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

    Neuronpedia

    INDEX
    Explanations

    words related to law, government, and security

    oai_token-act-pair · gpt-3.5-turbo

    letters or characters that appear in various contexts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cot
    -0.78
     Brach
    -0.77
     Spa
    -0.73
     Watkins
    -0.72
     Leopard
    -0.71
     Gaul
    -0.69
     Tactics
    -0.69
     Kau
    -0.69
     Jagu
    -0.69
     KP
    -0.68
    POSITIVE LOGITS
    vernment
    1.05
    undred
    0.99
    actory
    0.97
    terday
    0.95
    ancial
    0.93
    actly
    0.93
    onymous
    0.89
    udder
    0.87
    iable
    0.86
    iversity
    0.86
    Act Density 0.159%

    No Known Activations