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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating a commitment or assurance, such as "promised" and "vowed"

    oai_token-act-pair · gpt-3.5-turbo

    words related to promises and commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odox
    -0.83
    asse
    -0.77
    miah
    -0.76
    intage
    -0.73
    allery
    -0.73
     IMAGES
    -0.70
    asus
    -0.70
    ustration
    -0.66
    DragonMagazine
    -0.66
    ipop
    -0.66
    POSITIVE LOGITS
     to
    0.94
     allegiance
    0.92
     retribution
    0.90
     revenge
    0.84
     retaliation
    0.84
     vengeance
    0.77
     loyalty
    0.77
     someday
    0.76
     confidentiality
    0.75
     never
    0.75
    Act Density 0.046%

    No Known Activations