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

    Neuronpedia

    INDEX
    Explanations

    instances of quotes and other punctuation in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    al
    -0.66
    ory
    -0.65
    )');
    -0.62
    htë
    -0.62
    '));
    -0.60
    rá
    -0.60
    ']):
    -0.59
    ories
    -0.58
    es
    -0.58
    spesies
    -0.57
    POSITIVE LOGITS
    ">"
    0.92
     "\""
    0.87
    ագրություններ
    0.86
    greenrobot
    0.85
    ?"
    0.84
     sanitarios
    0.82
    \""
    0.82
     متعلقه
    0.81
    =\""
    0.81
     "%"
    0.81
    Act Density 0.068%

    No Known Activations