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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and technical terminology related to machine learning models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fumo
    -0.52
    CAUSE
    -0.48
    reducer
    -0.47
    lieve
    -0.47
     extruded
    -0.47
    endcsname
    -0.46
    aną
    -0.45
     Kemp
    -0.45
     Longo
    -0.45
     createState
    -0.45
    POSITIVE LOGITS
     training
    1.02
     train
    0.96
    train
    0.91
     Training
    0.91
    Training
    0.90
     DataLoader
    0.87
     sample
    0.86
    Train
    0.84
     TRAIN
    0.84
    training
    0.83
    Act Density 0.301%

    No Known Activations