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

    Neuronpedia

    INDEX
    Explanations

    dates and days of the week

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    egal
    -0.85
    respons
    -0.79
    kef
    -0.77
    leeve
    -0.75
    ordes
    -0.75
    adding
    -0.75
    eryl
    -0.73
    recent
    -0.71
    redit
    -0.69
    este
    -0.67
    POSITIVE LOGITS
     night
    1.07
     Night
    1.07
     evening
    1.05
     Nights
    1.05
     morning
    1.05
     afternoon
    1.04
     nights
    0.99
     mornings
    0.96
     NIGHT
    0.93
     Morning
    0.92
    Act Density 0.056%

    No Known Activations