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

    Neuronpedia

    INDEX
    Explanations

    terms related to specific laws, policies, and governmental actions

    oai_token-act-pair · gpt-3.5-turbo

    references to legislation and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    male
    -0.56
    form
    -0.56
     Grimoire
    -0.55
    tein
    -0.54
    Dialogue
    -0.54
    cific
    -0.53
    ground
    -0.53
    ktop
    -0.52
    inside
    -0.52
    stuff
    -0.52
    POSITIVE LOGITS
     boycot
    0.67
    Ü
    0.67
    士
    0.66
    TPP
    0.65
     riots
    0.64
     subsidies
    0.61
     bombings
    0.61
     screenings
    0.60
     protests
    0.58
     hurricanes
    0.58
    Act Density 0.741%

    No Known Activations