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

    Neuronpedia

    INDEX
    Explanations

    country names

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and symbols related to lists or groupings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaries
    -0.81
     grandchildren
    -0.73
    illions
    -0.71
    enary
    -0.70
    ADRA
    -0.69
    Cause
    -0.68
     sexes
    -0.66
    Unity
    -0.64
    cot
    -0.62
    ById
    -0.62
    POSITIVE LOGITS
     Tob
    0.74
    heit
    0.71
     bolts
    0.68
     tumble
    0.67
     gran
    0.64
     Mehran
    0.64
     lat
    0.62
     Alger
    0.62
     gas
    0.60
     chloride
    0.59
    Act Density 0.318%

    No Known Activations