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

    Neuronpedia

    INDEX
    Explanations

    quotations or statements of certainty

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     obsc
    -0.63
     Feminist
    -0.59
     contrasted
    -0.58
     Shutterstock
    -0.57
    often
    -0.56
    utterstock
    -0.56
    ĸļ
    -0.55
     Students
    -0.54
     often
    -0.53
    ria
    -0.53
    POSITIVE LOGITS
    initely
    0.85
    [/
    0.82
     somebody
    0.80
     ..."
    0.79
     gonna
    0.79
    %"
    0.78
    morrow
    0.77
     anybody
    0.75
     [
    0.74
     âĢ¦"
    0.73
    Act Density 0.709%

    No Known Activations