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

    Neuronpedia

    INDEX
    Explanations

    names of people, likely actors or characters in movies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.74
    ilial
    -0.72
    ascript
    -0.68
    nces
    -0.64
    Versions
    -0.63
    redients
    -0.61
    OURCE
    -0.60
    inarily
    -0.60
    theless
    -0.58
    irlf
    -0.58
    POSITIVE LOGITS
     Lumpur
    1.03
    ikuman
    1.03
    enei
    0.91
    EStream
    0.90
    EStreamFrame
    0.87
    zie
    0.86
    lyak
    0.85
    inski
    0.84
    chuk
    0.80
    istan
    0.75
    Act Density 1.217%

    No Known Activations