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

    Neuronpedia

    INDEX
    Explanations

    interactive questions and statements about learning and advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -1.01
     nahilalakip
    -1.00
    SourceChecksum
    -0.98
    XmlAccessorType
    -0.96
     disambiguazione
    -0.94
     gynhyrchwyd
    -0.90
    XmlAccessType
    -0.88
    Diwedd
    -0.87
     виправивши
    -0.87
    expandindo
    -0.85
    POSITIVE LOGITS
     your
    0.70
     yourself
    0.66
     you
    0.58
    ↵↵
    0.56
    your
    0.55
    you
    0.49
    Your
    0.47
    yourself
    0.46
    Вам
    0.44
     You
    0.44
    Act Density 0.457%

    No Known Activations