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

    Neuronpedia

    INDEX
    Explanations

    mentioning events and statements made at news conferences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    gans
    -0.85
    aceutical
    -0.77
     thri
    -0.73
    chrome
    -0.71
    killers
    -0.69
    holes
    -0.66
    Owner
    -0.65
     benefited
    -0.64
    sters
    -0.64
    REDACTED
    -0.64
    POSITIVE LOGITS
     halftime
    1.18
     CES
    1.10
     conferences
    1.07
     least
    1.00
     Cannes
    0.97
     PAX
    0.93
     Standing
    0.92
    onement
    0.91
    yp
    0.91
    rium
    0.87
    Act Density 0.128%

    No Known Activations