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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "exceptions" in various contexts

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

    exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    -0.40
    an
    -0.33
    ly
    -0.32
    время
    -0.31
    ServiceModel
    -0.31
    tgz
    -0.30
     Arbeitgeber
    -0.29
     ana
    -0.29
    er
    -0.29
    usermodel
    -0.29
    POSITIVE LOGITS
    Exceptions
    2.03
     exceptions
    1.92
     Exceptions
    1.84
    exceptions
    1.84
     exemptions
    1.06
    EXCEPT
    0.96
     EXCEPT
    0.87
     excepted
    0.76
     excep
    0.75
    ########.
    0.75
    Act Density 0.005%

    No Known Activations