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

    Neuronpedia

    INDEX
    Explanations

    references to the origins or beginnings of various subjects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aise
    -0.16
    inger
    -0.16
    eyes
    -0.15
    anson
    -0.15
    ington
    -0.15
    ey
    -0.15
    .dump
    -0.15
    jang
    -0.14
    sters
    -0.14
     frontier
    -0.14
    POSITIVE LOGITS
    ator
    0.23
    ATOR
    0.20
    /source
    0.19
    ators
    0.17
    bud
    0.16
     quán
    0.15
    iated
    0.15
     Pazar
    0.15
    üven
    0.14
    atings
    0.14
    Act Density 0.057%

    No Known Activations