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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurements and varying quantities of substances or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.53
    ########.
    -0.50
     
    -0.48
    plugins
    -0.45
     الاست
    -0.45
    ประ
    -0.44
     total
    -0.44
    ssaint
    -0.43
    utex
    -0.43
     ant
    -0.42
    POSITIVE LOGITS
     amounts
    1.54
    amounts
    1.50
     quantities
    1.46
     distances
    1.41
     speeds
    1.40
     thicknesses
    1.38
     Amounts
    1.37
     densities
    1.37
     Quantities
    1.37
     temperatures
    1.36
    Act Density 0.243%

    No Known Activations