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

    Neuronpedia

    INDEX
    Explanations

    terms related to business communications and corporate activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     vulgar
    -0.69
    lings
    -0.67
    chest
    -0.66
    geon
    -0.66
    worms
    -0.62
    loo
    -0.59
    liest
    -0.58
    vae
    -0.58
     Tribe
    -0.57
    draw
    -0.57
    POSITIVE LOGITS
    ittee
    1.27
    onsense
    1.23
    issions
    1.20
    ences
    1.19
    ittal
    1.18
    encing
    1.18
    otion
    1.18
    itted
    1.16
    ittees
    1.16
    utation
    1.13
    Act Density 0.018%

    No Known Activations