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

    Neuronpedia

    INDEX
    Explanations

    references to significant societal issues and the impact of external factors on communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wouldn
    -0.18
     neither
    -0.18
     doesn
    -0.17
    doesn
    -0.17
     nowhere
    -0.17
     didn
    -0.16
    æº
    -0.16
     somewhere
    -0.16
    ä¸įä¼ļ
    -0.16
     нелÑĮзÑı
    -0.15
    POSITIVE LOGITS
     proved
    0.22
     prove
    0.19
     proven
    0.18
     proves
    0.17
     proving
    0.16
    proved
    0.16
     becomes
    0.16
     sounded
    0.16
    olo
    0.15
     truly
    0.15
    Act Density 0.062%

    No Known Activations