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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.54
     and
    -0.51
     (
    -0.50
     of
    -0.46
     E
    -0.45
    .
    -0.44
     to
    -0.43
    ↵↵
    -0.42
     or
    -0.42
      
    -0.42
    POSITIVE LOGITS
     Monfieur
    1.07
     myſelf
    1.06
    SequentialGroup
    1.02
     Efq
    1.02
     ſche
    0.98
     propOrder
    0.93
     Reſ
    0.91
     Jefus
    0.89
     Савезне
    0.89
     ſeveral
    0.86
    Act Density 0.231%

    No Known Activations