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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to towns or individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual or entity associated with political discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.77
     Kinnikuman
    -0.72
    ãĥĥãĥī
    -0.68
     Io
    -0.67
    ignment
    -0.67
    figure
    -0.66
    é¾į
    -0.65
    ividual
    -0.65
     polymer
    -0.65
    transform
    -0.64
    POSITIVE LOGITS
     Sau
    1.27
     sauces
    1.07
    asant
    0.91
    reau
    0.91
    uve
    0.85
    illas
    0.85
     juices
    0.83
    ppo
    0.83
     Sauce
    0.81
     grapes
    0.81
    Act Density 0.016%

    No Known Activations