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

    Neuronpedia

    INDEX
    Explanations

    words related to organized public demonstrations or protests

    oai_token-act-pair · gpt-3.5-turbo

    references to protests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lasses
    -0.79
    efficients
    -0.76
    illac
    -0.71
    nown
    -0.70
     Wonders
    -0.68
    oiler
    -0.66
    efe
    -0.65
    ewater
    -0.65
    metics
    -0.63
    awed
    -0.63
    POSITIVE LOGITS
    ations
    1.01
     against
    0.99
     encamp
    0.91
     marches
    0.87
     march
    0.86
     organizers
    0.84
     rally
    0.83
    ant
    0.82
    aires
    0.82
     organizer
    0.81
    Act Density 0.060%

    No Known Activations