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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical thickness or thinness

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    OUP
    -0.72
    bucks
    -0.70
    zeb
    -0.68
    ILLE
    -0.64
    Particip
    -0.62
    kw
    -0.62
    PHOTOS
    -0.62
    eering
    -0.61
    CDC
    -0.61
    NL
    -0.60
    POSITIVE LOGITS
    ned
    1.49
    ning
    1.40
    ners
    1.20
    nesses
    1.00
    ness
    0.90
    bread
    0.89
    ening
    0.86
     slices
    0.86
    ware
    0.85
    med
    0.85
    Act Density 0.015%

    No Known Activations