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

    Neuronpedia

    INDEX
    Explanations

    connections to personal relationships and familial roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è®®
    -0.14
    à¥ģà¤Ī
    -0.14
     Bedrooms
    -0.14
    å®ľ
    -0.13
    forman
    -0.13
    ´Ī
    -0.13
    acked
    -0.13
    otec
    -0.13
    ãģ¡ãģ¯
    -0.13
    cbc
    -0.13
    POSITIVE LOGITS
     bag
    0.24
     belong
    0.20
     bags
    0.20
     dream
    0.20
     along
    0.19
     contested
    0.18
    bag
    0.18
     belongs
    0.18
     hog
    0.17
     dint
    0.17
    Act Density 0.123%

    No Known Activations