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

    Neuronpedia

    INDEX
    Explanations

    exclamations and celebratory statements

    oai_token-act-pair · gpt-3.5-turbo

    celebratory phrases and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estranged
    -0.78
     antit
    -0.76
     mistrust
    -0.67
    arians
    -0.67
     favoured
    -0.66
     hed
    -0.65
    etsk
    -0.64
    ifax
    -0.64
     manoeuv
    -0.64
     mistaken
    -0.64
    POSITIVE LOGITS
    âĻ¥
    0.91
    Anyway
    0.88
    =-=-=-=-=-=-=-=-
    0.87
    âĺħ
    0.87
    !!!
    0.86
    è¦ļéĨĴ
    0.86
    ³³³³³³³³³³³³³³³³
    0.85
    ³³³
    0.85
    ONSORED
    0.84
    ****************
    0.84
    Act Density 0.289%

    No Known Activations