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

    Neuronpedia

    INDEX
    Explanations

    phrases related to openness and accessibility in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegisterType
    -0.55
     sanity
    -0.54
    Uninitialized
    -0.52
    isContained
    -0.52
    自信
    -0.49
     Sieg
    -0.48
    LogFactory
    -0.48
     triumphantly
    -0.48
     T
    -0.48
     Kenney
    -0.48
    POSITIVE LOGITS
    tvguidetime
    0.94
    MLLoader
    0.85
     open
    0.81
    IsOpen
    0.81
     possibility
    0.77
    osoba
    0.76
    RectangleBorder
    0.76
     معرض
    0.74
    клопе
    0.74
    دانشنامهٔ
    0.73
    Act Density 0.174%

    No Known Activations