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

    Neuronpedia

    INDEX
    Explanations

    references to product recalls and safety concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.19
    raquo
    -0.15
    PÅĻi
    -0.15
    .dirty
    -0.15
     addCriterion
    -0.15
    #aa
    -0.14
    	Schema
    -0.14
    åIJįçĦ¡ãģĹ
    -0.14
    .appspot
    -0.14
     restarting
    -0.14
    POSITIVE LOGITS
     safety
    0.18
    ê·¹
    0.16
     Archer
    0.15
     Safety
    0.15
     corner
    0.15
     rep
    0.14
    abin
    0.14
     Pacific
    0.14
     manufacture
    0.14
     conc
    0.14
    Act Density 0.009%

    No Known Activations