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

    Neuronpedia

    INDEX
    Explanations

    references to vulnerable populations and their risks in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    consulté
    -0.56
    PYX
    -0.54
    richTextPanel
    -0.46
    crose
    -0.46
     fame
    -0.45
    ferencia
    -0.45
    cipit
    -0.45
     met
    -0.45
    同期
    -0.44
    enya
    -0.44
    POSITIVE LOGITS
     vulnerable
    0.76
    FontOfSize
    0.73
     Vulnerable
    0.70
    interopRequire
    0.64
     Elderly
    0.62
     speciale
    0.61
     speciali
    0.61
     للمعارف
    0.60
     vulné
    0.58
    DockStyle
    0.58
    Act Density 0.276%

    No Known Activations