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

    Neuronpedia

    INDEX
    Explanations

    concepts related to naturalness and authenticity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     descargar
    -0.16
    ipher
    -0.15
    aire
    -0.15
    .Foundation
    -0.14
    ilet
    -0.14
    bens
    -0.14
    agen
    -0.14
    /th
    -0.13
    sel
    -0.13
     NÄĽk
    -0.13
    POSITIVE LOGITS
     naturally
    0.27
     natural
    0.23
     Naturally
    0.22
     Natural
    0.22
    Natural
    0.21
     progression
    0.21
    /default
    0.20
    -born
    0.19
    aturally
    0.19
     doÄŁal
    0.18
    Act Density 0.051%

    No Known Activations