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

    Neuronpedia

    INDEX
    Explanations

    keywords related to sharing or spreading information online

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Share."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    schild
    -0.75
     destro
    -0.73
    paio
    -0.69
    wagen
    -0.67
    anthrop
    -0.64
    issance
    -0.63
    iatric
    -0.63
    quarter
    -0.63
     lineback
    -0.62
    sbm
    -0.61
    POSITIVE LOGITS
    holder
    1.22
    holders
    1.22
    ership
    0.93
    Tweet
    0.92
    edin
    0.91
     Tweet
    0.90
    holding
    0.88
    ables
    0.87
     Share
    0.86
    Point
    0.85
    Act Density 0.025%

    No Known Activations