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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal experiences or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ï¼ļ
    -0.15
     "[
    -0.14
     "\
    -0.14
     "
    -0.14
     "...
    -0.14
     Wo
    -0.13
    outine
    -0.13
     ":
    -0.13
    onne
    -0.13
    estre
    -0.13
    POSITIVE LOGITS
     _____
    0.20
     ____
    0.18
     _______,
    0.16
     XYZ
    0.16
     ___
    0.16
     ______
    0.15
    *this
    0.15
     THIS
    0.15
    à¹ĩà¸Ńà¸ķ
    0.15
     pÅĻece
    0.14
    Act Density 0.507%

    No Known Activations