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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "the" in various contexts, along with references to systems, structures, and methodologies

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

    Follows the article "the"

    np_acts-logits-general · gemini-2.0-flash

    the norm, the way, the same

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.53
    各
    -0.51
    corsi
    -0.51
     विश्वसनीयता
    -0.47
    чис
    -0.47
    httphttps
    -0.46
    ския
    -0.46
     кӀ
    -0.46
     appena
    -0.45
    눠
    -0.43
    POSITIVE LOGITS
     only
    1.03
     reason
    1.02
     result
    1.01
     same
    0.95
     norm
    0.91
     easiest
    0.90
     basis
    0.88
     culmination
    0.85
    RenderAtEndOf
    0.84
     epitome
    0.82
    Act Density 0.246%

    No Known Activations