INDEX
Explanations
instances of the word "so" indicating emphasis or conclusion
New Auto-Interp
Negative Logits
Autoritní
-1.00
`;
-0.98
>");
-0.96
.";
-0.94
*/;
-0.92
"]);
-0.92
)");
-0.91
-0.91
]');
-0.89
']);
-0.89
POSITIVE LOGITS
So
2.68
So
2.65
SO
1.34
SO
1.30
so
1.22
And
1.09
Therefore
1.07
But
1.04
Hence
1.02
Thus
1.01
Activations Density 0.079%