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

    Neuronpedia

    INDEX
    Explanations

    references to couples in various contexts

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

    relationships, marriage, or partners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     حالت
    -0.38
     PERT
    -0.38
    SceneManagement
    -0.36
    Chall
    -0.35
     Chall
    -0.35
     Handel
    -0.35
     пона
    -0.35
     تحد
    -0.35
     διά
    -0.35
     Pu
    -0.35
    POSITIVE LOGITS
    Couple
    0.71
     casal
    0.64
     Couple
    0.63
    weds
    0.63
    couple
    0.62
    Families
    0.60
     Couples
    0.60
     coppia
    0.60
     pareja
    0.60
     couple
    0.59
    Act Density 0.050%

    No Known Activations