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

    Neuronpedia

    INDEX
    Explanations

    sentences containing the word "without" followed by a noun

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    late
    -0.87
    raq
    -0.83
    geist
    -0.75
    cow
    -0.72
    mun
    -0.71
    iers
    -0.70
    lish
    -0.68
    mers
    -0.68
    des
    -0.66
    soon
    -0.65
    POSITIVE LOGITS
     regard
    1.05
     knowing
    1.03
     mentioning
    0.99
     hesitation
    0.97
     sacrificing
    0.97
     exception
    0.96
     necessarily
    0.95
     interruption
    0.95
     specifying
    0.90
     compromising
    0.90
    Act Density 0.358%

    No Known Activations