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

    Neuronpedia

    INDEX
    Explanations

    dates in the format of month and year

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Sep" followed by numbers, likely indicating specific dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    culosis
    -0.99
     tuberculosis
    -0.78
     Archdemon
    -0.69
     Jackets
    -0.65
    ãĥīãĥ©ãĤ´ãĥ³
    -0.64
    anza
    -0.63
    Reviewer
    -0.63
     modem
    -0.62
     bearer
    -0.61
    ngth
    -0.60
    POSITIVE LOGITS
    arate
    1.27
    aration
    1.13
    ay
    0.95
    aret
    0.92
    ul
    0.87
    ared
    0.85
    ayed
    0.85
    arat
    0.81
    rees
    0.81
    ih
    0.81
    Act Density 0.013%

    No Known Activations