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

    Neuronpedia

    INDEX
    Explanations

    dates in a specific format - month followed by day

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     basket
    -0.68
     phyl
    -0.66
     multiplying
    -0.65
     zones
    -0.63
     prolifer
    -0.62
     suitcase
    -0.62
     expansion
    -0.61
     expansions
    -0.60
    ngth
    -0.60
     purse
    -0.59
    POSITIVE LOGITS
     29
    1.01
     07
    0.98
     27
    0.98
     04
    0.98
     28
    0.97
     06
    0.97
     08
    0.96
     03
    0.96
     26
    0.95
     09
    0.94
    Act Density 0.054%

    No Known Activations