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

    Neuronpedia

    INDEX
    Explanations

    numerical information such as statistics, coordinates, instructions, and code snippets

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     inconce
    -1.10
     indestru
    -1.03
     disagre
    -1.00
     intrigu
    -1.00
     Mahomet
    -0.97
     unspeak
    -0.96
     Mlle
    -0.95
     reluct
    -0.95
     Gorb
    -0.94
     apprehen
    -0.93
    POSITIVE LOGITS
    (':
    0.74
    (":
    0.69
    ('/:
    0.67
    :::
    0.64
    ✨:
    0.64
     giuri
    0.63
    ("/:
    0.63
    ():
    0.60
    =:
    0.60
    }:
    0.60
    Act Density 0.174%

    No Known Activations