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

    Neuronpedia

    INDEX
    Explanations

    terms related to film genres and storytelling techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     who
    -0.20
    who
    -0.15
    iesta
    -0.15
     whom
    -0.14
     αÏħÏĦή
    -0.14
     Mill
    -0.13
    phe
    -0.13
    æ´ĭ
    -0.13
     Far
    -0.13
    oleon
    -0.13
    POSITIVE LOGITS
     itself
    0.36
     коÑĤоÑĢое
    0.31
     должно
    0.28
     Ñıке
    0.26
     koje
    0.22
     αÏħÏĦά
    0.22
     its
    0.21
    Its
    0.20
     бÑĭло
    0.20
     Its
    0.20
    Act Density 0.089%

    No Known Activations