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

    Neuronpedia

    INDEX
    Explanations

    references to weight and measurements related to physical health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.92
    ✨:
    -0.92
    expandindo
    -0.91
     bambú
    -0.82
     Mij
    -0.82
     mitosis
    -0.81
     hostels
    -0.81
     fotografico
    -0.79
    OGND
    -0.78
     Wikispecies
    -0.78
    POSITIVE LOGITS
     weight
    1.59
     weights
    1.58
    weight
    1.55
     Weight
    1.55
    weights
    1.51
     WEIGHT
    1.47
    WEIGHT
    1.36
    Weight
    1.34
     Weights
    1.27
    Weights
    1.16
    Act Density 0.077%

    No Known Activations