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

    Neuronpedia

    INDEX
    Explanations

    the use of the word "per" in various contexts, indicating frequency or ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "]
    -0.97
    ]$}
    -0.96
     
    -0.95
    )");
    -0.94
     "")
    -0.94
    $.
    -0.94
     "
    -0.93
     ་་
    -0.93
     ]
    -0.92
    "];
    -0.92
    POSITIVE LOGITS
    per
    1.59
    Per
    1.54
     PER
    1.41
    PER
    1.40
     Per
    1.40
     per
    1.29
     Peralta
    1.15
     Perkins
    1.05
     Peres
    1.02
    mper
    0.99
    Act Density 0.092%

    No Known Activations