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

    Neuronpedia

    INDEX
    Explanations

    information related to safety and compliance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    relating to "safe" or "safety"

    np_acts-logits-general · gemini-2.0-flash

    safety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.66
     <<<<<<<<<<<<<<
    -0.57
    StoryboardSegue
    -0.55
    hoots
    -0.55
    +:+
    -0.54
     rangs
    -0.53
    graphicx
    -0.49
    XmlAccessType
    -0.48
    protoimpl
    -0.48
    ponses
    -0.47
    POSITIVE LOGITS
     safety
    3.19
    safety
    2.77
     Safety
    2.76
    Safety
    2.72
     safe
    2.65
     safer
    2.56
     safely
    2.52
     SAFETY
    2.52
     safest
    2.46
    safe
    2.36
    Act Density 0.332%

    No Known Activations