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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government, laws, and political actions

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions connecting clauses with varying degrees of importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Powered
    -0.85
    SPA
    -0.77
    uta
    -0.77
    DX
    -0.76
    Tes
    -0.73
    busters
    -0.73
    doi
    -0.71
    Ĥİ
    -0.70
    BOOK
    -0.69
    Times
    -0.69
    POSITIVE LOGITS
     consequently
    1.29
     therefore
    1.11
     thence
    1.10
     furthermore
    1.09
     thus
    1.06
     hence
    1.04
     thereby
    1.02
     secondly
    0.98
     moreover
    0.97
     vice
    0.95
    Act Density 0.244%

    No Known Activations