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

    Neuronpedia

    INDEX
    Explanations

    phrases related to computer programming and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    elements related to software functionality and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alysis
    -0.70
    lier
    -0.69
     exception
    -0.67
    oÄŁ
    -0.65
     maneuvers
    -0.64
    ALLY
    -0.64
    ously
    -0.63
    aneously
    -0.63
     motions
    -0.62
    times
    -0.61
    POSITIVE LOGITS
    ource
    1.50
    ystem
    1.43
    heet
    1.33
    mith
    1.30
    hift
    1.27
    hip
    1.26
    pace
    1.20
    peed
    1.20
    chool
    1.19
    ilver
    1.19
    Act Density 0.249%

    No Known Activations