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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and relationships relevant to integers and equations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    WithPath
    -0.07
    UTERS
    -0.07
    strup
    -0.07
    iasi
    -0.07
    _DC
    -0.07
    itler
    -0.07
    mada
    -0.07
    .localization
    -0.06
    ãĤŃãĥ¥
    -0.06
    etu
    -0.06
    POSITIVE LOGITS
     am
    0.06
    thed
    0.06
    ongs
    0.06
     material
    0.06
     rod
    0.06
    ati
    0.06
     stem
    0.06
    ator
    0.06
     tr
    0.06
    th
    0.06
    Act Density 0.189%

    No Known Activations