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

    Neuronpedia

    INDEX
    Explanations

    terms related to mastery or authoritative roles

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

    Appearing after the word "Master" (capitalized or lowercase)

    np_acts-logits-general · gemini-2.0-flash

    master followed by roles or systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suff
    -0.59
     COMMENTS
    -0.56
    alipay
    -0.52
    idends
    -0.51
     gmin
    -0.49
     Zwiebel
    -0.49
    pumpe
    -0.48
     albicans
    -0.48
     Drou
    -0.47
    ˋ
    -0.47
    POSITIVE LOGITS
     Masters
    1.33
     masters
    1.27
    Masters
    1.20
     MASTER
    1.18
    MASTER
    1.16
    masters
    1.08
     Master
    1.06
     master
    1.02
    Master
    0.98
     maîtres
    0.94
    Act Density 0.174%

    No Known Activations