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

    Neuronpedia

    INDEX
    Explanations

    topics related to societal issues and trends

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to societal problems and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.72
    xit
    -0.61
    odan
    -0.61
    ushed
    -0.61
     thereof
    -0.60
    obos
    -0.59
    ushing
    -0.57
     unsuccessful
    -0.57
    oping
    -0.57
    isively
    -0.57
    POSITIVE LOGITS
     nowadays
    1.44
     today
    1.12
     lately
    1.07
     here
    1.04
     tonight
    0.96
     now
    0.96
     everywhere
    0.91
     internationally
    0.85
     anymore
    0.84
     worldwide
    0.80
    Act Density 0.780%

    No Known Activations