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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal matters and official statements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    worldly
    -0.74
    âĶĢâĶĢâĶĢâĶĢ
    -0.62
    sein
    -0.62
    ishers
    -0.61
    obin
    -0.60
     Romantic
    -0.60
    Reason
    -0.59
    owitz
    -0.58
    oir
    -0.58
    ARY
    -0.56
    POSITIVE LOGITS
     operates
    0.94
     conducts
    0.90
     dominates
    0.90
     governs
    0.90
     sprang
    0.87
     headquartered
    0.86
     employs
    0.86
     launched
    0.85
     debuted
    0.84
     consists
    0.83
    Act Density 0.184%

    No Known Activations