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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically commas and semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.88
     Efq
    -1.88
     itſelf
    -1.65
     Theſe
    -1.62
     pleaſure
    -1.56
     ſtate
    -1.55
     raiſ
    -1.55
     purpoſe
    -1.54
     Jefus
    -1.53
     themſelves
    -1.53
    POSITIVE LOGITS
    <eos>
    1.01
     $\
    0.95
    .)
    0.83
    ↵
    0.81
     }}$
    0.78
    .$,
    0.76
    \
    0.75
    }$.
    0.75
    $,
    0.74
     $=$
    0.74
    Act Density 0.239%

    No Known Activations