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

    Neuronpedia

    INDEX
    Explanations

    language related to political discussions, policies, and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of political strategies and plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ometimes
    -0.73
     errone
    -0.72
     incorrectly
    -0.69
     Locations
    -0.68
    atcher
    -0.67
     forbids
    -0.65
     Compton
    -0.65
     âĨij
    -0.64
     Errors
    -0.63
     Booth
    -0.63
    POSITIVE LOGITS
     coherent
    1.48
     cohesive
    1.24
     centrist
    1.16
     viable
    1.13
     leadership
    1.13
     electoral
    1.11
     populist
    1.10
     principled
    1.07
     unity
    1.05
     credible
    1.04
    Act Density 0.639%

    No Known Activations