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

    Neuronpedia

    INDEX
    Explanations

    symbolic notation and mathematical expressions related to formal proofs or equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    覧
    -0.17
    zk
    -0.16
    orro
    -0.14
    `${
    -0.14
     ç·
    -0.14
    ackbar
    -0.14
    ochen
    -0.14
    तम
    -0.14
    éļ
    -0.14
    олеÑĤ
    -0.13
    POSITIVE LOGITS
     {
    0.20
     {-
    0.17
     {{
    0.17
     {↵
    0.17
     {|
    0.17
    {{
    0.15
    {↵
    0.15
    hang
    0.15
    +=(
    0.15
    -=
    0.14
    Act Density 0.096%

    No Known Activations