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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political figures and their actions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the president

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.78
     Casting
    -0.72
     Mechdragon
    -0.65
     Variety
    -0.64
    ITAL
    -0.64
     Nadu
    -0.64
     Closed
    -0.63
     Kaf
    -0.63
     Blazing
    -0.62
     Dise
    -0.62
    POSITIVE LOGITS
    ially
    1.08
    clinton
    0.87
    trump
    0.81
    ial
    0.80
    manship
    0.76
     administration
    0.76
     presidency
    0.76
    's
    0.75
     Barack
    0.74
    care
    0.73
    Act Density 0.061%

    No Known Activations