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

    Neuronpedia

    INDEX
    Explanations

    references to political hypocrisy and critique of authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itone
    -0.15
    arkin
    -0.15
    :convert
    -0.15
    oldem
    -0.15
    kich
    -0.14
    IDEO
    -0.14
    ritz
    -0.14
    ãĥ¶
    -0.14
     Trinidad
    -0.14
    umeric
    -0.14
    POSITIVE LOGITS
     Apprentice
    0.25
     tweeting
    0.25
     MAG
    0.25
     tweet
    0.24
     golf
    0.23
     tweets
    0.23
     Golf
    0.21
     Oval
    0.21
     Tweets
    0.21
     Tweet
    0.21
    Act Density 0.216%

    No Known Activations