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

    Neuronpedia

    INDEX
    Explanations

    mentions of conflicts or war-related events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.68
    */(
    -0.66
    uez
    -0.64
     Vec
    -0.63
    HCR
    -0.62
     Dinner
    -0.61
     supra
    -0.61
     Square
    -0.61
     Manga
    -0.60
     Philos
    -0.59
    POSITIVE LOGITS
    ridden
    1.44
    induced
    1.28
    related
    1.25
    fighting
    1.24
    resistant
    1.19
    inducing
    1.19
    filled
    1.19
    prone
    1.17
    laden
    1.15
    torn
    1.14
    Act Density 0.064%

    No Known Activations