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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming conditions and expected outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    оваÑĢи
    -0.15
     addCriterion
    -0.15
    *)_
    -0.14
    вий
    -0.14
    NewProp
    -0.13
    .metro
    -0.13
    Ïģά
    -0.13
     planta
    -0.13
     CHIP
    -0.13
    bind
    -0.13
    POSITIVE LOGITS
     bucket
    0.47
     Bucket
    0.42
    bucket
    0.40
     Buck
    0.40
     buckets
    0.38
    Bucket
    0.38
    _bucket
    0.36
    (bucket
    0.36
    .bucket
    0.34
     Amazon
    0.33
    Act Density 0.033%

    No Known Activations