ivated+0.007
our+0.007
icker+0.007
 Def+0.006
 tant+0.006
Neg logit contributions
 polar-0.008
 ranger-0.007
 tow-0.007
 gn-0.007
 chimpan-0.007
Token and
Token ID290
Feature activation-1.32e+00

Pos logit contributions
 polar+0.001
 ranger+0.001
 gn+0.001
 tow+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.003
icker-0.003
nam-0.003
our-0.003
 hey-0.003
Token Lily
Token ID20037
Feature activation-8.66e-01

Pos logit contributions
 tant+0.027
nam+0.027
 Def+0.026
ivated+0.026
 Blood+0.026
Neg logit contributions
 polar-0.035
 waterfall-0.033
 gn-0.032
 ranger-0.032
 chimpan-0.032
Token felt
Token ID2936
Feature activation-6.15e-01

Pos logit contributions
 Him+0.025
 unnecessary+0.025
icker+0.024
ivated+0.024
oney+0.024
Neg logit contributions
 ranger-0.016
 polar-0.015
!-0.014
 gn-0.014
 tow-0.013
Token sad
Token ID6507
Feature activation-6.52e-02

Pos logit contributions
our+0.010
ivated+0.010
icker+0.009
 Def+0.009
oney+0.009
Neg logit contributions
 polar-0.020
 ranger-0.019
 tow-0.019
 gn-0.019
 chimpan-0.018
Token.
Token ID13
Feature activation+3.06e-01

Pos logit contributions
ivated+0.003
nam+0.002
icker+0.002
cient+0.002
 Def+0.002
Neg logit contributions
 polar-0.001
 ranger-0.001
 gn-0.001
 tow-0.001
 chimpan-0.000
Token They
Token ID1119
Feature activation-1.60e-01

Pos logit contributions
 polar+0.007
 ranger+0.006
 tow+0.006
 gn+0.006
 chimpan+0.006
Neg logit contributions
ivated-0.008
icker-0.008
our-0.008
nam-0.008
 hey-0.008
Token did
Token ID750
Feature activation-5.06e-02

Pos logit contributions
icker+0.005
ivated+0.005
 Him+0.005
ants+0.005
oney+0.005
Neg logit contributions
 polar-0.003
 ranger-0.003
!-0.002
 gn-0.002
 c-0.002
Token.
Token ID13
Feature activation+5.17e-02

Pos logit contributions
our+0.017
 tant+0.016
arre+0.016
care+0.015
 bored+0.015
Neg logit contributions
 polar-0.024
 tow-0.024
 chimpan-0.022
 waterfall-0.022
 Swan-0.021
Token He
Token ID679
Feature activation+1.26e-01

Pos logit contributions
 polar+0.001
 tow+0.001
 ranger+0.001
 gn+0.001
 chimpan+0.001
Neg logit contributions
ivated-0.001
icker-0.001
nam-0.001
 tant-0.001
obb-0.001
Token thought
Token ID1807
Feature activation-9.31e-01

Pos logit contributions
 polar+0.003
 ranger+0.003
 tow+0.003
 chimpan+0.003
 gn+0.003
Neg logit contributions
our-0.003
ivated-0.003
 tant-0.003
 Def-0.003
arre-0.003
Token about
Token ID546
Feature activation+1.53e-01

Pos logit contributions
ivated+0.023
our+0.023
 Def+0.023
icker+0.023
 tant+0.022
Neg logit contributions
 polar-0.022
 ranger-0.021
 gn-0.019
 chimpan-0.019
 tow-0.019
Token it
Token ID340
Feature activation-2.32e-01

Pos logit contributions
 polar+0.004
 ranger+0.004
 chimpan+0.004
 tow+0.004
glers+0.004
Neg logit contributions
nam-0.003
 Def-0.003
our-0.003
 hey-0.003
iable-0.003
Token for
Token ID329
Feature activation-8.33e-01

Pos logit contributions
our+0.006
ivated+0.006
 Def+0.005
arre+0.005
iable+0.005
Neg logit contributions
 polar-0.006
 tow-0.005
 ranger-0.005
 gn-0.005
 chimpan-0.005
Token a
Token ID257
Feature activation-3.97e-01

Pos logit contributions
ivated+0.021
nam+0.020
 hey+0.020
 Def+0.020
our+0.020
Neg logit contributions
 polar-0.020
 ranger-0.019
 gn-0.018
 tow-0.017
 chimpan-0.017
Token long
Token ID890
Feature activation-3.69e-01

Pos logit contributions
ivated+0.008
 tant+0.007
 Def+0.007
nam+0.007
icker+0.007
Neg logit contributions
 polar-0.012
 ranger-0.011
 tow-0.010
 gn-0.010
 chimpan-0.010
Token time
Token ID640
Feature activation+1.29e-01

Pos logit contributions
 tant+0.006
 Def+0.005
ivated+0.005
our+0.005
arre+0.005
Neg logit contributions
 polar-0.012
 ranger-0.012
 chimpan-0.011
 gn-0.011
 tow-0.011
Token.
Token ID13
Feature activation-8.89e-02

Pos logit contributions
 polar+0.003
 chimpan+0.003
 ranger+0.003
glers+0.003
 tow+0.003
Neg logit contributions
our-0.003
ivated-0.003
 hey-0.003
 ent-0.003
bs-0.003
Token
Token ID198
Feature activation+4.33e-01

Pos logit contributions
ivated+0.002
nam+0.002
icker+0.002
 tant+0.002
our+0.002
Neg logit contributions
 polar-0.002
 ranger-0.002
 tow-0.002
 gn-0.002
 chimpan-0.002