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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotions or reactions, particularly laughter and frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uppe
    -0.17
    igit
    -0.17
    upp
    -0.15
    aram
    -0.15
    alle
    -0.15
    _attached
    -0.15
    ÑĨÑİ
    -0.14
    екÑģи
    -0.13
    è¡ĵ
    -0.13
    adas
    -0.13
    POSITIVE LOGITS
     che
    0.21
     Che
    0.20
     Ham
    0.18
    æµľ
    0.18
    Che
    0.18
    _che
    0.18
     ham
    0.17
    che
    0.17
     Chester
    0.16
    ãĤ¿ãĥ¼
    0.16
    Act Density 0.026%

    No Known Activations