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

    Neuronpedia

    INDEX
    Explanations

    words related to permission or allowance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'o' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    channelAvailability
    -0.71
    terday
    -0.66
     Dickinson
    -0.66
     Ack
    -0.66
     Yel
    -0.66
    theless
    -0.63
     Staples
    -0.62
    DERR
    -0.62
     Buckley
    -0.62
     Classics
    -0.61
    POSITIVE LOGITS
    phthal
    1.21
    atmeal
    1.15
    mbudsman
    1.13
    vernight
    1.09
    lymp
    1.07
    ops
    1.06
    liv
    1.05
    mbuds
    1.03
    ceans
    1.02
    asis
    1.02
    Act Density 0.019%

    No Known Activations