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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases suggesting conditionality or contrast

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

    it followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gyhoeddwyd
    -0.49
    QMetaType
    -0.48
    ंदीखरीदारी
    -0.45
    sidemargin
    -0.43
    PyExc
    -0.43
     îng
    -0.41
    __*/
    -0.40
     spørs
    -0.35
    省市镇
    -0.35
     hierv
    -0.35
    POSITIVE LOGITS
    它
    0.54
    Swatch
    0.52
     它
    0.50
     it
    0.49
     nó
    0.48
     It
    0.47
    把它
    0.43
    delwed
    0.42
    malink
    0.40
     BoxDecoration
    0.40
    Act Density 0.068%

    No Known Activations