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

    Neuronpedia

    INDEX
    Explanations

    phrases related to instructions or commands given in authoritative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wikimedijinoj
    -0.86
     Adieu
    -0.63
    Pautan
    -0.60
     leaſt
    -0.60
     Сайт
    -0.59
     undersigned
    -0.58
    trums
    -0.57
    GOTREF
    -0.56
     épaules
    -0.56
    theoremstyle
    -0.55
    POSITIVE LOGITS
     causes
    0.92
    causes
    0.80
     Causes
    0.73
     thì
    0.71
    Causes
    0.70
    didSet
    0.67
    SpringRunner
    0.63
     terrorist
    0.63
    glGen
    0.62
     CWE
    0.62
    Act Density 0.058%

    No Known Activations