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

    Neuronpedia

    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Wednesday" and other days of the week

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egal
    -0.80
    respons
    -0.75
    kef
    -0.75
    leeve
    -0.74
    ordes
    -0.73
    into
    -0.70
    adding
    -0.68
    onne
    -0.68
    leading
    -0.67
    acc
    -0.66
    POSITIVE LOGITS
     mornings
    1.04
     Nights
    1.03
     night
    1.02
     evening
    1.02
     nights
    1.01
     Night
    1.01
     morning
    1.01
     afternoon
    1.00
     evenings
    0.95
     Morning
    0.94
    Act Density 0.062%

    No Known Activations