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

    Neuronpedia

    INDEX
    Explanations

    references to academic publications or articles

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific papers and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ''.
    -0.64
    usercontent
    -0.63
    '.
    -0.60
    .''.
    -0.59
    ".
    -0.58
    .'"
    -0.57
    .).
    -0.55
    NetMessage
    -0.55
    $.
    -0.52
    "!
    -0.52
    POSITIVE LOGITS
     Courier
    0.54
     Lust
    0.53
     Research
    0.53
     Bever
    0.53
     Journalism
    0.52
     Moss
    0.51
    Gall
    0.51
     Paran
    0.51
     Insight
    0.51
     Journals
    0.50
    Act Density 0.957%

    No Known Activations