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

    Neuronpedia

    INDEX
    Explanations

    phrases related to job roles and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shel
    -0.16
    rahim
    -0.16
    uta
    -0.15
     vyh
    -0.14
     Ferry
    -0.14
    otti
    -0.14
    jak
    -0.14
    erra
    -0.14
    igue
    -0.14
     bookstore
    -0.14
    POSITIVE LOGITS
    岡
    0.17
    ırak
    0.16
    ãģıãģł
    0.15
    ombat
    0.15
    azo
    0.15
     comm
    0.15
     reckon
    0.14
     BM
    0.14
    ìĦĿ
    0.14
    Deck
    0.14
    Act Density 0.078%

    No Known Activations