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

    Neuronpedia

    INDEX
    Explanations

    the keyword 'both'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    fecture
    -0.86
    Trend
    -0.80
    nect
    -0.76
    xit
    -0.74
    esis
    -0.70
    edin
    -0.70
    ournal
    -0.70
    hibition
    -0.70
    krit
    -0.69
    uel
    -0.69
    POSITIVE LOGITS
     sides
    1.18
     halves
    1.11
     sexes
    1.00
    edged
    0.88
     genders
    0.85
     sets
    0.77
     extremes
    0.76
    ocating
    0.76
     equally
    0.75
     coasts
    0.75
    Act Density 0.042%

    No Known Activations