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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific groups of people or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people and their interactions with laws or authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.71
    ggles
    -0.69
    ISION
    -0.64
    kefeller
    -0.64
     teamwork
    -0.63
    CONCLUS
    -0.62
    fecture
    -0.61
    itivity
    -0.61
    é¾
    -0.61
    SourceFile
    -0.60
    POSITIVE LOGITS
     who
    1.19
     whose
    1.16
     whom
    1.12
     suspected
    1.10
     unlawfully
    1.00
     illegally
    0.95
     deemed
    0.92
    who
    0.92
     fleeing
    0.92
     accused
    0.91
    Act Density 0.331%

    No Known Activations