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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to sports events and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Whitman
    -0.73
    Oregon
    -0.68
    California
    -0.65
    Seattle
    -0.65
    Defense
    -0.64
     Hawai
    -0.64
    Utah
    -0.64
    Houston
    -0.63
    Florida
    -0.63
     Neighbor
    -0.63
    POSITIVE LOGITS
     criticised
    1.10
     UKIP
    1.02
     organising
    0.99
     Ukip
    0.99
     Labour
    0.96
     apologised
    0.96
     emphas
    0.93
     organised
    0.93
     aluminium
    0.92
     centre
    0.92
    Act Density 3.457%

    No Known Activations