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

    Neuronpedia

    INDEX
    Explanations

    terms related to 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
    illac
    -0.73
    lasses
    -0.72
    efficients
    -0.71
    nown
    -0.71
    estone
    -0.67
    scribe
    -0.64
     Wonders
    -0.64
    theless
    -0.63
    oiler
    -0.63
    ewater
    -0.61
    POSITIVE LOGITS
    ations
    1.01
     against
    0.92
    aires
    0.85
     encamp
    0.85
    ant
    0.82
    ors
    0.80
    ational
    0.77
     marches
    0.76
     rally
    0.76
     march
    0.75
    Act Density 0.043%

    No Known Activations