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

    Neuronpedia

    INDEX
    Explanations

    references to the term "Vice" in various contexts

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

    vice + title or vice versa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dington
    -0.56
     smlou
    -0.55
    penters
    -0.54
     Lindgren
    -0.52
    clothing
    -0.52
    dfunding
    -0.52
     szkol
    -0.52
    rington
    -0.51
     Ashford
    -0.51
     expédi
    -0.50
    POSITIVE LOGITS
     Vice
    2.20
    Vice
    2.09
     vice
    1.95
     VICE
    1.66
    vice
    1.48
     vise
    1.10
     VP
    0.99
     Vise
    0.96
     viceversa
    0.96
     vices
    0.90
    Act Density 0.003%

    No Known Activations