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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Pl
    0.77
    ോ
    0.75
    Sch
    0.73
    ii
    0.72
    st
    0.71
    ona
    0.71
     величи
    0.71
     ఘ
    0.70
    of
    0.70
    ш
    0.69
    POSITIVE LOGITS
     Omicron
    0.97
     Godzilla
    0.93
     empê
    0.89
     influencer
    0.89
     psychopath
    0.88
     homeopathy
    0.88
     Viral
    0.87
     Meghan
    0.87
     sadistic
    0.86
     dirige
    0.86
    Act Density 0.000%

    No Known Activations