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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a reduction or decrease in quantity or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.85
    endphp
    -0.83
    skosten
    -0.80
    CreateMap
    -0.79
     Wib
    -0.76
    ‍♀️
    -0.76
     uintptr
    -0.74
     BoxDecoration
    -0.74
    harusnya
    -0.73
     Kirkwood
    -0.72
    POSITIVE LOGITS
     less
    1.33
     LESS
    1.30
     Less
    1.25
    Less
    1.21
     Lessing
    1.11
    less
    1.09
     menos
    0.97
    LESS
    0.97
     moins
    0.95
     weniger
    0.87
    Act Density 0.095%

    No Known Activations