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

    Neuronpedia

    INDEX
    Explanations

    specific phrases indicating support for certain political actions or ideas

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.76
    ontent
    -0.75
    reflect
    -0.72
    matched
    -0.70
    esters
    -0.68
    ngth
    -0.68
    days
    -0.67
    holes
    -0.66
     owing
    -0.65
     answered
    -0.65
    POSITIVE LOGITS
     idea
    1.57
     notion
    1.34
     proposition
    1.23
     proposal
    1.20
     candidacy
    1.12
     inclusion
    1.11
     legalization
    1.04
     creation
    1.02
     concept
    1.01
     thesis
    0.97
    Act Density 0.232%

    No Known Activations