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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and references to legal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mathrm
    -0.72
    <eos>
    -0.69
     saites
    -0.65
     […]
    -0.56
     …
    -0.56
     @"/
    -0.52
    enumi
    -0.52
    setcounter
    -0.51
     and
    -0.49
     ...
    -0.49
    POSITIVE LOGITS
     pleaſure
    1.10
     raiſ
    1.10
     purpoſe
    1.03
     poffe
    1.00
     myſelf
    0.98
     houſe
    0.97
     Efq
    0.94
     Chriftian
    0.92
     greateſt
    0.92
     ſever
    0.91
    Act Density 0.383%

    No Known Activations