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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and parameters related to media encoding and quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otto
    -0.18
     wah
    -0.15
    gmt
    -0.15
    ampie
    -0.14
    utor
    -0.14
    verity
    -0.14
    ghost
    -0.14
    _DECLARE
    -0.14
    atter
    -0.14
    arie
    -0.14
    POSITIVE LOGITS
     compress
    0.27
     compression
    0.26
     Compression
    0.25
    Compression
    0.24
    compress
    0.23
     compressor
    0.23
     compressed
    0.23
    compression
    0.22
    åİĭ
    0.21
    _tables
    0.20
    Act Density 0.024%

    No Known Activations