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

    Neuronpedia

    INDEX
    Explanations

    terms associated with social or political backlash and criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uldu
    -0.16
    maktan
    -0.15
    æ³ķ人
    -0.15
     Bren
    -0.14
    ellig
    -0.14
    аÑĤегоÑĢ
    -0.14
    eki
    -0.13
    éĵ¶
    -0.13
    agna
    -0.13
     balls
    -0.13
    POSITIVE LOGITS
    alarm
    0.15
    bery
    0.14
    idden
    0.14
    ibrator
    0.14
    uffer
    0.14
    ":[{↵
    0.14
     unst
    0.14
    otta
    0.14
     Tail
    0.13
    ãĥ¼ãĥ¬
    0.13
    Act Density 0.001%

    No Known Activations