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

    Neuronpedia

    INDEX
    Explanations

    hypothesized scientific statements or assertions

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    FileChooser
    -0.61
     ModelExpression
    -0.59
     OFDb
    -0.58
    AxisAlignment
    -0.55
    handled
    -0.55
    Билгалдахарш
    -0.55
    cherie
    -0.54
     hashtag
    -0.54
     memory
    -0.54
    ItemBackground
    -0.54
    POSITIVE LOGITS
     hypothesized
    2.52
     hypothe
    1.85
     postulated
    1.34
     theor
    0.91
     speculated
    0.81
     Hypothe
    0.76
     conject
    0.72
    awtextra
    0.65
    期刊论文
    0.65
    kwds
    0.56
    Act Density 0.001%

    No Known Activations