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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and social issues

    oai_token-act-pair · gpt-3.5-turbo

    instances of period punctuation indicating the end of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     glim
    -1.15
     carbohyd
    -0.91
     creek
    -0.82
     zo
    -0.80
     calf
    -0.79
     elig
    -0.79
     nodd
    -0.79
     paddle
    -0.78
     wire
    -0.78
     helper
    -0.78
    POSITIVE LOGITS
     Indeed
    1.46
     Worse
    1.44
     Hence
    1.39
     Moreover
    1.38
     Whereas
    1.37
     Ironically
    1.34
     Consequently
    1.34
     Yet
    1.34
     Governments
    1.32
     Thus
    1.31
    Act Density 0.444%

    No Known Activations