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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data, particularly counts and averages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     doInBackground
    -0.47
    hol
    -0.46
    omin
    -0.45
    gania
    -0.44
    feldt
    -0.44
    ɵɵ
    -0.44
    ządu
    -0.43
    /><
    -0.43
    SPJ
    -0.41
    dafrika
    -0.41
    POSITIVE LOGITS
     number
    1.94
     amount
    1.70
    number
    1.49
     Anzahl
    1.39
     aantal
    1.35
     NUMBER
    1.33
     número
    1.25
     Number
    1.25
    NUMBER
    1.23
    Number
    1.20
    Act Density 0.640%

    No Known Activations