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

    Neuronpedia

    INDEX
    Explanations

    scientific and technical terms related to physics and engineering

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    oxide
    -0.59
    orah
    -0.58
    tails
    -0.58
    acting
    -0.56
    inatory
    -0.56
    ocker
    -0.56
    unders
    -0.56
    oyal
    -0.55
    inn
    -0.55
    tail
    -0.55
    POSITIVE LOGITS
     radius
    0.76
     Radius
    0.65
    radius
    0.63
    angular
    0.61
    xia
    0.60
     circumference
    0.58
    mobi
    0.57
    ailability
    0.56
    ctic
    0.56
    limits
    0.56
    Act Density 9.864%

    No Known Activations