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

    Neuronpedia

    INDEX
    Explanations

    instances of the character "Ċ" followed by "10" activation, often occurring at the end of segment boundaries

    oai_token-act-pair · gpt-3.5-turbo

    expressions of evaluation or judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     orchestr
    -0.79
     estranged
    -0.77
     elect
    -0.77
     adversaries
    -0.77
     courier
    -0.77
     torpedo
    -0.76
    ¥ŀ
    -0.76
     favoured
    -0.75
     advancing
    -0.74
     decap
    -0.74
    POSITIVE LOGITS
    Anyway
    1.60
    Anonymous
    1.47
    ³³³³³³³³
    1.44
    Posted
    1.40
    ³³³³
    1.33
    Honestly
    1.28
    posted
    1.28
    ³³³
    1.28
    ³³³³³³³³³³³³³³³³
    1.28
    Yeah
    1.26
    Act Density 0.295%

    No Known Activations