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

    Neuronpedia

    INDEX
    Explanations

    narratives related to tragic events or disasters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orque
    -0.16
     YÃĸ
    -0.15
    ÙĤاÙĦ
    -0.15
    ternet
    -0.15
    anus
    -0.15
    DMI
    -0.14
     огÑĢа
    -0.14
    ãĥ³ãĥĦ
    -0.14
    à¤Ĺल
    -0.14
    IID
    -0.14
    POSITIVE LOGITS
    573
    0.14
     teammate
    0.14
    chner
    0.14
     rogue
    0.14
    avana
    0.14
     Payload
    0.14
    erty
    0.13
     Ends
    0.13
    066
    0.13
    uck
    0.13
    Act Density 0.011%

    No Known Activations