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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal matters and authority

    oai_token-act-pair · gpt-3.5-turbo

    repeated conjunctions and their use in connecting various clauses or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    renheit
    -0.60
    bub
    -0.59
     Vaugh
    -0.56
    fur
    -0.55
    ÑĮ
    -0.54
    iste
    -0.53
    ãĤ¤
    -0.53
    .'"
    -0.53
    ]."
    -0.52
    ا
    -0.51
    POSITIVE LOGITS
     secondly
    0.77
     thereby
    0.70
     avoids
    0.68
     thence
    0.68
     thus
    0.67
     subsequently
    0.67
     therefore
    0.67
     thereafter
    0.66
     assorted
    0.65
     discusses
    0.65
    Act Density 0.411%

    No Known Activations