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

    Neuronpedia

    INDEX
    Explanations

    occurrences of code structure elements, such as arrays and objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Vere
    -0.52
     Smal
    -0.49
      
    -0.49
    nungs
    -0.49
     καν
    -0.46
    binaan
    -0.45
     traitors
    -0.44
     rubles
    -0.44
     lattice
    -0.44
    obé
    -0.44
    POSITIVE LOGITS
    ########.
    0.82
    исленность
    0.81
    ={({
    0.77
     OMITBAD
    0.76
    synthesize
    0.76
    IonicModule
    0.76
    __(/*!
    0.75
     "..\..\..\
    0.73
    IContainer
    0.72
     propOrder
    0.65
    Act Density 0.048%

    No Known Activations