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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically quotation marks

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Portale
    -1.16
    AddHtmlAttribute
    -1.13
    Personendaten
    -1.13
    AndEndTag
    -1.12
     transfieras
    -1.11
     يتيمه
    -1.09
     autorytatywna
    -1.08
    ]='\
    -1.08
    InjectAttribute
    -1.03
     мәкал
    -1.02
    POSITIVE LOGITS
    ↵
    0.62
     in
    0.51
     on
    0.49
     (
    0.48
     
    0.47
    ?
    0.46
    </strong>
    0.45
     som
    0.43
      
    0.43
    .
    0.42
    Act Density 0.020%

    No Known Activations