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

    Neuronpedia

    INDEX
    Explanations

    mentions of colleagues or collaborative relationships among individuals

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

    colleague / colleagues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orghini
    -0.44
     Water
    -0.42
     Sand
    -0.40
    XmlAccessorType
    -0.39
     Air
    -0.38
     
    -0.37
     Sound
    -0.37
     Hols
    -0.37
     is
    -0.37
     EnglishChoose
    -0.37
    POSITIVE LOGITS
     colleague
    1.32
     colleagues
    1.27
     collega
    1.15
     Colleagues
    1.14
     collègues
    1.13
     colegas
    0.92
     Kollegen
    0.92
     colega
    0.92
    agues
    0.90
    同事
    0.88
    Act Density 0.003%

    No Known Activations