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

    Neuronpedia

    INDEX
    Explanations

    the repeated occurrence of the word "unwritten" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to breaking or defying rules

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    phrine
    -0.87
    senal
    -0.76
    ãĤ¼
    -0.71
    ysis
    -0.70
    ĺħ
    -0.70
    hyde
    -0.69
    onyms
    -0.68
    pmwiki
    -0.66
    uate
    -0.66
     Defenders
    -0.65
    POSITIVE LOGITS
    arranted
    1.18
    ield
    1.17
    avering
    1.14
    inding
    1.07
    ritten
    1.05
    elcome
    1.03
    orthy
    1.03
    ashington
    1.01
    nesday
    1.00
    atcher
    0.98
    Act Density 0.030%

    No Known Activations