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

    Neuronpedia

    INDEX
    Explanations

    mathematical and numerical notations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.73
     Tid
    -0.68
    Downloadha
    -0.66
     Lazarus
    -0.65
    creen
    -0.64
     Crusher
    -0.64
     Pension
    -0.62
    wagen
    -0.62
    WARD
    -0.62
     laugh
    -0.61
    POSITIVE LOGITS
    Ħ¢
    1.56
    Ĥ
    1.45
    ĵ
    1.41
    Ĥª
    1.40
    Ħ
    1.39
    ħ
    1.38
    Į
    1.34
    İ
    1.29
    Ĭ
    1.28
    ķ
    1.27
    Act Density 0.006%

    No Known Activations