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

    Neuronpedia

    INDEX
    Explanations

    phrases related to timeframes and events in the future

    oai_token-act-pair · gpt-3.5-turbo

    future predictions or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     complying
    -0.78
     quitting
    -0.75
     donating
    -0.70
     Osw
    -0.66
     withholding
    -0.65
     Friends
    -0.65
     Anon
    -0.63
     repairing
    -0.62
     unethical
    -0.61
     resisting
    -0.61
    POSITIVE LOGITS
     mark
    1.04
     unfold
    1.03
     hinge
    0.99
     culmin
    0.97
     feature
    0.96
     usher
    0.96
     see
    0.94
     consist
    0.93
     determine
    0.93
     coincide
    0.92
    Act Density 0.156%

    No Known Activations