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

    Neuronpedia

    INDEX
    Explanations

    symbols, particularly parentheses and brackets, indicating formatting or structuring elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    offsetof
    -0.61
    SharedCtor
    -0.61
    ٍ
    -0.58
    Réalisation
    -0.57
    argp
    -0.53
    )";
    -0.53
    methodName
    -0.52
    行
    -0.52
    󠁴
    -0.52
    なのが
    -0.50
    POSITIVE LOGITS
     (
    1.01
    <bos>
    0.81
    uxxxx
    0.79
    ">(</
    0.76
    >(</
    0.70
     (°
    0.68
    （
    0.68
    ItemBackground
    0.61
    '(
    0.61
    ⓧ
    0.58
    Act Density 0.931%

    No Known Activations