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

    Neuronpedia

    INDEX
    Explanations

    dates and time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of lateness or late occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebook
    -0.85
    tre
    -0.79
    ortion
    -0.75
    roma
    -0.74
    \\\\\\\\
    -0.73
    alach
    -0.73
    qua
    -0.72
    achus
    -0.71
    utenberg
    -0.70
    adr
    -0.69
    POSITIVE LOGITS
     afternoon
    1.00
     late
    0.99
     nights
    0.83
     evening
    0.81
    Late
    0.80
     Late
    0.78
     evenings
    0.77
     adolescence
    0.76
     night
    0.73
     mornings
    0.73
    Act Density 0.015%

    No Known Activations