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

    Neuronpedia

    INDEX
    Explanations

    common introductory phrases in text, possibly related to software documentation or announcements

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "This" and variations of it in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĭ±
    -0.88
    aneers
    -0.75
    uphem
    -0.75
    bugs
    -0.73
    cery
    -0.73
    ocks
    -0.70
    ARS
    -0.69
    ervatives
    -0.69
    mist
    -0.68
     Deaths
    -0.68
    POSITIVE LOGITS
     includes
    1.08
     entails
    1.05
     ensures
    1.05
     project
    1.01
     enables
    1.01
     week
    1.00
     initiative
    0.98
     endeavor
    0.97
     allows
    0.96
     year
    0.95
    Act Density 0.123%

    No Known Activations