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

    Neuronpedia

    INDEX
    Explanations

    items or supplies that are organized or not in use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Attached
    -0.15
    ÑĢÑĥн
    -0.15
    ikel
    -0.14
    Ñĥва
    -0.14
    atrix
    -0.14
    ichert
    -0.13
    ilater
    -0.13
    .Attach
    -0.13
     Emblem
    -0.13
    ıs
    -0.13
    POSITIVE LOGITS
     sitting
    0.42
     lying
    0.40
     laying
    0.34
     sit
    0.33
     gathering
    0.32
     Sitting
    0.31
     sits
    0.29
     collecting
    0.28
     langu
    0.27
     леж
    0.27
    Act Density 0.185%

    No Known Activations