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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Tuesday" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onse
    -0.80
    onductor
    -0.78
    abet
    -0.78
    ordes
    -0.75
    ategory
    -0.73
    ript
    -0.72
    ebook
    -0.72
    aeus
    -0.71
    luster
    -0.71
    Brit
    -0.71
    POSITIVE LOGITS
     morning
    1.58
     afternoon
    1.51
     night
    1.47
     evening
    1.47
     mornings
    1.30
    morning
    1.21
     nights
    1.11
     Night
    1.11
     evenings
    1.09
     Morning
    0.93
    Act Density 0.021%

    No Known Activations