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

    Neuronpedia

    INDEX
    Explanations

    observations and critiques regarding societal narratives and perceptions of crime and social progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kazy
    -0.15
    ÏĩÏĮ
    -0.15
    ange
    -0.13
    irting
    -0.13
    odash
    -0.13
    latin
    -0.13
    ãĥ¼ãĤº
    -0.13
    ÙĪاج
    -0.13
    詳細
    -0.12
    ocities
    -0.12
    POSITIVE LOGITS
     view
    0.45
     perception
    0.43
     understanding
    0.40
     perceptions
    0.39
     views
    0.38
     notions
    0.34
     notion
    0.33
     assumptions
    0.32
     understand
    0.32
     Perception
    0.32
    Act Density 0.648%

    No Known Activations