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

    Neuronpedia

    INDEX
    Explanations

    days of the week

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATOR
    -0.84
    ate
    -0.77
    fect
    -0.73
    egal
    -0.72
    åĬ
    -0.72
    aeda
    -0.71
    onne
    -0.70
    ators
    -0.69
    respons
    -0.69
    agos
    -0.68
    POSITIVE LOGITS
     afternoon
    1.58
     morning
    1.55
     mornings
    1.50
     night
    1.49
     evening
    1.42
     Night
    1.32
     nights
    1.29
     evenings
    1.11
     Evening
    1.07
    morning
    1.06
    Act Density 0.030%

    No Known Activations