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

    Neuronpedia

    INDEX
    Explanations

    elements related to algebraic structures and mathematical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.64
     
    -0.62
    ↵↵↵
    -0.55
     ger
    -0.55
     O
    -0.52
     Sk
    -0.52
     Z
    -0.49
     lo
    -0.49
     ro
    -0.49
     Ver
    -0.49
    POSITIVE LOGITS
     pleaſure
    0.98
     whoſe
    0.97
     ſtate
    0.97
     reaſon
    0.92
    SBATCH
    0.92
    GEBURTSDATUM
    0.90
     Majefty
    0.89
     myſelf
    0.89
     Normdatei
    0.89
     purpoſe
    0.88
    Act Density 1.684%

    No Known Activations