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

    Neuronpedia

    INDEX
    Explanations

    questions involving quantitative aspects or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DeleteBehavior
    -0.46
     venganza
    -0.46
     pérd
    -0.46
     tarko
    -0.46
    DoubleQuotes
    -0.45
    principalColumn
    -0.45
    EndContext
    -0.44
     mahdol
    -0.43
     Jesucristo
    -0.43
    ineno
    -0.42
    POSITIVE LOGITS
    どれだけ
    0.54
     چقدر
    0.52
    有多少
    0.52
     насколько
    0.48
     कित
    0.47
     Chi
    0.43
     Seg
    0.43
     Lev
    0.42
     each
    0.41
     Lag
    0.41
    Act Density 0.670%

    No Known Activations