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

    Neuronpedia

    INDEX
    Explanations

    phrases related to commitments or assurances

    oai_token-act-pair · gpt-3.5-turbo

    references to commitments or promises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.89
    sf
    -0.79
    entimes
    -0.78
    sin
    -0.78
    asus
    -0.77
    DOS
    -0.75
    DAQ
    -0.74
    ansk
    -0.74
    ento
    -0.74
    aughed
    -0.73
    POSITIVE LOGITS
     promises
    0.95
    fulness
    0.86
     promise
    0.83
     fulfilled
    0.83
     Promise
    0.79
    breaker
    0.73
     Deliver
    0.71
     Gamble
    0.69
     Prom
    0.68
     opio
    0.68
    Act Density 0.030%

    No Known Activations