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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and parameters within code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etric
    -0.15
     lic
    -0.14
    edic
    -0.14
     cle
    -0.14
    jpeg
    -0.13
     Morrow
    -0.13
    avenport
    -0.13
    práv
    -0.13
    à¸łà¸²à¸ŀ
    -0.13
     VS
    -0.13
    POSITIVE LOGITS
    igham
    0.14
    tics
    0.14
    å¯Ħ
    0.14
    anian
    0.14
    chers
    0.14
    utzer
    0.14
    atest
    0.14
    å¾Ħ
    0.13
    abbo
    0.13
    .Alpha
    0.13
    Act Density 0.111%

    No Known Activations