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

    Neuronpedia

    INDEX
    Explanations

    political-related words, including names of politicians and specific political events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    angular
    -0.84
    undai
    -0.78
    eon
    -0.76
    obyl
    -0.76
    rices
    -0.72
    amber
    -0.71
    razen
    -0.69
    opal
    -0.67
    ronic
    -0.67
    allery
    -0.66
    POSITIVE LOGITS
     Rapids
    0.91
     Brewers
    0.84
    waukee
    0.82
    Madison
    0.82
    kers
    0.81
    Wisconsin
    0.80
     WI
    0.79
     Bucks
    0.76
    DL
    0.74
    stown
    0.72
    Act Density 0.063%

    No Known Activations