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

    Neuronpedia

    INDEX
    Explanations

    numeric formats, particularly those related to citations and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Numerade
    -1.13
     itſelf
    -1.07
     فريبيس
    -0.94
    reactstrap
    -0.88
     iſt
    -0.87
    BufferException
    -0.86
    ſelves
    -0.86
     незавершена
    -0.82
    ſelf
    -0.81
     ་་
    -0.81
    POSITIVE LOGITS
     
    0.52
     secours
    0.48
     Jer
    0.48
    уз
    0.47
    [
    0.46
     ordres
    0.46
    s
    0.46
    forhold
    0.45
     partículas
    0.45
     [
    0.45
    Act Density 0.030%

    No Known Activations