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

    Neuronpedia

    INDEX
    Explanations

    references to instances of structural failure, collapse, or the term "collapsed" in the text

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     Richard
    -0.74
    pédie
    -0.70
    Richard
    -0.69
    ásban
    -0.63
    Legende
    -0.56
    avía
    -0.54
     RICHARD
    -0.54
    sproz
    -0.54
    TextWatcher
    -0.54
    weile
    -0.53
    POSITIVE LOGITS
     collapse
    1.68
     collapsed
    1.66
     collapses
    1.58
     collapsing
    1.52
     Collapse
    1.20
    collapsed
    0.91
     оригіналу
    0.85
    AutoScale
    0.66
    ulation
    0.64
    lapsing
    0.64
    Act Density 0.002%

    No Known Activations