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

    Neuronpedia

    INDEX
    Explanations

    questions related to identifying truths or falsehoods about specific subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.63
    BeginContext
    -0.62
    atically
    -0.55
     facie
    -0.54
    KommentareTeilen
    -0.54
    ,:),
    -0.52
     interchangeably
    -0.51
     الاطلاع
    -0.50
    selves
    -0.50
    rrggbb
    -0.48
    POSITIVE LOGITS
    +#+#
    1.07
    IndentedString
    0.65
    ensement
    0.58
     himo
    0.54
     OMITBAD
    0.53
     referrerpolicy
    0.52
    rifft
    0.51
    hasMoreElements
    0.51
     kasarigan
    0.50
    UrlResolution
    0.50
    Act Density 0.367%

    No Known Activations