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

    Neuronpedia

    INDEX
    Explanations

    references to characters and narrative elements in fiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Assertions
    -0.49
    RegressionTest
    -0.47
    ү
    -0.46
    みたいです
    -0.45
     spos
    -0.44
     accol
    -0.44
     initialized
    -0.42
     (?)
    -0.42
     gema
    -0.41
    हाय
    -0.41
    POSITIVE LOGITS
    dafx
    0.87
     autorytatywna
    0.86
     مشين
    0.85
     שוליים
    0.73
     ISNI
    0.72
    windowFixed
    0.71
    Искәрмәләр
    0.70
    Portail
    0.69
     lenker
    0.67
    ReusableCell
    0.66
    Act Density 0.309%

    No Known Activations