INDEX
Explanations
references to a specific individual named Bryant
New Auto-Interp
Negative Logits
951
-0.14
osit
-0.14
_ASSUME
-0.14
#af
-0.14
#ab
-0.14
urdu
-0.14
grim
-0.14
uiten
-0.14
urg
-0.13
chio
-0.13
POSITIVE LOGITS
ant
0.22
antine
0.20
anton
0.19
son
0.19
ce
0.17
anna
0.17
ony
0.17
ants
0.16
antd
0.16
ophy
0.15
Activations Density 0.011%