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

    Neuronpedia

    INDEX
    Explanations

    dates that are often associated with news articles or events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jriwal
    -0.81
    Reviewer
    -0.74
    edIn
    -0.73
    irlf
    -0.65
     Kush
    -0.65
    maid
    -0.65
    --------------------------------------------------------
    -0.64
    adder
    -0.63
    Reloaded
    -0.63
    holding
    -0.63
    POSITIVE LOGITS
    uary
    0.90
    isco
    0.90
    ices
    0.88
    ice
    0.87
    omore
    0.87
    ionics
    0.85
    imal
    0.79
    etta
    0.79
    isions
    0.79
    iet
    0.79
    Act Density 0.008%

    No Known Activations