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

    Neuronpedia

    INDEX
    Explanations

    references to foundational elements or building blocks in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    иÑĨ
    -0.15
     Bun
    -0.14
    ê·
    -0.14
     Burl
    -0.13
    ugar
    -0.13
     Barker
    -0.13
     Baum
    -0.12
    basket
    -0.12
    -basket
    -0.12
    ahir
    -0.12
    POSITIVE LOGITS
     block
    1.55
     Block
    1.42
    block
    1.37
     blocks
    1.34
    -block
    1.30
    Block
    1.30
     BLOCK
    1.24
     Blocks
    1.22
    _block
    1.19
    blocks
    1.16
    Act Density 0.326%

    No Known Activations