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

    Neuronpedia

    INDEX
    Explanations

    phrases related to winning or successes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tes
    -0.19
    vore
    -0.16
    EB
    -0.16
    als
    -0.16
     libertine
    -0.15
    ei
    -0.14
    uteur
    -0.14
    les
    -0.14
    otte
    -0.14
    visor
    -0.13
    POSITIVE LOGITS
    nable
    0.24
    throp
    0.17
    -win
    0.17
    ners
    0.15
    imbledon
    0.15
    rate
    0.14
    eyse
    0.14
    ildo
    0.14
    now
    0.14
    «ng
    0.14
    Act Density 0.066%

    No Known Activations