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

    Neuronpedia

    INDEX
    Explanations

    references to statistical models or formulas

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    TagMode
    -1.11
     veille
    -0.80
     myſelf
    -0.76
    pośred
    -0.74
     schia
    -0.73
     Sols
    -0.72
     vaisselle
    -0.72
     Beams
    -0.71
     célè
    -0.69
     elettron
    -0.69
    POSITIVE LOGITS
    y
    0.70
     Gough
    0.67
    })));
    0.64
    gameserver
    0.64
     McKay
    0.64
    ه
    0.63
    ва
    0.63
    Personensuche
    0.63
    رشف
    0.61
    ografija
    0.61
    Act Density 0.014%

    No Known Activations