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

    Neuronpedia

    INDEX
    Explanations

    terms related to exclusivity and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Conley
    -0.67
     useRef
    -0.60
     Great
    -0.59
    didSet
    -0.59
    utas
    -0.59
    NamedQueries
    -0.55
    nodoc
    -0.54
    estacks
    -0.54
    EventQueue
    -0.52
    Nef
    -0.51
    POSITIVE LOGITS
    toxicity
    1.26
     BoxDecoration
    0.89
    تقاوى
    0.78
     Koran
    0.78
     **/
    0.75
     muualla
    0.74
     myſelf
    0.73
     PhpStorm
    0.72
    ſelf
    0.71
     Majefty
    0.71
    Act Density 0.024%

    No Known Activations