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

    Neuronpedia

    INDEX
    Explanations

    terms related to safety and risk, particularly in industrial or medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.72
    Cyfeiriadau
    -0.71
    featureID
    -0.70
     intStringLen
    -0.67
    yntaxException
    -0.66
    fvar
    -0.65
    URLEncoder
    -0.61
    WithIOException
    -0.60
     referenties
    -0.60
    parsedMessage
    -0.59
    POSITIVE LOGITS
     safety
    1.21
    safety
    1.12
     Safety
    1.11
    Safety
    1.10
     SAFETY
    0.99
     hazard
    0.96
    SAFETY
    0.91
     unsafe
    0.86
    afety
    0.82
    hazard
    0.81
    Act Density 0.420%

    No Known Activations