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

    Neuronpedia

    INDEX
    Explanations

    references to legal issues and arrests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelState
    -0.15
    eh
    -0.14
    urator
    -0.14
    loven
    -0.14
     Wet
    -0.14
     wet
    -0.14
     steam
    -0.14
    ŀ
    -0.14
    ulta
    -0.13
     pose
    -0.13
    POSITIVE LOGITS
    ansa
    0.19
    hazi
    0.15
    OMPI
    0.15
    »
    0.15
     Baum
    0.14
    ãĥªãĤ«
    0.14
    .Html
    0.14
    issan
    0.14
     Ø®ÙĪ
    0.14
     desn
    0.14
    Act Density 0.135%

    No Known Activations