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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating levels of importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DeleteMapping
    -0.57
    ptonshire
    -0.56
     marty
    -0.54
     Leningrad
    -0.54
     Archiproducts
    -0.52
    APOLIS
    -0.52
    Brooklyn
    -0.51
    AllAfrica
    -0.51
    Customized
    -0.50
    Indianapolis
    -0.50
    POSITIVE LOGITS
     تضيفلها
    0.75
    sizeCache
    0.75
    Skocz
    0.72
    ResumeLayout
    0.66
     beginnetje
    0.64
     uska
    0.63
     Och
    0.63
    DebuggerStep
    0.62
     Serif
    0.62
     very
    0.62
    Act Density 0.221%

    No Known Activations