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

    Neuronpedia

    INDEX
    Explanations

    terminology related to artificial intelligence and chat systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iefs
    -0.17
    ÄĽr
    -0.14
     Burr
    -0.14
    LAY
    -0.14
     Groups
    -0.13
    .groups
    -0.13
    avr
    -0.13
    ủng
    -0.13
    irtual
    -0.13
    legates
    -0.13
    POSITIVE LOGITS
    BERT
    0.18
     sentiment
    0.17
    bert
    0.17
     advers
    0.16
     pretrained
    0.15
     utter
    0.15
     Shard
    0.15
    CLS
    0.15
     reading
    0.15
     corpor
    0.15
    Act Density 0.061%

    No Known Activations