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

    Neuronpedia

    INDEX
    Explanations

    characters and symbols in a non-English language

    oai_token-act-pair · gpt-3.5-turbo

    sequences of characters that resemble Unicode or special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     solicitation
    -0.70
    ilts
    -0.67
    ilation
    -0.64
    undai
    -0.63
     bombshell
    -0.63
     nonpartisan
    -0.62
     bidder
    -0.61
    lisher
    -0.61
     spur
    -0.60
     crossover
    -0.60
    POSITIVE LOGITS
    е
    1.11
    ا
    1.04
    ãģĨ
    1.03
    и
    1.03
    ãĤ£
    0.95
    ÑĮ
    0.92
    н
    0.92
    à¤
    0.91
    ç¥ŀ
    0.90
    andise
    0.88
    Act Density 0.014%

    No Known Activations