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

    Neuronpedia

    INDEX
    Explanations

    second-person pronouns and phrases addressing the reader directly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.97
    KommentareTeilen
    -0.85
     صوتيه
    -0.81
    MigrationBuilder
    -0.81
     okuyayım
    -0.72
    ValueStyle
    -0.71
    :✨
    -0.71
    Tembelea
    -0.71
     ujednoznacz
    -0.70
     >=",
    -0.69
    POSITIVE LOGITS
     kanton
    0.48
     possibly
    0.44
    versiti
    0.43
    消
    0.42
     happen
    0.42
    poz
    0.42
     EClass
    0.42
     TextAlign
    0.42
     cellspacing
    0.41
     Holz
    0.41
    Act Density 0.138%

    No Known Activations