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

    Neuronpedia

    INDEX
    Explanations

    Cyrillic characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters or non-standard text symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Franch
    -0.80
     Bun
    -0.66
     panels
    -0.65
     Ada
    -0.63
     admission
    -0.62
    theless
    -0.62
     bounds
    -0.62
     TTL
    -0.62
     comparisons
    -0.60
     Bran
    -0.60
    POSITIVE LOGITS
    ³
    1.54
    ²
    1.54
    ¿
    1.54
    ¾
    1.53
    º
    1.52
    ¼
    1.50
    ´
    1.49
    ¸
    1.49
    ±
    1.48
    ļ
    1.43
    Act Density 0.011%

    No Known Activations