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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating future actions or events

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

    Following "will," "team," or "strongest"

    np_acts-logits-general · gemini-2.0-flash

    expressing expectation or anticipation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.74
    fjspx
    -0.64
     irgendwann
    -0.61
     picioare
    -0.60
     cesse
    -0.59
     Eventually
    -0.58
    Epilogue
    -0.58
    Eventually
    -0.58
    تقاوى
    -0.58
     Gradually
    -0.57
    POSITIVE LOGITS
    Expect
    0.90
     expecting
    0.86
     Expect
    0.86
    expect
    0.82
     expect
    0.80
     expected
    0.79
     expects
    0.72
     EXPECT
    0.71
     expectation
    0.69
     hoping
    0.68
    Act Density 0.156%

    No Known Activations