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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific events or topics related to history, government, and controversies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    etheless
    -0.89
     lapse
    -0.83
    swer
    -0.78
     disarm
    -0.77
     remembrance
    -0.77
     stale
    -0.77
     standby
    -0.76
    vironment
    -0.74
     analges
    -0.72
     secrecy
    -0.72
    POSITIVE LOGITS
    ratch
    1.40
    apers
    1.39
    ulpt
    1.37
    reens
    1.35
    ouring
    1.30
    rupulous
    1.29
    attered
    1.29
    rawl
    1.28
    atter
    1.25
    rawling
    1.24
    Act Density 7.825%

    No Known Activations