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

    Neuronpedia

    INDEX
    Explanations

    references to the term "Mal" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verifyException
    -0.75
     raiſ
    -0.74
     åt
    -0.71
     tué
    -0.71
    IContainer
    -0.70
    ыгана
    -0.70
    UnitTesting
    -0.68
     préfé
    -0.67
     iſt
    -0.67
     ainfi
    -0.67
    POSITIVE LOGITS
     Mal
    4.51
    Mal
    4.31
     mal
    4.28
    mal
    3.80
     MAL
    3.44
    MAL
    3.31
     Malt
    1.87
     Malcolm
    1.84
     malt
    1.81
     Маль
    1.79
    Act Density 0.033%

    No Known Activations