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

    Neuronpedia

    INDEX
    Explanations

    references to technical or programming-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     animate
    -0.15
    Compiler
    -0.14
     sweat
    -0.14
    ÑĢÑĥн
    -0.14
    asia
    -0.13
    azine
    -0.13
    cheduler
    -0.13
    quake
    -0.13
    isia
    -0.13
    anan
    -0.13
    POSITIVE LOGITS
     Assertion
    0.29
     assertion
    0.27
     Sam
    0.26
    Assertion
    0.25
     SP
    0.24
     assertions
    0.24
     logout
    0.24
     Logout
    0.24
    SAM
    0.24
     Assertions
    0.23
    Act Density 0.018%

    No Known Activations