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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "well" is used, indicating a conversational or rhetorical pivot

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

    introduction of a statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UserEntity
    -0.42
    actionMode
    -0.39
    thâu
    -0.37
     messaging
    -0.36
     aci
    -0.36
    neſs
    -0.35
     Arka
    -0.35
     parap
    -0.34
    édia
    -0.34
     RTP
    -0.33
    POSITIVE LOGITS
    Well
    1.11
     Well
    1.04
    well
    0.82
     well
    0.79
     WELL
    0.78
    Bueno
    0.71
    WELL
    0.71
    Welp
    0.69
    Pues
    0.64
     Pues
    0.63
    Act Density 0.006%

    No Known Activations