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

    Neuronpedia

    INDEX
    Explanations

    instances of the beginning of various sections or paragraphs in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iformis
    -0.47
     Oester
    -0.47
    deles
    -0.42
     виправивши
    -0.40
    UnsafeEnabled
    -0.40
     процессов
    -0.40
     specialise
    -0.40
    ules
    -0.40
    Hauptartikel
    -0.40
    leda
    -0.40
    POSITIVE LOGITS
     propOrder
    0.89
     invokingState
    0.84
     الحره
    0.82
     <>",
    0.79
     Majefty
    0.79
    Попис
    0.75
     himſelf
    0.74
     Cabinet
    0.74
     Cæsar
    0.73
    SBATCH
    0.72
    Act Density 0.043%

    No Known Activations