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

    Neuronpedia

    INDEX
    Explanations

    words indicating transitions and significance in narratives or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     meanwhile
    -0.17
     allerdings
    -0.16
     sice
    -0.15
     however
    -0.15
    amen
    -0.14
    çĦ¶èĢĮ
    -0.14
    nt
    -0.14
     однако
    -0.14
     either
    -0.13
     ainsi
    -0.13
    POSITIVE LOGITS
    forth
    0.20
     importantly
    0.20
    vice
    0.18
     vice
    0.16
    ebek
    0.16
    /OR
    0.15
     (?)
    0.15
    (!
    0.15
     some
    0.15
    even
    0.15
    Act Density 0.236%

    No Known Activations