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

    Neuronpedia

    INDEX
    Explanations

    concepts related to mathematical dimensions and spectral measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oref
    -0.15
    sik
    -0.15
    angi
    -0.15
    .Fat
    -0.15
     statuses
    -0.14
    otti
    -0.14
    ilim
    -0.14
    contri
    -0.14
     kür
    -0.14
    ania
    -0.14
    POSITIVE LOGITS
     Shannon
    0.26
     compression
    0.21
     Compression
    0.21
     rate
    0.21
     Rate
    0.21
     channel
    0.20
     CHANNEL
    0.20
     rates
    0.20
     Rates
    0.20
     capacity
    0.19
    Act Density 0.014%

    No Known Activations