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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of the word "ib."

    oai_token-act-pair · gpt-3.5-turbo

    the repeated occurrence of the same sequence of letters "ib"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ceres
    -0.69
    bilt
    -0.66
     Russ
    -0.65
     Vald
    -0.65
     Blizzard
    -0.64
     marsh
    -0.64
    ISTER
    -0.63
    isters
    -0.62
    ||||
    -0.62
     Bender
    -0.61
    POSITIVE LOGITS
    ilib
    1.13
    raltar
    1.09
    ulous
    1.09
    ibl
    1.05
    odies
    1.04
    bole
    0.98
    rahim
    0.96
    acter
    0.96
    ody
    0.94
    iotics
    0.93
    Act Density 0.015%

    No Known Activations