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

    Neuronpedia

    INDEX
    Explanations

    the ends of sentences and clauses, and words related to writing/publishing.

    oai_token-act-pair · gemini-2.0-flash

    various forms of the word "sound"

    np_token-act-pair-logits · gpt-4o-mini

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     well
    -0.83
    well
    -0.76
     Well
    -0.73
    Well
    -0.65
     WELL
    -0.63
     even
    -0.57
     bien
    -0.56
    WELL
    -0.56
    ]")]
    -0.54
     also
    -0.53
    POSITIVE LOGITS
     sounds
    0.72
    sound
    0.71
     Those
    0.67
    Those
    0.66
     Sounds
    0.66
    sounds
    0.65
     SOUND
    0.64
     sound
    0.62
     klingt
    0.62
     Sound
    0.61
    Act Density 1.593%

    No Known Activations