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

    Neuronpedia

    INDEX
    Explanations

    phrases related to attribution and citation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ault
    -0.15
    ì¼ĵ
    -0.15
    айд
    -0.14
     Assault
    -0.14
    allen
    -0.14
    ansson
    -0.13
    arie
    -0.13
    acin
    -0.13
    ayah
    -0.13
    angu
    -0.13
    POSITIVE LOGITS
     attribute
    0.73
     attributes
    0.67
     Attribute
    0.64
    attribute
    0.63
    Attribute
    0.60
     atrib
    0.57
     Attributes
    0.57
    attributes
    0.56
     attrib
    0.56
     attr
    0.55
    Act Density 0.110%

    No Known Activations