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

    Neuronpedia

    INDEX
    Explanations

    punctuation and specific structure indicators within documentation or transcripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.73
    tagHelperRunner
    -0.69
    GEBURTSDATUM
    -0.65
    elemField
    -0.63
    principalColumn
    -0.58
    xmlhttp
    -0.57
    لينكات
    -0.56
     surla
    -0.56
    writeField
    -0.52
    Jereo
    -0.52
    POSITIVE LOGITS
     becauſe
    0.67
     whoſe
    0.65
     greateſt
    0.65
     ſmall
    0.63
     firſt
    0.61
     Immediately
    0.61
     Monfieur
    0.60
     initially
    0.59
     ſame
    0.59
     ſeveral
    0.59
    Act Density 0.085%

    No Known Activations