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

    Neuronpedia

    INDEX
    Explanations

    terms related to dangerous or violent situations

    oai_token-act-pair · gpt-3.5-turbo

    references to protests and civil unrest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #$
    -0.82
    Thumbnail
    -0.73
    INTON
    -0.69
    ãĤ£
    -0.68
    Benz
    -0.67
    Care
    -0.66
    endment
    -0.66
    acha
    -0.66
     Difference
    -0.64
     Balance
    -0.62
    POSITIVE LOGITS
     prolifer
    1.54
     commonplace
    1.38
     abound
    1.33
     popping
    1.30
     frequent
    1.26
     sporadic
    1.20
     spor
    1.16
     occurring
    1.09
     plentiful
    1.07
     rampant
    1.05
    Act Density 0.452%

    No Known Activations