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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases or structures in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amus
    -0.17
     Dank
    -0.15
     ç¯
    -0.15
    ASN
    -0.14
    _METADATA
    -0.14
    lum
    -0.14
    .kr
    -0.14
    owie
    -0.14
    amt
    -0.13
    nika
    -0.13
    POSITIVE LOGITS
    oret
    0.17
     Sever
    0.16
     Barth
    0.15
     absl
    0.14
    oola
    0.14
    oud
    0.14
     Horton
    0.14
    onis
    0.13
    etric
    0.13
    oppers
    0.13
    Act Density 0.003%

    No Known Activations