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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various events and announcements

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and statements indicating potential outcomes or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "}],"
    -0.70
    phasis
    -0.68
    isphere
    -0.66
    FW
    -0.66
    fw
    -0.66
    qus
    -0.65
    ealous
    -0.65
    ::::::::
    -0.65
    ~~~~
    -0.65
    Footnote
    -0.64
    POSITIVE LOGITS
     Donald
    1.18
     Barack
    1.07
     Hillary
    1.04
     Bernie
    1.02
     Elon
    1.01
     President
    0.99
     Conor
    0.95
     LeBron
    0.95
     Kanye
    0.94
     NASCAR
    0.94
    Act Density 0.736%

    No Known Activations