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

    Neuronpedia

    INDEX
    Explanations

    references to examples and illustrative cases within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ched
    -0.16
    ier
    -0.16
    lier
    -0.16
    èĢħçļĦ
    -0.15
    ibs
    -0.15
    elper
    -0.15
    agn
    -0.14
    erdem
    -0.14
    ogle
    -0.14
    eliac
    -0.14
    POSITIVE LOGITS
    /tutorial
    0.16
    psilon
    0.16
    ãģĪãģ°
    0.15
    aad
    0.15
    387
    0.15
    ENCIL
    0.14
    oeff
    0.14
    991
    0.14
    /example
    0.14
    d
    0.14
    Act Density 0.051%

    No Known Activations