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

    Neuronpedia

    INDEX
    Explanations

    phrases related to removing outer layers of objects

    oai_token-act-pair · gpt-3.5-turbo

    words related to the action of peeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umble
    -0.88
    isSpecialOrderable
    -0.71
    rio
    -0.69
    raq
    -0.68
    Saharan
    -0.67
    alias
    -0.61
     Ober
    -0.61
    eem
    -0.61
    ourke
    -0.60
    founded
    -0.60
    POSITIVE LOGITS
     peel
    1.13
    utical
    0.99
     peeled
    0.97
    utic
    0.86
    utics
    0.85
     Peel
    0.84
    isode
    0.80
    ovember
    0.74
    hens
    0.72
    rers
    0.70
    Act Density 0.013%

    No Known Activations