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

    Neuronpedia

    INDEX
    Explanations

    words related to autonomy or self-direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    бина
    -0.16
    mani
    -0.14
    atar
    -0.14
    unga
    -0.14
    ovah
    -0.14
    ibraltar
    -0.14
    ĺìĿ´
    -0.13
    quip
    -0.13
    antino
    -0.13
    ảng
    -0.13
    POSITIVE LOGITS
    iful
    0.18
    лив
    0.15
    agi
    0.15
    sled
    0.15
     Liberties
    0.14
    baugh
    0.14
    inen
    0.14
    apest
    0.14
    sen
    0.13
    .poi
    0.13
    Act Density 0.007%

    No Known Activations