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

    Neuronpedia

    INDEX
    Explanations

    words related to trust and safety

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.89
    theme
    -0.70
    dos
    -0.69
    zz
    -0.68
    ploy
    -0.66
    nesota
    -0.66
    mort
    -0.62
     Wax
    -0.61
     Vide
    -0.61
    oths
    -0.61
    POSITIVE LOGITS
    worthiness
    1.77
    lessly
    1.06
    worthy
    1.00
     trusting
    0.95
    fulness
    0.83
    ees
    0.80
     trustworthy
    0.79
     trust
    0.79
    iliate
    0.79
     healer
    0.77
    Act Density 0.692%

    No Known Activations