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

    Neuronpedia

    INDEX
    Explanations

    arguments or debates in textual content

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    cler
    -0.72
     livest
    -0.66
     Seym
    -0.65
    ookie
    -0.64
    eco
    -0.64
    idays
    -0.63
    aches
    -0.62
     Carbuncle
    -0.62
     Atomic
    -0.62
    lights
    -0.61
    POSITIVE LOGITS
    ative
    1.12
    uments
    1.10
     against
    1.06
     arguments
    0.92
    abl
    0.88
    ument
    0.87
     persu
    0.86
     argument
    0.86
    Against
    0.83
     arguing
    0.83
    Act Density 0.032%

    No Known Activations