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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of people

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Mark" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ILLE
    -0.77
    urses
    -0.72
     adolesc
    -0.68
    Interstitial
    -0.65
    bably
    -0.63
    ught
    -0.62
    RIPT
    -0.61
    elvet
    -0.61
    abama
    -0.60
     decomp
    -0.60
    POSITIVE LOGITS
     Twain
    1.24
    eting
    1.22
     Zuckerberg
    1.15
    eters
    1.10
    ipl
    1.05
    edly
    1.00
    owitz
    0.98
    down
    0.95
    eter
    0.91
     Dupl
    0.89
    Act Density 0.017%

    No Known Activations