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

    Neuronpedia

    INDEX
    Explanations

    words related to grains or kernels

    oai_token-act-pair · gpt-3.5-turbo

    references to kernels in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Diamond
    -0.74
     Jac
    -0.70
     Harriet
    -0.70
     Tit
    -0.69
    icent
    -0.67
     Div
    -0.66
    chester
    -0.66
     Eag
    -0.66
    Elect
    -0.65
    resses
    -0.65
    POSITIVE LOGITS
     kernel
    3.58
    kernel
    3.01
     kernels
    2.82
     Kernel
    2.79
    ernel
    2.08
    ernels
    1.72
     systemd
    1.48
     linux
    1.45
    linux
    1.29
     firmware
    1.28
    Act Density 0.028%

    No Known Activations