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

    Neuronpedia

    INDEX
    Explanations

    proper names and specific references related to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ehir
    -0.17
    innamon
    -0.17
    ossible
    -0.14
    _exceptions
    -0.14
    rette
    -0.14
    hei
    -0.13
    ksam
    -0.13
    asu
    -0.13
    acter
    -0.13
    eah
    -0.13
    POSITIVE LOGITS
    son
    0.20
    sson
    0.19
    oldt
    0.15
    desc
    0.14
    spath
    0.14
    pher
    0.14
    utow
    0.14
     son
    0.14
    ellow
    0.14
    IEWS
    0.14
    Act Density 0.244%

    No Known Activations