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

    Neuronpedia

    INDEX
    Explanations

    numeric values used in technical contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    gow
    -0.63
     Tant
    -0.63
     Kad
    -0.62
     Toledo
    -0.61
    ropy
    -0.61
     Lew
    -0.61
    emet
    -0.60
    eer
    -0.59
     hypert
    -0.59
    kar
    -0.59
    POSITIVE LOGITS
    1
    1.47
     1
    1.20
    ãĥĺãĥ©
    1.11
    2
    1.06
    ĥ
    0.91
    3
    0.86
     2
    0.84
    ½
    0.82
    1001
    0.81
     ½
    0.80
    Act Density 0.150%

    No Known Activations