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

    Neuronpedia

    INDEX
    Explanations

    the repeated use of the word "come" in various contexts

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

    come with particles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſche
    -0.50
     PRACT
    -0.50
     Szk
    -0.50
     ſmall
    -0.48
    jobId
    -0.48
    ſtre
    -0.48
    atlas
    -0.47
    employ
    -0.47
    ipolar
    -0.46
    acamata
    -0.46
    POSITIVE LOGITS
     come
    1.27
     comes
    1.07
     came
    1.05
     COME
    1.03
    come
    1.00
     Come
    1.00
    Come
    0.98
     Comes
    0.97
    Comes
    0.95
     coming
    0.90
    Act Density 0.025%

    No Known Activations