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

    Neuronpedia

    INDEX
    Explanations

    terms related to weight and its management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.78
     Wikispecies
    -0.74
    FontOfSize
    -0.72
    sslich
    -0.68
    harusnya
    -0.65
    mejores
    -0.62
    ✨:
    -0.62
    цездатний
    -0.61
    :✨
    -0.61
     Diener
    -0.60
    POSITIVE LOGITS
     weights
    1.36
    weight
    1.35
     Weight
    1.30
     weight
    1.30
    WEIGHT
    1.27
    weights
    1.26
     WEIGHT
    1.25
    Weight
    1.19
     Weights
    1.15
    Weights
    1.06
    Act Density 0.137%

    No Known Activations