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

    Neuronpedia

    INDEX
    Explanations

    the use of single quotation marks or apostrophes in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Савезне
    -1.36
    SequentialGroup
    -1.20
    WriteTagHelper
    -1.16
    Datuak
    -1.15
    featureID
    -1.12
    NUMX
    -1.11
    tagHelperRunner
    -1.10
    SourceChecksum
    -1.06
     مشين
    -1.04
    AddTagHelper
    -1.04
    POSITIVE LOGITS
     
    0.81
    ,
    0.70
    .
    0.66
     -
    0.62
    (
    0.58
    -
    0.57
    ↵↵
    0.55
     (
    0.53
    /
    0.51
     in
    0.51
    Act Density 0.476%

    No Known Activations