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

    Neuronpedia

    INDEX
    Explanations

    concepts related to hidden or concealed qualities and deceitful appearances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PyExc
    -0.61
    oredCriteria
    -0.57
    tonode
    -0.52
    expandindo
    -0.50
    IContainer
    -0.50
    disposing
    -0.50
    uxxxx
    -0.49
    branche
    -0.48
    shape
    -0.48
     Sehingga
    -0.47
    POSITIVE LOGITS
     underlying
    0.66
    実は
    0.63
     hidden
    0.61
     ẩn
    0.59
     actually
    0.58
     steckt
    0.58
    中身
    0.58
     transfieras
    0.58
     behind
    0.57
    背后
    0.57
    Act Density 0.403%

    No Known Activations