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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or conditionality

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

    Follows a comma, or starts a clause

    np_acts-logits-general · gemini-2.0-flash

    commas followed by conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    camb
    -0.51
    räck
    -0.45
     EIR
    -0.43
     betweenstory
    -0.42
     culturelles
    -0.40
    tki
    -0.40
     Hicks
    -0.39
     packs
    -0.39
    condu
    -0.39
    ješ
    -0.38
    POSITIVE LOGITS
    etheless
    0.99
    setVerticalGroup
    0.86
     Wikimedijinoj
    0.84
     propOrder
    0.81
    DoubleQuotes
    0.79
    \"");
    0.76
    AddHtmlAttribute
    0.74
    complexContent
    0.71
     Réponses
    0.71
    CodedInputStream
    0.70
    Act Density 0.230%

    No Known Activations