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

    Neuronpedia

    INDEX
    Explanations

    references to events or actions that took place 'yesterday'

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "yesterday."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahn
    -0.60
     Appears
    -0.57
    depending
    -0.55
    enser
    -0.54
    taboola
    -0.54
    ically
    -0.54
     ens
    -0.54
    Menu
    -0.53
    ographical
    -0.53
     associated
    -0.53
    POSITIVE LOGITS
     yesterday
    3.46
    Yesterday
    2.45
     Yesterday
    2.42
    terday
    2.20
     tomorrow
    2.15
     today
    2.14
     tonight
    1.97
    Tomorrow
    1.58
    today
    1.52
     Tuesday
    1.48
    Act Density 0.007%

    No Known Activations