INDEX
Explanations
sentences related to significant events or topics in politics and society
New Auto-Interp
Negative Logits
n
-0.18
Murray
-0.16
cal
-0.16
cal
-0.15
ike
-0.15
id
-0.15
FS
-0.14
jit
-0.14
omin
-0.14
s
-0.14
POSITIVE LOGITS
brtc
0.18
GOODMAN
0.17
649
0.16
Äįan
0.15
ırak
0.15
alnız
0.15
/renderer
0.15
ruta
0.15
ýt
0.15
ythe
0.14
Activations Density 0.017%