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

    Neuronpedia

    INDEX
    Explanations

    numerical references and identifiers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arer
    -0.18
    rys
    -0.17
    ijkstra
    -0.17
    ogle
    -0.15
    xea
    -0.15
    andom
    -0.14
    ano
    -0.14
    岡
    -0.14
    iram
    -0.14
    loth
    -0.14
    POSITIVE LOGITS
    enta
    0.16
     impr
    0.15
    度
    0.14
    å®Ļ
    0.14
    .rgb
    0.14
     root
    0.14
     equivalence
    0.13
     اÙĦÙĪÙĤت
    0.13
     Fischer
    0.13
     now
    0.13
    Act Density 0.002%

    No Known Activations