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

    Neuronpedia

    INDEX
    Explanations

    numerical references to time durations in days or minutes

    oai_token-act-pair · gpt-3.5-turbo

    numerical references related to time and quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ettings
    -0.83
    venge
    -0.70
    tern
    -0.69
     inherit
    -0.66
    bear
    -0.65
    medi
    -0.65
    vati
    -0.62
    plement
    -0.62
    hers
    -0.61
    Fram
    -0.60
    POSITIVE LOGITS
    %
    1.31
    %"
    1.25
    %-
    1.24
     percent
    1.20
    Hz
    1.12
     Minutes
    1.11
    %.
    1.09
     minutes
    1.05
    mph
    1.04
    mins
    1.03
    Act Density 0.195%

    No Known Activations