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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of promises and whether they have been fulfilled or not

    oai_token-act-pair · gpt-3.5-turbo

    terms related to promises and commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asus
    -0.92
    pmwiki
    -0.84
    bia
    -0.71
    sin
    -0.70
    nton
    -0.69
    geant
    -0.68
    ento
    -0.66
    nery
    -0.66
    DOS
    -0.66
    ican
    -0.64
    POSITIVE LOGITS
     fulfilled
    1.08
     promises
    0.82
     promise
    0.79
     pledges
    0.78
     promised
    0.75
     signed
    0.74
     enshr
    0.74
    Deal
    0.74
     made
    0.73
     delivered
    0.72
    Act Density 0.093%

    No Known Activations