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

    Neuronpedia

    INDEX
    Explanations

    names of authors and researchers in scientific papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bill
    -0.56
    <eos>
    -0.55
     (
    -0.54
      
    -0.53
    φό
    -0.53
    ↵↵
    -0.53
    /
    -0.52
     "
    -0.52
     –
    -0.52
     «
    -0.49
    POSITIVE LOGITS
     photolibrary
    0.74
     houſe
    0.73
    évaluateur
    0.71
     Shakspeare
    0.70
     Phry
    0.69
     ſeveral
    0.69
    ंदीखरीदारी
    0.67
     Forumite
    0.65
     betweenstory
    0.65
     estimés
    0.63
    Act Density 0.198%

    No Known Activations