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

    Neuronpedia

    INDEX
    Explanations

    terms associated with the prefix "per" and words related to permissions or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "per" followed by a word or punctuation

    np_acts-logits-general · gemini-2.0-flash

    per unit or per se

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    toJson
    -0.82
     
    -0.79
    )");
    -0.77
     "
    -0.74
    ')"
    -0.73
    "));
    -0.72
    ":
    -0.71
    âtel
    -0.71
    $.
    -0.70
     "")
    -0.70
    POSITIVE LOGITS
    per
    1.27
    PER
    1.19
     PER
    1.18
    Per
    1.17
     Per
    1.09
     Peres
    1.05
     Peralta
    1.04
     per
    1.01
     diem
    0.88
     Perkins
    0.86
    Act Density 0.112%

    No Known Activations