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

    Neuronpedia

    INDEX
    Explanations

    sequences of numerical statistics or scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ops
    -0.14
    _ctxt
    -0.14
    ewise
    -0.14
    شت
    -0.14
    agh
    -0.14
     fix
    -0.14
    bere
    -0.14
    siz
    -0.14
    ushi
    -0.14
    alc
    -0.14
    POSITIVE LOGITS
    686
    0.15
     Priv
    0.15
    709
    0.14
    errat
    0.14
    udes
    0.14
    teenth
    0.14
    vue
    0.14
    iterr
    0.14
     CTRL
    0.14
    ney
    0.14
    Act Density 0.004%

    No Known Activations