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

    Neuronpedia

    INDEX
    Explanations

    references to monetary comparisons indicating that something is more affordable

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    хьтан
    -0.71
     AssemblyVersion
    -0.68
     costly
    -0.65
    -0.61
     FontWeight
    -0.60
    ValueStyle
    -0.59
    Sock
    -0.58
     Comédie
    -0.58
     fragility
    -0.58
    etheless
    -0.57
    POSITIVE LOGITS
     cheaper
    2.00
     Cheaper
    1.56
     cheapest
    1.32
     cheap
    0.88
     дешевле
    0.87
     günstiger
    0.81
    icker
    0.80
    cheap
    0.77
     Cheapest
    0.75
    Cheap
    0.70
    Act Density 0.003%

    No Known Activations