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

    Neuronpedia

    INDEX
    Explanations

    programmable functions and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to programming, particularly variable declarations and control structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.99
    Leaks
    -0.95
    Beast
    -0.92
    Unity
    -0.91
    Bridge
    -0.89
    Community
    -0.89
    DNA
    -0.88
    OVER
    -0.88
    Earth
    -0.87
    Freedom
    -0.87
    POSITIVE LOGITS
     q
    1.37
     k
    1.33
     ml
    1.32
     mc
    1.29
     y
    1.27
     pc
    1.25
     u
    1.25
     x
    1.24
     h
    1.23
     s
    1.22
    Act Density 0.320%

    No Known Activations