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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparison and evaluation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of rarity or uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Proceed
    -0.62
     Locations
    -0.61
     Realms
    -0.61
     Units
    -0.60
     Various
    -0.59
     IMAGES
    -0.59
     quarry
    -0.57
     settlements
    -0.57
     Unit
    -0.56
     Eventually
    -0.56
    POSITIVE LOGITS
     adequately
    0.74
    paralle
    0.72
     nor
    0.72
    clusively
    0.72
     truly
    0.69
    acea
    0.68
    steen
    0.68
    efe
    0.66
     sufficiently
    0.65
     "$:/
    0.65
    Act Density 0.411%

    No Known Activations