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

    Neuronpedia

    INDEX
    Explanations

    doubled periods in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of ellipses or pauses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.97
    uers
    -0.79
    ously
    -0.78
     purse
    -0.74
    ratulations
    -0.71
    ãĥ³ãĤ¸
    -0.70
     greens
    -0.69
     TAMADRA
    -0.68
    opol
    -0.66
     positives
    -0.64
    POSITIVE LOGITS
    etc
    1.03
    walking
    0.89
    ordered
    0.86
    where
    0.83
    quote
    0.81
    sites
    0.81
    orders
    0.80
    please
    0.78
    Va
    0.78
    they
    0.78
    Act Density 0.014%

    No Known Activations