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

    Neuronpedia

    INDEX
    Explanations

    punctuation and structural elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apus
    -0.14
    Ùĩر
    -0.13
    izzas
    -0.13
    .openg
    -0.13
     flame
    -0.13
    HW
    -0.13
     dress
    -0.13
    ftware
    -0.13
    ///<
    -0.12
     sil
    -0.12
    POSITIVE LOGITS
    anchise
    0.16
    aley
    0.15
    unday
    0.15
    serter
    0.15
     Lore
    0.15
     Coleman
    0.14
    opoly
    0.14
    isque
    0.14
    mpr
    0.14
    arella
    0.14
    Act Density 0.059%

    No Known Activations