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

    Neuronpedia

    INDEX
    Explanations

    references to weight, weight measurement, and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -0.89
     nahilalakip
    -0.81
    ✨:
    -0.81
    Legături
    -0.79
    OGND
    -0.76
     animado
    -0.75
     bambú
    -0.74
     desapar
    -0.74
     Solano
    -0.73
     Вікіпе
    -0.72
    POSITIVE LOGITS
     weight
    1.65
     weights
    1.60
    weight
    1.59
     Weight
    1.59
    weights
    1.53
     WEIGHT
    1.52
    WEIGHT
    1.42
    Weight
    1.41
     Weights
    1.40
    Weights
    1.20
    Act Density 0.135%

    No Known Activations