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

    Neuronpedia

    INDEX
    Explanations

    words related to naming, renaming, and rebranding

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "renounce" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Crate
    -0.78
    arella
    -0.68
     Pend
    -0.68
     Secretary
    -0.68
     Traps
    -0.66
     Bulletin
    -0.66
     Errors
    -0.64
     Townsend
    -0.63
    Fine
    -0.63
     Shoals
    -0.61
    POSITIVE LOGITS
    thood
    1.04
    naissance
    0.97
    dom
    0.97
    esis
    0.95
    ingen
    0.94
    ciation
    0.91
    unci
    0.89
    etics
    0.88
    cipled
    0.86
    ters
    0.86
    Act Density 0.051%

    No Known Activations