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

    Neuronpedia

    INDEX
    Explanations

    words indicating comparison or emphasis, where one thing is more or less than another

    oai_token-act-pair · gpt-3.5-turbo

    frequently used words and phrases that indicate continuity or addition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Subject
    -0.69
    etting
    -0.64
    Rap
    -0.59
    yond
    -0.59
    onto
    -0.57
    ensing
    -0.57
    Behind
    -0.57
    avier
    -0.55
    acle
    -0.55
     Mats
    -0.54
    POSITIVE LOGITS
    been
    1.50
     been
    1.40
     undergone
    1.22
     become
    1.06
     gotten
    1.04
     begun
    1.01
     gone
    1.01
     fallen
    0.99
     Been
    0.98
     come
    0.96
    Act Density 0.152%

    No Known Activations