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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating skepticism or critical evaluations of movies or series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nett
    -0.16
    atti
    -0.14
    atern
    -0.14
    utsche
    -0.14
    ru
    -0.14
    almost
    -0.14
    çe
    -0.14
    atri
    -0.14
    venes
    -0.14
     Voor
    -0.14
    POSITIVE LOGITS
    acente
    0.17
     nor
    0.16
     Äijá»Ļt
    0.15
     anch
    0.14
    RIORITY
    0.14
    ÑĭÑģ
    0.14
    leet
    0.14
    _ENCODING
    0.14
     Choice
    0.14
    _complex
    0.14
    Act Density 0.144%

    No Known Activations