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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, likely related to companies, technologies, or products

    oai_token-act-pair · gpt-3.5-turbo

    names of specific brands, technologies, or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orsche
    -0.71
    ammy
    -0.69
    redd
    -0.67
    mble
    -0.66
    aughtered
    -0.66
    uristic
    -0.63
    buquerque
    -0.62
    rontal
    -0.62
    actionDate
    -0.62
    ãĥīãĥ©ãĤ´ãĥ³
    -0.62
    POSITIVE LOGITS
     itself
    0.68
     Citadel
    0.67
     workforce
    0.66
     herself
    0.66
     fandom
    0.65
     ecosystem
    0.64
     merchandise
    0.63
     populace
    0.62
     electorate
    0.61
     garments
    0.61
    Act Density 0.495%

    No Known Activations