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

    Neuronpedia

    INDEX
    Explanations

    references to authors and their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enson
    -0.16
    .Magenta
    -0.16
    erno
    -0.15
    raya
    -0.15
    ux
    -0.14
    аÑĢан
    -0.14
    ilated
    -0.14
    ÑĦÑĸ
    -0.14
    ulta
    -0.14
    лиÑħ
    -0.14
    POSITIVE LOGITS
     himself
    0.19
     his
    0.17
    orz
    0.15
    abcdefghijkl
    0.15
     whom
    0.15
    mpl
    0.14
     our
    0.14
    eyin
    0.14
    ç»ĻæĪij
    0.14
    itone
    0.14
    Act Density 0.216%

    No Known Activations