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

    Neuronpedia

    INDEX
    Explanations

    elements expressing duality or complexity in relationships and identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.67
    Reparto
    -0.65
     pleaſure
    -0.64
    Pozdrawiam
    -0.62
     myſelf
    -0.61
    fromCharCode
    -0.61
    ERVIEW
    -0.60
     Monfieur
    -0.60
    равда
    -0.57
     pilas
    -0.57
    POSITIVE LOGITS
    却又
    0.67
    SharedDtor
    0.60
     yet
    0.58
    styleType
    0.55
     zugleich
    0.55
     одновременно
    0.54
    yet
    0.53
     dennoch
    0.53
     חיצוניים
    0.50
     ändå
    0.49
    Act Density 0.190%

    No Known Activations