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

    Neuronpedia

    INDEX
    Explanations

    elements related to social identity and belonging

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

    "belong" or blending in

    np_acts-logits-general · gemini-2.0-flash

    belong to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    뀐
    -0.41
     Pública
    -0.39
    heli
    -0.37
     Cobalt
    -0.37
     Cyc
    -0.37
    ソッド
    -0.36
    fficiency
    -0.36
    ΑΙ
    -0.36
    VERT
    -0.35
    台
    -0.35
    POSITIVE LOGITS
     belong
    1.59
    belong
    1.47
     belonged
    1.45
     belonging
    1.43
     belongs
    1.36
     Belong
    1.28
     joining
    1.19
     perten
    1.17
     membership
    1.16
     join
    1.13
    Act Density 0.268%

    No Known Activations