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

    Neuronpedia

    INDEX
    Explanations

    the structural elements of code, particularly parentheses and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -
    -0.55
    aarrggbb
    -0.54
      
    -0.52
     –
    -0.52
    <em>
    -0.52
    unanje
    -0.51
    <eos>
    -0.50
    <strong>
    -0.50
     […]
    -0.50
     (
    -0.50
    POSITIVE LOGITS
    <bos>
    1.73
    '")
    1.02
    ']")
    0.93
    '},
    0.91
    ')")
    0.88
    }")
    0.87
    */)
    0.86
    €)
    0.85
    ''')
    0.84
    }")
    0.84
    Act Density 0.469%

    No Known Activations