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

    Neuronpedia

    INDEX
    Explanations

    conjunctions linking different ideas

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating connections or relationships between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EMS
    -0.67
    ATS
    -0.64
    DragonMagazine
    -0.61
    wic
    -0.60
    UC
    -0.60
    pees
    -0.59
    UNCH
    -0.59
    odcast
    -0.59
    hack
    -0.59
    avin
    -0.59
    POSITIVE LOGITS
     consequently
    1.16
     therefore
    1.16
     thus
    1.13
     thereby
    1.13
     hence
    1.11
     vice
    0.90
     thence
    0.86
     secondly
    0.85
     furthermore
    0.84
     consequ
    0.82
    Act Density 0.562%

    No Known Activations