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

    Neuronpedia

    INDEX
    Explanations

    phrases involving the infinitive "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    just to phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Putih
    -0.47
     gemens
    -0.46
     móvel
    -0.41
     coupable
    -0.40
     medarbe
    -0.39
     súčas
    -0.38
     księ
    -0.38
     träd
    -0.37
     använd
    -0.37
     śnie
    -0.37
    POSITIVE LOGITS
     GenerationType
    0.74
    just
    0.71
    Just
    0.69
     JUST
    0.66
     Just
    0.65
    JUST
    0.62
    random
    0.61
    uxxxx
    0.58
     فريبيس
    0.58
    tagext
    0.57
    Act Density 0.005%

    No Known Activations