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

    Neuronpedia

    INDEX
    Explanations

    large groups of people

    oai_token-act-pair · gpt-3.5-turbo

    quantitative expressions indicating large groups of people or crowds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     uniqueness
    -0.66
    Honest
    -0.64
     relativity
    -0.64
     monopoly
    -0.63
    Interstitial
    -0.61
     omission
    -0.60
    Recomm
    -0.59
    ļéĨĴ
    -0.57
     causation
    -0.57
    Anything
    -0.56
    POSITIVE LOGITS
     marched
    1.05
     gathered
    0.99
     protested
    0.97
     flock
    0.97
    ourcing
    0.95
     rallied
    0.94
     fleeing
    0.91
     gather
    0.90
     of
    0.88
     mobilized
    0.88
    Act Density 0.047%

    No Known Activations