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

    Neuronpedia

    INDEX
    Explanations

    references to significant events or phenomena that have impactful consequences

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     correctes
    -0.53
    giai
    -0.48
    pielt
    -0.45
    AttributeSet
    -0.45
     little
    -0.45
    perror
    -0.44
    číta
    -0.43
     kereszt
    -0.43
     merid
    -0.43
    графії
    -0.43
    POSITIVE LOGITS
    Hentet
    0.92
     such
    0.91
    such
    0.89
    Such
    0.83
     solche
    0.82
    期刊论文
    0.80
    windowFixed
    0.79
     nahilalakip
    0.79
     Such
    0.79
    Jeografia
    0.78
    Act Density 0.085%

    No Known Activations