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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation or symbols, particularly brackets and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ’
    -0.54
    bní
    -0.52
     lượng
    -0.48
    </strong>
    -0.47
     Her
    -0.44
     ‘
    -0.43
    бий
    -0.43
    radan
    -0.43
     pattern
    -0.43
    AsUp
    -0.43
    POSITIVE LOGITS
    \[
    3.60
     \[
    2.15
    \[\
    1.76
    \\[
    1.61
     \\[
    1.39
    \]
    1.30
     \]
    1.15
    \{\\
    1.12
    \[
    1.11
    %\[
    1.10
    Act Density 0.160%

    No Known Activations