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

    Neuronpedia

    INDEX
    Explanations

    phrases related to international locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of square brackets and commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seams
    -0.75
     antioxid
    -0.67
     exchanges
    -0.64
    etic
    -0.63
    arnaev
    -0.62
    matically
    -0.62
    ãĥ¼ãĥ³
    -0.60
     SAM
    -0.59
    eday
    -0.59
    oÄŁ
    -0.57
    POSITIVE LOGITS
    ...]
    1.39
    Pg
    1.27
    âĢ¦]
    1.26
    Footnote
    1.09
    note
    1.03
    ?]
    0.97
    sic
    0.90
    :]
    0.89
    src
    0.87
    via
    0.86
    Act Density 0.019%

    No Known Activations