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

    Neuronpedia

    INDEX
    Explanations

    references to expertise or skill in a particular subject

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPLE
    -0.75
    IDER
    -0.69
    hedon
    -0.65
    enegger
    -0.65
     Torn
    -0.64
    IGH
    -0.64
    vernment
    -0.63
    AAF
    -0.62
    tics
    -0.60
     Aren
    -0.60
    POSITIVE LOGITS
    pieces
    1.47
    piece
    1.29
    mind
    1.18
    stroke
    1.05
    classes
    0.98
    class
    0.98
    fully
    0.91
    sonian
    0.91
    work
    0.89
    minded
    0.88
    Act Density 0.074%

    No Known Activations