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

    Neuronpedia

    INDEX
    Explanations

    references to specific cultural artifacts or identifiers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    expandindo
    -0.69
     beginnetje
    -0.66
    Personensuche
    -0.65
     Normdatei
    -0.63
    HandlerContext
    -0.61
    发表于
    -0.56
    äfts
    -0.56
     behalf
    -0.56
    verwijspagina
    -0.56
     Sancho
    -0.54
    POSITIVE LOGITS
    setVerticalGroup
    0.73
    __':
    0.52
    __':
    0.52
    TERY
    0.51
    tetés
    0.51
    äki
    0.51
    бор
    0.50
    रीदारी
    0.49
     <",
    0.49
    MLLoader
    0.47
    Act Density 0.002%

    No Known Activations