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

    Neuronpedia

    INDEX
    Explanations

    dates mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    days of the week and specific dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agos
    -0.86
    allo
    -0.86
    abet
    -0.84
    ordes
    -0.82
    rahim
    -0.82
    ris
    -0.79
    omething
    -0.78
    igated
    -0.78
    abe
    -0.78
    uchin
    -0.77
    POSITIVE LOGITS
     mornings
    1.23
     nights
    1.22
     Night
    1.20
     morning
    1.20
     afternoon
    1.18
     night
    1.17
     evenings
    1.12
     evening
    1.11
     Nights
    0.95
    Night
    0.92
    Act Density 0.088%

    No Known Activations