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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "only" and its variations, indicating exclusivity or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hemd
    -0.50
     hashCode
    -0.48
     βά
    -0.46
    SpringBootTest
    -0.45
     czeko
    -0.44
     pomysł
    -0.43
     hmot
    -0.42
     arbet
    -0.42
     trän
    -0.42
    gridLayout
    -0.42
    POSITIVE LOGITS
    Only
    0.94
     only
    0.93
    only
    0.89
     Only
    0.88
     ONLY
    0.84
    ONLY
    0.83
     רק
    0.76
     onlyOwner
    0.73
    Hanya
    0.72
    僅
    0.72
    Act Density 0.143%

    No Known Activations