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

    Neuronpedia

    INDEX
    Explanations

    numeric data and values, particularly financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mush
    -0.17
    712
    -0.17
     Roose
    -0.17
    702
    -0.17
    709
    -0.16
    703
    -0.16
    710
    -0.16
     Sahara
    -0.15
    704
    -0.15
    701
    -0.15
    POSITIVE LOGITS
    82
    0.71
    83
    0.66
    823
    0.62
    821
    0.60
    828
    0.60
    822
    0.59
    827
    0.58
    829
    0.58
    832
    0.58
    81
    0.58
    Act Density 0.054%

    No Known Activations