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

    Neuronpedia

    INDEX
    Explanations

    special characters and non-English language characters that appear in the text

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols used in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atche
    -0.81
     Franch
    -0.77
     Wynne
    -0.75
    aday
    -0.71
     Murdoch
    -0.71
     Skydragon
    -0.69
    20439
    -0.68
    utenberg
    -0.68
     Paddock
    -0.67
     Finch
    -0.67
    POSITIVE LOGITS
    ĭ
    1.11
    ì
    1.10
    í
    1.05
    §
    1.03
    ŀ
    1.03
     ì
    1.02
    Ĥ¬
    1.01
    ĺ
    1.01
    ķ
    1.00
    ¹
    1.00
    Act Density 0.008%

    No Known Activations