Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     (
    1.09
    ).
    1.03
    )
    1.01
    ),
    0.97
    );
    0.91
    ↵↵
    0.86
    (
    0.82
     (=
    0.78
    ,
    0.76
    ↵
    0.76
    POSITIVE LOGITS
     criminals
    1.03
     processos
    1.03
    criminals
    0.98
    viruses
    0.96
     piensan
    0.93
    zechoslovakia
    0.92
     vassals
    0.92
     δεν
    0.91
     direitos
    0.90
     знают
    0.89
    Act Density 0.005%

    No Known Activations