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

    Neuronpedia

    INDEX
    Explanations

    emotions expressed in personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himself
    -0.17
    妻
    -0.17
    leo
    -0.15
    ighton
    -0.14
    zÄħd
    -0.14
    Analyzer
    -0.14
    auen
    -0.14
    alim
    -0.14
    bsolute
    -0.14
     Unsigned
    -0.14
    POSITIVE LOGITS
    ä¸Ī夫
    0.22
     herself
    0.21
     Ñģама
    0.18
    esh
    0.15
     Hao
    0.15
    pher
    0.14
    /div
    0.14
     Fav
    0.14
     publi
    0.14
    ová
    0.14
    Act Density 2.524%

    No Known Activations