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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "all" and other variants related to collective or comprehensive terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CPR
    -0.71
     Metatron
    -0.70
    ĪĴ
    -0.64
     defe
    -0.62
     Pastebin
    -0.61
     HIS
    -0.60
     basis
    -0.59
    rawdownloadcloneembedreportprint
    -0.59
     Kens
    -0.58
     reversible
    -0.57
    POSITIVE LOGITS
    oslav
    1.06
    jen
    0.70
    én
    0.69
    dro
    0.68
    gaard
    0.68
    ongo
    0.67
    iors
    0.66
    anmar
    0.66
    uan
    0.65
     Boh
    0.65
    Act Density 0.145%

    No Known Activations