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

    Neuronpedia

    INDEX
    Explanations

    website features like social media sharing buttons

    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
    -0.85
    panic
    -0.78
    issance
    -0.74
    conservancy
    -0.74
    undai
    -0.74
    morrow
    -0.73
    anthrop
    -0.73
    rift
    -0.73
    sbm
    -0.72
    prime
    -0.71
    POSITIVE LOGITS
    holders
    1.15
    holder
    1.09
    ership
    0.96
     Share
    0.88
    ables
    0.86
    able
    0.84
    ABLE
    0.83
    Tweet
    0.83
    Share
    0.78
     Shares
    0.76
    Act Density 0.013%

    No Known Activations