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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific industries or sectors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to industries, government organizations, and economic activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oneself
    -0.71
    orph
    -0.64
     weeds
    -0.63
     iterations
    -0.61
    pedia
    -0.60
     increments
    -0.59
     payoff
    -0.58
     fractures
    -0.58
    depending
    -0.58
     delete
    -0.57
    POSITIVE LOGITS
     abroad
    0.87
    vre
    0.83
    assies
    0.79
    ureau
    0.77
    isine
    0.73
     Expo
    0.72
     Prix
    0.70
     Ambassador
    0.68
     diplomat
    0.68
     consulate
    0.66
    Act Density 0.859%

    No Known Activations