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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and measurements related to graphics or resolution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    247
    -0.17
    rogram
    -0.15
     Roose
    -0.15
    fang
    -0.14
     ê
    -0.14
    ailable
    -0.14
     Mus
    -0.14
    allee
    -0.14
     roller
    -0.14
    dbe
    -0.14
    POSITIVE LOGITS
    102
    0.27
    800
    0.21
    128
    0.20
    960
    0.20
    192
    0.20
    640
    0.20
    384
    0.19
    768
    0.18
    480
    0.18
    854
    0.18
    Act Density 0.005%

    No Known Activations