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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences related to opinions or viewpoints

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Brist
    -0.81
    anwhile
    -0.79
     Osw
    -0.79
     RAD
    -0.76
     Cosmetic
    -0.75
     airs
    -0.74
     horizont
    -0.74
    ifications
    -0.73
     Palest
    -0.72
    Downloadha
    -0.72
    POSITIVE LOGITS
    ¬
    1.47
    Ļ
    1.22
    ¥
    1.14
    ¡
    1.14
    ı
    1.11
    £
    1.10
    Ķ
    1.08
    Ń
    1.04
    Ĵ
    1.03
    ª
    1.03
    Act Density 0.323%

    No Known Activations