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

    Neuronpedia

    INDEX
    Explanations

    statements related to opinion or critique

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Bris
    -0.95
     Raqqa
    -0.92
     Qiao
    -0.91
     Reed
    -0.90
     Brist
    -0.86
     Coul
    -0.86
     Laf
    -0.82
     Cruz
    -0.82
     Leban
    -0.82
     Fab
    -0.79
    POSITIVE LOGITS
    game
    1.68
    games
    1.67
    Game
    1.67
     GAME
    1.66
     games
    1.65
     game
    1.64
     Game
    1.59
    Games
    1.58
    GAME
    1.48
     gaming
    1.48
    Act Density 0.269%

    No Known Activations