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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific food items

    oai_token-act-pair · gpt-3.5-turbo

    terms related to jellyfish and soap

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hend
    -0.69
    xual
    -0.66
     Rag
    -0.64
    Course
    -0.64
    rued
    -0.62
    iple
    -0.61
     Tire
    -0.60
    ¿
    -0.59
    etus
    -0.59
     Accountability
    -0.59
    POSITIVE LOGITS
    acity
    0.82
    atories
    0.80
    bean
    0.78
    acious
    0.74
    glers
    0.73
    tub
    0.72
    âĸĦ
    0.71
    atory
    0.70
    iencies
    0.70
    tle
    0.68
    Act Density 0.070%

    No Known Activations