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

    Neuronpedia

    INDEX
    Explanations

    references to authority, creation, and philosophical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     al
    -0.15
    iris
    -0.15
     æ¥Ń
    -0.14
     Viagra
    -0.14
    лада
    -0.14
    hir
    -0.14
    ãĤīãģĦ
    -0.13
    ohn
    -0.13
    ech
    -0.13
    orta
    -0.13
    POSITIVE LOGITS
    .scalablytyped
    0.19
    fov
    0.17
     Fucking
    0.15
    unate
    0.15
    Å¡t
    0.15
    andom
    0.14
     Straw
    0.14
    zimmer
    0.14
     USHORT
    0.14
     Salv
    0.14
    Act Density 0.004%

    No Known Activations