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

    Neuronpedia

    INDEX
    Explanations

    instances of novelty or newness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.46
     inevitable
    -0.42
    Slice
    -0.42
    Einzelnachweise
    -0.41
    <bos>
    -0.40
    ক্ত
    -0.39
    langle
    -0.39
    acija
    -0.38
     choose
    -0.38
     slice
    -0.38
    POSITIVE LOGITS
     المعيارى
    0.98
     unfamiliar
    0.91
     hitherto
    0.91
     inconn
    0.86
     heretofore
    0.83
    expandindo
    0.82
     new
    0.80
     впервые
    0.79
     newcomers
    0.78
     newcomer
    0.78
    Act Density 0.354%

    No Known Activations