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

    Neuronpedia

    INDEX
    Explanations

    phrases related to awards and honors

    oai_token-act-pair · gpt-3.5-turbo

    references to prestigious military and journalism awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    smoking
    -0.74
    Gi
    -0.72
    BP
    -0.69
    rene
    -0.68
    FER
    -0.67
    York
    -0.66
    LI
    -0.65
    alter
    -0.64
    ITIES
    -0.64
    Ger
    -0.63
    POSITIVE LOGITS
     Medal
    1.36
     Medals
    1.03
    ĺħ
    0.87
     Award
    0.81
    eous
    0.81
    naire
    0.81
    escription
    0.80
    ophon
    0.80
    ãģĨ
    0.79
     Breaker
    0.79
    Act Density 0.009%

    No Known Activations