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

    Neuronpedia

    INDEX
    Explanations

    references to modern or contemporary concepts and practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.67
     BrowserModule
    -0.67
    IsPostBack
    -0.63
    TestBed
    -0.62
    Intrinsic
    -0.61
    Rüyada
    -0.59
     myö
    -0.57
    ModelSerializer
    -0.57
    rodow
    -0.56
     chì
    -0.56
    POSITIVE LOGITS
    izing
    0.94
    istic
    0.87
     day
    0.86
     era
    0.73
    ising
    0.72
    izations
    0.72
     conveniences
    0.71
     times
    0.68
    izes
    0.66
    times
    0.65
    Act Density 0.083%

    No Known Activations