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

    Neuronpedia

    INDEX
    Explanations

    references to leadership titles and positions of authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zers
    -0.73
     pieces
    -0.69
    ©
    -0.68
     informants
    -0.67
    worth
    -0.66
    worldly
    -0.65
    cards
    -0.65
    pieces
    -0.63
    mort
    -0.63
    uders
    -0.63
    POSITIVE LOGITS
     Sierra
    0.91
     Ministry
    0.80
     Tata
    0.79
     Kinnikuman
    0.78
     Programming
    0.77
     NCT
    0.77
     Carnegie
    0.76
     NEC
    0.75
     Greenpeace
    0.74
     MPH
    0.74
    Act Density 0.060%

    No Known Activations