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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antics
    -0.75
    icators
    -0.72
    vantage
    -0.68
    urers
    -0.67
    aneous
    -0.67
    commit
    -0.66
    ridges
    -0.63
    Express
    -0.63
    ooters
    -0.62
    factor
    -0.62
    POSITIVE LOGITS
     retiring
    0.75
     coached
    0.72
     nicknamed
    0.72
     worshipped
    0.72
     presided
    0.71
     stationed
    0.70
     hereafter
    0.70
     renown
    0.70
     chaired
    0.70
    named
    0.69
    Act Density 0.222%

    No Known Activations