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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing additional information or context

    oai_token-act-pair · gpt-3.5-turbo

    recurrent conjunctions used for additive phrasing in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Fed
    -0.69
    bush
    -0.64
    ERN
    -0.63
    KEN
    -0.62
    ÃĤ
    -0.62
    Tes
    -0.60
    NBA
    -0.60
    zu
    -0.60
     Puzzle
    -0.59
    ESA
    -0.59
    POSITIVE LOGITS
     consequ
    0.83
    withstanding
    0.78
    rogens
    0.76
    romeda
    0.76
     especially
    0.76
     assuming
    0.72
     consequently
    0.70
     possibly
    0.70
     subsequent
    0.68
     subsequently
    0.68
    Act Density 0.379%

    No Known Activations