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

    Neuronpedia

    INDEX
    Explanations

    phrases related to text condensing and summarizing

    oai_token-act-pair · gpt-3.5-turbo

    specific non-standard characters or symbols, appearing to represent certain expressions or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.73
     STATS
    -0.72
    20439
    -0.69
    assetsadobe
    -0.67
    anwhile
    -0.66
     Glou
    -0.65
    ãĥ¼ãĥĨ
    -0.65
     Marketable
    -0.64
     è£ıè
    -0.63
    ãĥĵ
    -0.63
    POSITIVE LOGITS
    ¬
    1.06
    Ļ
    1.00
    ¼
    0.92
    º
    0.92
    £
    0.92
    ª
    0.91
    Ĵ
    0.89
    ¤
    0.88
    ĸ
    0.87
    ĵ
    0.86
    Act Density 0.397%

    No Known Activations