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

    Neuronpedia

    INDEX
    Explanations

    terms related to safety and secure environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    complexContent
    -0.92
    ="@+
    -0.78
     MenuView
    -0.78
    RegressionTest
    -0.78
    Literatur
    -0.72
     TableColumn
    -0.72
    Посилання
    -0.70
     Marr
    -0.70
     pró
    -0.69
     Wiktionnaire
    -0.69
    POSITIVE LOGITS
     Safe
    1.65
     safe
    1.64
     SAFE
    1.56
    SAFE
    1.55
    Safe
    1.46
     safer
    1.43
    safe
    1.40
     safely
    1.31
     safest
    1.31
    Saf
    1.27
    Act Density 0.051%

    No Known Activations