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

    Neuronpedia

    INDEX
    Explanations

    terms related to correctness and accuracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hauptartikel
    -0.80
    ManagedBean
    -0.78
    OrBuilder
    -0.77
    HasMaxLength
    -0.77
    StackNavigator
    -0.76
    ($__
    -0.76
     SizedBox
    -0.75
    ]`
    -0.75
    Personensuche
    -0.74
     Darby
    -0.73
    POSITIVE LOGITS
     correct
    2.28
     Correct
    2.25
     CORRECT
    2.13
    Correct
    2.11
    correct
    2.08
     correctly
    1.71
     correctness
    1.68
    CORRECT
    1.63
     incorrect
    1.58
     corect
    1.58
    Act Density 0.066%

    No Known Activations