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

    Neuronpedia

    INDEX
    Explanations

    terms related to safety and protective measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gameserver
    -0.71
    ochim
    -0.69
     TableColumn
    -0.69
     ARCHITECTURE
    -0.68
    malink
    -0.65
     trekken
    -0.64
    ⓧ
    -0.63
    MLLoader
    -0.61
    JMenu
    -0.61
    handlungen
    -0.61
    POSITIVE LOGITS
     safety
    3.46
     Safety
    3.28
    Safety
    3.23
    safety
    3.11
     SAFETY
    2.96
    SAFETY
    2.84
    afety
    2.40
    安全
    2.17
     safe
    2.14
     Safe
    2.09
    Act Density 0.056%

    No Known Activations