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

    Neuronpedia

    INDEX
    Explanations

    phrases related to security and authority

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Canaver
    -0.81
    Brexit
    -0.80
    Netflix
    -0.78
    ghazi
    -0.77
    abetes
    -0.76
    ibaba
    -0.76
    Minecraft
    -0.76
     dstg
    -0.76
    Scotland
    -0.75
    olkien
    -0.75
    POSITIVE LOGITS
     latter
    1.38
     resultant
    1.10
     aforementioned
    1.09
     ensuing
    1.09
     discrepancy
    1.08
     resulting
    1.08
     entire
    1.08
     remainder
    1.05
     same
    1.05
     implication
    1.04
    Act Density 0.691%

    No Known Activations