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

    Neuronpedia

    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "John" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favour
    -0.69
     civ
    -0.66
    MENTS
    -0.64
     modernization
    -0.64
    âĺħ
    -0.63
     favor
    -0.61
    pmwiki
    -0.61
    BALL
    -0.60
     improper
    -0.58
     vetting
    -0.58
    POSITIVE LOGITS
    athan
    1.38
     Doe
    1.17
    stone
    1.16
    nie
    1.10
    ston
    1.09
     Cena
    1.06
     Lennon
    1.03
    athon
    0.96
     Wooden
    0.90
     Quincy
    0.89
    Act Density 0.022%

    No Known Activations