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

    Neuronpedia

    INDEX
    Explanations

    adjectives and nouns related to loyalty and faithfulness

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to loyalty and faithfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Drugs
    -0.75
     Surgery
    -0.63
    OUT
    -0.62
    Drug
    -0.62
    OPA
    -0.60
    phrine
    -0.59
     viruses
    -0.59
    çīĪ
    -0.59
     vetoed
    -0.59
    adish
    -0.59
    POSITIVE LOGITS
    glers
    0.97
    itiz
    0.94
    iciary
    0.86
    ists
    0.85
    ist
    0.82
    actor
    0.81
    enough
    0.80
     servant
    0.79
    ados
    0.79
    ettes
    0.79
    Act Density 0.026%

    No Known Activations