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

    Neuronpedia

    INDEX
    Explanations

    specific symbols or characters that represent unique or important elements in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Clintons
    -0.15
     اختÛĮار
    -0.14
     Lands
    -0.14
     Bent
    -0.14
    Capability
    -0.13
     Choice
    -0.13
    clas
    -0.13
     Option
    -0.13
     Clippers
    -0.13
     Bundle
    -0.13
    POSITIVE LOGITS
     Protection
    0.29
     protection
    0.29
     protect
    0.29
     Protect
    0.28
     protecting
    0.28
     protects
    0.28
    Protect
    0.28
    ä¿ĿæĬ¤
    0.27
    Protection
    0.27
    protect
    0.27
    Act Density 0.027%

    No Known Activations