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

    Neuronpedia

    INDEX
    Explanations

    phrases related to belonging or categorization

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

    belonging and possession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ulgação
    -0.38
    Kilde
    -0.38
     ainfi
    -0.36
    uvres
    -0.35
    atemala
    -0.34
     Internazionale
    -0.34
     LIRE
    -0.34
    atrième
    -0.33
    archiwizowane
    -0.33
     jednost
    -0.33
    POSITIVE LOGITS
     belong
    1.50
     belongs
    1.48
     belonged
    1.40
     Belong
    1.38
     belonging
    1.36
    belong
    1.33
    belongs
    1.18
     pertence
    1.18
     gehören
    1.15
     gehört
    1.14
    Act Density 0.036%

    No Known Activations