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

    Neuronpedia

    INDEX
    Explanations

    dates expressed as month and year

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the month "September."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    culosis
    -0.75
     tuberculosis
    -0.73
     bearer
    -0.70
    Reviewer
    -0.69
     Archdemon
    -0.65
    anza
    -0.64
     modem
    -0.64
     Wand
    -0.63
     liking
    -0.61
     fart
    -0.60
    POSITIVE LOGITS
    arate
    1.46
    aration
    1.37
    arations
    1.13
    arat
    1.07
    ay
    0.92
    aret
    0.92
    sis
    0.89
    rees
    0.87
    ar
    0.87
    uter
    0.85
    Act Density 0.017%

    No Known Activations