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

    Neuronpedia

    INDEX
    Explanations

    elements related to safety regulations and guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.82
    ArrowToggle
    -0.79
     CreateTagHelper
    -0.68
     ModelExpression
    -0.68
    ंदीखरीदारी
    -0.68
     Paglinawan
    -0.65
    PreferredItem
    -0.63
    twimg
    -0.63
    +#+#
    -0.62
    GEBURTSDATUM
    -0.61
    POSITIVE LOGITS
     LEYENDO
    0.57
    KommentareTeilen
    0.56
    nameof
    0.54
    pters
    0.52
    resetPassword
    0.51
    upsi
    0.50
    tonode
    0.49
    0
    0.49
     Chartres
    0.49
    ToAction
    0.47
    Act Density 0.061%

    No Known Activations