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

    Neuronpedia

    INDEX
    Explanations

    technical details and measurements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     goose
    -0.60
    eanor
    -0.60
     unpre
    -0.58
    opausal
    -0.57
     Scully
    -0.56
     Lauder
    -0.56
     Sans
    -0.56
     Leap
    -0.56
     gro
    -0.56
    andise
    -0.55
    POSITIVE LOGITS
    fig
    0.72
    figure
    0.66
    Ele
    0.64
     reper
    0.64
    ĥ
    0.64
    inch
    0.63
    ĪĴ
    0.63
    ibu
    0.62
    wid
    0.62
    9
    0.62
    Act Density 0.250%

    No Known Activations