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

    Neuronpedia

    INDEX
    Explanations

    scientific terminology and references related to experiments and studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.76
    MLLoader
    -0.72
    MigrationBuilder
    -0.72
     وتسجيلات
    -0.71
    tvguidetime
    -0.71
    rungsseite
    -0.70
     Italijanski
    -0.70
     '\\;'
    -0.68
    AddTagHelper
    -0.65
    UrlResolution
    -0.65
    POSITIVE LOGITS
    IsContent
    0.59
     Ma
    0.53
     which
    0.46
    viste
    0.46
    Ma
    0.45
     Their
    0.45
    LEncoder
    0.44
    Bbb
    0.44
     even
    0.43
    which
    0.43
    Act Density 1.558%

    No Known Activations