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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "them" in phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people or entities described collectively

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     RTX
    -0.75
    Rush
    -0.70
    Press
    -0.67
    Charg
    -0.66
    âĢ¢âĢ¢
    -0.66
    politics
    -0.63
    Barn
    -0.63
     Sadd
    -0.62
    Fine
    -0.62
    Deal
    -0.62
    POSITIVE LOGITS
    atic
    1.04
    atically
    0.97
     selves
    0.91
     perished
    0.79
    alian
    0.74
    selves
    0.74
     clustered
    0.73
     succeeded
    0.73
     sprinkled
    0.73
    atics
    0.72
    Act Density 0.037%

    No Known Activations