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

    Neuronpedia

    INDEX
    Explanations

    code-related comments and documentation markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilha
    -0.18
    親
    -0.17
    emmel
    -0.17
    itra
    -0.16
    ола
    -0.16
    ìļ°ë¦¬
    -0.15
    ละ
    -0.15
    (æ°´
    -0.15
    OLA
    -0.15
    venes
    -0.15
    POSITIVE LOGITS
     in
    0.16
     fur
    0.15
     Conserv
    0.14
     Eins
    0.14
     Kaw
    0.14
     do
    0.14
     Skyl
    0.14
    376
    0.14
     Ragnar
    0.14
     mix
    0.14
    Act Density 0.010%

    No Known Activations