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

    Neuronpedia

    INDEX
    Explanations

    dates in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numerical representations of dates and times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exha
    -0.76
     upkeep
    -0.74
     subdiv
    -0.71
     misuse
    -0.70
     imperson
    -0.70
     cheated
    -0.67
     sacrifice
    -0.66
     themselves
    -0.64
     tampering
    -0.64
     stomp
    -0.64
    POSITIVE LOGITS
    LOS
    1.08
    PRESS
    1.04
    Dear
    1.00
    Abstract
    0.99
    IRO
    0.95
    SAN
    0.95
    HOU
    0.94
    ³³³
    0.94
    WASHINGTON
    0.91
    THIS
    0.91
    Act Density 0.093%

    No Known Activations