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

    Neuronpedia

    INDEX
    Explanations

    references to best practices in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ady
    -0.16
    isor
    -0.15
    ookie
    -0.14
     Suc
    -0.14
    Suc
    -0.14
    ouv
    -0.14
     vere
    -0.14
    ccion
    -0.14
    ohan
    -0.14
    nut
    -0.14
    POSITIVE LOGITS
    é©
    0.17
    avel
    0.17
    bash
    0.15
    feit
    0.15
    fully
    0.15
    heets
    0.14
    005
    0.14
    ries
    0.14
    otas
    0.14
     DÄĽ
    0.13
    Act Density 0.012%

    No Known Activations