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

    Neuronpedia

    INDEX
    Explanations

    phrases suggesting introducing a new concept or idea

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to borrowing and quoting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arnaev
    -0.67
    utenberg
    -0.65
    commit
    -0.65
    uador
    -0.64
    acca
    -0.60
    ebra
    -0.60
    uterte
    -0.60
     HRC
    -0.60
    20439
    -0.59
    owa
    -0.58
    POSITIVE LOGITS
    ...)
    0.70
    _.
    0.67
    *)
    0.66
    âĢ¦)
    0.66
     inclined
    0.65
     paraph
    0.64
     Byz
    0.63
     charism
    0.62
    ,)
    0.60
     arg
    0.60
    Act Density 0.300%

    No Known Activations