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

    Neuronpedia

    INDEX
    Explanations

    references to counts of days and their various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nights
    -0.24
     nights
    -0.21
     evenings
    -0.19
     evening
    -0.18
     Weeks
    -0.18
     Evening
    -0.18
     Night
    -0.17
     Week
    -0.17
    pard
    -0.17
     overnight
    -0.17
    POSITIVE LOGITS
     Yesterday
    0.18
    Yesterday
    0.17
    aney
    0.17
     yesterday
    0.16
    -long
    0.15
    /day
    0.15
    /year
    0.15
    /e
    0.15
    Anchor
    0.15
     siguiente
    0.15
    Act Density 0.036%

    No Known Activations