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

    Neuronpedia

    INDEX
    Explanations

    URLs for sharing or reading stories

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "story."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seiz
    -0.70
     spons
    -0.68
    pex
    -0.60
    VIDIA
    -0.56
     obser
    -0.56
     mosqu
    -0.55
    chwitz
    -0.55
    ighed
    -0.54
    osate
    -0.54
     bragging
    -0.54
    POSITIVE LOGITS
    illian
    0.64
    cha
    0.59
    Subscribe
    0.59
    raine
    0.59
    eng
    0.58
    walker
    0.58
     Birch
    0.57
    eta
    0.55
    ender
    0.55
    else
    0.55
    Act Density 0.016%

    No Known Activations