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

    Neuronpedia

    INDEX
    Explanations

    events or situations that start with the word "just"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     quo
    -0.63
    amen
    -0.62
     Pett
    -0.61
    risk
    -0.59
     Likely
    -0.59
    similar
    -0.58
     manifold
    -0.58
     Proto
    -0.57
     Pattern
    -0.56
    ses
    -0.56
    POSITIVE LOGITS
    ifiable
    1.05
    itia
    0.97
    ifications
    0.96
    ifi
    0.91
    if
    0.91
    IFIED
    0.87
    iffe
    0.83
    IFIC
    0.82
    inic
    0.80
    iciary
    0.79
    Act Density 0.061%

    No Known Activations