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

    Neuronpedia

    INDEX
    Explanations

    references to protests or protest-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to protests or acts of demonstration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nown
    -0.79
    theless
    -0.78
    illac
    -0.74
    efficients
    -0.72
    oiler
    -0.70
    ccording
    -0.69
    ewater
    -0.69
    ubi
    -0.67
    paste
    -0.67
    estial
    -0.65
    POSITIVE LOGITS
     encamp
    0.87
    ations
    0.87
     protestors
    0.79
     protesting
    0.78
    aires
    0.77
    rained
    0.76
     protest
    0.76
    atos
    0.74
    ors
    0.74
    istas
    0.74
    Act Density 0.036%

    No Known Activations