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

    Neuronpedia

    INDEX
    Explanations

    specific statistical values or metrics related to research results

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Phry
    -0.50
     letti
    -0.50
     conditions
    -0.45
     lyon
    -0.45
     Continuing
    -0.44
    TagMode
    -0.44
     exponentially
    -0.44
    nowu
    -0.44
    pośred
    -0.43
     condition
    -0.43
    POSITIVE LOGITS
     autorytatywna
    0.94
    ValueStyle
    0.90
    verwijspagina
    0.86
     nahilalakip
    0.81
    contentLoaded
    0.78
     propOrder
    0.77
     فريبيس
    0.76
    expandindo
    0.76
    __':
    0.75
    abestanden
    0.73
    Act Density 0.002%

    No Known Activations