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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to complexity and data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Clarkson
    -0.16
    Batch
    -0.14
    ouro
    -0.14
    yor
    -0.14
     dog
    -0.14
    lox
    -0.14
    .bulk
    -0.13
    Pod
    -0.13
    778
    -0.13
    olid
    -0.13
    POSITIVE LOGITS
     prediction
    0.25
     Prediction
    0.25
     coding
    0.25
     Coding
    0.24
     predictors
    0.23
     Motion
    0.23
     quant
    0.22
     motion
    0.22
     bit
    0.22
    prediction
    0.22
    Act Density 0.002%

    No Known Activations