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

    Neuronpedia

    INDEX
    Explanations

    titles, headings, or labels within a document

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Jagu
    -0.83
    467
    -0.82
     SolidGoldMagikarp
    -0.81
     1947
    -0.80
     Invaders
    -0.79
     Kira
    -0.79
    ault
    -0.78
     Kra
    -0.77
     Archer
    -0.77
     Lich
    -0.75
    POSITIVE LOGITS
    10
    1.46
     10
    1.29
     1070
    1.09
    2010
    1.07
    1027
    1.02
     ten
    0.97
    102
    0.96
     1050
    0.94
     2010
    0.94
    1024
    0.93
    Act Density 0.439%

    No Known Activations