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

    Neuronpedia

    INDEX
    Explanations

    physical properties and weight-related terms in the context of objects and apparatus

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Legături
    -0.62
     Paglinawan
    -0.61
    ochim
    -0.54
    جوايز
    -0.51
    Smarty
    -0.51
    windig
    -0.50
    árqu
    -0.49
    аг
    -0.49
     networks
    -0.48
     YM
    -0.48
    POSITIVE LOGITS
     weight
    1.06
     heavier
    0.97
     weighing
    0.94
    重量
    0.94
     WEIGHT
    0.94
    weight
    0.93
     weights
    0.92
     Weight
    0.91
    Weight
    0.88
     weighs
    0.87
    Act Density 0.059%

    No Known Activations