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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal proceedings and potential consequences

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to societal critique and human behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.73
    */
    -0.67
    "}],"
    -0.65
    else
    -0.64
    ))))
    -0.63
     meanwhile
    -0.62
    âĸº
    -0.62
    ebus
    -0.62
    kson
    -0.60
    »Ĵ
    -0.60
    POSITIVE LOGITS
     fundamentally
    0.65
     excessively
    0.63
     singular
    0.61
     sexually
    0.61
     certain
    0.61
     civilizations
    0.60
     radically
    0.60
     stereotypical
    0.60
     superheroes
    0.59
     extrater
    0.59
    Act Density 1.140%

    No Known Activations