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

    Neuronpedia

    INDEX
    Explanations

    occurrences of placeholder references in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tual
    -0.18
    arih
    -0.17
    spb
    -0.17
    .epam
    -0.16
    å¡ļ
    -0.15
     Düz
    -0.14
    ijken
    -0.14
    rupa
    -0.14
    emma
    -0.14
    sci
    -0.14
    POSITIVE LOGITS
    yet
    0.15
    _mi
    0.15
    antes
    0.14
    å°½
    0.14
     bump
    0.14
     بÙĪابة
    0.14
    991
    0.14
     Roberts
    0.14
    Conv
    0.14
     tempor
    0.13
    Act Density 0.003%

    No Known Activations