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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical or logical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.58
     Opel
    -0.55
    aarrggbb
    -0.54
    Flynn
    -0.53
     Barra
    -0.53
     Lupin
    -0.52
     Pegasus
    -0.52
     Lando
    -0.52
     Hough
    -0.52
     Flynn
    -0.51
    POSITIVE LOGITS
     Burnet
    0.70
     Fowler
    0.62
    
    0.60
     Currie
    0.59
     Daniele
    0.56
     {:.
    0.56
     Fonda
    0.55
     Qiu
    0.53
     PIE
    0.52
     JDK
    0.52
    Act Density 0.956%

    No Known Activations