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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people, places, or significant terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ellt
    -0.15
     Wie
    -0.15
    quam
    -0.15
    eph
    -0.14
    illing
    -0.14
    lesia
    -0.14
    ilee
    -0.14
    athers
    -0.14
    UCKET
    -0.14
    mie
    -0.14
    POSITIVE LOGITS
    .BorderFactory
    0.16
    combe
    0.15
    achts
    0.14
    ansson
    0.14
    0.14
    ataire
    0.13
     Nina
    0.13
     DCHECK
    0.13
    orgot
    0.13
    овиÑĩ
    0.13
    Act Density 0.313%

    No Known Activations