INDEX
Explanations
elements of irony or satire in text
New Auto-Interp
Negative Logits
ÙĬات
-0.16
ICT
-0.15
IGN
-0.15
839
-0.15
fid
-0.14
AtPath
-0.14
InetAddress
-0.13
/in
-0.13
IGN
-0.13
inski
-0.13
POSITIVE LOGITS
ir
0.99
ir
0.98
Ir
0.89
IR
0.83
IR
0.82
_ir
0.80
Ir
0.79
(ir
0.73
.ir
0.73
иÑĢ
0.66
Activations Density 0.196%