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

    Neuronpedia

    INDEX
    Explanations

    references to specific periods of time, particularly recent ones

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods or durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lees
    -0.86
    pherd
    -0.79
    olor
    -0.79
    aband
    -0.73
    marks
    -0.68
    á
    -0.67
    then
    -0.67
    acers
    -0.66
    olas
    -0.66
    ollow
    -0.66
    POSITIVE LOGITS
     decade
    1.34
     millenn
    1.16
     few
    1.07
     gasp
    1.04
     couple
    1.02
     month
    1.01
     millennium
    0.99
     installment
    0.99
     century
    0.99
     week
    0.98
    Act Density 0.045%

    No Known Activations