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

    Neuronpedia

    INDEX
    Explanations

    punctuation patterns and structural elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     and
    -0.68
     for
    -0.58
     in
    -0.58
    setopt
    -0.56
     hand
    -0.55
     inter
    -0.55
    мети
    -0.55
     mat
    -0.55
     that
    -0.54
     an
    -0.53
    POSITIVE LOGITS
    expandindo
    0.94
     ostavi
    0.92
    ⓧ
    0.91
    ])
    0.82
     Италијани
    0.82
    WillAppear
    0.82
    ")
    0.81
     Réponses
    0.80
    __))
    0.80
    ].)
    0.79
    Act Density 0.554%

    No Known Activations