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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to locations, individuals, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prec
    -0.74
     briefs
    -0.69
     Caps
    -0.67
     vacuum
    -0.66
     tab
    -0.65
     capsule
    -0.64
     backdrop
    -0.63
     caps
    -0.62
     dime
    -0.62
     CPI
    -0.61
    POSITIVE LOGITS
    agascar
    1.02
    mosp
    1.02
    romeda
    1.00
    nesty
    0.98
    dinand
    0.97
    peror
    0.96
    emis
    0.95
    withstanding
    0.94
    anyahu
    0.94
    jamin
    0.94
    Act Density 0.181%

    No Known Activations