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

    Neuronpedia

    INDEX
    Explanations

    words that indicate qualitative assessments or evaluations about situations or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    exterity
    -0.14
    _visibility
    -0.14
    ìĤ¬
    -0.14
    icorn
    -0.14
    461
    -0.14
    eus
    -0.14
    urma
    -0.14
    ĶĦ
    -0.13
    olumn
    -0.13
     Auditor
    -0.13
    POSITIVE LOGITS
    ê·ł
    0.15
    ekil
    0.15
    enko
    0.15
    rlen
    0.14
    cott
    0.14
    .mean
    0.14
    cen
    0.14
    olo
    0.14
    elters
    0.13
    еж
    0.13
    Act Density 0.005%

    No Known Activations