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

    Neuronpedia

    INDEX
    Explanations

    terms related to political extremism and racial tension

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    neau
    -0.82
    IOR
    -0.78
    payer
    -0.72
    hower
    -0.70
     Veter
    -0.67
    cit
    -0.67
    ysis
    -0.67
    fixed
    -0.66
    mination
    -0.65
     Canal
    -0.64
    POSITIVE LOGITS
     extremists
    0.93
     rally
    0.93
     extremist
    0.88
     extremism
    0.88
     supremacists
    0.86
     hate
    0.86
     ideology
    0.86
    ervative
    0.86
     ideologies
    0.85
     thugs
    0.84
    Act Density 0.085%

    No Known Activations