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

    Neuronpedia

    INDEX
    Explanations

    names or terms containing the sequence "io"

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the substring "io."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancies
    -0.71
     Shades
    -0.69
    holder
    -0.68
     ILCS
    -0.65
     Shattered
    -0.64
     quarters
    -0.62
     poppy
    -0.61
     complimentary
    -0.61
    INGS
    -0.60
     embodiments
    -0.60
    POSITIVE LOGITS
    ppo
    1.20
    ctl
    1.08
    zzi
    1.06
    cean
    1.03
    ption
    1.02
    io
    0.97
    lli
    0.90
    ctor
    0.90
    vernment
    0.90
    lett
    0.89
    Act Density 0.015%

    No Known Activations