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

    Neuronpedia

    INDEX
    Explanations

    statements or phrases expressing opinions or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ſammen
    -0.71
    出版年
    -0.63
    Personensuche
    -0.63
    rbrakk
    -0.61
     dieſes
    -0.61
    ᅝ
    -0.60
     パンチラ
    -0.59
    aryen
    -0.57
    linawan
    -0.57
    <unused8>
    -0.57
    POSITIVE LOGITS
    <bos>
    0.43
    protoimpl
    0.42
     isNameExpr
    0.34
     كومونز
    0.32
    like
    0.32
    Fatalf
    0.32
    Nearly
    0.31
    -
    0.31
    offsetof
    0.31
    Errorf
    0.30
    Act Density 0.248%

    No Known Activations