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

    Neuronpedia

    INDEX
    Explanations

    instances where two entities are being compared or contrasted

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ļéĨĴ
    -0.80
    renheit
    -0.79
    nect
    -0.76
    cise
    -0.72
    ocaust
    -0.72
    ugu
    -0.72
    uable
    -0.71
    Enlarge
    -0.71
    istle
    -0.69
    ylon
    -0.69
    POSITIVE LOGITS
     sides
    1.56
     sexes
    1.46
     parties
    1.31
     genders
    1.28
     halves
    1.20
     factions
    0.98
     versions
    0.98
     men
    0.95
     Houses
    0.94
     Parties
    0.92
    Act Density 0.054%

    No Known Activations