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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ienne
    -0.68
     notor
    -0.67
    awar
    -0.65
     improvised
    -0.65
    usable
    -0.64
    estone
    -0.64
     mercenaries
    -0.63
     rog
    -0.62
     scaven
    -0.62
     granite
    -0.60
    POSITIVE LOGITS
    za
    0.85
    kef
    0.84
    tera
    0.79
    zza
    0.75
    ocaly
    0.75
    heit
    0.74
    ENC
    0.72
    cens
    0.71
    zers
    0.68
     Kendrick
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.