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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating positive outcomes and affirmations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äįe
    -0.17
    urette
    -0.15
    erp
    -0.15
    variant
    -0.14
    аÑĩе
    -0.14
    ned
    -0.14
    planes
    -0.14
    oko
    -0.14
    eri
    -0.14
    331
    -0.13
    POSITIVE LOGITS
    ãĥ¼ãĥĩ
    0.15
    ghi
    0.15
    stellen
    0.15
     Ngh
    0.15
     Neck
    0.14
    uno
    0.14
    ,exports
    0.14
    IAL
    0.13
    upp
    0.13
    /doc
    0.13
    Act Density 0.028%

    No Known Activations