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

    Neuronpedia

    INDEX
    Explanations

    references to the original version of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "original."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wal
    -0.81
    rosso
    -0.77
    %%%%
    -0.73
    =-=-=-=-=-=-=-=-
    -0.72
    rolling
    -0.71
    robe
    -0.71
    owler
    -0.70
    walk
    -0.69
    adel
    -0.68
    urches
    -0.68
    POSITIVE LOGITS
    ity
    0.99
     incarnation
    0.95
     trilogy
    0.93
     conception
    0.85
     impetus
    0.85
    ITY
    0.83
    iator
    0.81
     batch
    0.79
     iteration
    0.78
     version
    0.76
    Act Density 0.023%

    No Known Activations