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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly those that denote boundaries or separations in text

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

    punctuation followed by conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.65
    :✨
    -0.50
     Pál
    -0.49
    jsii
    -0.49
     EconPapers
    -0.48
     ſche
    -0.45
     sánchez
    -0.44
    ListTile
    -0.43
     pleaſure
    -0.43
    ItemType
    -0.42
    POSITIVE LOGITS
     but
    0.68
     while
    0.59
     although
    0.58
     sehingga
    0.55
     whilst
    0.54
     zodat
    0.54
     and
    0.53
     despite
    0.52
    although
    0.51
     meski
    0.51
    Act Density 0.180%

    No Known Activations