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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols or expressions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ILON
    -0.16
    pts
    -0.16
    zel
    -0.14
    aze
    -0.14
    asper
    -0.14
     nữa
    -0.14
    \Active
    -0.14
     princess
    -0.14
    roz
    -0.14
    ENAME
    -0.14
    POSITIVE LOGITS
    AEA
    0.16
    зд
    0.15
    urat
    0.15
    داÙħ
    0.15
     Vert
    0.14
    uria
    0.14
    ugu
    0.13
     pist
    0.13
    amilia
    0.13
    PEG
    0.13
    Act Density 0.055%

    No Known Activations