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

    Neuronpedia

    INDEX
    Explanations

    mentions of people and their actions or roles in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" indicating connections or relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.56
    steam
    -0.55
    ãĥ¼ãĥ
    -0.55
    piring
    -0.54
    pires
    -0.54
    sed
    -0.54
     Powered
    -0.53
    spir
    -0.53
    ppa
    -0.53
    burgh
    -0.53
    POSITIVE LOGITS
     nor
    1.51
     therefore
    1.41
     consequently
    1.36
     neither
    1.29
     furthermore
    1.28
     thus
    1.26
     Nor
    1.22
     hence
    1.22
     instead
    1.21
     moreover
    1.17
    Act Density 0.200%

    No Known Activations