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

    Neuronpedia

    INDEX
    Explanations

    syntax elements like code comments and dots before newlines

    oai_token-act-pair · gpt-3.5-turbo

    ellipses and unfinished sentences or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.92
    uers
    -0.76
     Galile
    -0.70
    ratulations
    -0.69
    ously
    -0.66
     aven
    -0.65
     Stall
    -0.64
     Krug
    -0.64
     slope
    -0.63
     slopes
    -0.62
    POSITIVE LOGITS
    etc
    1.04
    walking
    0.87
    please
    0.83
    where
    0.81
     fixme
    0.81
    ordered
    0.80
    SER
    0.77
    999
    0.77
    cum
    0.76
    ser
    0.76
    Act Density 0.011%

    No Known Activations