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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their relationships in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.65
     (
    -0.57
     in
    -0.52
    /
    -0.50
     P
    -0.50
     co
    -0.50
     di
    -0.50
     
    -0.48
    ↵
    -0.48
     im
    -0.47
    POSITIVE LOGITS
    AddTagHelper
    1.20
    MemoryWarning
    1.17
     raiſ
    1.09
     myſelf
    1.08
     Jefus
    1.07
     iſt
    1.07
     resourceCulture
    1.02
     Majefty
    1.02
     NSCoder
    1.02
     itſelf
    1.01
    Act Density 0.608%

    No Known Activations