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

    Neuronpedia

    INDEX
    Explanations

    mentions of different types of abuse and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to sexual violence and abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angular
    -0.71
    é¾įåĸļ士
    -0.62
    æĸ¹
    -0.62
    angelo
    -0.60
    çīĪ
    -0.59
    hin
    -0.59
    éĩ
    -0.58
    Iv
    -0.56
    Split
    -0.54
    èĪ
    -0.54
    POSITIVE LOGITS
     perpetrated
    0.75
     indiscrim
    0.69
     crimes
    0.68
     pervasive
    0.65
     PTSD
    0.65
     terrorism
    0.64
     unlawful
    0.63
     violence
    0.62
     medically
    0.62
     unlawfully
    0.62
    Act Density 1.404%

    No Known Activations