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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to the masses of people

    oai_token-act-pair · gpt-3.5-turbo

    references to large groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.86
    cer
    -0.75
    Acknowled
    -0.75
    stood
    -0.73
    ties
    -0.70
    Britain
    -0.69
    ces
    -0.68
    LAND
    -0.65
    Es
    -0.64
    ten
    -0.64
    POSITIVE LOGITS
     masses
    1.01
    ysis
    0.78
    ourcing
    0.76
    hare
    0.75
    olutions
    0.73
    urch
    0.73
    rats
    0.72
    uling
    0.72
    rake
    0.71
    ourced
    0.69
    Act Density 0.008%

    No Known Activations