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

    Neuronpedia

    INDEX
    Explanations

    specific terms and phrases related to numbers and their arrangement or format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sevent
    -0.19
     Nin
    -0.18
    issance
    -0.17
    entieth
    -0.16
     xxx
    -0.15
    uyên
    -0.15
    ost
    -0.15
     Seven
    -0.14
    yles
    -0.14
     oct
    -0.14
    POSITIVE LOGITS
    12
    0.94
     Twelve
    0.81
     twelve
    0.79
    åįģäºĮ
    0.73
     XII
    0.63
    Û±Û²
    0.59
    Tw
    0.56
     tw
    0.50
     Tw
    0.50
    012
    0.49
    Act Density 0.249%

    No Known Activations