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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "original."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilde
    -0.21
    ia
    -0.16
    udi
    -0.15
    amer
    -0.15
    unc
    -0.15
    iro
    -0.14
     Dank
    -0.14
    ogle
    -0.14
    ias
    -0.14
    kel
    -0.14
    POSITIVE LOGITS
    аÑĢам
    0.19
     Huck
    0.16
    ledon
    0.15
    eniz
    0.15
    ekten
    0.14
    aneous
    0.14
    füg
    0.14
    ario
    0.14
    μÏĨ
    0.14
    arily
    0.14
    Act Density 0.017%

    No Known Activations