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

    Neuronpedia

    INDEX
    Explanations

    key characters and elements from a popular film series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    енз
    -0.17
    phalt
    -0.15
    atar
    -0.15
    ATAR
    -0.15
    ael
    -0.15
    lacak
    -0.15
    umat
    -0.14
    éĮ
    -0.14
    amina
    -0.14
    تبÙĩ
    -0.14
    POSITIVE LOGITS
     survival
    0.16
     spons
    0.16
     Twe
    0.16
     rigged
    0.16
     Consultants
    0.15
     подÑģ
    0.15
     twe
    0.15
     sponsor
    0.15
     sponsors
    0.14
    -unused
    0.14
    Act Density 0.017%

    No Known Activations