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

    Neuronpedia

    INDEX
    Explanations

    concepts related to mathematical precision and definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actéristique
    -0.79
     Hertz
    -0.76
     Marcy
    -0.75
     Newberry
    -0.74
     Odys
    -0.73
    Besch
    -0.73
    ʁ
    -0.71
     Kers
    -0.71
    עיף
    -0.69
     FetchType
    -0.69
    POSITIVE LOGITS
    ↵
    0.85
    ↵↵↵
    0.80
    <eos>
    0.79
      (
    0.77
    ')],
    0.75
     referrerpolicy
    0.75
    }{*}{
    0.74
    )))),
    0.74
    )，
    0.73
    ↵↵
    0.72
    Act Density 0.041%

    No Known Activations