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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possession or ownership

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

    Following "have" or "has"

    np_acts-logits-general · gemini-2.0-flash

    have/has statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sidemargin
    -0.77
    NameInMap
    -0.68
     للمعارف
    -0.61
    rawDesc
    -0.59
    ectoria
    -0.59
    endphp
    -0.57
    PreferredItem
    -0.57
     AssemblyTitle
    -0.56
    :✨
    -0.55
    simpleType
    -0.54
    POSITIVE LOGITS
     plenty
    0.65
     nothing
    0.62
     choices
    0.59
     enough
    0.57
     nowhere
    0.56
     Plenty
    0.56
    ultades
    0.55
     reasons
    0.55
     no
    0.54
     genug
    0.54
    Act Density 0.176%

    No Known Activations