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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize improvements, solutions, or positive modifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    more or better

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     toes
    -0.35
    AndEndTag
    -0.34
    enderror
    -0.33
     Jungfrau
    -0.33
     プリーツ
    -0.33
    iconque
    -0.32
    enough
    -0.32
     للغاية
    -0.32
     Cæsar
    -0.32
    pyplot
    -0.32
    POSITIVE LOGITS
     Stronger
    1.08
     better
    1.07
     stronger
    1.05
     brighter
    1.04
     happier
    1.03
    better
    1.00
     clearer
    0.98
     quicker
    0.97
     Better
    0.96
    Better
    0.96
    Act Density 1.258%

    No Known Activations