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

    Neuronpedia

    INDEX
    Explanations

    non-standard characters and symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     omas
    -0.17
    .AutoComplete
    -0.15
    ocuk
    -0.15
    ...č↵
    -0.15
     gezocht
    -0.14
    ode
    -0.14
    utorials
    -0.14
    azole
    -0.14
    erreur
    -0.14
    aves
    -0.14
    POSITIVE LOGITS
    Ñķ
    0.18
     Pearce
    0.15
    IGIN
    0.15
     Niet
    0.14
    ãĥ³ãĤº
    0.14
    Ö
    0.14
     Fir
    0.14
     Ñ
    0.14
    677
    0.14
    ofil
    0.14
    Act Density 0.003%

    No Known Activations