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

    Neuronpedia

    INDEX
    Explanations

    references to governmental or state entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inne
    -0.15
    озем
    -0.15
    (CharSequence
    -0.15
     sede
    -0.14
    asser
    -0.14
    imet
    -0.14
    ãĥ«ãĥķ
    -0.14
    arus
    -0.13
    andering
    -0.13
    ầu
    -0.13
    POSITIVE LOGITS
    hood
    0.28
    MENTS
    0.21
    (State
    0.20
    -of
    0.19
     createState
    0.19
    craft
    0.18
     Department
    0.18
    833
    0.18
    356
    0.17
    MENT
    0.17
    Act Density 0.036%

    No Known Activations