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

    Neuronpedia

    INDEX
    Explanations

    references to experimental research and studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pagen
    -0.18
    ongs
    -0.16
    lier
    -0.16
    uracy
    -0.16
    elper
    -0.15
    oping
    -0.14
    erator
    -0.14
    nap
    -0.14
    ough
    -0.14
    achi
    -0.14
    POSITIVE LOGITS
    ally
    0.20
    室
    0.20
    ALLY
    0.16
    ogue
    0.16
    elling
    0.15
    ative
    0.15
    allback
    0.15
    elles
    0.15
    peri
    0.15
    ìĭ¤
    0.14
    Act Density 0.019%

    No Known Activations