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

    Neuronpedia

    INDEX
    Explanations

    phrases and language that indicate clarity and distinctness in descriptions or definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     الاطلاع
    -0.66
    发表于
    -0.65
     للمعارف
    -0.60
     getNum
    -0.59
    (;;)
    -0.59
    enumi
    -0.58
    VersionUID
    -0.58
    hardy
    -0.57
    Lur
    -0.57
     estimés
    -0.56
    POSITIVE LOGITS
     clear
    1.24
     clearly
    1.13
     CLEAR
    1.03
    clearly
    0.99
     claros
    0.97
    clear
    0.95
     Clearly
    0.94
     klare
    0.93
     clearest
    0.93
     claras
    0.92
    Act Density 0.453%

    No Known Activations