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

    Neuronpedia

    INDEX
    Explanations

    references to scientific measurement tools and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chartInstance
    -0.15
    ãĤ·ãĥ£ãĥ«
    -0.15
    kaar
    -0.15
    ORMAL
    -0.14
    iek
    -0.14
     Jama
    -0.14
    ."&
    -0.14
    <context
    -0.14
    Invoker
    -0.14
    uchar
    -0.13
    POSITIVE LOGITS
     calor
    0.27
     hit
    0.25
     sc
    0.24
     veto
    0.22
     shower
    0.21
     read
    0.20
     hits
    0.19
     drift
    0.19
     barrel
    0.19
     Hits
    0.19
    Act Density 0.006%

    No Known Activations