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

    Neuronpedia

    INDEX
    Explanations

    numerical measurements with units of length

    oai_token-act-pair · gpt-3.5-turbo

    items associated with numerical measurements and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gillespie
    -0.73
     solicitation
    -0.70
     Scrib
    -0.68
     moderation
    -0.68
     hes
    -0.67
     Zar
    -0.67
     Moreno
    -0.66
     Creator
    -0.66
    ulhu
    -0.65
     coward
    -0.65
    POSITIVE LOGITS
    pound
    1.22
    plus
    1.11
    dollar
    1.02
    capacity
    1.01
    scale
    0.99
    year
    0.99
    odd
    0.98
    mile
    0.97
    based
    0.96
    caliber
    0.95
    Act Density 0.068%

    No Known Activations