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

    Neuronpedia

    INDEX
    Explanations

    instances of opening tags and specific punctuation in markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.58
    WEBPACK
    -0.55
    </td>
    -0.54
    <eos>
    -0.53
    ipen
    -0.52
    ↵↵↵
    -0.52
    <tr>
    -0.50
    -0.50
    -0.50
                
    -0.50
    POSITIVE LOGITS
    <bos>
    1.04
     myſelf
    1.03
     itſelf
    0.98
     Majefty
    0.94
     leaſt
    0.89
     Jefus
    0.88
     Houſe
    0.87
     pleaſure
    0.84
     raiſ
    0.84
     Reſ
    0.83
    Act Density 0.072%

    No Known Activations