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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of violence, including rape and cyber violence

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual assault and related statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dise
    -0.65
     sorely
    -0.64
     Profit
    -0.62
     Sov
    -0.60
    rules
    -0.60
    archs
    -0.60
     legions
    -0.59
    Sov
    -0.59
    pots
    -0.58
     anarchy
    -0.57
    POSITIVE LOGITS
     âī¥
    0.95
     spouse
    0.92
     acquaintance
    0.87
     respondent
    0.83
     or
    0.83
     partner
    0.82
     themselves
    0.81
     anten
    0.81
     oneself
    0.76
     compared
    0.76
    Act Density 0.401%

    No Known Activations