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

    Neuronpedia

    INDEX
    Explanations

    news articles discussing specific events or reports

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     sacrific
    -0.81
    BILITIES
    -0.76
    atics
    -0.73
     discriminate
    -0.71
    iva
    -0.67
     disagree
    -0.65
    anka
    -0.63
    pert
    -0.62
     perceive
    -0.62
     discharged
    -0.61
    POSITIVE LOGITS
     Scrib
    0.99
    NPR
    0.95
     Wikileaks
    0.91
     Pastebin
    0.90
     Billboard
    0.87
     Archives
    0.86
     Collider
    0.86
     February
    0.85
     Newsweek
    0.85
     Politico
    0.84
    Act Density 1.480%

    No Known Activations