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

    Neuronpedia

    INDEX
    Explanations

    instances where the concept of loyalty or faithfulness is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing allegiance or loyalty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llo
    -0.80
    TPPStreamerBot
    -0.70
    employed
    -0.69
    going
    -0.68
    ersed
    -0.68
    rio
    -0.67
     waived
    -0.65
     headed
    -0.65
    sky
    -0.64
     elig
    -0.64
    POSITIVE LOGITS
    wered
    0.92
     coincide
    0.89
     appease
    0.86
     ensure
    0.84
     conserve
    0.83
    ggles
    0.82
     signify
    0.82
    pless
    0.79
    days
    0.79
     minimize
    0.78
    Act Density 0.262%

    No Known Activations