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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to safety and secure environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.22
    inous
    -0.17
     safety
    -0.17
    afety
    -0.17
     Safety
    -0.16
    chers
    -0.15
    pers
    -0.15
    ETERS
    -0.15
    Safety
    -0.15
    idia
    -0.15
    POSITIVE LOGITS
    -guard
    0.29
     harbor
    0.27
     haven
    0.27
    keeping
    0.27
     hav
    0.25
     Haven
    0.24
    AreaView
    0.24
     Harbor
    0.24
    (r
    0.23
     passage
    0.21
    Act Density 0.044%

    No Known Activations