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

    Neuronpedia

    INDEX
    Explanations

    special characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    symbols and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exha
    -0.83
     unfinished
    -0.80
    geries
    -0.76
     unborn
    -0.69
     contrace
    -0.69
     misunder
    -0.69
    esan
    -0.69
     unex
    -0.69
     unintended
    -0.68
     exhib
    -0.67
    POSITIVE LOGITS
    ï¸ı
    1.54
    ï¸
    1.26
    âĸł
    1.10
    âĸº
    0.92
    âĿ
    0.92
    °
    0.91
    âĢ
    0.90
    âĶĢâĶĢâĶĢâĶĢ
    0.90
    ÙĦ
    0.88
    ÙĨ
    0.88
    Act Density 0.050%

    No Known Activations