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

    Neuronpedia

    INDEX
    Explanations

    words related to clothing items and financial/legal terms concerning contracts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     doman
    -0.80
     ridu
    -0.79
     compil
    -0.78
     desir
    -0.77
     fei
    -0.77
     Ause
    -0.77
     zimmer
    -0.76
     nece
    -0.76
     cabrio
    -0.75
     cana
    -0.74
    POSITIVE LOGITS
     button
    1.54
    button
    1.41
     buttons
    1.35
     Button
    1.31
    Button
    1.22
    BUTTON
    1.14
    buttons
    1.14
     BUTTON
    1.10
     btn
    1.03
    Buttons
    1.01
    Act Density 0.083%

    No Known Activations