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

    Neuronpedia

    INDEX
    Explanations

    sources or citations in text

    oai_token-act-pair · gpt-3.5-turbo

    the source of information or references in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    joice
    -0.82
    wagen
    -0.78
    ending
    -0.74
    ailability
    -0.69
     attracted
    -0.69
    anooga
    -0.68
    uve
    -0.68
    rones
    -0.68
    oor
    -0.68
    mble
    -0.66
    POSITIVE LOGITS
     Cosponsors
    0.89
     ???
    0.80
     Wikimedia
    0.80
     Various
    0.78
     Via
    0.76
     IR
    0.74
     Xin
    0.74
     Unicorn
    0.74
     Nex
    0.73
     FF
    0.73
    Act Density 0.028%

    No Known Activations