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

    Neuronpedia

    INDEX
    Explanations

    words related to physical movement or action

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of 'ur'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otle
    -0.72
     Clarkson
    -0.67
     Mellon
    -0.67
    eah
    -0.64
     Quit
    -0.64
     Citation
    -0.64
     Schultz
    -0.63
     Schn
    -0.62
     Bastard
    -0.62
     Scand
    -0.61
    POSITIVE LOGITS
    geons
    1.22
    geon
    1.18
    rences
    1.14
    andom
    1.04
    thur
    0.96
    ricular
    0.95
    rier
    0.92
    anium
    0.91
    rr
    0.89
    geoning
    0.88
    Act Density 0.019%

    No Known Activations