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

    Neuronpedia

    INDEX
    Explanations

    comparative expressions using the word "than"

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that highlight superiority or inferiority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     centr
    -0.67
    maid
    -0.67
     stead
    -0.64
    ALE
    -0.61
    keeper
    -0.61
     Purg
    -0.59
     largeDownload
    -0.58
     clearance
    -0.58
    roller
    -0.58
     bearer
    -0.58
    POSITIVE LOGITS
    atos
    1.17
    than
    0.99
    ormal
    0.90
    vis
    0.84
    stellar
    0.76
    lihood
    0.71
    iors
    0.71
    izoph
    0.71
    average
    0.70
    thur
    0.70
    Act Density 0.011%

    No Known Activations