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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate exceptions or deviations from a norm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.83
    InputBorder
    -0.61
     Karma
    -0.53
     '\\;'
    -0.53
    zysz
    -0.51
     hoods
    -0.51
    yatı
    -0.50
    bular
    -0.50
     faker
    -0.50
    ishman
    -0.49
    POSITIVE LOGITS
     exceptions
    0.96
     exception
    0.94
     except
    0.86
     Ausnahme
    0.84
     Exceptions
    0.82
    Except
    0.78
    except
    0.78
    EXCEPT
    0.75
     Except
    0.72
     excep
    0.71
    Act Density 0.348%

    No Known Activations