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

    Neuronpedia

    INDEX
    Explanations

    names of companies or projects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    internal
    -1.00
    unc
    -1.00
    arching
    -0.99
    tc
    -0.96
    exec
    -0.91
    adal
    -0.90
    unal
    -0.87
    private
    -0.87
    aaa
    -0.86
    overe
    -0.85
    POSITIVE LOGITS
     Ones
    1.00
     Dome
    0.97
     Suit
    0.90
     Shack
    0.90
     Flight
    0.88
     Arts
    0.86
     Cause
    0.86
     Friends
    0.86
     Widow
    0.86
     Eater
    0.85
    Act Density 0.249%

    No Known Activations