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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating likelihood or probability of outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ở
    -0.59
    iomanip
    -0.58
    FileOutputStream
    -0.58
     BoxFit
    -0.56
    rungsseite
    -0.56
     BoxDecoration
    -0.56
     بيها
    -0.54
     IService
    -0.54
    kapnya
    -0.54
     MaterialApp
    -0.54
    POSITIVE LOGITS
     likely
    1.53
     Likely
    1.45
    likely
    1.39
    Likely
    1.33
     likelihood
    0.96
     probable
    0.95
     Likelihood
    0.94
    Likelihood
    0.88
    likelihood
    0.87
     Probable
    0.85
    Act Density 0.141%

    No Known Activations