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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases indicating coordination or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     doz
    -0.14
    abcdefghijkl
    -0.14
     adalah
    -0.14
     konkrét
    -0.13
    abcdefghijklmnop
    -0.13
    ãģ¨ãģ¯
    -0.13
    esty
    -0.12
    abcdefgh
    -0.12
    PHA
    -0.12
    ABCDEFGHI
    -0.12
    POSITIVE LOGITS
    /or
    0.48
    /OR
    0.28
    rogen
    0.23
    rog
    0.21
     hence
    0.20
    ä¸Ķ
    0.19
     therefore
    0.19
    /of
    0.19
    quot
    0.19
     hatta
    0.18
    Act Density 0.302%

    No Known Activations