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

    Neuronpedia

    INDEX
    Explanations

    phrases related to public speaking events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "at" related to events or speaking engagements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gans
    -0.89
    aceutical
    -0.72
     thri
    -0.69
    chrome
    -0.67
    shell
    -0.65
    REDACTED
    -0.65
    sters
    -0.64
    killers
    -0.63
    holes
    -0.63
     benefited
    -0.61
    POSITIVE LOGITS
     halftime
    1.16
     CES
    1.05
     conferences
    1.01
     least
    0.97
    yp
    0.94
    onement
    0.93
     Cannes
    0.91
    rium
    0.90
     PAX
    0.86
     seminars
    0.85
    Act Density 0.152%

    No Known Activations