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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases indicating causation or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reverted
    -0.16
    enty
    -0.16
    ãĤ¹ãĤ¯
    -0.14
    аÑĢан
    -0.14
     simultaneous
    -0.14
     revert
    -0.14
     unidentified
    -0.14
    etty
    -0.14
    sson
    -0.14
    orman
    -0.14
    POSITIVE LOGITS
     further
    0.39
    è¿Ľä¸ĢæŃ¥
    0.32
     Further
    0.31
    Further
    0.31
     thêm
    0.31
     weitere
    0.28
     weiter
    0.28
     additional
    0.28
     ì¶Ķê°Ģ
    0.28
    additional
    0.27
    Act Density 0.004%

    No Known Activations