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

    Neuronpedia

    INDEX
    Explanations

    quantitative comparisons related to statistical rates or levels of various characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     box
    -0.43
    well
    -0.43
     well
    -0.40
     multi
    -0.40
    yorsunuz
    -0.39
     Züge
    -0.39
    irent
    -0.38
     BOX
    -0.38
    atrice
    -0.37
    rdag
    -0.37
    POSITIVE LOGITS
    RegistryLite
    0.87
     fewest
    0.81
    ModelAdmin
    0.76
    SharedDtor
    0.76
    XmlAccessorType
    0.76
    TestBed
    0.75
    highest
    0.74
     safest
    0.74
     initComponents
    0.74
     fastest
    0.74
    Act Density 0.471%

    No Known Activations