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

    Neuronpedia

    INDEX
    Explanations

    technical terms and notations in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gallagher
    -0.17
    swer
    -0.16
    lam
    -0.16
     пÑĢим
    -0.14
    iar
    -0.14
    holm
    -0.14
    ÑģÑĮ
    -0.14
    992
    -0.13
    Kn
    -0.13
    alic
    -0.13
    POSITIVE LOGITS
    ķ
    0.18
    Ñīин
    0.17
    çµIJ
    0.16
    .raise
    0.15
    ç´Ļ
    0.15
    ÑĦÑĦ
    0.14
    _as
    0.14
    Raised
    0.14
    sın
    0.14
    ÙĪسط
    0.14
    Act Density 0.033%

    No Known Activations