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

    Neuronpedia

    INDEX
    Explanations

    terms related to "active" statuses or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roperties
    -0.15
    EXIT
    -0.15
    ãĤ¡
    -0.14
    ãĥĢãĥ¼
    -0.14
    PRIVATE
    -0.14
    Exiting
    -0.13
    ãĥ¬ãĤ¹
    -0.13
    uito
    -0.13
    exion
    -0.13
    laden
    -0.13
    POSITIVE LOGITS
    /pass
    0.16
    ernal
    0.14
    .Active
    0.14
     Nose
    0.14
    -active
    0.14
    prenom
    0.14
    yonel
    0.13
     dÆ°
    0.13
    stvo
    0.13
    -duty
    0.13
    Act Density 0.019%

    No Known Activations