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

    Neuronpedia

    INDEX
    Explanations

    words indicating causation or emphasis in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     allerdings
    -0.18
     meanwhile
    -0.17
     sice
    -0.17
     however
    -0.15
     HOWEVER
    -0.15
     однако
    -0.15
    nt
    -0.14
    /w
    -0.13
     totiž
    -0.13
    横
    -0.13
    POSITIVE LOGITS
     importantly
    0.21
    vice
    0.20
    forth
    0.18
     vice
    0.17
     some
    0.17
    ebek
    0.16
    /OR
    0.16
    ìĿ¸ì§Ģ
    0.14
     (?)
    0.14
    ä¸ĢäºĽ
    0.14
    Act Density 0.220%

    No Known Activations