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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the concept of "optimal"

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

    optimal followed by descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    depuis
    -0.48
    SizeMode
    -0.47
    \`
    -0.47
    Autoritní
    -0.46
     algebra
    -0.46
    StructEnd
    -0.46
    mauer
    -0.44
    Algebra
    -0.43
     beards
    -0.43
     rembour
    -0.42
    POSITIVE LOGITS
     optimal
    1.98
    Optimal
    1.91
     Optimal
    1.82
    optimal
    1.75
     optimally
    1.67
     optimum
    1.55
     optimale
    1.50
     Optimum
    1.37
     optima
    1.32
     оптима
    1.22
    Act Density 0.010%

    No Known Activations