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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming functions and structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Савезне
    -0.39
    ########.
    -0.37
    GenerationType
    -0.34
    FontStyle
    -0.34
    RegressionTest
    -0.33
     ostavi
    -0.30
    zec
    -0.30
     internazionale
    -0.30
    ียว
    -0.30
    تقاوى
    -0.30
    POSITIVE LOGITS
     ew
    0.63
     purpoſe
    0.55
     للمعارف
    0.55
     EW
    0.52
     kaynağından
    0.52
    EW
    0.51
    CppMethod
    0.50
    Bakgrunnsstoff
    0.50
     houſe
    0.50
     pellic
    0.48
    Act Density 0.177%

    No Known Activations