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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts involving prime numbers and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rias
    -0.16
    ersed
    -0.15
    elm
    -0.14
    ovny
    -0.14
    errer
    -0.14
    ownik
    -0.14
    ebo
    -0.13
    obj
    -0.13
     Lump
    -0.13
    -bordered
    -0.13
    POSITIVE LOGITS
     fixed
    0.30
    fixed
    0.24
    .fixed
    0.23
     natural
    0.22
     arbitrary
    0.22
     sufficiently
    0.21
     given
    0.21
     Fixed
    0.21
     integers
    0.21
     positive
    0.20
    Act Density 0.146%

    No Known Activations