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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political events and controversies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    yrinth
    -0.88
    interstitial
    -0.73
    itous
    -0.72
    SIGN
    -0.72
    RPG
    -0.72
    itual
    -0.72
    ITAL
    -0.71
    cffffcc
    -0.70
    ulus
    -0.70
    Downloadha
    -0.70
    POSITIVE LOGITS
     supremacist
    1.16
    house
    1.08
     supremacists
    1.07
    bread
    1.01
    hall
    0.99
    caps
    0.95
     supremacy
    0.95
     suprem
    0.90
    houses
    0.90
     Sox
    0.86
    Act Density 1.343%

    No Known Activations