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

    Neuronpedia

    INDEX
    Explanations

    discussion points related to societal issues and their impact

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant societal issues or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Write
    -0.71
     originals
    -0.64
     viz
    -0.64
    Versions
    -0.63
    sburg
    -0.62
    ENSE
    -0.62
    Tour
    -0.62
     WRITE
    -0.61
    resp
    -0.60
     Jr
    -0.58
    POSITIVE LOGITS
     prevalent
    1.02
     pervasive
    1.00
     prolifer
    0.99
     booming
    0.99
     ubiquitous
    0.97
     rife
    0.96
     fraught
    0.96
     commonplace
    0.96
     abound
    0.95
     rampant
    0.95
    Act Density 0.456%

    No Known Activations