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

    Neuronpedia

    INDEX
    Explanations

    values associated with measurement or rating

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.53
    ’
    -0.52
     jo
    -0.50
    -
    -0.49
    ↵↵
    -0.49
    '
    -0.48
     
    -0.48
    arum
    -0.48
     Best
    -0.48
     Sü
    -0.47
    POSITIVE LOGITS
    المناصب
    1.18
     nahilalakip
    1.15
     autorytatywna
    1.12
    вгений
    1.01
     Савезне
    1.01
     pinulongan
    0.92
     الدولى
    0.92
    NUMX
    0.92
     Efq
    0.89
    بوابة
    0.89
    Act Density 0.634%

    No Known Activations