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

    Neuronpedia

    INDEX
    Explanations

    references to caps or capital-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elp
    -0.16
     __("
    -0.15
    IGHL
    -0.15
    ikan
    -0.15
    636
    -0.15
    eya
    -0.15
    имÑĥ
    -0.15
    ees
    -0.14
    ż
    -0.14
    OLOR
    -0.14
    POSITIVE LOGITS
     cap
    0.27
    illary
    0.27
    itol
    0.25
     Cap
    0.25
    itulo
    0.24
    ÃŃtulo
    0.23
    cap
    0.23
    ric
    0.23
    Cap
    0.22
    stone
    0.22
    Act Density 0.017%

    No Known Activations