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

    Neuronpedia

    INDEX
    Explanations

    expressions related to belief and recognition of others' perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    大家
    -0.54
     meille
    -0.44
     everyone
    -0.43
    皆さん
    -0.42
    everyone
    -0.41
    ſſen
    -0.40
    urno
    -0.40
     gerekli
    -0.40
    给大家
    -0.40
    Приятного
    -0.40
    POSITIVE LOGITS
    featureID
    0.56
    ThroughAttribute
    0.56
    MigrationBuilder
    0.50
     NSCoder
    0.50
    ValueStyle
    0.49
     BoxFit
    0.49
    ViewImports
    0.47
    MockBean
    0.46
    HasIndex
    0.46
     ProtoMessage
    0.46
    Act Density 0.700%

    No Known Activations