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

    Neuronpedia

    INDEX
    Explanations

    text related to opting out or agreeing to terms and conditions

    oai_token-act-pair · gpt-3.5-turbo

    language regarding user consent and opt-out options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leilan
    -0.70
     Artemis
    -0.70
     coord
    -0.57
    aceae
    -0.57
     dyn
    -0.57
     governors
    -0.57
     gent
    -0.55
     gangs
    -0.54
     Elves
    -0.53
     Argon
    -0.53
    POSITIVE LOGITS
    rame
    0.77
    thumbnails
    0.76
    çīĪ
    0.69
    scription
    0.69
    Subscribe
    0.67
    Interstitial
    0.67
    interstitial
    0.67
    lect
    0.66
    Ń·
    0.65
    elsen
    0.65
    Act Density 0.006%

    No Known Activations