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

    Neuronpedia

    INDEX
    Explanations

    constructs and control structures commonly used in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]='\
    -0.56
    $_['
    -0.54
     ungef
    -0.54
    reuung
    -0.52
     creation
    -0.51
     Creation
    -0.49
    cheinend
    -0.47
    ]}"
    -0.47
     مفص
    -0.46
    }]
    -0.46
    POSITIVE LOGITS
    ++
    1.85
     ++
    1.81
    ++,
    1.42
    (++
    1.40
     (++
    1.36
    ++$
    1.23
    ++.
    1.23
    (--
    1.18
    ++)
    1.16
    --
    1.14
    Act Density 0.283%

    No Known Activations