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

    Neuronpedia

    INDEX
    Explanations

    terms that emphasize specificity or particularity in a context

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

    Following the word "specific"

    np_acts-logits-general · gemini-2.0-flash

    particular instances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rowCount
    -0.68
    NameInMap
    -0.59
    tagHelperRunner
    -0.56
     GridLayout
    -0.56
     Wallet
    -0.54
    barrow
    -0.54
    LAYOUT
    -0.49
    userModel
    -0.49
    ochond
    -0.49
    airbnb
    -0.49
    POSITIVE LOGITS
     specific
    1.09
    specific
    1.02
    Specific
    1.02
     Specific
    0.98
     SPECIFIC
    0.98
    SPECIFIC
    0.88
     specifically
    0.83
     particular
    0.81
    particular
    0.79
     spesifik
    0.78
    Act Density 0.086%

    No Known Activations