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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "bos" indicating section breaks or separations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __':
    -1.05
    цездатний
    -0.95
     autorytatywna
    -0.88
     MenuView
    -0.84
    }")]
    -0.82
     Савезне
    -0.81
    InjectAttribute
    -0.81
    Geplaatst
    -0.80
    BibitemShut
    -0.80
    "])
    -0.80
    POSITIVE LOGITS
    <eos>
    0.64
     =
    0.60
     stesso
    0.58
    ...
    0.57
    のは
    0.56
     ...
    0.55
    的
    0.55
     of
    0.54
    '
    0.53
    …
    0.53
    Act Density 3.600%

    No Known Activations