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

    Neuronpedia

    INDEX
    Explanations

    violence-related content

    oai_token-act-pair · gpt-3.5-turbo

    references to violence and serious social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     supplemental
    -0.71
    Specifically
    -0.70
     dude
    -0.67
     workout
    -0.66
    aska
    -0.65
     ASAP
    -0.64
     tweaked
    -0.64
    gee
    -0.63
     Specifically
    -0.63
     maximizing
    -0.62
    POSITIVE LOGITS
     sectarian
    0.85
     imperialist
    0.82
     tragedies
    0.80
     rumours
    0.80
     testimonies
    0.80
     politicians
    0.80
     geop
    0.80
     neighbouring
    0.80
    Pakistan
    0.79
     martyr
    0.78
    Act Density 1.330%

    No Known Activations