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

    Neuronpedia

    INDEX
    Explanations

    terms related to optimization and maximizing potential

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eled
    -0.17
    leton
    -0.16
    516
    -0.16
    esis
    -0.15
    heits
    -0.15
    e
    -0.15
    apon
    -0.15
    iard
    -0.15
    añ
    -0.15
    sie
    -0.15
    POSITIVE LOGITS
    ally
    0.24
    izes
    0.23
    izing
    0.23
    ized
    0.22
    izers
    0.22
    ALSE
    0.21
    arily
    0.21
    ised
    0.20
    isation
    0.20
    ise
    0.20
    Act Density 0.008%

    No Known Activations