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

    Neuronpedia

    INDEX
    Explanations

    significant initial tokens or phrases that may indicate the beginning of a structured thought or new section in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UNIDENTIFIED
    -0.63
    fizierung
    -0.63
    ()}}
    -0.63
     }}$}
    -0.63
     most
    -0.62
     lots
    -0.61
    CopyWith
    -0.60
    ofition
    -0.60
    PMailer
    -0.59
    undle
    -0.59
    POSITIVE LOGITS
    <bos>
    0.72
    Datuak
    0.65
     Roskov
    0.63
     Réponses
    0.63
    onViewCreated
    0.62
    AddHtmlAttribute
    0.60
    Rüyada
    0.60
    protoimpl
    0.57
     defrost
    0.55
     propOrder
    0.55
    Act Density 0.329%

    No Known Activations