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

    Neuronpedia

    INDEX
    Explanations

    ly adverbs describing processes or actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    aily
    -0.71
    ilion
    -0.67
    orem
    -0.67
    hao
    -0.66
    Liter
    -0.66
     Cause
    -0.65
     League
    -0.64
    arella
    -0.64
     Memories
    -0.63
     Parenthood
    -0.61
    POSITIVE LOGITS
     positioned
    0.97
     situated
    0.92
     priced
    0.91
     housed
    0.89
     transitioned
    0.89
     separated
    0.86
     challenged
    0.86
     spaced
    0.85
    gged
    0.83
     formulated
    0.83
    Act Density 0.759%

    No Known Activations