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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals and their birth years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wards
    -0.17
    etim
    -0.15
    opleft
    -0.15
    feit
    -0.14
    ersist
    -0.14
    ìĸ´ê°Ģ
    -0.14
    elope
    -0.14
    erea
    -0.14
    edor
    -0.14
    анÑĮ
    -0.14
    POSITIVE LOGITS
    iane
    0.17
    softmax
    0.15
    ongan
    0.15
    /bind
    0.15
     Gregg
    0.14
    .foundation
    0.14
    bil
    0.14
     Alman
    0.14
    ansa
    0.14
    sÃŃ
    0.14
    Act Density 0.010%

    No Known Activations