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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence structures indicative of formal writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surla
    -0.83
     للمعارف
    -0.77
     للاسماء
    -0.77
     Biôgrafia
    -0.77
     Italijanski
    -0.75
     EconPapers
    -0.74
     increí
    -0.74
     ligiloj
    -0.73
    majánló
    -0.71
    ſicht
    -0.70
    POSITIVE LOGITS
    ↵
    0.31
    ¡
    0.28
    rapp
    0.26
    ,
    0.26
     relationships
    0.26
    0.26
     soit
    0.26
     har
    0.26
    sies
    0.26
    <eos>
    0.26
    Act Density 0.503%

    No Known Activations