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

    Neuronpedia

    INDEX
    Explanations

    XML declaration and attribute definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Powers
    -0.18
    gh
    -0.15
    gere
    -0.14
    inati
    -0.14
    afka
    -0.14
     Rap
    -0.14
    Reached
    -0.14
     imper
    -0.13
    509
    -0.13
    omain
    -0.13
    POSITIVE LOGITS
    IPA
    0.16
    icho
    0.15
    zos
    0.14
    arte
    0.13
    arc
    0.13
    aires
    0.13
    éĸ
    0.13
    zens
    0.13
     Asi
    0.13
    .bs
    0.13
    Act Density 0.012%

    No Known Activations