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

    Neuronpedia

    INDEX
    Explanations

    numerical data and percentages in a text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahead
    -0.60
     Also
    -0.58
    similar
    -0.57
    also
    -0.56
    clerosis
    -0.56
    robat
    -0.55
    odus
    -0.55
    align
    -0.54
    chwitz
    -0.54
    ashington
    -0.52
    POSITIVE LOGITS
     marginally
    0.87
     spor
    0.86
    anke
    0.82
     fraction
    0.82
     fleeting
    0.81
    iffe
    0.79
     ONE
    0.75
     superficial
    0.75
     curs
    0.74
     finite
    0.73
    Act Density 0.971%

    No Known Activations