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

    Neuronpedia

    INDEX
    Explanations

    terms related to writing and document formatting

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    FROM
    -0.72
    OSP
    -0.72
     McGu
    -0.66
    zono
    -0.66
    racuse
    -0.64
     kanton
    -0.64
     Stato
    -0.62
    Everywhere
    -0.62
    ubble
    -0.61
     Everywhere
    -0.61
    POSITIVE LOGITS
    enterOuterAlt
    0.88
    OfYear
    0.85
     الحره
    0.83
    ollectionView
    0.82
    Writer
    0.82
    stateProvider
    0.81
     Мексичка
    0.81
     Writers
    0.80
    jectable
    0.80
     writer
    0.79
    Act Density 0.007%

    No Known Activations