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

    Neuronpedia

    INDEX
    Explanations

    punctuation and numeric values in legal or formal text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enumi
    -0.67
    yntaxException
    -0.64
    Spoljašnje
    -0.57
    ParallelGroup
    -0.57
     Vereine
    -0.56
     Grüsse
    -0.55
     desmotivaciones
    -0.55
    InputBorder
    -0.53
    ագրություններ
    -0.52
     invokingState
    -0.52
    POSITIVE LOGITS
    .-.
    0.64
    +'.
    0.63
    .'.
    0.61
    +".
    0.60
    \,.
    0.58
     ".",
    0.58
    ?.
    0.58
    !.
    0.57
    .$.
    0.56
    )._
    0.55
    Act Density 0.712%

    No Known Activations