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

    Neuronpedia

    INDEX
    Explanations

    symbols or special characters that indicate emphasis

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.66
    pton
    -0.65
     Spit
    -0.64
     Spice
    -0.63
    idine
    -0.62
     Ultr
    -0.61
    pher
    -0.60
    plex
    -0.60
    iland
    -0.59
    warts
    -0.58
    POSITIVE LOGITS
    ŀ
    1.34
    Ĭ
    1.15
    Ĺ
    1.15
    ļ
    1.05
    ĵ
    1.01
    ¿
    1.00
    Ĩ
    0.99
    µ
    0.99
    ł
    0.98
    ³
    0.97
    Act Density 0.003%

    No Known Activations