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

    concepts related to loyalty and allegiance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Opera
    -0.67
     Neurolog
    -0.65
     Parenthood
    -0.64
    nos
    -0.62
     Zo
    -0.62
     Zeit
    -0.62
     Zucker
    -0.60
    _-
    -0.59
    ////////////////////////////////
    -0.59
     Horizon
    -0.59
    POSITIVE LOGITS
     allegiance
    1.39
     loyalty
    1.18
     oath
    1.09
     devotion
    0.93
     uncond
    0.91
    cipled
    0.88
    atical
    0.87
    doms
    0.84
     obedience
    0.83
     destro
    0.80
    Act Density 0.023%

    No Known Activations