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

    Neuronpedia

    INDEX
    Explanations

    titles of works or notable phrases in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quote
    -0.16
    ikki
    -0.15
    imonial
    -0.14
    lin
    -0.14
    latable
    -0.14
    CAF
    -0.13
    uling
    -0.13
    GOR
    -0.13
    lock
    -0.13
     building
    -0.13
    POSITIVE LOGITS
    aklı
    0.14
    éĨ´
    0.14
    phyl
    0.14
    æ£
    0.14
    bard
    0.14
    ocz
    0.14
    asca
    0.14
    overy
    0.14
    oret
    0.14
    roe
    0.13
    Act Density 0.066%

    No Known Activations