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

    Neuronpedia

    INDEX
    Explanations

    words related to politics

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures or governmental roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Mex
    -1.10
    oglu
    -1.02
    Samsung
    -0.99
     Xperia
    -0.98
     Azerbai
    -0.97
     Romo
    -0.96
    Mexico
    -0.95
     Samsung
    -0.95
     Astros
    -0.92
     Mexican
    -0.92
    POSITIVE LOGITS
     Maine
    1.97
     Worcester
    1.63
     Suffolk
    1.62
     Rhode
    1.60
     Connecticut
    1.57
     Vermont
    1.57
     Dartmouth
    1.57
     Massachusetts
    1.56
     Glou
    1.44
     Hartford
    1.43
    Act Density 0.303%

    No Known Activations