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

    Neuronpedia

    INDEX
    Explanations

    references to origins or beginnings

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of origins or foundations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asel
    -0.71
    isites
    -0.70
    hammad
    -0.70
    tein
    -0.69
    eers
    -0.68
    verages
    -0.67
    eor
    -0.65
    MRI
    -0.63
    ramer
    -0.61
    nesota
    -0.61
    POSITIVE LOGITS
     roots
    1.18
     Roots
    1.12
    roots
    1.07
    waters
    0.83
    pring
    0.82
    ourcing
    0.82
    dale
    0.78
    lore
    0.75
     moss
    0.75
    pora
    0.72
    Act Density 0.009%

    No Known Activations