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

    Neuronpedia

    INDEX
    Explanations

    phrases related to computer programming and technological advancements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    pload
    -0.75
    ITED
    -0.69
    Õ
    -0.68
    ãĤ§
    -0.68
    pton
    -0.68
    veyard
    -0.64
    BOOK
    -0.64
    Discuss
    -0.61
    Wheel
    -0.61
    giene
    -0.60
    POSITIVE LOGITS
    hetics
    1.26
    hetically
    1.07
    uary
    1.05
    hetic
    1.03
    imate
    0.97
    ruct
    0.96
    imates
    0.96
    rus
    0.95
    rogens
    0.94
    rella
    0.93
    Act Density 0.013%

    No Known Activations