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

    Neuronpedia

    INDEX
    Explanations

    instances of special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "[
    -0.16
    æ³Ĭ
    -0.13
    ÄįÃŃ
    -0.13
    ãĥ¼ãĥł
    -0.13
    ¼åIJĪ
    -0.12
    ÑģоÑĢ
    -0.12
    館
    -0.12
    oran
    -0.12
    kle
    -0.12
    olynomial
    -0.12
    POSITIVE LOGITS
     Sales
    0.28
     sales
    0.27
     Pharma
    0.25
    Sales
    0.24
     reps
    0.23
     Territory
    0.23
     territory
    0.22
    sales
    0.22
     salesman
    0.22
    -sales
    0.21
    Act Density 0.003%

    No Known Activations