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

    Neuronpedia

    INDEX
    Explanations

    the preposition "for" in various contexts

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

    just for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aveug
    -0.53
     medarbe
    -0.41
    cemment
    -0.39
     étrangère
    -0.39
     wszyst
    -0.39
     interiores
    -0.38
     Meksika
    -0.38
     ehemal
    -0.38
     ότι
    -0.38
     perió
    -0.38
    POSITIVE LOGITS
    :✨
    0.60
     esternos
    0.57
     AssemblyTitle
    0.56
    enjoy
    0.55
     Савезне
    0.54
     autorytatywna
    0.52
    ENJOY
    0.52
     صوتيه
    0.51
    toHaveBeenCalled
    0.49
    ########.
    0.48
    Act Density 0.012%

    No Known Activations