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

    Neuronpedia

    INDEX
    Explanations

    nested parentheses in code expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     bort
    -0.60
    elevator
    -0.58
     musique
    -0.58
     planeta
    -0.56
    platten
    -0.56
     planetas
    -0.55
     صوتيه
    -0.55
     rather
    -0.54
    topf
    -0.54
    +=
    -0.54
    POSITIVE LOGITS
    0.77
     AssemblyProduct
    0.63
    Française
    0.62
     незавершена
    0.60
     ArrayAdapter
    0.59
    ])):
    0.57
    ioutil
    0.57
     Aix
    0.57
    KeySpec
    0.56
     ostavi
    0.55
    Act Density 0.002%

    No Known Activations