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

    Neuronpedia

    INDEX
    Explanations

    specific examples of topics or areas related to various nouns provided, including physical attacks, environmental issues, crimes, industries, medical care, daily activities, cultural references, online platforms, and technology products

    oai_token-act-pair · gpt-3.5-turbo

    terms related to different types of crimes or illicit activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minist
    -0.84
    galitarian
    -0.74
    issance
    -0.73
    ongyang
    -0.73
     cannabin
    -0.71
    formance
    -0.69
    ournals
    -0.69
    malink
    -0.68
    ividual
    -0.68
    uyomi
    -0.68
    POSITIVE LOGITS
    âĨĴ
    0.63
     toddlers
    0.63
     mats
    0.63
     champ
    0.61
    Wave
    0.57
    !).
    0.55
     wives
    0.55
    Boss
    0.55
    )—
    0.55
    bright
    0.54
    Act Density 0.610%

    No Known Activations