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

    Neuronpedia

    INDEX
    Explanations

    time-related information

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with time durations or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dearly
    -0.75
    liest
    -0.74
    dale
    -0.65
    rower
    -0.62
    grave
    -0.60
    stained
    -0.60
    abee
    -0.59
    ursed
    -0.59
    dating
    -0.59
     boldly
    -0.57
    POSITIVE LOGITS
    %"
    1.05
     dozen
    1.02
    dozen
    0.97
     percent
    0.90
    %
    0.82
     miles
    0.79
     thous
    0.78
     thirds
    0.78
     minutes
    0.76
    cms
    0.76
    Act Density 0.142%

    No Known Activations