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

    Neuronpedia

    INDEX
    Explanations

    references to safety in various contexts

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

    Safety and its contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     medium
    -0.44
    PathVariable
    -0.43
     başına
    -0.42
    (
    -0.42
    ronique
    -0.42
    “
    -0.41
     instituição
    -0.41
     wide
    -0.41
     transfieras
    -0.40
     kyse
    -0.40
    POSITIVE LOGITS
    Safety
    1.19
     Safety
    1.17
    afety
    1.13
     SAFETY
    1.11
    safety
    1.10
     safety
    1.09
    SAFETY
    1.03
     sécurité
    0.77
    Seguridad
    0.75
    Sicherheit
    0.73
    Act Density 0.005%

    No Known Activations