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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve conditional statements or assumptions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.57
    ষ্
    -0.51
    stod
    -0.51
     Mun
    -0.49
     nawr
    -0.49
     Mo
    -0.46
    usercontent
    -0.46
    XmlAccessType
    -0.46
    AspNetCore
    -0.45
     Ver
    -0.42
    POSITIVE LOGITS
    ніципа
    0.75
    WebElementEntity
    0.72
    featureID
    0.68
     thermique
    0.62
     للمعارف
    0.61
     Hera
    0.60
    دانشنامهٔ
    0.60
     cilia
    0.59
    expandindo
    0.57
     quoque
    0.56
    Act Density 0.006%

    No Known Activations