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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "exception" and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    exceptions and differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.47
     noDo
    -0.44
     télévis
    -0.42
     flotante
    -0.41
     pourrez
    -0.41
     ettei
    -0.41
     PUSTAKA
    -0.41
     chrétien
    -0.40
     Turquía
    -0.40
    ylate
    -0.40
    POSITIVE LOGITS
     exception
    0.64
     exceptions
    0.57
    exceptions
    0.54
     Савезне
    0.52
     Exceptions
    0.50
    0.49
     nahilalakip
    0.48
    theless
    0.47
    exception
    0.45
    Exceptions
    0.45
    Act Density 0.003%

    No Known Activations