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

    Neuronpedia

    INDEX
    Explanations

    significant mentions or occurrences of specific proper nouns or specialized terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourd
    -0.16
    lied
    -0.15
    lement
    -0.14
     erg
    -0.14
     fit
    -0.14
    edd
    -0.14
    627
    -0.13
     Hag
    -0.13
     uncertainties
    -0.13
    igi
    -0.13
    POSITIVE LOGITS
     Formation
    0.16
    izzle
    0.15
    Formation
    0.15
    ñana
    0.14
    ÙĨدÙĩ
    0.14
    imiz
    0.14
    uiltin
    0.14
    INES
    0.14
    éĩı
    0.14
     Kür
    0.14
    Act Density 0.004%

    No Known Activations