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

    Neuronpedia

    INDEX
    Explanations

    the surname "En" with varying levels of specificity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "en"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hitch
    -0.62
     unrecogn
    -0.61
     Canaveral
    -0.61
     unfavorable
    -0.58
     unnamed
    -0.58
     exceptional
    -0.57
     aborted
    -0.57
     humor
    -0.57
     Nicarag
    -0.56
     humour
    -0.56
    POSITIVE LOGITS
    bach
    1.32
    baum
    1.29
    heimer
    1.28
    berger
    1.23
    esis
    1.20
    wald
    1.19
    baugh
    1.15
    feld
    1.13
    zyme
    1.12
    burgh
    1.11
    Act Density 0.084%

    No Known Activations