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

    Neuronpedia

    INDEX
    Explanations

    the word "Us" occurring with different degrees of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "Us" or references relevant to a collective group or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    served
    -0.73
     chaired
    -0.63
    hetti
    -0.62
     confinement
    -0.60
    sticks
    -0.59
     Sands
    -0.58
     sucker
    -0.57
     plateau
    -0.56
     hots
    -0.56
     laureate
    -0.56
    POSITIVE LOGITS
    hers
    1.21
    agi
    1.07
    chwitz
    0.98
    urers
    0.91
    ern
    0.90
    selves
    0.90
    ages
    0.90
    nyder
    0.88
    cul
    0.87
    earchers
    0.83
    Act Density 0.020%

    No Known Activations