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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to relationships and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -1.01
     Efq
    -0.95
     becauſe
    -0.88
     Theſe
    -0.86
     whoſe
    -0.86
    TestingModule
    -0.83
     ſmall
    -0.82
     Monfieur
    -0.81
    DockStyle
    -0.81
     itſelf
    -0.81
    POSITIVE LOGITS
     relationships
    0.82
    Relationships
    0.66
     status
    0.63
     relationship
    0.59
     Beziehungen
    0.59
     Relationships
    0.54
    Ship
    0.53
     issues
    0.52
     between
    0.50
     string
    0.49
    Act Density 0.181%

    No Known Activations