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

    Neuronpedia

    INDEX
    Explanations

    specific programming terms and keywords related to policies and data structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     OMITBAD
    -0.54
     nutricional
    -0.48
    principalTable
    -0.48
    QMetaType
    -0.48
     duradero
    -0.47
    nalités
    -0.47
    -0.46
     psicológico
    -0.46
     אחרים
    -0.46
     diarios
    -0.45
    POSITIVE LOGITS
     referrerpolicy
    0.51
    UserScript
    0.40
    < 
    0.39
     FID
    0.37
     Gout
    0.36
     inse
    0.35
    gram
    0.35
    FileInputStream
    0.35
    teknik
    0.35
    holes
    0.34
    Act Density 3.141%

    No Known Activations