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

    Neuronpedia

    INDEX
    Explanations

    references to human rights and freedoms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Simpl
    -0.18
     Closure
    -0.15
    935
    -0.15
     Transparent
    -0.15
     ADVISED
    -0.14
     Modular
    -0.14
    MBProgressHUD
    -0.14
    closure
    -0.14
    rio
    -0.14
    atron
    -0.14
    POSITIVE LOGITS
     guaranteed
    0.36
     guarantee
    0.35
     protected
    0.31
     guarantees
    0.31
     Guarantee
    0.31
     protections
    0.31
     guar
    0.31
     Guaranteed
    0.29
     protection
    0.29
     recognition
    0.28
    Act Density 0.482%

    No Known Activations