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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legislation, social issues, and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     모ëĵł
    -0.19
    æīĢæľī
    -0.18
     sometimes
    -0.17
    illions
    -0.17
    ä¸ĢåĪĩ
    -0.15
     иногда
    -0.15
    sometimes
    -0.15
    alles
    -0.15
     occasionally
    -0.15
    477
    -0.14
    POSITIVE LOGITS
     either
    0.30
    either
    0.25
     Either
    0.24
     либо
    0.23
    Either
    0.20
     soit
    0.17
     именно
    0.17
    äºĽ
    0.17
     EITHER
    0.16
     clustered
    0.15
    Act Density 0.195%

    No Known Activations