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

    Neuronpedia

    INDEX
    Explanations

    references to harm or injury

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    خاÙĨÙĩ
    -0.16
    ropa
    -0.16
    IFI
    -0.15
    irie
    -0.15
    swith
    -0.15
    sWith
    -0.14
    bil
    -0.14
    bie
    -0.14
    bies
    -0.14
    arehouse
    -0.14
    POSITIVE LOGITS
     done
    0.23
    aceutical
    0.18
    ois
    0.17
     repair
    0.17
    ola
    0.17
     DONE
    0.17
     Done
    0.17
    ะ
    0.16
    Done
    0.16
    proof
    0.16
    Act Density 0.023%

    No Known Activations