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

    Neuronpedia

    INDEX
    Explanations

    instances of the term "no" and related phrases indicating negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _keeper
    -0.17
    еÑı
    -0.16
     Islands
    -0.15
    gu
    -0.14
    -vars
    -0.14
    eya
    -0.14
    cmc
    -0.14
    価
    -0.14
    asje
    -0.14
    èĸĦ
    -0.14
    POSITIVE LOGITS
    arend
    0.15
    tractor
    0.14
     Cov
    0.14
     Bett
    0.13
    icular
    0.13
    Cha
    0.13
     [("
    0.13
    ÑģÑĤин
    0.13
    orado
    0.13
     diz
    0.13
    Act Density 0.059%

    No Known Activations