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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "per," particularly in contexts that quantify rates or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     per
    -1.14
     Per
    -0.81
    Per
    -0.73
    per
    -0.63
     PER
    -0.57
    InjectAttribute
    -0.52
    PER
    -0.43
     пер
    -0.40
    tagHelperRunner
    -0.39
    RegistryLite
    -0.39
    POSITIVE LOGITS
     becauſe
    0.56
    الحياه
    0.56
     ſtand
    0.54
    :].
    0.53
     الرياضيه
    0.52
    loit
    0.50
    styleType
    0.49
    ftagPool
    0.47
     faſt
    0.47
    agaimana
    0.47
    Act Density 0.008%

    No Known Activations