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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and titles, particularly related to film or notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ervas
    -0.15
    419
    -0.15
    ç½²
    -0.14
    jan
    -0.14
    urd
    -0.14
    ibar
    -0.14
    obe
    -0.14
    abol
    -0.14
    ikan
    -0.13
    igu
    -0.13
    POSITIVE LOGITS
    .nz
    0.20
    elves
    0.15
    ANI
    0.15
    athers
    0.15
    ansen
    0.15
    -columns
    0.14
    .Assembly
    0.14
    vens
    0.14
     Stap
    0.14
     оÑĤвеÑĤ
    0.14
    Act Density 0.009%

    No Known Activations