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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "optimum."

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

    finding the optimum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Stal
    -0.58
     lenker
    -0.58
    :✨
    -0.56
    walled
    -0.56
    ternal
    -0.55
     Viral
    -0.54
     epile
    -0.53
    ḷ
    -0.52
    Stal
    -0.52
     Dal
    -0.52
    POSITIVE LOGITS
     optimum
    1.49
     Optimum
    1.24
    IMUM
    0.72
    MAXIMUM
    0.62
     maksimum
    0.60
     Einfluß
    0.58
     optima
    0.57
     maximum
    0.56
     MAXIMUM
    0.55
     Maximum
    0.54
    Act Density 0.008%

    No Known Activations