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

    Neuronpedia

    INDEX
    Explanations

    references to discrete mathematical concepts or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     дописавши
    -0.52
    ScopeManager
    -0.51
     myſelf
    -0.49
    Personendaten
    -0.48
     ब्रेकडाउन
    -0.47
     CreateTagHelper
    -0.47
     méri
    -0.46
     surla
    -0.45
     اطلع
    -0.45
    IVEREF
    -0.45
    POSITIVE LOGITS
     discrete
    0.68
     Discrete
    0.60
     regression
    0.60
    Discrete
    0.60
    discrete
    0.59
     freeze
    0.56
    ito
    0.56
     lag
    0.55
     Freeze
    0.54
     Regression
    0.53
    Act Density 0.533%

    No Known Activations