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

    Neuronpedia

    INDEX
    Explanations

    words related to legal or criminal actions

    oai_token-act-pair · gpt-3.5-turbo

    topics related to social and environmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.77
    agame
    -0.76
    undrum
    -0.75
    mma
    -0.67
    agonist
    -0.64
    uzzle
    -0.62
    ologue
    -0.61
    */(
    -0.59
    ilogy
    -0.59
     Originally
    -0.58
    POSITIVE LOGITS
     groups
    0.86
     institutions
    0.84
     rivals
    0.81
     minorities
    0.79
     organizations
    0.79
     emergencies
    0.79
     populations
    0.79
     sites
    0.78
     targets
    0.78
     establishments
    0.78
    Act Density 0.812%

    No Known Activations