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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment or terms related to disapproval and criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tags
    -0.77
     substitutes
    -0.73
     XL
    -0.72
     coat
    -0.70
     GEAR
    -0.70
     tackles
    -0.70
     grades
    -0.70
     orientation
    -0.70
     CHO
    -0.70
     servings
    -0.69
    POSITIVE LOGITS
    famous
    1.35
    existing
    1.23
    successful
    1.21
    mentioned
    1.15
    recent
    1.14
    prev
    1.11
    nas
    1.10
    established
    1.10
    popular
    1.09
    larg
    1.08
    Act Density 0.096%

    No Known Activations