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

    Neuronpedia

    INDEX
    Explanations

    phrases related to connections or relationships between people or entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifter
    -0.75
    oker
    -0.68
    imates
    -0.67
    \\\\\\\\
    -0.64
    onew
    -0.62
    oufl
    -0.62
    âķIJ
    -0.61
     Muller
    -0.60
    aneers
    -0.60
    ypes
    -0.58
    POSITIVE LOGITS
     thereto
    1.29
    worldly
    0.80
     to
    0.78
    ities
    0.74
     ancest
    0.73
     principally
    0.73
     closely
    0.72
    ively
    0.71
     specifically
    0.70
    iments
    0.70
    Act Density 0.105%

    No Known Activations