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

    Neuronpedia

    INDEX
    Explanations

    mentions of formal ceremonies or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific prefixes and suffixes related to a particular theme or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongyang
    -0.76
     brightly
    -0.73
     Mehran
    -0.69
    imir
    -0.69
     honour
    -0.68
    jri
    -0.68
     honor
    -0.66
     favour
    -0.65
    arella
    -0.64
    pedia
    -0.61
    POSITIVE LOGITS
    ipel
    0.75
    aves
    0.75
    lement
    0.72
     Wrest
    0.69
    prises
    0.67
    tainment
    0.65
    ById
    0.64
     Lauder
    0.64
    prise
    0.64
    mere
    0.63
    Act Density 0.086%

    No Known Activations