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

    Neuronpedia

    INDEX
    Explanations

    information and opinions related to politics and societal issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     thut
    -0.83
     fta
    -0.76
     ftu
    -0.75
     »>
    -0.75
     quitted
    -0.75
     purcha
    -0.75
     poff
    -0.73
     guarante
    -0.72
     feen
    -0.72
     tranf
    -0.71
    POSITIVE LOGITS
     years
    0.76
     decades
    0.74
     centuries
    0.63
     awhile
    0.61
     YEARS
    0.60
     months
    0.58
     Years
    0.57
    years
    0.57
     decade
    0.55
     Depuis
    0.55
    Act Density 0.159%

    No Known Activations