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

    Neuronpedia

    INDEX
    Explanations

    mentions of victims in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to victims of various forms of violence or abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arily
    -0.71
    hed
    -0.71
    heads
    -0.70
    liness
    -0.70
    ortment
    -0.70
    ahead
    -0.69
     susp
    -0.68
    hey
    -0.68
    ulum
    -0.67
    HK
    -0.66
    POSITIVE LOGITS
     injustice
    0.96
     violence
    0.91
     vandalism
    0.87
     persecution
    0.87
     abuse
    0.86
     discrimination
    0.85
     oppression
    0.85
     arson
    0.84
     crime
    0.84
     tyranny
    0.81
    Act Density 0.089%

    No Known Activations