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

    Neuronpedia

    INDEX
    Explanations

    formatted string specifiers related to input/output in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    клопе
    -0.76
    PerformLayout
    -0.74
    ValueStyle
    -0.73
    apimachinery
    -0.71
     Whipple
    -0.70
    UCLA
    -0.70
     aspirin
    -0.68
     ISTAT
    -0.68
    }$​
    -0.67
     مصرى
    -0.67
    POSITIVE LOGITS
    ("%
    1.73
    ,"%
    1.33
     ("%
    1.31
     "%
    1.23
    ('%
    1.08
    ="%
    1.03
    ("%.
    1.03
    "%
    0.88
    ='%
    0.84
     '%
    0.79
    Act Density 0.080%

    No Known Activations