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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers or codes, such as scores or dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isle
    -0.16
    issan
    -0.15
    ÑģиÑı
    -0.15
    ÙİØ£
    -0.15
    isan
    -0.14
    aku
    -0.14
    |{↵
    -0.13
     Äijức
    -0.13
    ond
    -0.13
    anda
    -0.13
    POSITIVE LOGITS
    heit
    0.15
    hattan
    0.14
    KHR
    0.14
    CharacterSet
    0.14
    egin
    0.14
    ÑĥÑĤ
    0.14
    ut
    0.14
    utas
    0.14
    -picture
    0.13
     sm
    0.13
    Act Density 0.016%

    No Known Activations