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

    Neuronpedia

    INDEX
    Explanations

    references to the word "persons" or derivatives of the word

    oai_token-act-pair · gpt-3.5-turbo

    mentions or discussions of 'persons' or 'people'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Triangle
    -0.70
    Book
    -0.68
    Rated
    -0.67
    é¾
    -0.65
     Passage
    -0.64
    RAFT
    -0.62
    liest
    -0.61
     minus
    -0.60
     Franken
    -0.59
    APE
    -0.59
    POSITIVE LOGITS
    pers
    1.16
    pect
    1.02
    afety
    0.95
    erver
    0.94
     veter
    0.91
    ervative
    0.82
    istence
    0.82
    ystem
    0.80
     pse
    0.78
    NetMessage
    0.78
    Act Density 0.008%

    No Known Activations