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

    Neuronpedia

    INDEX
    Explanations

    references to inclusivity and the entirety of existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.50
     ✭✭
    -0.47
     Meat
    -0.47
    tanleria
    -0.46
     Friction
    -0.42
     Birth
    -0.41
     terse
    -0.40
     mainstay
    -0.40
    enterOuterAlt
    -0.40
     Hygien
    -0.40
    POSITIVE LOGITS
     everything
    0.78
    everything
    0.68
     anything
    0.64
    Everything
    0.64
     Everything
    0.62
    一切
    0.60
     EVERYTHING
    0.60
    的一切
    0.59
     whatever
    0.56
     any
    0.56
    Act Density 0.016%

    No Known Activations