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

    Neuronpedia

    INDEX
    Explanations

    a recurring pattern in the text, specifically the representation of the abbreviation "eb."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.81
     Monfieur
    -1.70
     Majefty
    -1.66
     pleaſure
    -1.62
     houſe
    -1.58
     myſelf
    -1.55
     Houſe
    -1.53
     itſelf
    -1.48
     Theſe
    -1.45
     Jefus
    -1.45
    POSITIVE LOGITS
     
    0.94
     I
    0.82
    ↵↵
    0.79
     [
    0.76
     B
    0.74
    ↵
    0.73
     in
    0.73
     (
    0.72
    <eos>
    0.69
     T
    0.69
    Act Density 0.321%

    No Known Activations