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

    Neuronpedia

    INDEX
    Explanations

    words related to creativity and innovation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    HUD
    -0.71
    hound
    -0.70
    tsky
    -0.64
     Mara
    -0.63
    Bah
    -0.62
    IU
    -0.62
    watching
    -0.62
     Dawson
    -0.62
    Installation
    -0.61
     DOJ
    -0.59
    POSITIVE LOGITS
    ories
    1.13
    ously
    1.00
     invented
    1.00
    iveness
    0.86
     invention
    0.86
    urous
    0.85
    eers
    0.84
    uristic
    0.84
    rious
    0.83
    ulence
    0.82
    Act Density 0.067%

    No Known Activations