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

    Neuronpedia

    INDEX
    Explanations

    references to appending or manipulating elements in a document

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    expandindo
    -1.20
     Majefty
    -1.19
     Efq
    -1.19
     виправивши
    -1.17
    AndEndTag
    -1.13
     Савезне
    -1.10
    ništvo
    -1.09
     houſe
    -1.09
     snippetHide
    -1.09
    dafx
    -1.08
    POSITIVE LOGITS
    ↵
    0.75
      
    0.70
    </b>
    0.68
    <eos>
    0.64
    ↵↵
    0.64
     
    0.61
    ...
    0.60
    </h1>
    0.59
     […]
    0.58
     =
    0.57
    Act Density 0.105%

    No Known Activations