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

    Neuronpedia

    INDEX
    Explanations

    words related to loyalty and dedication

    oai_token-act-pair · gpt-3.5-turbo

    references to loyalty towards individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EVA
    -0.68
    _-
    -0.68
     Puzz
    -0.67
     Surgery
    -0.66
    phrine
    -0.64
    OUT
    -0.63
     Zucker
    -0.62
     Drugs
    -0.62
     Colleges
    -0.62
     Jacobs
    -0.61
    POSITIVE LOGITS
    ties
    0.99
    itiz
    0.99
     loyal
    0.97
     loyalty
    0.90
    ty
    0.87
    hip
    0.87
    iciary
    0.87
     allegiance
    0.85
    alty
    0.85
    ist
    0.85
    Act Density 0.013%

    No Known Activations