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

    Neuronpedia

    INDEX
    Explanations

    terms related to various types of algebras and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <pad>
    -0.97
    <unused17>
    -0.96
    <unused43>
    -0.96
    bildtitel
    -0.95
    <unused47>
    -0.95
    <unused23>
    -0.95
    <unused41>
    -0.95
    <unused8>
    -0.95
    <unused3>
    -0.95
    [@BOS@]
    -0.95
    POSITIVE LOGITS
     
    0.34
     world
    0.27
     out
    0.26
     z
    0.26
    </strong>
    0.26
     (
    0.26
     re
    0.25
    ↵↵
    0.24
     table
    0.24
    ↵
    0.24
    Act Density 3.413%

    No Known Activations