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

    Neuronpedia

    INDEX
    Explanations

    JavaScript function syntax related keywords

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly single and double quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REE
    -0.68
    umm
    -0.65
     Dinner
    -0.65
    sych
    -0.65
    robe
    -0.64
    hunt
    -0.64
    conom
    -0.63
    FW
    -0.63
     Parables
    -0.62
     Logged
    -0.62
    POSITIVE LOGITS
    ooters
    0.91
     etc
    0.77
     meaning
    0.69
     whence
    0.68
     which
    0.68
     respectively
    0.66
    ð
    0.63
     indicating
    0.63
    pmwiki
    0.62
     adjective
    0.61
    Act Density 0.043%

    No Known Activations