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

    Neuronpedia

    INDEX
    Explanations

    phrases related to percentages and ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ་་
    -0.80
     itſelf
    -0.76
     Anſ
    -0.75
    ""}
    -0.74
    "];
    -0.73
    )++;
    -0.72
     Eſ
    -0.71
    "]}
    -0.70
     ―――――
    -0.69
    ()")
    -0.69
    POSITIVE LOGITS
     per
    2.66
    per
    1.58
     Per
    1.46
    Per
    1.45
     PER
    1.33
    PerPage
    0.98
    PER
    0.96
    每
    0.95
     each
    0.94
     apiece
    0.90
    Act Density 0.058%

    No Known Activations