INDEX
Explanations
occurrences of the name "Travis."
New Auto-Interp
Negative Logits
hw
-0.16
tabl
-0.16
_subplot
-0.15
mts
-0.14
ambre
-0.14
tering
-0.14
ollipop
-0.14
spiel
-0.14
eva
-0.14
STANDARD
-0.14
POSITIVE LOGITS
-ci
0.26
CI
0.25
CI
0.21
Walton
0.17
_CI
0.17
kalan
0.16
Scott
0.16
aurus
0.16
esti
0.16
ci
0.15
Activations Density 0.003%