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

    Neuronpedia

    INDEX
    Explanations

    words indicating physical descriptions and conditions of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     magique
    -0.66
    RectangleBorder
    -0.63
     Theſe
    -0.62
     spéciaux
    -0.59
     nahilalakip
    -0.58
     Monfieur
    -0.56
    verge
    -0.55
    Portail
    -0.55
    fauna
    -0.55
     Jefus
    -0.54
    POSITIVE LOGITS
     previous
    0.86
    Someone
    0.82
    Somebody
    0.82
     someone
    0.79
    previous
    0.79
    someone
    0.77
     past
    0.76
    somebody
    0.76
     recent
    0.76
     Somebody
    0.74
    Act Density 0.384%

    No Known Activations