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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "come" and its various forms in multiple contexts

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

    invitations and prompts for action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     africaine
    -0.50
     Pública
    -0.47
     fabrique
    -0.42
     méri
    -0.41
     strade
    -0.38
    Bibliograf
    -0.38
     aérienne
    -0.38
     História
    -0.37
     History
    -0.37
     África
    -0.37
    POSITIVE LOGITS
     Come
    1.45
    Come
    1.39
     COME
    1.05
     come
    0.97
    come
    0.93
    COME
    0.90
    __":
    0.68
    Personensuche
    0.64
    __":
    0.64
    पया
    0.61
    Act Density 0.007%

    No Known Activations