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

    "have" followed by indefinite articles

    np_acts-logits-general · gemini-2.0-flash

    have a/many, have to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sidemargin
    -0.78
    DeleteBehavior
    -0.74
    Diwedd
    -0.72
    pædia
    -0.71
    Clik
    -0.70
     Мексичка
    -0.68
    fjspx
    -0.68
    expandindo
    -0.67
     PicClick
    -0.66
    Хьажоргаш
    -0.65
    POSITIVE LOGITS
     lyst
    0.55
    PERT
    0.55
     friends
    0.54
     questions
    0.54
    lateinit
    0.52
    randa
    0.51
     a
    0.50
     Тер
    0.50
     multiple
    0.50
     experience
    0.49
    Act Density 0.210%

    No Known Activations