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

    Neuronpedia

    INDEX
    Explanations

    names containing the subsequence "io"

    oai_token-act-pair · gpt-3.5-turbo

    the abbreviation "io" or its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holder
    -0.72
    puter
    -0.68
    ancies
    -0.67
    rap
    -0.65
    ivities
    -0.64
     Shattered
    -0.64
    OWS
    -0.63
     Shades
    -0.63
     ILCS
    -0.61
     Compass
    -0.61
    POSITIVE LOGITS
    ppo
    1.19
    ctl
    1.01
    zzi
    1.01
    cean
    0.97
    ctor
    0.96
    ption
    0.91
    ichi
    0.91
    hazard
    0.90
    ffic
    0.89
    io
    0.89
    Act Density 0.020%

    No Known Activations