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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and parameters related to neural network configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancellable
    -0.17
    akedown
    -0.15
    aro
    -0.14
     mlx
    -0.13
    稿
    -0.13
    Lint
    -0.13
    nap
    -0.13
    ette
    -0.13
    eking
    -0.13
     Secretary
    -0.13
    POSITIVE LOGITS
    relu
    0.17
     outputs
    0.17
    InputLabel
    0.17
    .jasper
    0.15
    urm
    0.15
     input
    0.15
     learn
    0.15
    ReLU
    0.14
    learn
    0.14
     output
    0.14
    Act Density 0.004%

    No Known Activations