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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships in a given context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atz
    -0.14
     ifdef
    -0.14
    ellan
    -0.14
    ãĥĥãĤ·ãĥ¥
    -0.13
    UX
    -0.13
     PureComponent
    -0.13
    ker
    -0.13
    ESH
    -0.13
     redeem
    -0.13
    eria
    -0.13
    POSITIVE LOGITS
     twice
    0.29
     Twice
    0.26
     half
    0.20
     gấp
    0.18
    half
    0.18
     equal
    0.18
    equal
    0.17
    -half
    0.17
     EQUAL
    0.17
     multiples
    0.17
    Act Density 0.165%

    No Known Activations