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

    Neuronpedia

    INDEX
    Explanations

    numbers or numerical information

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "number of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĺ
    -0.76
    ury
    -0.73
    IER
    -0.71
    ĸļ
    -0.70
    HF
    -0.69
    rust
    -0.69
    Rog
    -0.67
    NW
    -0.67
    forward
    -0.66
    ļéĨĴ
    -0.66
    POSITIVE LOGITS
     times
    0.86
     digits
    0.84
     entries
    0.83
     allowable
    0.81
     occurrences
    0.80
     repet
    0.79
     servings
    0.78
     entrants
    0.75
     pounds
    0.74
     births
    0.74
    Act Density 0.070%

    No Known Activations