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

    Neuronpedia

    INDEX
    Explanations

    descriptive terms related to environmental conditions and settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inclus
    -0.15
     inclusive
    -0.15
     actual
    -0.14
     ModelState
    -0.14
    uga
    -0.14
     overlap
    -0.14
     overlaps
    -0.14
     actually
    -0.13
     relativ
    -0.13
     kem
    -0.13
    POSITIVE LOGITS
    inside
    0.18
     lately
    0.15
    ÄĽtÅ¡
    0.15
    çĴ°
    0.14
    ogany
    0.14
    :animated
    0.14
    "class
    0.14
    ritz
    0.14
     inside
    0.13
    Ìĥ
    0.13
    Act Density 0.284%

    No Known Activations