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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an individual's origin or residence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulp
    -0.17
    ãĤ¤ãĥĪ
    -0.16
     Signature
    -0.15
    423
    -0.15
    fixtures
    -0.14
    educt
    -0.14
     inspiration
    -0.14
    hiba
    -0.14
     signature
    -0.14
     inspirational
    -0.14
    POSITIVE LOGITS
    uyla
    0.16
    sky
    0.15
    acco
    0.15
    ment
    0.14
    anon
    0.14
    梨
    0.14
    nun
    0.14
    oucher
    0.14
    ìł¤
    0.14
    aps
    0.14
    Act Density 0.090%

    No Known Activations