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

    Neuronpedia

    INDEX
    Explanations

    references to privacy and policy-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enta
    -0.16
    eron
    -0.16
    atern
    -0.15
    454
    -0.15
    934
    -0.14
    779
    -0.14
     sum
    -0.14
    ãĤ¹ãĥĨãĤ£
    -0.13
    ãĤ·ãĤ§
    -0.13
    ,
    -0.13
    POSITIVE LOGITS
    ãĥ¼ãĥ
    0.15
    amon
    0.15
    cco
    0.14
    imli
    0.14
    Ñģли
    0.14
    ngo
    0.14
     imageSize
    0.14
    LOS
    0.13
    udu
    0.13
    .bt
    0.13
    Act Density 0.014%

    No Known Activations