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

    Neuronpedia

    INDEX
    Explanations

    general expressions of routine activities and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _sym
    -0.16
    brero
    -0.16
    yll
    -0.15
    aret
    -0.14
     instead
    -0.14
     Dong
    -0.14
    Symfony
    -0.14
    éĿĪ
    -0.14
    abbo
    -0.13
    lash
    -0.13
    POSITIVE LOGITS
    ãģ¥
    0.16
     Hopkins
    0.16
    iores
    0.15
    iani
    0.15
    ocking
    0.15
    à¥įà¤Ĺत
    0.15
    (æ°´
    0.14
     FITNESS
    0.14
    [src
    0.14
    inen
    0.14
    Act Density 0.276%

    No Known Activations