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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation, particularly involving powers and parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olec
    -0.15
    otel
    -0.15
     Jako
    -0.14
     pencil
    -0.14
     dressing
    -0.14
    kir
    -0.13
    592
    -0.13
    amation
    -0.13
    BUF
    -0.13
    raud
    -0.12
    POSITIVE LOGITS
    .Addr
    0.15
    orest
    0.15
    andaÅŁ
    0.15
     Mile
    0.14
    rapper
    0.14
    ãĥ³ãĥķ
    0.14
    enville
    0.14
    ĮĢ
    0.14
    åĦ
    0.14
    ossier
    0.14
    Act Density 0.051%

    No Known Activations