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

    Neuronpedia

    INDEX
    Explanations

    keywords related to promises or commitments

    oai_token-act-pair · gpt-3.5-turbo

    references to commitments or expectations related to agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asus
    -0.91
    pmwiki
    -0.88
    sf
    -0.82
    itaire
    -0.79
    ento
    -0.77
    sin
    -0.77
    intage
    -0.77
    entimes
    -0.76
    geant
    -0.74
    aughed
    -0.74
    POSITIVE LOGITS
     promises
    0.88
     fulfilled
    0.86
    fulness
    0.85
     promise
    0.77
     confidentiality
    0.73
    worthiness
    0.72
     Prom
    0.72
     Deliver
    0.68
     Promise
    0.67
     fulfil
    0.66
    Act Density 0.041%

    No Known Activations