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

    Neuronpedia

    INDEX
    Explanations

    phrases related to investigations and legal actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     reluct
    -0.91
     suscep
    -0.87
     aen
    -0.86
     indestru
    -0.86
     yves
    -0.83
     fluo
    -0.82
     jacques
    -0.81
     desir
    -0.81
     disagre
    -0.79
     miu
    -0.79
    POSITIVE LOGITS
     underway
    0.78
     commenced
    0.76
     begun
    0.76
     started
    0.74
     began
    0.66
     ongoing
    0.65
     undertaken
    0.63
    FetchType
    0.63
     conducted
    0.62
    started
    0.61
    Act Density 0.548%

    No Known Activations