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

    Neuronpedia

    INDEX
    Explanations

    long, thoughtful statements or discussions on various topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ares
    -0.74
    strip
    -0.65
    eal
    -0.62
    assisted
    -0.62
    buster
    -0.62
    bies
    -0.60
     endeavors
    -0.60
    achi
    -0.60
    icut
    -0.57
     bombed
    -0.55
    POSITIVE LOGITS
     plenty
    1.15
     ample
    0.94
     overlap
    0.89
     precedent
    0.87
     no
    0.85
     similarities
    0.83
     lots
    0.81
     unanim
    0.81
     disagreement
    0.80
     variability
    0.77
    Act Density 2.842%

    No Known Activations