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

    Neuronpedia

    INDEX
    Explanations

    references to political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to the Gandhi family and their political significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lations
    -0.73
    swick
    -0.68
     Bret
    -0.68
    rd
    -0.67
    lopp
    -0.66
     Webster
    -0.66
    changes
    -0.66
    lines
    -0.65
    eric
    -0.65
    amen
    -0.63
    POSITIVE LOGITS
     Gandhi
    1.42
     Sharma
    0.87
     Jinn
    0.87
     Nadu
    0.84
     crore
    0.80
    weed
    0.78
     lakh
    0.75
     Modi
    0.75
     Neh
    0.72
    ashtra
    0.72
    Act Density 0.006%

    No Known Activations