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

    Neuronpedia

    INDEX
    Explanations

    words related to loyalty and allegiance

    oai_token-act-pair · gpt-3.5-turbo

    references to loyalty and allegiance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _-
    -0.75
     Modified
    -0.73
     Errors
    -0.72
    FER
    -0.68
    Org
    -0.68
     Greens
    -0.67
     Tropical
    -0.67
     Neurolog
    -0.66
     Klu
    -0.66
     Frog
    -0.66
    POSITIVE LOGITS
     loyalty
    1.46
     allegiance
    1.29
     destro
    1.06
     oath
    1.06
     loyal
    1.01
     uncond
    0.92
     devotion
    0.89
    alties
    0.89
    avorite
    0.88
    atility
    0.88
    Act Density 0.008%

    No Known Activations