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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical sensations and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to physical sensations or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebin
    -0.80
     Inher
    -0.75
     yourselves
    -0.70
    ahime
    -0.69
     defic
    -0.69
     Patreon
    -0.68
    prises
    -0.66
     hiatus
    -0.66
    imum
    -0.66
    orem
    -0.65
    POSITIVE LOGITS
     smelled
    1.32
     resembled
    1.03
     wore
    0.97
     seemed
    0.96
     hadn
    0.95
     yelled
    0.94
     didn
    0.94
     hugged
    0.93
     couldn
    0.90
     sounded
    0.88
    Act Density 0.395%

    No Known Activations