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

    Neuronpedia

    INDEX
    Explanations

    references to speed and ability in actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    quick to, one for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __":
    -0.56
     فريبيس
    -0.50
    ########.
    -0.47
    InSection
    -0.45
    __":
    -0.44
    rungsseite
    -0.42
    __;
    -0.42
    spesies
    -0.41
    LabelTagHelper
    -0.40
     etkili
    -0.40
    POSITIVE LOGITS
     ones
    0.82
     quick
    0.56
     celui
    0.54
     willing
    0.51
     Ones
    0.50
    ArgumentParser
    0.50
     ready
    0.50
    ones
    0.47
     Quick
    0.47
    quick
    0.46
    Act Density 0.023%

    No Known Activations