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

    Neuronpedia

    INDEX
    Explanations

    terms related to reduction and minimizing quantities or risks

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

    reduction or decrease

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ddelweddau
    -0.53
    bootstrapcdn
    -0.48
    igraph
    -0.48
    ╮
    -0.47
     hyö
    -0.47
    pulseira
    -0.47
     Мексичка
    -0.46
    phanumeric
    -0.46
     الاطلاع
    -0.46
    ſchaft
    -0.45
    POSITIVE LOGITS
     reduction
    1.23
     reduce
    1.21
     Reduce
    1.18
     reduced
    1.17
    Reduce
    1.12
     Reducing
    1.12
     reducing
    1.09
     Reduced
    1.09
    reduce
    1.08
     reductions
    1.08
    Act Density 0.071%

    No Known Activations