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

    Neuronpedia

    INDEX
    Explanations

    references to exceptions or special cases in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     magasiner
    -0.70
    ://
    -0.54
    遣
    -0.54
    yargs
    -0.53
     Sanders
    -0.53
    ardo
    -0.47
    锆
    -0.47
    ...
    -0.46
    zegovina
    -0.45
    Germain
    -0.45
    POSITIVE LOGITS
     exception
    3.65
     exceptions
    3.24
     Exceptions
    2.72
    exception
    2.66
     excepción
    2.49
     excep
    2.41
    exceptions
    2.31
     Ausnahme
    2.24
    例外
    2.11
     EXCEPT
    2.06
    Act Density 0.116%

    No Known Activations