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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nineteen
    -0.96
     Nine
    -0.91
     Nineteen
    -0.91
     seventies
    -0.86
     Sixth
    -0.82
     sixties
    -0.80
     seventh
    -0.77
     sixth
    -0.77
     Ninth
    -0.76
    Nine
    -0.75
    POSITIVE LOGITS
     isComment
    0.50
    ловек
    0.49
     onOptions
    0.48
    ieteur
    0.47
     universelle
    0.46
    躇
    0.46
    sedur
    0.45
     villaggio
    0.44
     élevées
    0.43
    وق
    0.42
    Act Density 0.440%

    No Known Activations