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

    Neuronpedia

    INDEX
    Explanations

    time-related information, specifically related to the concept of "less than."

    oai_token-act-pair · gpt-3.5-turbo

    numerical information related to time, percentages, and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     foremost
    -0.69
     dearly
    -0.69
     attendant
    -0.61
     pillar
    -0.61
    PLA
    -0.59
     Exodus
    -0.59
     ãĤµ
    -0.59
     Everywhere
    -0.57
    ras
    -0.57
    orian
    -0.54
    POSITIVE LOGITS
     percent
    0.85
     anymore
    0.84
     (<
    0.74
    %.
    0.68
    $$
    0.66
     GHz
    0.65
    uster
    0.64
    %
    0.63
     dstg
    0.61
     comprom
    0.61
    Act Density 0.161%

    No Known Activations