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

    Neuronpedia

    INDEX
    Explanations

    names of politicians and discussion of political topics

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cub
    -0.77
     Beacon
    -0.74
     Hydra
    -0.74
    Weiss
    -0.72
     neoc
    -0.69
     Sounders
    -0.68
     [...]
    -0.66
     Myr
    -0.65
     Normandy
    -0.65
     Weiss
    -0.65
    POSITIVE LOGITS
    jriwal
    1.23
     Sharma
    1.23
     Singh
    1.17
    umbai
    1.17
    ashtra
    1.15
    athi
    1.14
     Kumar
    1.12
     Gandhi
    1.12
     Gujarat
    1.11
     Kejriwal
    1.11
    Act Density 0.389%

    No Known Activations