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

    Neuronpedia

    INDEX
    Explanations

    instances of text formatted as citations

    oai_token-act-pair · gpt-3.5-turbo

    references to brackets or similar markers in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intensive
    -0.73
     clash
    -0.71
     extinction
    -0.67
     embargo
    -0.67
     consumption
    -0.66
     smuggling
    -0.65
     dere
    -0.65
     maximum
    -0.64
     seams
    -0.63
     imperson
    -0.63
    POSITIVE LOGITS
    Pg
    1.29
    âĢ¦]
    1.27
    ...]
    1.22
    sic
    1.07
    src
    1.03
    ?]
    0.99
    :]
    0.96
    actionDate
    0.96
    nb
    0.96
    paragraph
    0.95
    Act Density 0.027%

    No Known Activations