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

    Neuronpedia

    INDEX
    Explanations

    political terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political contexts or motivations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chiefs
    -0.78
     Vikings
    -0.74
     Rams
    -0.73
     Seasons
    -0.72
     Jackets
    -0.71
     Isle
    -0.70
     Cannes
    -0.70
     Royals
    -0.70
     Rune
    -0.70
     Viking
    -0.68
    POSITIVE LOGITS
     speaking
    0.89
     correct
    0.89
     motivated
    0.81
     affili
    0.81
     incorrect
    0.81
     minded
    0.80
     handic
    0.79
    speaking
    0.75
     engineered
    0.74
     advant
    0.73
    Act Density 0.007%

    No Known Activations