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

    Neuronpedia

    INDEX
    Explanations

    comparisons of physical appearances

    oai_token-act-pair · gpt-3.5-turbo

    comparisons or similes involving the word "like."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itage
    -0.71
    ongyang
    -0.70
    Enlarge
    -0.70
    cies
    -0.70
    taboola
    -0.67
    Located
    -0.67
    Companies
    -0.67
     exposures
    -0.66
    negie
    -0.66
    RFC
    -0.65
    POSITIVE LOGITS
     Trayvon
    1.04
     Superman
    1.03
     Adolf
    1.01
     someone
    1.01
     somebody
    1.00
     Darth
    0.99
     Jesus
    0.97
     oneself
    0.93
     royalty
    0.91
     Elvis
    0.90
    Act Density 0.196%

    No Known Activations