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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '/';
    -0.93
    колеп
    -0.85
    ">:
    -0.83
     })}
    -0.83
    ]]]
    -0.81
    "){
    -0.80
    "},
    -0.78
    })}\
    -0.78
    ].(
    -0.77
    \}\\
    -0.77
    POSITIVE LOGITS
     num
    1.62
    num
    1.59
    Num
    1.54
     Num
    1.43
    NUM
    1.40
     nums
    1.34
    setNum
    1.30
    nums
    1.26
    getNum
    1.20
     NUM
    1.16
    Act Density 0.059%

    No Known Activations