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

    Neuronpedia

    INDEX
    Explanations

    words that indicate new entities or concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ComVisible
    -0.72
     Italij
    -0.62
     pareti
    -0.62
     saites
    -0.61
    #+#
    -0.60
    SourceChecksum
    -0.60
    chufe
    -0.58
    ViewFeatures
    -0.58
     varandra
    -0.58
    abinieri
    -0.57
    POSITIVE LOGITS
     new
    1.46
    新的
    1.28
     nueva
    1.23
    new
    1.21
    新
    1.18
     nuevos
    1.15
     nuevas
    1.14
     nuevo
    1.12
     baru
    1.12
     novas
    1.10
    Act Density 0.196%

    No Known Activations