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

    Neuronpedia

    INDEX
    Explanations

    references to a specific place or entity named "Liberty"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Liberty."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -1.01
    ãģ¦
    -0.92
     à¨
    -0.86
    enegger
    -0.81
    ¯¯
    -0.80
    ynthesis
    -0.79
    ¯¯¯¯
    -0.76
    older
    -0.69
    âĹ¼
    -0.69
    ħĭ
    -0.69
    POSITIVE LOGITS
     Liberty
    1.24
    tarian
    0.94
     Mutual
    0.84
    tarians
    0.83
     Reserve
    0.80
    atility
    0.79
    itud
    0.75
     Patriot
    0.74
     Liberties
    0.73
     Counsel
    0.72
    Act Density 0.010%

    No Known Activations