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

    Neuronpedia

    INDEX
    Explanations

    references to statistical data and research studies

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions, particularly the word "and"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DX
    -0.83
     incent
    -0.70
    meet
    -0.69
    Times
    -0.67
    FL
    -0.65
    POST
    -0.64
     opio
    -0.64
    bub
    -0.63
    bda
    -0.62
    itans
    -0.62
    POSITIVE LOGITS
     thence
    0.90
     consequently
    0.89
     thus
    0.86
     then
    0.85
    chard
    0.83
     therefore
    0.82
     thereby
    0.80
    rea
    0.77
    hra
    0.75
     vice
    0.75
    Act Density 0.238%

    No Known Activations