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

    Neuronpedia

    INDEX
    Explanations

    references to time periods, particularly years and weeks

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, particularly years and weeks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uckland
    -0.79
    OTUS
    -0.72
    insula
    -0.68
     mathemat
    -0.67
    ierrez
    -0.66
     Borders
    -0.63
    monary
    -0.62
     WATCHED
    -0.62
    ACTED
    -0.61
    liction
    -0.60
    POSITIVE LOGITS
    dream
    0.94
    table
    0.89
    lies
    0.87
    wise
    0.84
    mar
    0.82
    cakes
    0.81
    ning
    0.81
    days
    0.81
    cake
    0.80
    worms
    0.79
    Act Density 0.118%

    No Known Activations