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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty and conjecture

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

    Comes before modal verbs ("would", "might", "may", "could")

    np_acts-logits-general · gemini-2.0-flash

    modal verb followed by 'have'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    were
    -0.88
     been
    -0.86
    been
    -0.78
    was
    -0.77
     Was
    -0.72
    Were
    -0.71
    Was
    -0.70
    Been
    -0.69
     were
    -0.69
     Did
    -0.66
    POSITIVE LOGITS
     للاسماء
    1.12
     itſelf
    1.04
     Efq
    1.02
     leaſt
    0.98
     myſelf
    0.97
     chofe
    0.97
     Houſe
    0.96
    ########.
    0.94
     houſe
    0.91
     Monfieur
    0.90
    Act Density 0.097%

    No Known Activations