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

    Neuronpedia

    INDEX
    Explanations

    expressions of relativity or comparison in terms of measurements or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Relative" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    relative comparisons and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    样的
    -0.56
     delegado
    -0.56
    يكب
    -0.54
     voulez
    -0.54
    ържа
    -0.53
    gestone
    -0.52
     ellers
    -0.51
    ագրություններ
    -0.49
     medži
    -0.49
    scribers
    -0.48
    POSITIVE LOGITS
     speaking
    0.79
     (%)
    0.70
     newcomer
    0.69
    RTHOOK
    0.69
    speaking
    0.67
     @}
    0.67
     humidity
    0.66
    ussis
    0.63
     strangers
    0.62
     stranger
    0.62
    Act Density 0.118%

    No Known Activations