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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names or titles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.80
    Disclaimer
    -0.80
    SOURCE
    -0.75
    izoph
    -0.73
    wana
    -0.72
    ritis
    -0.71
    agascar
    -0.68
    Shape
    -0.68
    CVE
    -0.67
     Machina
    -0.66
    POSITIVE LOGITS
     Abrams
    0.91
     Walker
    0.90
     Phelps
    0.87
     Johnson
    0.84
     Smith
    0.84
     McD
    0.83
     Simmons
    0.83
     Sullivan
    0.83
     Ballard
    0.79
     Watt
    0.78
    Act Density 0.038%

    No Known Activations