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

    Neuronpedia

    INDEX
    Explanations

    references to legal charges and criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otti
    -0.08
    ruz
    -0.07
    ãĥ¥ãĥ¼
    -0.07
    pag
    -0.07
    mey
    -0.07
     EntryPoint
    -0.07
    éĺħ读次æķ°
    -0.07
     embr
    -0.06
     smrt
    -0.06
     Larson
    -0.06
    POSITIVE LOGITS
    aged
    0.07
    aging
    0.07
    æ´ŀ
    0.06
    agit
    0.06
    renom
    0.06
    comed
    0.06
     older
    0.05
    je
    0.05
     evac
    0.05
    378
    0.05
    Act Density 0.030%

    No Known Activations