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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Master" with varying spellings and contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Master" or related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPLE
    -0.74
    IDER
    -0.73
    hedon
    -0.67
    enegger
    -0.67
     Torn
    -0.65
    IGHTS
    -0.64
    vernment
    -0.63
    IGH
    -0.62
     SNAP
    -0.62
    tics
    -0.60
    POSITIVE LOGITS
    pieces
    1.42
    piece
    1.28
    mind
    1.15
    stroke
    1.02
    class
    0.92
    classes
    0.89
    fully
    0.86
    sonian
    0.86
    minded
    0.86
    abilia
    0.86
    Act Density 0.045%

    No Known Activations