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

    Neuronpedia

    INDEX
    Explanations

    references to flat surfaces or concepts related to flatness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zimmer
    -0.16
    ahr
    -0.16
    inkel
    -0.16
    elson
    -0.15
    iest
    -0.15
    asto
    -0.15
    lest
    -0.14
    holes
    -0.14
    ppelin
    -0.14
    ieder
    -0.14
    POSITIVE LOGITS
    ulence
    0.34
    ulent
    0.29
    -flat
    0.27
     flat
    0.23
    iron
    0.23
    .Flat
    0.23
    flat
    0.22
    foot
    0.22
     Flat
    0.22
    ness
    0.22
    Act Density 0.010%

    No Known Activations