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

    Neuronpedia

    INDEX
    Explanations

    technical terms and software-related words related to the KDE desktop environment

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    IBLE
    -0.98
    Ö¼
    -0.97
    phrine
    -0.95
    ources
    -0.92
    ential
    -0.91
    encers
    -0.90
    eric
    -0.87
    天
    -0.86
    iments
    -0.85
    ently
    -0.84
    POSITIVE LOGITS
    istani
    1.25
    patrick
    1.18
    lar
    1.16
    laus
    1.02
     Klux
    0.99
    ernel
    0.99
    ratom
    0.98
    lyak
    0.98
    erala
    0.95
    won
    0.95
    Act Density 2.629%

    No Known Activations