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

    Neuronpedia

    INDEX
    Explanations

    references to display racks and related terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    newcommand
    -0.77
    balleur
    -0.75
     estimés
    -0.71
     disponibilités
    -0.69
    DaoImpl
    -0.64
    onViewCreated
    -0.64
    sprozess
    -0.63
    gehen
    -0.63
     Hearn
    -0.63
     FLOW
    -0.63
    POSITIVE LOGITS
     Rack
    1.84
    Rack
    1.80
     rack
    1.77
     racks
    1.62
    rack
    1.49
    racks
    1.48
     racking
    1.14
     racked
    0.98
     ラック
    0.93
    ラック
    0.82
    Act Density 0.002%

    No Known Activations