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

    Neuronpedia

    INDEX
    Explanations

    words related to inventing or creating new things

    oai_token-act-pair · gpt-3.5-turbo

    instances related to invention and creativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Installation
    -0.66
    cffffcc
    -0.62
     Warden
    -0.62
     Dah
    -0.61
    swer
    -0.59
     Nieto
    -0.59
     Ibid
    -0.58
    expected
    -0.58
     Returning
    -0.58
    hunter
    -0.58
    POSITIVE LOGITS
    ories
    1.30
    arus
    1.15
    iveness
    1.14
    ively
    1.01
    ivity
    0.98
     invent
    0.94
    iating
    0.94
    iencies
    0.91
    iates
    0.90
    ors
    0.89
    Act Density 0.010%

    No Known Activations