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

    Neuronpedia

    INDEX
    Explanations

    references to disagreement or conflict in opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ήÏĤ
    -0.15
    ournal
    -0.14
    m
    -0.14
    arra
    -0.14
     sustain
    -0.14
     fare
    -0.13
    indi
    -0.13
    æ
    -0.13
    SETS
    -0.13
    ηÏĤ
    -0.13
    POSITIVE LOGITS
    erse
    0.17
    eria
    0.15
    verse
    0.15
    ibir
    0.15
    lint
    0.15
    EncodingException
    0.14
    idges
    0.14
    676
    0.14
    Argb
    0.14
     Burk
    0.14
    Act Density 0.167%

    No Known Activations