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

    Neuronpedia

    INDEX
    Explanations

    numerical quantities and time references

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     a
    -0.61
     long
    -0.56
     kés
    -0.55
     
    -0.53
    ↵↵
    -0.51
    рат
    -0.49
     vė
    -0.48
     Sagan
    -0.48
    ↵
    -0.48
    kapan
    -0.47
    POSITIVE LOGITS
     myſelf
    1.04
     Jefus
    0.92
     Monfieur
    0.91
    AutoresizingMask
    0.91
     itſelf
    0.91
    oredCriteria
    0.91
    tableFuture
    0.89
     Roskov
    0.88
     himſelf
    0.87
     BoxFit
    0.85
    Act Density 0.127%

    No Known Activations