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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or behaviors in a public setting

    oai_token-act-pair · gpt-3.5-turbo

    references to public and private actions or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cknowled
    -0.65
    icent
    -0.65
    illin
    -0.64
     deductible
    -0.62
    insula
    -0.61
     itch
    -0.60
    inguished
    -0.59
    itle
    -0.58
    andum
    -0.58
    gged
    -0.57
    POSITIVE LOGITS
     mode
    1.05
     guise
    1.02
    rooms
    0.95
     circles
    0.85
     situations
    0.83
     booths
    0.83
     settings
    0.81
     classrooms
    0.81
     contexts
    0.80
    boxes
    0.80
    Act Density 0.216%

    No Known Activations