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

    Neuronpedia

    INDEX
    Explanations

    data structures and function definitions in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anſ
    -1.11
     Reſ
    -1.10
     myſelf
    -1.07
     itſelf
    -1.04
     Efq
    -1.03
     fevere
    -1.01
     ſeveral
    -1.01
     ſche
    -1.00
     doubtnut
    -1.00
     iſt
    -1.00
    POSITIVE LOGITS
    ↵↵
    1.20
    ↵
    0.84
    <eos>
    0.72
    ↵↵↵
    0.65
    ↵↵↵↵
    0.62
    .
    0.57
    ↵↵↵↵↵
    0.50
      
    0.46
    ↵↵↵↵↵↵
    0.45
                                   
    0.42
    Act Density 0.365%

    No Known Activations