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

    Neuronpedia

    INDEX
    Explanations

    emails or usernames

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Labyrinth
    -0.75
     Rebellion
    -0.73
     Inher
    -0.73
     Characters
    -0.73
     Lite
    -0.72
     Masquerade
    -0.72
     Ribbon
    -0.72
     Zoo
    -0.71
     Symb
    -0.70
     Fortune
    -0.70
    POSITIVE LOGITS
    bryce
    1.25
    john
    1.12
    maxwell
    1.09
    brown
    1.01
    etsy
    1.00
    thur
    0.98
    patrick
    0.98
    anders
    0.97
    ryan
    0.97
    iann
    0.95
    Act Density 0.048%

    No Known Activations