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

    Neuronpedia

    INDEX
    Explanations

    phrases related to promotions and offers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.69
    NameInMap
    -0.68
    fromnode
    -0.63
    }")]
    -0.61
    >*/
    -0.60
     snippetHide
    -0.59
    ']
    -0.57
    >")
    -0.55
    ">',
    -0.54
    تقاوى
    -0.54
    POSITIVE LOGITS
     trusted
    0.74
     superiori
    0.68
     fiable
    0.64
    trusted
    0.61
     विश्वसनीय
    0.61
     reliable
    0.60
     trustworthy
    0.59
    perma
    0.58
     dependable
    0.58
     confiance
    0.58
    Act Density 0.119%

    No Known Activations