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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal terms and issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    esses
    -0.84
     Seconds
    -0.82
    ellen
    -0.80
    erves
    -0.76
    essors
    -0.74
    lists
    -0.74
    ĸļ
    -0.73
     Rodrigo
    -0.72
     Minutes
    -0.71
     Below
    -0.71
    POSITIVE LOGITS
     thing
    1.01
     behavior
    0.86
     activity
    0.83
     luck
    0.82
     relationship
    0.81
     warfare
    0.80
     magic
    0.80
     insanity
    0.80
     trauma
    0.79
     weaponry
    0.79
    Act Density 0.645%

    No Known Activations