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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Hal."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    질
    -0.69
     retro
    -0.63
    fil
    -0.59
    retro
    -0.59
    lien
    -0.59
    antic
    -0.58
    ISF
    -0.57
    ObjectModel
    -0.57
     Genocide
    -0.57
    lia
    -0.57
    POSITIVE LOGITS
    Hal
    1.10
     Hal
    1.10
    HAL
    0.99
     hal
    0.96
     HAL
    0.92
     PLWABN
    0.91
    RenderAtEndOf
    0.90
    hal
    0.88
     caves
    0.86
    disclosure
    0.84
    Act Density 0.065%

    No Known Activations