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

    Neuronpedia

    INDEX
    Explanations

    references to the World Trade Center and related locations or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igos
    -0.16
    ondon
    -0.15
    ichten
    -0.15
    aight
    -0.15
    abel
    -0.15
    ego
    -0.15
     Trigger
    -0.14
    rooms
    -0.14
    iration
    -0.14
    Trigger
    -0.14
    POSITIVE LOGITS
     diff
    0.17
    овоÑĢ
    0.15
    енÑĮ
    0.15
    ombine
    0.15
     Conc
    0.15
    infeld
    0.14
     conc
    0.14
    owi
    0.14
    conc
    0.14
     herd
    0.14
    Act Density 0.007%

    No Known Activations