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

    Neuronpedia

    INDEX
    Explanations

    references to large groups of people

    oai_token-act-pair · gpt-3.5-turbo

    references to crowds and large gatherings of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lege
    -0.67
    Sword
    -0.66
    oma
    -0.66
     KB
    -0.65
    pel
    -0.65
    mi
    -0.64
     ·
    -0.60
    �
    -0.60
     Note
    -0.60
     Reply
    -0.59
    POSITIVE LOGITS
     crowds
    4.09
     crowd
    2.36
     Crowd
    2.17
    rowd
    2.02
     audiences
    1.52
     mobs
    1.43
     gatherings
    1.36
     hordes
    1.34
     queues
    1.19
     rallies
    1.17
    Act Density 0.013%

    No Known Activations