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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving exponents and bases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    marle
    -0.65
     zafira
    -0.64
    +#+
    -0.63
    )\}
    -0.59
     bezig
    -0.59
    \}\
    -0.59
    vieja
    -0.57
    chtenstein
    -0.57
    tokio
    -0.57
     honoured
    -0.57
    POSITIVE LOGITS
     exponent
    0.70
    |^{
    0.68
    HasAnnotation
    0.67
    )^{
    0.65
     exponents
    0.63
    ^{
    0.62
    ))^{
    0.60
    SuccessListener
    0.60
    paramref
    0.58
    )^
    0.58
    Act Density 0.508%

    No Known Activations