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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically quotation marks and apostrophes

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

    quoted text usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.59
    addGap
    -0.59
    kawi
    -0.55
    ciers
    -0.52
    Попис
    -0.51
    AxisAlignment
    -0.50
    trane
    -0.50
    Insee
    -0.49
    eners
    -0.49
    躇
    -0.49
    POSITIVE LOGITS
     مشين
    0.59
    httphttps
    0.48
     nôtre
    0.47
    ?”
    0.44
     defaultstate
    0.42
    empereur
    0.42
     rač
    0.41
    BIÉN
    0.40
    !”
    0.40
    .”
    0.40
    Act Density 0.027%

    No Known Activations