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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the term "split" in various contexts related to data processing or programming

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     itſelf
    -1.31
     myſelf
    -1.17
     pleaſure
    -1.13
     houſe
    -1.11
     Anſ
    -1.10
     Majefty
    -1.09
     iſt
    -1.06
     ―――――
    -1.05
     Houſe
    -1.05
     Theſe
    -1.05
    POSITIVE LOGITS
     “
    0.65
     mit
    0.63
     j
    0.59
     
    0.59
    <eos>
    0.56
    split
    0.56
     P
    0.55
     J
    0.54
     ‘
    0.54
     N
    0.54
    Act Density 0.002%

    No Known Activations