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

    Neuronpedia

    INDEX
    Explanations

    dates and events related to news articles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "On" followed by a date

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MODE
    -0.88
    $$
    -0.69
    QB
    -0.67
    Cod
    -0.65
    SourceFile
    -0.63
    BP
    -0.62
    ACTED
    -0.61
    OULD
    -0.61
    RL
    -0.60
    @#
    -0.60
    POSITIVE LOGITS
    slaught
    1.24
    coming
    1.19
     behalf
    1.08
    eness
    1.03
     occasion
    0.97
    etime
    0.95
    assis
    0.94
    look
    0.93
    yx
    0.90
    sight
    0.89
    Act Density 0.081%

    No Known Activations