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

    Neuronpedia

    INDEX
    Explanations

    parts in text where there are multiple periods appearing in sequence

    oai_token-act-pair · gpt-3.5-turbo

    ellipses or other punctuation indicating a pause or omission in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Krug
    -0.70
    ãĥ¼ãĥĨãĤ£
    -0.70
    ously
    -0.70
    uers
    -0.69
    olas
    -0.68
     slope
    -0.66
     slopes
    -0.65
     Galile
    -0.64
    iosyncr
    -0.63
    govtrack
    -0.62
    POSITIVE LOGITS
    etc
    1.01
    Ħ¢
    0.84
    please
    0.83
    walking
    0.83
    where
    0.81
    WOR
    0.75
    Pa
    0.75
    err
    0.75
    MORE
    0.75
    which
    0.74
    Act Density 0.019%

    No Known Activations