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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "original"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "original" within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wal
    -0.78
    robe
    -0.78
    walk
    -0.72
    asia
    -0.70
    rogens
    -0.69
    opping
    -0.66
    rolling
    -0.66
    avis
    -0.65
    annis
    -0.65
    inging
    -0.65
    POSITIVE LOGITS
     incarnation
    0.98
     impetus
    0.85
    ITY
    0.85
     trilogy
    0.83
     batch
    0.82
     version
    0.81
    ity
    0.81
     conception
    0.79
     wording
    0.75
     iteration
    0.74
    Act Density 0.018%

    No Known Activations