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

    Neuronpedia

    INDEX
    Explanations

    references to reasoning and explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    especie
    -0.63
    WebElementEntity
    -0.58
    PhysRevD
    -0.57
     ویکی‌پدی
    -0.57
    IsPostBack
    -0.56
    MigrationBuilder
    -0.55
     Majefty
    -0.55
    rawtypes
    -0.54
    enchymal
    -0.53
     Infórmanos
    -0.53
    POSITIVE LOGITS
     why
    2.46
     reason
    2.00
    why
    1.93
     Why
    1.75
    Why
    1.72
     reasons
    1.68
     pourquoi
    1.64
    reason
    1.57
    WHY
    1.55
     WHY
    1.55
    Act Density 0.368%

    No Known Activations