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

    Neuronpedia

    INDEX
    Explanations

    probability and uncertainty in predictions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portail
    -0.49
    jsonwebtoken
    -0.47
    RegressionTest
    -0.46
     denken
    -0.45
    rungsseite
    -0.45
    endpush
    -0.42
     дума
    -0.41
     للاسماء
    -0.40
     Administrativna
    -0.40
     think
    -0.40
    POSITIVE LOGITS
     happen
    0.89
     mean
    0.83
     involve
    0.82
     affect
    0.78
     depend
    0.78
     include
    0.77
     result
    0.76
     occur
    0.75
     entail
    0.73
     necessitate
    0.69
    Act Density 0.646%

    No Known Activations