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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different types of people

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various categories of people or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceFile
    -0.92
    £ı
    -0.67
    yss
    -0.67
     Priest
    -0.62
     Butt
    -0.62
    cknow
    -0.61
     Buk
    -0.58
    achu
    -0.57
     Samar
    -0.57
    ?????-
    -0.57
    POSITIVE LOGITS
    hip
    1.09
    ourcing
    0.85
    ourced
    0.83
    pace
    0.83
    hips
    0.78
    umers
    0.77
    '
    0.74
    ']
    0.72
    /$
    0.71
    ele
    0.71
    Act Density 0.291%

    No Known Activations