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

    Neuronpedia

    INDEX
    Explanations

    identifiers, numerical values, and legal or official terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rance
    -0.16
    dy
    -0.14
    Ùĩ
    -0.14
    nea
    -0.14
    oney
    -0.14
    reeNode
    -0.14
    onga
    -0.14
    кÑĥÑĤ
    -0.14
     ÑģоÑģÑĤоÑı
    -0.14
    eper
    -0.14
    POSITIVE LOGITS
    (s
    0.20
    sWith
    0.17
    ss
    0.17
    sss
    0.17
    ssp
    0.15
     nÃło
    0.14
    们
    0.14
    upe
    0.14
    ÏĢα
    0.14
    [s
    0.14
    Act Density 0.256%

    No Known Activations