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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the degree or extent of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that measure the degree or scope of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RY
    -0.74
    wark
    -0.68
    reth
    -0.67
    pton
    -0.66
    stitial
    -0.65
     Bans
    -0.65
    ivas
    -0.64
    cair
    -0.64
    ton
    -0.64
    byte
    -0.63
    POSITIVE LOGITS
     extent
    0.98
    essment
    0.78
     practicable
    0.73
    tenance
    0.71
    ially
    0.68
    iary
    0.68
    eme
    0.68
    conom
    0.67
    enaries
    0.65
    afety
    0.65
    Act Density 0.016%

    No Known Activations