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

    Neuronpedia

    INDEX
    Explanations

    multiple instances of punctuation, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.92
     Efq
    -1.86
     Theſe
    -1.76
    ^(@)
    -1.75
     Jefus
    -1.74
     Monfieur
    -1.69
     Majefty
    -1.68
     itſelf
    -1.67
     houſe
    -1.65
     pleaſure
    -1.64
    POSITIVE LOGITS
    .
    1.03
    -
    1.02
    ,
    1.02
    :
    0.99
    <eos>
    0.96
    ;
    0.95
    i
    0.94
    en
    0.91
    a
    0.91
     -
    0.89
    Act Density 0.463%

    No Known Activations