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

    Neuronpedia

    INDEX
    Explanations

    the substring "ur" within words

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "ur."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Citation
    -0.72
    otle
    -0.72
     Bastard
    -0.70
     Tables
    -0.69
     Clarkson
    -0.64
    isSpecialOrderable
    -0.63
     Plays
    -0.63
     BaseType
    -0.62
    xon
    -0.62
     Develop
    -0.62
    POSITIVE LOGITS
    geons
    1.13
    geon
    1.06
    rences
    1.03
    anium
    0.92
    thur
    0.92
    ricular
    0.90
    rier
    0.88
     Rahman
    0.88
    ricane
    0.87
    andom
    0.86
    Act Density 0.017%

    No Known Activations