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

    Neuronpedia

    INDEX
    Explanations

    verbs related to commitment or assurance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.86
    DragonMagazine
    -0.85
    ento
    -0.75
    nesota
    -0.73
    intage
    -0.72
    isol
    -0.71
    NetMessage
    -0.71
    atin
    -0.70
    FactoryReloaded
    -0.69
    sf
    -0.68
    POSITIVE LOGITS
     allegiance
    0.89
     confidentiality
    0.87
     forgiveness
    0.83
     secrecy
    0.80
     commitment
    0.78
     vow
    0.77
     repayment
    0.77
    fulness
    0.76
     promise
    0.76
     loyalty
    0.76
    Act Density 0.769%

    No Known Activations