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

    Neuronpedia

    INDEX
    Explanations

    expressions of commitment or promise

    oai_token-act-pair · gpt-3.5-turbo

    words related to commitments or pledges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odox
    -0.82
    allery
    -0.79
    asse
    -0.76
    andem
    -0.76
    isol
    -0.75
    FactoryReloaded
    -0.73
    DragonMagazine
    -0.72
    éĸ
    -0.72
    intage
    -0.71
    pmwiki
    -0.68
    POSITIVE LOGITS
     allegiance
    0.94
     retribution
    0.82
     forgiveness
    0.78
     retaliation
    0.77
     revenge
    0.76
     followers
    0.73
     confidentiality
    0.73
     amnesty
    0.73
     loyalty
    0.72
     vengeance
    0.72
    Act Density 0.066%

    No Known Activations