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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to variable declarations and assignments

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

    code or programming-related syntax and operations.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.98
    SequentialGroup
    -0.90
     kasarigan
    -0.88
     パンチラ
    -0.85
    <unused76>
    -0.84
    <unused43>
    -0.84
    <unused41>
    -0.84
    <unused42>
    -0.82
    <unused17>
    -0.82
    <pad>
    -0.82
    POSITIVE LOGITS
     temporary
    0.45
     temporarily
    0.37
     permanent
    0.36
    temporary
    0.34
    Temporary
    0.31
     Temporary
    0.30
     permanently
    0.26
    bereitung
    0.26
     tạm
    0.25
     reg
    0.24
    Act Density 0.108%

    No Known Activations