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

    Neuronpedia

    INDEX
    Explanations

    initial markers or indicators in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     كومونز
    -0.95
     &___
    -0.89
    ⓧ
    -0.80
     autorytatywna
    -0.79
    Халык
    -0.77
     سكانية
    -0.72
    SharedDtor
    -0.71
     CreateTagHelper
    -0.71
    WriteBarrier
    -0.71
    RTLD
    -0.71
    POSITIVE LOGITS
     useStyles
    0.65
    
    0.52
    ówczas
    0.50
    ,
    0.49
    7
    0.48
    ۟
    0.48
    러한
    0.46
    2
    0.46
     meeste
    0.46
    8
    0.46
    Act Density 0.078%

    No Known Activations