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

    Neuronpedia

    INDEX
    Explanations

    references to political opposition and dissent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tron
    -0.17
    ystone
    -0.16
    ibus
    -0.15
    aniem
    -0.15
    $$$$
    -0.15
    tings
    -0.15
    ills
    -0.15
    irst
    -0.15
    igans
    -0.15
    juan
    -0.15
    POSITIVE LOGITS
    /op
    0.25
     forces
    0.22
     parties
    0.18
    ive
    0.18
     camp
    0.18
    /conf
    0.18
    -minded
    0.17
     minded
    0.17
     camps
    0.17
     groups
    0.17
    Act Density 0.058%

    No Known Activations