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

    Neuronpedia

    INDEX
    Explanations

    high-powered mathematical expressions or formulas

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.66
    minin
    -0.56
     према
    -0.53
    ่าน
    -0.52
    “.
    -0.52
    "".
    -0.52
    afety
    -0.52
    ’.
    -0.51
    なんでも
    -0.51
    irsk
    -0.50
    POSITIVE LOGITS
     kasarigan
    0.77
    帖最后由
    0.67
    Externe
    0.66
    matchCondition
    0.66
     okuyayım
    0.65
     autorytatywna
    0.65
     poveznice
    0.63
    abestanden
    0.62
    #+#
    0.62
     Bessel
    0.61
    Act Density 0.014%

    No Known Activations