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

    Neuronpedia

    INDEX
    Explanations

    patterns of structure and syntax in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    	↵
    -0.22
    R
    -0.20
    M
    -0.19
    F
    -0.18
    u
    -0.18
    y
    -0.18
    el
    -0.18
    N
    -0.18
     ↵
    -0.18
    B
    -0.17
    POSITIVE LOGITS
    0.20
    orna
    0.16
    least
    0.15
    upy
    0.15
    mlx
    0.14
    caf
    0.14
    Least
    0.14
    	and
    0.14
     least
    0.14
    hire
    0.14
    Act Density 0.125%

    No Known Activations