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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate assistance or support in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    XmlAccessorType
    -0.65
    szönöm
    -0.50
     CreateTagHelper
    -0.45
    StructEnd
    -0.44
    GenerationType
    -0.44
     absol
    -0.43
    BeforeClass
    -0.42
    Absol
    -0.41
    oforms
    -0.41
     Französ
    -0.39
    POSITIVE LOGITS
     aid
    2.61
     Aid
    2.44
    Aid
    2.22
    aid
    2.11
     aids
    2.11
     AID
    1.88
     Aids
    1.83
     aiding
    1.80
    AID
    1.65
     aide
    1.64
    Act Density 0.127%

    No Known Activations