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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expectations and forecasts about future events

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

    Preceding "to" after "expected"

    np_acts-logits-general · gemini-2.0-flash

    expected to or scheduled for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chrétien
    -0.45
     imaginación
    -0.45
     protección
    -0.44
     definición
    -0.43
     personnalisée
    -0.43
     âme
    -0.42
     exprimer
    -0.41
     respiración
    -0.40
     verdaderas
    -0.40
     monasterio
    -0.40
    POSITIVE LOGITS
     Expected
    0.69
    parsedMessage
    0.67
    <unused3>
    0.66
    <unused8>
    0.66
    <unused51>
    0.66
    <unused52>
    0.66
    <unused43>
    0.66
    <unused41>
    0.66
    <unused14>
    0.66
    <unused23>
    0.66
    Act Density 0.175%

    No Known Activations