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

    Neuronpedia

    INDEX
    Explanations

    the letters 'ib' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "ib" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ISTER
    -0.67
     Defender
    -0.65
    CHO
    -0.63
     CPS
    -0.63
     Russ
    -0.63
     Bender
    -0.63
     Blizzard
    -0.62
     Ceres
    -0.62
     seriousness
    -0.61
    ||||
    -0.60
    POSITIVE LOGITS
    ilib
    1.34
    ibl
    1.08
    ulous
    1.07
    ib
    1.01
    raltar
    0.98
    acter
    0.97
    uilt
    0.97
    rahim
    0.93
    odies
    0.90
    uana
    0.90
    Act Density 0.010%

    No Known Activations