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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and functions related to probability or statistical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AccessFile
    -0.60
    -0.51
    usercontent
    -0.47
    seamnă
    -0.47
    genheim
    -0.46
    NameInMap
    -0.46
    哂
    -0.45
    hlin
    -0.45
     sorella
    -0.45
    ién
    -0.45
    POSITIVE LOGITS
     $$
    0.57
     \[
    0.53
    \[
    0.52
    ↵↵
    0.50
     kasarigan
    0.47
    ContentAsync
    0.42
    :
    0.42
     given
    0.40
    \[
    0.39
    --}}
    0.38
    Act Density 1.694%

    No Known Activations