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

    Neuronpedia

    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    names of politicians and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nikov
    -0.73
     analysed
    -0.70
    sterdam
    -0.68
    Games
    -0.68
     realised
    -0.66
     rehearsal
    -0.66
    idas
    -0.65
    seys
    -0.65
    nis
    -0.65
     catalogue
    -0.64
    POSITIVE LOGITS
     Reps
    1.35
     Dianne
    1.28
     Corker
    1.25
     Congressman
    1.23
     Jeanne
    1.22
     Lindsey
    1.21
     Senator
    1.21
     Tuls
    1.20
     Susan
    1.19
     Representative
    1.16
    Act Density 0.161%

    No Known Activations