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

    Neuronpedia

    INDEX
    Explanations

    key concepts related to accountability and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HeaderCode
    -0.17
    миÑĢ
    -0.15
    agma
    -0.15
     Lic
    -0.15
     Marketable
    -0.14
    668
    -0.14
     Gallagher
    -0.14
    achsen
    -0.14
    Enlarge
    -0.14
    unities
    -0.14
    POSITIVE LOGITS
    iten
    0.15
     alg
    0.15
     Known
    0.15
    IH
    0.14
    worth
    0.14
    enance
    0.14
     Independent
    0.14
     Lie
    0.14
    夢
    0.14
    nk
    0.14
    Act Density 0.140%

    No Known Activations