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

    Neuronpedia

    INDEX
    Explanations

    occurrences of names and their associated narrative elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uds
    -0.15
    izzy
    -0.15
    ukkan
    -0.14
    ÑĢеж
    -0.14
     cush
    -0.14
    egers
    -0.13
    825
    -0.13
    ewater
    -0.13
    afa
    -0.13
    ocracy
    -0.13
    POSITIVE LOGITS
     who
    0.44
     whom
    0.43
    who
    0.35
     whose
    0.32
     quien
    0.29
    whose
    0.27
     himself
    0.23
     qui
    0.21
    è°ģ
    0.20
     Who
    0.20
    Act Density 0.182%

    No Known Activations