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

    Neuronpedia

    INDEX
    Explanations

    references to programming/testing scenarios and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intStringLen
    -0.60
    UserScript
    -0.55
    Gweler
    -0.50
    bibitem
    -0.43
    enschappelijke
    -0.39
    setattr
    -0.39
    windowFixed
    -0.38
    bitat
    -0.37
    tät
    -0.37
    nthetic
    -0.37
    POSITIVE LOGITS
     חיצוניים
    0.96
     <<<<<<<<<<<<<<
    0.94
    참고
    0.92
    Tembelea
    0.90
    IntoConstraints
    0.84
     lenker
    0.80
     كومونز
    0.77
    tvguidetime
    0.75
    ंदीखरीदारी
    0.73
    ValueStyle
    0.72
    Act Density 0.564%

    No Known Activations