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

    Neuronpedia

    INDEX
    Explanations

    words in a specific script or language that convey strong emotions or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibel
    -0.16
    poÄį
    -0.14
    ÑĮ
    -0.14
    hipster
    -0.14
    -neutral
    -0.14
     Sutton
    -0.14
    иÑĤ
    -0.13
    Ñģ
    -0.13
     ret
    -0.13
    Ñİ
    -0.13
    POSITIVE LOGITS
     hone
    0.17
    zell
    0.16
    å¾Ĵ
    0.15
     NÄĽm
    0.15
    å¼ı
    0.14
     à¤ľ
    0.14
    eka
    0.14
    hone
    0.14
    ¤
    0.14
    à¥ĩ
    0.14
    Act Density 0.021%

    No Known Activations