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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to significant conditions or exceptions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arges
    -0.16
    857
    -0.16
     simply
    -0.16
     least
    -0.15
     just
    -0.15
    ena
    -0.14
    least
    -0.14
    ouve
    -0.14
    571
    -0.14
    267
    -0.14
    POSITIVE LOGITS
    è¡
    0.17
    imus
    0.16
    CEEDED
    0.16
    é¸
    0.16
    alars
    0.15
    ectl
    0.15
    anko
    0.15
     WCHAR
    0.14
    YRO
    0.14
    à¹Ħหà¸Ļ
    0.14
    Act Density 0.144%

    No Known Activations