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

    Neuronpedia

    INDEX
    Explanations

    references to performance or entertainment skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mart
    -0.17
    ooks
    -0.17
    маÑħ
    -0.16
    .priv
    -0.16
    OST
    -0.15
    ies
    -0.15
    recated
    -0.15
    iew
    -0.14
    chor
    -0.14
    /DTD
    -0.14
    POSITIVE LOGITS
    awai
    0.14
    andler
    0.14
    richt
    0.14
    erland
    0.14
     Zak
    0.14
    enk
    0.14
    HING
    0.13
    eyn
    0.13
    enger
    0.13
     Bureau
    0.13
    Act Density 0.037%

    No Known Activations