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

    Neuronpedia

    INDEX
    Explanations

    references to the action of editing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    placeholder
    -0.56
     <<<<<<<<<<<<<<
    -0.55
    tiva
    -0.54
     relatively
    -0.54
     benefit
    -0.54
    elementType
    -0.54
    passo
    -0.54
    مج
    -0.53
     autorytatywna
    -0.52
    ftype
    -0.52
    POSITIVE LOGITS
     فريبيس
    1.00
     edit
    0.90
     Edit
    0.85
     edits
    0.76
     stairs
    0.75
    webElementXpaths
    0.74
    BorderFactory
    0.74
    tableFuture
    0.73
    setVerticalGroup
    0.73
     snippetHide
    0.73
    Act Density 0.091%

    No Known Activations