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

    Neuronpedia

    INDEX
    Explanations

    adverbs indicating frequency or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     allerdings
    -0.19
     sice
    -0.17
    nt
    -0.15
     meanwhile
    -0.15
     HOWEVER
    -0.15
     ainsi
    -0.14
     however
    -0.14
     однако
    -0.14
    rne
    -0.13
    /w
    -0.13
    POSITIVE LOGITS
     importantly
    0.21
    vice
    0.19
    /OR
    0.18
     some
    0.18
     vice
    0.18
    forth
    0.16
    /or
    0.16
    ebek
    0.16
     suffer
    0.15
     (?)
    0.15
    Act Density 0.258%

    No Known Activations