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

    Neuronpedia

    INDEX
    Explanations

    references to government officials and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inflate
    -0.16
    té
    -0.15
    ovenant
    -0.15
    ofile
    -0.15
    .createClass
    -0.15
    aab
    -0.15
    ((__
    -0.14
    ï¼ĪæĺŃåĴĮ
    -0.14
    stav
    -0.14
    ÑĢÑĥн
    -0.14
    POSITIVE LOGITS
     Cabinet
    0.18
     Minister
    0.17
     Sv
    0.15
     cabinet
    0.15
     minister
    0.15
     patron
    0.15
    -toggle
    0.15
    AH
    0.15
    åħ¼
    0.14
     Ministers
    0.14
    Act Density 0.036%

    No Known Activations