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

    Neuronpedia

    INDEX
    Explanations

    instances of loyalty

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "loyal" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Drugs
    -0.76
    OUT
    -0.75
     Helmet
    -0.73
     Colleges
    -0.72
     Injury
    -0.72
     Graduate
    -0.72
     Cologne
    -0.71
    EVA
    -0.70
    Medic
    -0.70
     Surgery
    -0.70
    POSITIVE LOGITS
     loyal
    1.42
    emouth
    1.01
    oyal
    0.95
     loyalty
    0.94
     citiz
    0.93
    atile
    0.89
    itiz
    0.88
     destro
    0.88
    leader
    0.88
    alties
    0.84
    Act Density 0.004%

    No Known Activations