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

    Neuronpedia

    INDEX
    Explanations

    occurrences of special tokens or formatting elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    text beginning sequences, particularly with high activation values at the start of documents or sections.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     MessageBoxIcon
    -0.98
     BorderRadius
    -0.91
    VERTISEMENT
    -0.88
     FontWeight
    -0.85
    initializeApp
    -0.85
    onViewCreated
    -0.84
    HasForeignKey
    -0.84
     BoxDecoration
    -0.84
     CommandType
    -0.82
     TextInputType
    -0.82
    POSITIVE LOGITS
    ↵
    1.73
    <eos>
    1.57
    ↵↵
    1.45
    ↵↵↵
    1.32
    ↵↵↵↵
    1.20
        
    1.14
    ↵↵↵↵↵
    1.13
            
    1.07
          
    1.05
    1.04
    Act Density 1.094%

    No Known Activations