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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.86
    IContainer
    -0.77
     Siberian
    -0.76
     yonder
    -0.73
     Ruman
    -0.72
     Houſe
    -0.71
     ་་
    -0.71
     itſelf
    -0.71
     Monfieur
    -0.70
     iſt
    -0.70
    POSITIVE LOGITS
     reach
    0.66
     alturas
    0.62
    Rohy
    0.56
     reaches
    0.52
     ceea
    0.51
    reach
    0.50
     hozz
    0.50
     amortigu
    0.49
     Dostupné
    0.49
     florales
    0.47
    Act Density 0.172%

    No Known Activations