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

    Neuronpedia

    INDEX
    Explanations

    terms related to departures and sentencing in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Manuela
    -0.68
    awaiter
    -0.65
     Reverso
    -0.61
     recherchez
    -0.61
     helft
    -0.61
     eggs
    -0.60
    brandt
    -0.59
    utnik
    -0.58
     œufs
    -0.58
    ynki
    -0.57
    POSITIVE LOGITS
     fiction
    1.04
     Fiction
    1.01
     Virgin
    1.00
     grammar
    0.98
    Fiction
    0.96
     gramm
    0.94
     Virginia
    0.92
    Virgin
    0.92
    LITER
    0.91
     Grammar
    0.91
    Act Density 0.118%

    No Known Activations