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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their varied frequencies within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    punctuation with tilde

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.50
    mobileqq
    -0.45
     bezeichneter
    -0.44
    matchCondition
    -0.43
     imageNamed
    -0.42
    ParallelGroup
    -0.42
    .
    -0.41
     nhật
    -0.41
    medriver
    -0.40
     BrowserModule
    -0.40
    POSITIVE LOGITS
    .~
    1.15
     يتيمه
    0.60
    . 
    0.58
    ,~
    0.56
     
    0.56
    :~
    0.55
    /~
    0.51
    ~$
    0.51
    .}~\
    0.50
    -~
    0.49
    Act Density 0.062%

    No Known Activations