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

    Neuronpedia

    INDEX
    Explanations

    discussions surrounding political accountability and public service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Strategies
    -0.16
     contested
    -0.15
    jar
    -0.15
     gender
    -0.15
    STIT
    -0.15
     poorly
    -0.14
    km
    -0.14
     www
    -0.14
     aka
    -0.14
     corp
    -0.14
    POSITIVE LOGITS
     discriminatory
    0.16
    inery
    0.15
    éri
    0.14
    sched
    0.14
    roup
    0.14
    essen
    0.14
     nationals
    0.14
     Hemisphere
    0.14
     factual
    0.14
     ceilings
    0.14
    Act Density 0.035%

    No Known Activations